WO2016103198A1

WO2016103198A1 - Parameter and context stabilisation

Info

Publication number: WO2016103198A1
Application number: PCT/IB2015/059908
Authority: WO
Inventors: Jonathan Ackland
Original assignee: Performance Lab Technologies Limited
Priority date: 2014-12-23
Filing date: 2015-12-23
Publication date: 2016-06-30

Abstract

The invention relates to a method of detecting stability within an activity performed by a user. The method comprises receiving activity data indicative of the activity performed by the user during a first time interval, the activity data comprising a plurality of measurements and respective timestamps associated to at least one activity parameter monitored during the first time interval; receiving cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and cardiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval; a processor comparing at least some of the cardiovascular and cardiac data with at least one threshold range; and on the processor detecting a threshold set of cardiovascular and cardiac data lying within the at least one threshold range within a third time interval: generating a stability alert associated to the cardiovascular and cardiac data; and generating a stability alert associated to the activity data having respective timestamps not earlier than the timestamps associated to the threshold set of cardiovascular and cardiac data. The invention also relates to similar systems and computer-executable instructions.

Description

PARAMETER AND CONTEXT STABILISATION FIELD OF INVENTION

The invention relates to exercise and/or activity monitoring and in particular to classification of exercise or activity measurement data where identification of periods of stable data is important for accuracy in interpreting a user's physiological and psychological state.

BACKGROUND

Automated analysis of human and animal physiology presents some difficulties. In particular, there are several problems that occur when using wearable biometric devices.

The first is that users increasingly want 'meaning' from their data. It is not good enough anymore that data is simply available. Unless the data can be used to positively change a user's behaviour then the mountains of data are meaningless. Numbers alone don't tell people what the identified measurement situation is or what it means.

Another problem is that users cannot be expected to work in a very disciplined manner to capture the data. Life is too full of other demands, so the capture of vital user data is more effective if it is automatic.

A further problem is that the data must be accurate so as not to provide false

information. How this user data is processed is therefore extremely important. It is an object of preferred embodiments of the present invention to address some of the aforementioned disadvantages. An additional or alternative object is to at least provide the public with a useful choice.

SUMMARY OF THE INVENTION

In one aspect the invention comprises a method of detecting stability within an activity performed by a user, the method comprising : receiving activity data indicative of the activity performed by the user during a first time interval, the activity data comprising a plurality of measurements and respective timestamps associated to at least one activity parameter monitored during the first time interval; receiving cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and cardiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval; a processor comparing at least some of the cardiovascular and cardiac data with at least one threshold range; and on the processor detecting a threshold set of cardiovascular and cardiac data lying within the at least one threshold range within a third time interval : generating a stability alert associated to the cardiovascular and cardiac data; and generating a stability alert associated to the activity data having respective timestamps not earlier than the timestamps associated to the threshold set of cardiovascular and cardiac data.

The term "comprising" as used in this specification means "consisting at least in part of". When interpreting each statement in this specification that includes the term

"comprising", features other than that or those prefaced by the term may also be present. Related terms such as "comprise" and "comprises" are to be interpreted in the same manner.

Preferably a lower bound of the first time interval is the same as a lower bound of the second time interval.

Preferably an upper bound of the first time interval is the same as an upper bound of the second time interval. Preferably a lower bound of the third time interval is later than a lower bound of the second time interval.

Preferably the at least one threshold range is defined by a lower threshold value and an upper threshold value, or respective lower threshold and upper threshold values.

Preferably the at least one threshold range is defined by a target value and a tolerance value, or respective target and tolerance values.

Preferably the processor is configured to adjust the at least one threshold range.

Preferably a user interface is configured to obtain from a user adjustments to the at least one threshold range.

Preferably the processor is configured to adjust the duration of the third time interval.

Preferably a user interface is configured to obtain from a user adjustments to the duration of the third time interval. Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval. Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval .

Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprise consecutive values within the third time interval .

Preferably the cardiovascular and cardiac data is measured by the at least one cardiovascular and cardiac parameter selected from hea rt rate, electrocardiograph, oxygen saturation, respiration, ventilation, oxygen uptake, and blood pressure.

Preferably the cardiovascular and cardiac data comprises neurocardiogenic data measured by the at least one cardiovascular and cardiac parameter selected from heart rate variability, AVNN, SDNN, SD1, SD2, HF, LF, rRMSSD, pNN50, and total power. Preferably the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity parameters monitored during the first time interval.

Preferably the cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of ca rdiovascular and cardiac pa rameters monitored during the second time interval.

In another aspect the invention comprises a system configured to detect stability within an activity performed by a user, the system comprising at least one computer-readable medium; and at least one processor, the at least one processor programmed to : receive activity data indicative of the activity performed by the user during a first time interval, the activity data comprising a plurality of measurements and respective timestamps associated to at least one activity parameter monitored during the first time interval ; receive cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and cardiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval ; compare at least some of the cardiovascular and cardiac data with at least one threshold range; and on detecting a threshold set of cardiovascular and cardiac data lying within the at least one threshold range within a third time interval : generate a stability alert associated to the cardiovascular and cardiac data; and generate a stability alert associated to the activity data having respective timestamps not earlier than the timestarmps associated to the threshold set of cardiovascular and cardiac data.

Preferably an upper bound of the first time interval is the same as an upper bound of the second time interval.

Preferably a lower bound of the third time interval is later than a lower bound of the second time interval. Preferably the at least one threshold range is defined by a lower threshold value and an upper threshold value, or respective lower threshold and upper threshold values.

Preferably a user interface is configured to obtain from a user adjustments to the duration of the third time interval.

Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval. Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval. Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprise consecutive values within the third time interval .

Preferably the cardiovascular and cardiac data comprises neurocardiogenic data measured by the at least one cardiovascular and cardiac parameter selected from heart rate variability, AVNN, SDNN, SD1, SD2, HF, LF, rRMSSD, pNN50, and total power.

Preferably the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity parameters monitored during the first time interval.

Preferably the cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of ca rdiovascular and cardiac pa rameters monitored during the second time interval. In another aspect the invention comprises a computer-readable medium having stored thereon computer-executable instructions that, when executed by at least one processor, cause the at least one processor to perform a method of detecting stability within an activity performed by a user, the method comprising receiving activity data indicative of the activity performed by the user during a first time interval, the activity data comprising a plurality of measurements and respective timestamps associated to at least one activity parameter monitored during the first time interval ; receiving cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and cardiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval; comparing at least some of the ca rdiovascular and cardiac data with at least one threshold range; and on detecting a threshold set of cardiovascular and cardiac data lying within the at least one threshold range within a third time interval : generating a stability alert associated to the cardiovascular and cardiac data ; and generating a stability alert associated to the activity data having respective timestamps not earlier than the timestamps associated to the threshold set of cardiovascular and cardiac data.

Preferably a lower bound of the first time interval is the same as a lower bound of the second time interval. Preferably an upper bound of the first time interval is the same as an upper bound of the second time interval. Preferably a lower bound of the third time interval is later than a lower bound of the second time interval.

Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval.

Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval.

Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprise consecutive values within the third time interval. Preferably the cardiovascular and cardiac data is measured by the at least one cardiovascular and cardiac parameter selected from heart rate, electrocardiograph, oxygen saturation, respiration, ventilation, oxygen uptake, and blood pressure. Preferably the cardiovascular and cardiac data comprises neurocardiogenic data measured by the at least one cardiovascular and cardiac parameter selected from heart rate variability, AVNN, SDNN, SD1, SD2, HF, LF, rRMSSD, pNN50₍ and total power. Preferably the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity parameters monitored during the first time interval.

In another aspect the invention comprises a method of detecting stability within an activity performed by a user, the method comprising : receiving activity data indicative of the activity performed by the user during a first time interval, the activity data comprising a plurality of measurements and respective timestamps associated to at least one activity parameter monitored during the first time interval ; receiving cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and cardiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval; a processor comparing at least some of the activity data with at least one threshold range; and on the processor detecting a threshold set of activity data lying within the at least one threshold range within a third time interval : generating a stability alert associated to the activity data; and generating a stability alert associated to the cardiovascular and cardiac data having respective timestamps not earlier than the timestamps associated to the threshold set of activity data .

Preferably the at least one threshold range is defined by a lower threshold value and an upper threshold value, or respective lower threshold and upper threshold values. Preferably the at least one threshold range is defined by a target value and a tolerance value, or respective ta rget and tolerance values. Preferably the processor is configured to adj ust the at least one threshold range.

Preferably a user interface is configured to obtain from a user adjustments to the at least one threshold range. Preferably the processor is configured to adj ust the duration of the third time interval .

Preferably a user interface is configured to obtain from a user adjustments to the duration of the third time interval. Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval.

Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval .

Preferably the cardiovascular and cardiac data is measured by the at least one cardiovascular and cardiac parameter selected from hea rt rate, electrocardiograph, oxygen saturation, respiration, ventilation, oxygen uptake, and blood pressure. Preferably the cardiovascular and cardiac data comprises neurocardiogenic data measured by the at least one cardiovascular and cardiac parameter selected from heart rate variability, AVNN, SDNN, SD1, SD2, HF, LF, rRMSSD, pNN50, and total power.

Preferably the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity parameters monitored during the first time interval. Preferably the cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of cardiovascular and cardiac parameters monitored during the second time interval. In another aspect the invention comprises a system configured to detect stability within an activity performed by a user, the system comprising at least one computer-readable medium; and at least one processor, the at least one processor programmed to: receive activity data indicative of the activity performed by the user during a first time interval, the activity data comprising a plurality of measurements and respective timestamps associated to at least one activity parameter monitored during the first time interval; receive cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and cardiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval; compare at least some of the activity data with at least one threshold range; and on detecting a threshold set of activity data lying within the at least one threshold range within a third time interval : generate a stability alert associated to the activity data; and generate a stability alert associated to the cardiovascular and cardiac data having respective timestamps not earlier than the timestamps associated to the threshold set of activity data.

Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval . Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprise consecutive values within the third time interval .

Preferably the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity parameters monitored during the first time interval. Preferably the cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of ca rdiovascular and cardiac pa rameters monitored during the second time interval.

In another aspect the invention comprises a computer-readable medium having stored thereon computer-executable instructions that, when executed by at least one processor, cause the at least one processor to perform a method of detecting stability within an activity performed by a user, the method comprising receiving activity data indicative of the activity performed by the user during a first time interval, the activity data comprising a plurality of measurements and respective timestamps associated to at least one activity parameter monitored during the first time interval; receiving cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and cardiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval; comparing at least some of the activity data with at least one threshold range; and on detecting a threshold set of activity data lying within the at least one threshold range within a third time interval : generating a stability alert associated to the activity data; and generating a stability alert associated to the cardiovascular and cardiac data having respective timestamps not earlier than the timestamps associated to the threshold set of activity data.

Preferably a lower bound of the first time interval is the same as a lower bound of the second time interval. Preferably an upper bound of the first time interval is the same as an upper bound of the second time interval.

Preferably a lower bound of the third time interval is later than a lower bound of the second time interval.

Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval. Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval .

Preferably the cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of ca rdiovascular and cardiac pa rameters monitored during the second time interval. Preferably the method further comprises generating sta ble activity data at least partly from the activity data to which the stability alert is associated .

Preferably the processor is further configured to generate stable activity data at least pa rtly from the activity data to which the stability alert is associated .

Preferably the method further comprises generating sta ble activity data at least partly from the activity data to which the stability alert is associated .

Preferably the method further comprises generating sta ble cardiovascular and cardiac data at least partly from the ca rdiovascular and cardiac data to which the stability alert is associated . Preferably the processor is further configured to generate stable ca rdiovascular and cardiac data at least partly from the cardiovascular and cardiac data to which the stability alert is associated . Preferably the method further comprises generating sta ble cardiovascular and cardiac data at least partly from the ca rdiovascular and cardiac data to which the stability alert is associated .

The invention in one aspect comprises several steps. The relation of one or more of such steps with respect to each of the others, the apparatus embodying features of construction, and combinations of elements and arrangement of parts that are adapted to affect such steps, are all exemplified in the following detailed disclosure.

This invention may also be said broadly to consist in the parts, elements and features referred to or indicated in the specification of the application, individually or collectively, and any or all combinations of any two or more said parts, elements or features, and where specific integers are mentioned herein which have known equivalents in the art to which this invention relates, such known equivalents are deemed to be incorporated herein as if individually set forth .

As used herein, '(s)' following a noun means the plural and/or singular forms of the noun . As used herein, the term 'and/or' means 'and' or 'or' or both.

It is intended that reference to a range of numbers disclosed herein (for example, 1 to 10) also incorporates reference to all rational numbers within that range (for example, 1, 1.1, 2, 3, 3.9, 4, 5, 6, 6.5, 7, 8, 9, and 10) and also any range of rational numbers within that range (for example, 2 to 8, 1.5 to 5.5, and 3.1 to 4.7) and, therefore, all subranges of all ranges expressly disclosed herein are hereby expressly disclosed . These a re only examples of what is specifically intended and all possible combinations of numerical values between the lowest value and the highest value enumerated are to be considered to be expressly stated in this application in a similar manner.

In this specification where reference has been made to patent specifications, other external documents, or other sources of information, this is generally for the purpose of providing a context for discussing the features of the invention. Unless specifically stated otherwise, reference to such external documents or such sources of information is not to be construed as an admission that such documents or such sources of information, in any j urisdiction, are prior art or form part of the common general knowledge in the art. The term 'connected to' includes all direct or indirect types of communication, including wired and wireless, via a cellular network, via a data bus, or any other computer structure. It is envisaged that they may be intervening elements between the connected integers. Variants such as 'in communication with', 'joined to', and 'attached to' are to be interpreted in a similar manner. Related terms such as 'connecting' and 'in connection with' are to be interpreted in the same manner.

The term "computer-readable medium" should be taken to include a single medium or multiple media . Examples of multiple media include a centralised or distributed database and/or associated caches. These multiple media store the one or more sets of computer executable instructions. The term "computer readable medium" should also be taken to include any medium that is capable of storing, encoding or carrying a set of instructions for execution by a processor and that cause the processor to perform any one or more of the methods described above. The computer-readable medium is also capable of storing, encoding or carrying data structures used by or associated with these sets of

instructions. The term "computer-readable medium" includes solid-state memories, optical media and magnetic media.

The terms 'component', 'module', 'system', 'interface', and/or the like are generally intended to refer to a computer-related entity,either hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of illustration, both an application running on a controller and the controller can be a component. One or more components may reside within a process and/or thread of execution and a component may be localized on one computer and/or distributed between two or more computers.

Although the present invention is broadly as defined above, those persons skilled in the art will appreciate that the invention is not limited thereto and that the invention also includes embodiments of which the following description gives examples.

BRIEF DESCRIPTION OF THE DRAWINGS

Preferred embodiments of the invention will be described by way of example only and with reference to the accompanying figures, in which :

Figure 1 shows exemplary analysis engine, data acquisition, and data analysis components. Figure 2 shows an embodiment of the analysis engine of figure 1.

Figure 3 shows how cardiovascular data such as heart rate can remain relatively stable and within a zone while Activity Data like speed is highly unstable and changes significantly.

Figure 4 shows how Activity Data like speed can remain relatively stable while a cardiovascular parameter like heart rate changes ma rkedly. Figure 5 shows that differences in assessment of a ca rdiovascular parameter like average heart rate can have significant inaccuracies depending on the method of analysis comparing Parameter Stability or Context Stability with a more standard method .

Figure 6 shows the different kinds of data that can be used in Parameter Stability or Context Stability analysis.

Figure 7 shows the difference between and Activity, Activity Type and a Cardiovascular and cardiac Event. Figure 8 shows how parameter thresholds or zones can be used to detect Activities and Activity types.

Figure 9 shows how multiple parameters can be used simultaneously to detect an Activity or Activity type.

Figure 10 shows how a Cardiovascular and cardiac Event can occur and a 'snapshot' or a recording of surrounding sensors can occur simultaneously.

Figure 11 shows the duration required for a ca rdiovascular parameter like heart rate to stabilize to a change in speed.

Figure 12 shows the duration required for a ca rdiovascular parameter like heart rate to stabilize with a change in incline or gradient.

DETAILED DESCRIPTION

1. Parameter Stabilisation and Context Stabilisation Overview Described below is an a nalysis engine. The engine forms part of an automated system for obtaining accurate analysis of cardiovascular a nd cardiac and ca rdiac data or data on the physica l activity of a user who is engaged in a form of exercise or activity. In an embodiment the data further includes external data like environmental data or equipment recognition data . Alternatively or additionally the data includes data obtained for a coach, trainer or medical practitioner that has not generated the exercise/activity data but needs the data to provide some form of analysis and feedback or advice to the user. The analysis engine is configured so that only accurate data representations are utilised for analysis of user activity and physiology.

Ca rdiovascular and Cardiac data measures include all forms of data that relate to the heart, lungs and/or blood vessels. In this definition Ca rdiovascular and cardiac data relates to factors such as but not limited by heart rate, heart function

(Electrocardiograph), Heart Rate Va riability, Blood Oxygen saturation, Muscle Oxygen Saturation, Skeletal Oxygen Saturation, blood pressure and derivations that can be extracted from heart rate analysis like respiration rate. This includes changes in

Ca rdiovascular and cardiac data .

Physica l Data as described below measures includes additional measures beyond cardiovascular and cardiac measures of the user's activity a nd movements.

Environmental data reflects the stress of the environment on the user's body like temperature, air pressure, altitude, humidity and wind speed.

Equipment recognition data includes identification data for example RFID tags for equipment. Figure 1 shows an exemplary diagram of a user 100 exercising or engaging in one or more activities, for example engaging in an activity session. The user 100 wears one or more pa rameter sensing devices 102. Examples of sensing devices include one or more of Heart Rate (chest strap or optical), GPS, speed foot pods, cycle sensors, rowing and kayaking sensors, Accelerometry, fused 9 axis data (accelerometer, magnetometer, gyroscope), ECG, Blood Pressure (direct or optical), Oxygen Saturation, power meters, Equipment ID transmitters, inclinometers, pressure sensors, wind sensors, temperature and humidity sensors, respiration, electromyog raphy and EEG sensors, barometers, DEM, and/or hyd ration sensors. The device(s) 102 collect information on the activity session and in particular data streams associated with the parameters required to classify the activities performed during the user's exercise/activity session. In an embodiment, device(s) 102 automatically process the data 'on board', or manually when the user prompts the device to process the data for example, if the classification system is housed within the monitoring device(s) .

Alternatively or in addition the data are transmitted to an analysis engine 104 (which may reside in a remote server or a home computer), either wirelessly or via cables, and if sent to a remote server preferably e.g. via a network. The analysis engine 104 is connected to a memory 106 in which at least some of the data is stored .

Instead of automatic transmission of the data, the user may upload the data manually to a desktop or laptop computing device 108 connected to the analysis engine 104 via a wired or wireless network 110.

Analysis engine 104 processes the data by accessing memory 106 containing

classification system algorithms, threshold criteria and/or user information . These components a re described in more detail below. Analysis engine 104 determines activities conducted and the level of performance as described below. It will be appreciated that the analysis engine 104 additionally or alternatively accesses at least one memory associated to sensing device(s) 102, computing device 108, and/or a server on which the analysis engine 104 is maintained .

In an embodiment, analysis engine 104 interprets the retrieved data and/or any other data provided by the device(s) 102 to provide feedback to the user 100. In an embodiment the analysis engine 104 alters a training program maintained for example in memory 106. In an embodiment the analysis engine 104 communicates with at least one computing device or other device of the user 100 using a wired or wireless network.

Figure 2 shows an example of the analysis engine 104 from Figure 1. An identification engine 200 receives sensor data directly or indirectly from sensing device(s) 102. The identification engine 200 is configured to, in real time or post activity, identify Activities, Activity Types or Ca rdiovascular and cardiac Events.

Data of a user 100 is measured during an activity session or during their activities over a period of time like a day or many days. Multiple data parameters are recorded during this time using one or more data measurement devices. Once the identification engine 200 identifies an Activity, Activity Type or Cardiovascular and cardiac Event, a stabilisation engine 202 receives the data to ensure accurate data is obtained from within the Activity, Activity Type or Cardiac/Cardiovascular Event.

A data analysis engine 204 receives the data from the stabilisation engine 202. The data analysis engine 204 applies algorithms to provide comparisons between the data.

These comparisons are provided to an insights engine 206 in order to provide insights to a user. Insights include adjustments to a Training Program/Plan or Activity Schedule and/or information that the user can use to mod ify their current or future behaviour.

A feedback module 208 provides information and/or alerts to a user as will be further described below.

In an embodiment the analysis engine 104 maintains multiple pre stored parameter thresholds or zones to detect activity. When one or multiple measured parameters match, meet or exceed the pre stored thresholds or zones the engine 104 automatically prepares to begin recording data which is transmitted to identification engine 200.

Recording of accurate data occurs once a period of stabilisation is identified by stabilisation engine 202.

In an embodiment, the identification engine 200 obtains or records raw activity data when an Activity Parameter Match has been identified . Once the stabilisation engine 202 determines that a key parameter is stable, the system then analyses the data . This happens in an exercise where cardiovascular and cardiac responses like heart rate take a period of several minutes to 'catch up' with the user's change in intensity to accurately characterise the user's effort. A user may be engaging in some speed training exercise and move their effort from lOkm/hr to 13krm/hr. The speed change happens very quickly; speed moves from lOkm/hr to 13km/hr in a few seconds but hea rt rate ta kes several minutes to move from 150 b/min to 185b/min so there is a heart rate lag in relation to speed during changes in intensity.

Pa rameter stabilisation means that only heart rate data that accurately portrays the effort is recorded for analysis. Data where the heart rate was slowly adapting to the new intensity during the 'catch up' phase is not recorded due to its inaccuracy. This can be seen in Figure 3 and Figure 4. In Figure 3 Heart rate is uniformly in the heart rate zone shown at 300. However, speed is not stable as speed has moved from intense 302 to moderate 304. Conversely in Figure 4 speed is uniform as shown at 400. However, heart rate is still rising to adapt to the increase in speed 402 before it finally becomes stable 404. In both cases there is a lag time between when speed changes and when heart rate reaches a point where it accurately characterises the situation . Figure 5 shows accuracy effects with and without parameter stabilisation . The parameter to ascertain stability is heart rate for varying speed . Heart rate changes to reach a point of stability at 12 km/hr at the 30 second mark 500 while a user is doing running speed training. Heart rate takes a further 2 minutes and 30 seconds before it stabilises at 180 beats per minute indicated at 502.

As shown in the figure, Hea rt rate data is averaged as soon as speed reaches 12km/hr 500 even though heart rate has not stabilised at 180 beats per minute yet and is only 142 beats per minute. This leads to an average heart rate of 168 beats per minute shown at 504.

Alternatively in the other example shown in Figure 5, heart rate is not averaged until it stabilises at 510 leading to a more accurate analysis of average hea rt rate of 180 beats per minute shown at 512. Any algorithms applied to 168 beats per minute 504 versus 180 beats per minute 512 will result in highly erroneous results for 168 beats per minute.

In another example of Parameter Stability when recording Hea rt Rate Variability data, the analysis engine 104 detects various events or activities 110. The events/activities include for example :

• sitting still for more than 2 mins, and

· within 20mins of lying down for a long period, a nd

• in the morning, and

• with slow relaxed breathing .

Once this activity, made up of a series of parametric events, is detected to be within specific threshold criteria, the Activity is detected . Next Heart Rate Variability data is recorded once the stabilisation engine 202 determines that the data are stable and the engine takes a snap shot of a key parameter like Heart Rate Variability which may include the context data established for the data analysis engine 104. In an embodiment, this context data includes one or more of the fact that the user is sitting, has been inactive for a period, the time of day, whether the day is a weekend or work day and/or the respiration rate. The reason that they context data may be included is for future comparisons.

Alternatively, the key metric, in this case Hea rt Rate Variability may be sampled without the contextual data. Pa rameter Stabilisation is set up to solve severa l problems.

The first is that hea rt data in constantly a summation of the previous few minutes of activity. It is therefore very hard to compare heart data to activity as they are slightly offset from each other.

The second problem to be solved is teaching a machine to automatically find the most appropriate times and situations to obtain good quality activity data . A user analysed by the stabilisation engine 202 may be running and have to slow their speed to pause at a traffic light even though heart rate is still elevated, another user may have an anomaly reading in their ECG or blood pressure due to a sensor error.

Still another user may start exercising with a heart rate monitor strap that has not been pre moistened. The lack of moisture between the strap and the skin leads to poor electrica l conductivity which usually means very high aberrant readings are recorded. Similar situations are possible with wireless technology when there is a strong electrical source present that can interfere with a user's sensor data .

In each case the problem of bad quality data must be solved for effective analysis of user activity requiring a form of filtering which involves parametric stabilisation.

Once good quality data has been obtained, in some cases algorithms can then be applied to the parameter stabilised accurate data so that the insights engine 206 is able to obtain trustworthy insights. These insights can be automatically provided to the user 100 as feedback from feedback module 208, adjustments to an Activity Plan or an Activity Schedule or the metrics can be provided to the user or retained for use in future analysis. Insights are a preferable feature of the invention and may alternatively not be supplied by the system and instead handled manually by a physical trainer, coach, rehabilitation technician, doctor or some other source for exa mple. Stabilisation of data also provides the trainer or doctor with a more concisely processed data set to analyse and draw conclusions from without the fear of drawing incorrect conclusions based on bad data or spending significant processing the data themselves.

The information is received by the system either manually via the user initiating uploading of the information from the monitoring device or automatically via the monitoring device, or from some other source for analysis, and is received and/or analysed either during activity or post activity. The system may be part of the monitoring device or may be separate, running on a personal computer for example, or a remote server accessible by and in communication with a personal computer and/or one or more monitoring devices.

Formats in which the Stabilisation Engine 202 is Used

The exercise/activity data is received during the activity session and the step of utilizing the identification engine 200 and the stabilisation engine 202 can be performed sequentially and in real time during the measured session or may be processed post activity.

The Stabilisation engine 202 records data that has already been classified by Activity or further by Activity Type or Cardiovascular/Cardiac Event.

An Activity is a distinct set of recognisable movements within broad thresholds involving movement of the body or limbs where the user is doing something classifiable or causing something to happen. Examples of more genera l activity can include running, walking, cycling, swimming, lying down, standing still, sitting .

An Activity Type occurs within an Activity and describes a sub category or nuance of an activity. There are many different possible Activity Types but to illustrate a few; in the case of an Activity like running, the Activity Types might be running fast, running slow or running up a hill. In an Activity like Cycling the Activity Types might be sprinting, pedalling at a high cadence in a little gear or pedalling at a high cadence in a big gear.

Ca rdiovascular and Cardiac Events include forms of heart, heart/lung and/or blood vascular system occurrences particularly marked changes and depictions of both health and ill health in cardiovascular and cardiac measures. An occurrence may be an anomaly in data measured or data that exceeds a threshold. This includes measures of Heart Rate Variability and extracting respiration rate from heart rate. Preferably the step of utilizing the stabilisation engine 202 involves classification of an Activity or Activity Type and further comprises grouping consecutive data points classified under the same activity to define an instance of the activity during a period of activity or inactivity, the number of consecutive data points being indicative of the duration of the instance of the activity.

Preferably the method further comprises composing a response based on the

physiological, biomedical or autonomic nervous system status based on the classified data points, and outputting the response to the user. The response may be output in an auditory, graphical and/or text form and may be output to the user in real time or post activity.

The response for example may be in the form of coaching advice which may alter how the user engages in a particular activity or it may alter an activity plan associated with the user.

The response may also be manually or automatically output.

Preferably the at least one parameter monitored during the activity session is obtained from an activity monitoring device and the data is received from the monitoring device. Preferably the data is received in real time. Alternatively, the data is received post activity. Preferably the device is wearable.

Pa rameter stabilisation is important in several cases; obtaining accurate data including exercise data, accurate medical data and accurate physiological status data and can use multiple types of data, as shown in Figure 6.

Examples of Parameters used in Activity, Activity Type, Cardiovascular/Cardiac Events and Stabilised Data within these Formats.

Ca rdiovascular and Cardiac Measures

Preferably, cardiovascular and cardiac parameters include heart rate or change in heart rate, electrocardiograph waveform, and other aspects of heart function and changes in electrocardiograph waveform and other aspects of heart function, oxygen saturation (blood oxygen saturation, muscle oxygen saturation, skeletal oxygen saturation) or changes in oxygen saturation, include respiration or change in respiration, ventilation or changes in ventilation, oxygen uptake or change in oxygen uptake, lactate concentrations and changes in lactate concentrations and blood pressure or changes in blood pressure. They also include heart rate variability or changes in heart rate variability which specifically includes measures of RR interval, AVNN, SDNN, SDl, SD2, HF, LF, RMSSD, InRMSSD, pNN50, and Total Power. ECG feature extraction can occur through mathematical analysis on the clean signal of all channels, to identify and measure a number of features which are important for interpretation and diagnosis. These include components such as the peak amplitude, area under the curve, displacement in relation to baseline of the P, Q, R, S and T waves,-the time delay between these peaks and valleys, heart rate frequency (instantaneous and average).

Inferred data and derivations of these parameters a re also included. Physica l Data Measures

Preferably Physical Data measures include speed of the user or change in speed of the user, power output of the user or changes in power output of the user, limb turnover of the user or changes in limb turnover of the user, distance per limb turnover of the user or changes in distance per limb turnover, force or the user or changes in force of the user, postural incline of the user or changes in postural incline of the user, degree of movement of the user or change in degree of movement of the user and weight lifted of the user including body weight.

Environmental Measures

Preferably Environmental measures include temperature, humidity, wind speed, air pressure, altitude and changes in the Environmental measures.

Equipment Recognition Measures

Preferably Equipment measures include forms of equipment associated with the user. This could be equipment the user is ca rrying or may be equipment that the user is interfacing with like a weight lifting strength machine in a gym like a bench press device. It may also include equipment that the user is using intermittently like a ball or medicine ba ll . In each case the user would be able to manually input the equipment label or the equipment would have an automatic method for identifying itself to the user stabilisation system via Bluetooth, Wi-Fi, ant+, proximity or some other form of identification.

2. Steps to Parameter Stability and Context Stability

2.1 Identification (Classification)

The identification system 110 enables different kinds of data to be identified.

The first identification involves detecting Activities and Activity Types. The second kind of identification involves detecting stepped or marked changes or situations where a pa rameter goes above or falls below a threshold for a short consistent time which is called a Cardiovascular or Cardiac Event.

The first form of identification requires an Activity Identification Engine which precedes the Stabilisation Engine. The Activity Identification does not necessa rily apply to

Ca rdiovascular and Cardiac Events. These can be detected on their own without needing Activity Identification.

Three examples of Identification are:

· Activity Identification

• Activity Type Identification

• Cardiovascular and cardiac Event Identification

Activity Identification Data can be used to differentiate between Activities like the difference between cycling, running, walking, swimming, sitting, standing, lying down. This identification can occur due to manual input or to the sensing used in one or more sensors.

Acitivity Type Identification

Subtler Activity Types that occur within an Activity can be detected. Examples include cycling up a hill, running fast, cycling in a big gear at a low cadence can also be identified . With more sensors, more context can be determined and therefore subtler differentiations may be determined .

To identify an Activity and Activity Type, the Activity Detection Engine has knowledge of one or more Activities or Activity Types and their specific relationship with one or more pa rameters to achieve this. This knowledge may be simple or complex based on the application and/or desired accuracy of the system.

Referring to Figure 8, the Activity Detection Engine uses multiple simultaneous pa rameters to identify Activities or Activity Types. Each Activity or Activity Type requires at least one threshold criteria such as value or zone associated with each parameter. Each parameter 800 has magnitude 802 and a threshold or zone 804 associated to it in the Activity Detection Engine. If the magnitude of the parameter values drop below a threshold or go above a threshold or go into or out of a zone then a match occurs 806.

If the values do not go over the threshold or into or out of the zone then no match occurs 808 and no identification occurs for the particular set of stored thresholds/zones.

Referring to Figure 9, a n Activity or Activity Type can be identified by the Activity Detection Engine. For example, in some cases every threshold criteria or enough threshold criteria are satisfied for each of a combination of parameters that define that Activity or Activity Type.

An Activity or Activity Type may be identified from different combinations of parameters. This diversifies the compatibility of the system with different monitoring devices. For example, an 'easy walking' activity may be defined by a stride rate threshold (such as less than 60 steps per minute) and a terrain threshold (such as a gradient of less than 2° ), or a speed threshold (less than 8km/hr) and a terrain threshold (gradient of less than 2°), or a heart rate threshold (such as between 40 and 110 beats per min) and a terrain threshold (such as a gradient of less than 2° ) .

This allows for different types of monitoring devices to be used alongside the system. For instance, a mobile phone with GPS capability for measuring speed can be the monitoring device, or a more advanced device such as those branded under Polar, Suunto, Timex, Ga rmin, Adidas or Nike can be used for measuring heart rate and other parameters such as speed, altitude, distance, time and turnover (e.g. stride rate) .

There is a tolerance built in for classification where one or more parameters can move outside the classification thresholds for a brief time and still maintain the classification .

Ca rdiovascular and Cardiac Event Identification

Figure 10 shows identification of a cardiovascular or CC event 1000. Events can also occur where there is a ca rdiovascular and cardiac change in a user and the Para meter Stabilisation Engine can take a 'snapshot' of all the data from each sensor present to show context that surrounds the Cardiovascula r and Cardiac Event. The goal is not so much to identify the medical issue but to identify the situation or context it occurs in .

A Cardiovascular and Cardiac Event is less an Activity and more an occurrence of something . For example, high blood pressure may be identified or ECG readings may show medical issues in certain situations.

This is extremely important with the proliferation of cheap wearable sensors in that many more physiological parameters can be measured in situ more readily than ever before.

A Cardiovascular and Cardiac Event identification operates differently from Activity Identification and Activity Type Identification in that only one parameter needs to be identified . When a stable Cardiovascular and Cardiac Event occurs, for example heart rate abnormalities stable for more than 20 seconds then a single 'snapshot' or a recording of all the data being measured is taken. The reason stability is important is so there are no false alarms where the Activity Detection Engine picks up a n alert which has only occurred due to erroneous data. For example, if an ECG abnormality occurred like an ectopic, a snapshot or recording of heart rate, ECG, blood pressure, temperature, altitude, terrain, location, speed, postural incline could be taken to help ascertain contributing conditions to the Cardiovascular or Cardiac Event. This data could be exported to a Doctor or Medical facility and could also include data that precedes the Ca rdiovascular/Cardiac Event by 30 minutes or a time period to show lead up Activities and Activity Types with their data.

In the case of Activity Identification, Activity Type Identification and Cardiovascular and Ca rdiac Event Identification, a plurality of data and potentially activity parameters is usually received which are also time stamped .

Activity Detection Engine identifications can therefore occur at the Activity and Activity Type levels. (Figure 7. 700, 702 and 704) Also shown is workout 706. Ca rdiovascular and cardiac Events are usually a single parameter and then capturing the context in further sensored data .

In accordance with the invention, activities are identified using more than one data stream with each stream being associated with a parameter and an identification occurs where multiple parameters match a set of stored thresholds or zones which are used to identify a particular Activity, Activity Type or Cardiovascular and cardiac Event.

During Activity, data is recorded or sampled over a period of time which can be referred to as the first time interval. During that time period a plurality of data may be received, recorded and or sampled.

Ca rdiovascular and Cardiac or Physical data may be received, recorded or sampled at a slightly different time interval, referred to as the second time interval, to the rest of the data although this is unusual. In most situations activity data and cardiovascular and cardiac data are received, recorded or sampled at the same time meaning the first time interval and the second time interval are usually the same.

In both cases a plurality of time stamped data is received .

2.2 Stabilization

The stabilization system 120 automatically ensures that the identified data containing Activity, Activity Type or Cardiovascular and Cardiac Event data is accurate. It takes into account that some measured parameters take time to adapt. Each key parameter is physiological or physical in nature and includes any form of Cardiovascular and Cardiac measure or Activity Data. It can be supported by other contextual data .

Reasons why Stabilisation is Important:

• Cardiovascular/Ca rdiac and Biomedical Delays

· Brief Pa rameter Changes

• Optimal Measurement Conditions a. Cardiovascular/Ca rdiac and Biomedical Delays

One of the biggest problems with analysing heart data is that the heart's responses and the issues that cause the hea rts response are often offset by a time period . The

Pa rameter Stabilisation Engine will not allow classified cardiovascular/ cardiac or biomedical data to be used for analysis until the data becomes relatively uniform. Any data preceding the period where the data becomes uniform is eliminated . Data stability is important for situations that involve both Activities and Activity Types where the Activity is known . The person is running and subtler differentiations are occu rring like the runner is running faster and the runner is running up a hill . Referring to Figure 11, if a runner moves from lOkm/hr to 12km/hr 1100 into the classified Activity Type of running in a Tempo zone/speed, their heart rate slowly begins to rise 1102 lagging behind the change in speed . In this case it will take approximately 2 minutes to stabilise 1104 at a heart rate value that accurately reflects the cardiovascular and cardiac effort of 12km/hr.

As shown in Figure 12, the issue also occurs when a runner begins to run up a hill when doing the classified Activity Type of a Medium Hill in their run. As the altitude begins to rise 1200, the effort becomes harder as the user must now move their weight vertically as well as horizontally. Heart rate begins to rise from the flat running state of 130 heart beats per minute to adapt to the uphill running state of 170 heart beats per minute 1202. It takes the heart rate nearly 2 minutes to stabilise for the context to accurately reflect the cardiovascular load on the body 1204. In both cases only the period of heart rate stability and its contextual data (speed, altitude, running cadence) are accepted to represent an Activity Type classified.

These problems affect more than heart rate, they affect all factors that make up cardiovascular and cardiac measures. These include heart rate, heart rate variability, respiration rate, ECG, a nd blood pressure as well as other cardiovascular and cardiac measures.

The system may also be used in a similar way for automated Cardiovascular and Cardiac Event measures of electrocardiography and measurement of blood pressures. In terms of heart function, often heart abnormalities do not occur unless the user's heart rate is elevated and blood pressures change markedly depending on the level of intensity of activity that the user is engaged in . For example, an exercise blood pressure may be 200/70 whereas their resting blood pressure in a low stress environment might be 120/75. In a high stress resting blood pressure, where some people have 'white coat syndrome' meaning their anxiety is increased when a doctor takes their blood pressure, the value maybe 150/100. To know the context that certain Cardiovascular and cardiac Events occur in and then see what the stabilised accurate value is would prove useful . For many users with poor fitness levels, a resting blood pressure of 135/85 for example may be normal at rest but when the user's activity levels are higher in a situation like wa lking up flights of stairs, their blood pressure may become very elevated to 220/115 for example. In this way the user can learn key health insights quickly and early on and what cause these Cardiovascular and cardiac Events due to the context that is also collected along with Cardiovascular and cardiac Event data . In each case, stabilised values ensure greater accuracy of data for analysis, comparison, interpretation and advice.

Due to this cardiovascular and cardiac delay, parametric stabilisation is needed to eliminate all data that occurs before the plateau in heart rate that signifies that the heart rate has adapted to the new effort and thereby accurately reflects the effort required. b. Brief Parameter Changes:

The second reason that Stabilisation is important is that life is not uniform where people move from one clearly differentia ble Activity or Activity Type to the next. Often the user's movements can show multiple Activities or Activity Types at once. Stability is needed to remove as many variables as possible so that data is comparable from one situation to the next. A runner may take a short cut through the park while running. This may seem

inconsequential but a number of changes to the runner's data occurs in comparison to their road running immediately before and after running through the park. The ground in the park is softer under foot than the road so foot strike impact goes down, speed often drops and stride rate often reduces for the same heart rate. If data containing running in the park is compared to standard road running the resultant metrics will be reduced to lower levels affecting analysis of the data.

Another example is a cyclist slowing their speed to time the arrival at an intersection to coincide with a green light. This slowed speed is not useful data as it does not accurately reflect the user's ability. Once again if data obtained while slowing for a traffic light is contained in a segment of data that is compared to data of normal continuous riding, it may skew the interpretations drawn from the data.

Having stringent data capture rules and thresholds to ensure Nike vs like' data comparisons is extremely important. c. Optimal Test Conditions

Often when data is obtained, it needs to be compared 'like vs like'. Often these optimal test situations are brief and sporadic. There might exist a brief window of opportunity when the user is sitting quietly, breathing in a relaxed manner, not long after waking up, on Wednesday and then have to wait till the following Friday to find the same optimised conditions again to record their heart rate variability. It is also difficult for the user to remember to manually capture this data at such infrequent times. Ideally an automatic system is able to find these periods of optimal test conditions a nd initiate data recording automatically. Optimal test conditions are situations where a context is stable and optimal for measurement. Sub Optimal Test Conditions are times when measurement of data is not appropriate. Having a system that ca n differentiate between the two situations is useful . This can also be applied to measured values regarding stationary situations for a user.

To correctly ascertain heart rate va riability, the user must be in an upright posture, breathing slowly and regularly and have been inactive for long enough for the user's heart rate to accurately reflect their stationary nature. This may take 3 mins of inactivity in an upright position, breathing slowly and regularly. The classification senses automatically that all the factors are in place for a classification and the stabilization system waits until heart rate and breathing have stabilised for the situation before allowing a measurement of data for this occurrence. At this point an assessment of the user's heart rate variability can be assessed automatically in a chance situation that occu rs during the user's daily life routine with a 24-hour wearable device. Fatigue, lack of fatigue, stress and relaxation can then be observed.

Pa rametric Stabilization ensures that only data that truly represents the user's actions and physiological reactions to activity are accepted for analysis. This ensures high accuracy of data for analysis.

The effect each type of activity/exercise has on the user's overall fitness, performance or fatigue is different and therefore it is necessary to distinguish between them to provide satisfactory analysis and appropriate feedback/advice. In some embodiments the data once classified is processed ( 130) for the various identified activity types to translate collective data into a tutorial or advice (step 140) for example. The data may be processed with or without the rest of the activity session data . The data relating to a pa rticular activity may be processed against a plan, historic data, an ideal zone (the zone all users would ideally fall under - not specific to the history of the individual but rather applies to all individuals, e.g. an ideal zone for example is a pedal cadence of between 85 and 95 revolutions per minute for all cyclists riding at an easy pace), a threshold or environmental conditions for example. In some embodiments a response is generated from the output of the processing stage which may be advice provided in the form of a prescription (method for modifying a plan) or a solution (method for modifying how a user engages in an activity) for example. The advice may be output (step 150) in either a text, auditory or graphical form as opposed to a visual or auditory display of raw or derived exercise data in real time or post activity. The Advice Generation and Advice Output steps (150) may not be used . The system may be stabilised and analysed and the metrics obtained may be used as part of a wider analysis or comparison at some time in the future.

In one embodiment the data is automatically received by the classification system in one or more streams and then trawled, with the data points being compared against one or more threshold criteria associated with each parameter relating to that stream. This includes alternate data sampling. In an alternative embodiment the system may be arranged to enable a user to manually time stamp a block of data (e.g. by pushing a time stamp or lap split button on a device) and the time stamp block for each monitored parameter is then trawled and compared against the one or more threshold criteria. For both embodiments, corresponding data points of the one or more streams or blocks (that relate to one or more parameters associated with a particular activity) are associated with a particular activity when the system recognizes that the data points satisfy the one or more threshold criteria defining that activity, and therefore associates the

corresponding data points with the activity. Also for both embodiments the stabilization system is applied to ensure the uniformity and comparability of data and therefore accuracy.

2.3 Data Analysis and Insights Once data identification occurs and only stabilised data has been filtered out, analysis of the data can occur. Many different kinds of algorithms can now be applied to the data to gain further Insights. The reason data is often too hard to analyse for insightful information is that the original raw data is not filtered adequately. This makes it impossible to compare Nike with like' data. Parameter or Context Stable data means that data is more uniform and therefore more comparable.

It is preferred that the Parameter Stabilisation Engine is able to automatically analyse the measured data and provide Insights to the user. This could include physiological performance analysis, more accurate comparisons between data sets, situations where medical conditions prove to be worse or improved and accurate information on cardiovascular and cardiac status can be observed.

2.4 Feedback, Schedule Adjustments and Metrics

It is also preferred that the user receives insights gained from the Parameter

Stabilisation Engine.

These insights can take the form of Advice or Feedback which could be delivered in text, symbols, colours, auditory, or contain graphical depictions. A training plan/program or another form of activity schedule like a user's daily routine, could be automatically updated or in a lot of cases, the metrics obtained from the analysis are retained for further use in the future or for manual analysis by a coach or medical practitioner.

Preferably the method further comprises prior to receiving the cardiovascular and cardiac and activity data presenting or downloading onto a device an activity plan or daily activity schedule comprising one or more activities to be performed.

Preferably the method further comprises updating the training program or activity plan for a future activity session based on the response.

Preferably the identification, parameter and context stabilisation, data analysis and insights and feedback, schedule adjustments and metrics are all automated.

2.5 Potential Uses of Parametric Stabilization

Preferably the Parameter and Context Stabilisation system comprises any one or more of measurement of a weight loss activity, activity status monitoring or general activity monitoring, running, walking, cycling, swimming, rowing, kayaking and team sports such as soccer, rugby union and league, ice and field hockey, American football, basketball, baseball and softball, water polo, equestrian, horse racing, handball, netball, lacrosse, skating and cross country skiing. These are also transferrable across other activities like treadmills, rowing machines, elliptical trainers, stationary cycling.

It is particularly applicable to activities that require high degrees of emotional control including surgery, flying, chess, archery, shooting, biathlon, luge, bobsled and many other activities where stress, pressure, emotion and concentration are needed as in high performance activities.

The system may even be used for measuring working environments to ascertain the user's capacities to check for cognitive impairments through fatigue assessment, illness or likelihood of risk of cardiovascular and cardiac events like a heart attack or other more minor heart and blood pressure incidents. If a pilot for example is highly stressed, very fatigued, shows heart abnormalities or is at risk of collapsing due to low blood pressure values; these are all risks to passengers aboard the pilot's aircraft. This would apply to users in dangerous situations like mining or operation of heavy machinery like large diggers or even large trucks on the road. It would also apply to users whose job has the responsibility to keep other people in their job safe. This could be bus drivers, surgeons, military leaders in the field, fire department and paramedic personnel.

It may also be useful for diagnosis of some psychological and sleeping difficulties including sleep apnoea and may be useful in determining long term mental or physical fatigue. This includes fatigue that has occurred for at least more than 4 weeks like Central Nervous system fatigue, Chronic Fatigue and other such diagnoses that imply long term fatigue.

Preferred Embodiment(s)

The system and method of the stabilization invention may be implemented following a Parameter and Context Stabilisation system. This implementation should not be considered as limiting the scope of the invention but rather a preferred embodiment of the underlying classification concept defined above.

3. Detailed Steps Required to Ensure Parametric and Context Stability

There are several data processing steps required to automatically ensure accuracy of data measured from a dynamic system like a human being or animal. These steps are as follows:

Identification

o Activity

o Activity Types

o Cardiovascular and Cardiac Events

Filtering of data

Stabilization

Data Analysis and Insights

Feedback, Schedule Adjustments and Metrics

3.1 Activity Identification:

Activity, Activity Type and Cardiovascular and Cardiac Events are segments of data which can involve a plurality of measurements with respective time stamps for the period of each identified Activity, Activity Type or Cardiovascular and Cardiac Event. Often Activity and Cardiovascular/Cardiac Events only need a single parameter whereas Activity Types always require multiple parameters. The duration, occurrence in time or occurrence in elapsed time is called the first time interval .

Each Activity, Activity Type or Cardiovascular and Cardiac Event uses at least one pa rameter measured for the first time interval within the data received, recorded or sampled or associated to the identified Activity, Activity Type or Cardiovascular and Ca rdiac Event.

Minimum Activity Identification :

Activity and Activity Type Identification is used to determine the type of activity the user is engaged in. Filtering removes wildly aberrant data and stabilisation removes data that ensures that adapting data, fluctuating data and large changes in data are processed accurately. It is the third step, the stabilization process that we will concentrate on as the inventive step.

Activities as has been previously stated can be detected in 2 ways; manually or automatically. a. Manual Activity Detection :

Manual Activity Detection involves a user manually time stamping a segment of data and possibly inputting the label, code or description of the Activity that they are or were engaged in . This could be into a computer remote to the Activity in location, connectivity or time. It could also be a mobile 'all in one' purpose built measurement device. b. Automatic Activity Detection :

Automated Activity detection involves the Activity Detection Engine sensing the Activity. These can be achieved via sensing a single parameter or by contextualising the Activity from multiple parameters. c. Setting Thresholds and Zones to for Identification of Activities, Activity Types and Cardiovascular and Ca rdiac Events:

Thresholds and zones for parameters can be set manually by inputting the upper bound and lower bound for a zone or by inputting values that set a threshold that if data in some cases goes above the threshold and in other cases goes below the threshold, a pa rameter match to the pre-configured Activity Type or Activity Detection settings occu rs.

The system can also learn the thresholds by applying statistical methods to historic data using methods like machine learning and more simple methods like a mean, median, a percentile or confidence limits. d. Single Parameter Sensing :

Determining the Activity from a single parameter is possible in that the Activity Identification Engine determines the Activity based on the sensor it is picking data up from. For an example, knowing that a user is cycling can be as simple as the fact that the users paired cycle sensor is connected and operating. If the user then got on a rowing machine, the fact that the user's device is now connected to their operating rowing machine is indication enough that the user is now using their rowing machine. A further confirmation of the Activity can occur when the Identification Engine receives data that is consistent with a sensed Activity like cycling. For example, sensing cycle sensors like speed and cadence can be confirmed when the speed exceeds 20km/hr and the cadence is above 60 revs per minute. RFID data can also identify a type of sensor and therefore the Activity it measures. e. Multiple Parameter Sensing :

Using multiple sensors to contextualise an Activity can occur where the sensor identification information does not provide adequate data on the Activity's identification. In this case a number of sensors and their data can be used to confirm the Activity.

A GPS speed of below 7km/hr with measures of accelerometer decelerations that are consistent and occur at 130 heavy decelerations per minute of greater than an impact threshold may indicate walking where as a speed of 25km/hr without consistent decelerations and with decelerations of less than the impact threshold may indicate cycling. Other context parameters may include following the path of known roads on a digital map, stopping at street corners on the map, an upper body postural incline that is bent forward and not upright could also be used . f. Activity Identification Parameters Activity Identification uses one or more of the following methods or parameters :

Walking • Accelerometer Decelerations (greater than a set threshold) below 140 per minute

• Stride Rate sensor with stride rate less than 140 steps per minute

• Speed between 0 and 7km/hr (GPS, footpod)

• Walking Sensor ID (sensor has unique ID) Running :

• Accelerometer Decelerations (greater than a set threshold) greater than 140 per minute

• Stride Rate sensor with stride rate greater than 140 steps per minute

• Speed between 7 and 22km/hr (GPS, footpod)

· Running Sensor ID (sensor has unique ID)

Cycling :

• Cycling Sensor ID (sensor has unique ID)

• Motion pattern is consistent with Cycling (one or more of accelerometer, gyro, magnetometer)

· Power Sensor or sports equipment inclinometer present

Rowing :

• Rowing Sensor ID (sensor has unique ID)

• Motion pattern is consistent with Rowing (one or more of accelerometer, gyro, magnetometer)

· Impeller or rowing stroke rate sensor is present

Swimming :

• Swimming Sensor ID (sensor has unique ID)

• Motion pattern is consistent with Swimming (one or more of accelerometer, gyro, magnetometer)

· Swimming stroke rate sensor is present

Kayaking :

• Kayaking Sensor ID (sensor has unique ID)

• Motion pattern is consistent with Kayaking (one or more of accelerometer, gyro, magnetometer)

· Impeller or kayaking stroke rate sensor is present

Skating or Cross Country Skiing :

• Skating or Cross Country Skiing Sensor ID (sensor has unique ID)

Motion pattern is consistent with Skating or Cross Country Skiing (one or more of accelerometer, gyro, magnetometer) Sitting :

Lower body (femur) postural incline is near horizontal (one or more of accelerometer, gyro, magnetometer) Standing : • Body postural incline is vertical (one or more of accelerometer, gyro, magnetometer)

Lying Down :

• Body postural incline is horizontal (one or more of accelerometer, gyro, magnetometer)

Travelling (motorised) :

• User is following tra nsport routes including stops at intersections, stations etc (GPS)

• Motorized equipment sensor ID (sensor has unique ID)

Multiple Parameter Contextualisation would use more than one of the following : Walking

• Accelerometer Decelerations (greater than a set threshold) below 140 per minute · Stride Rate sensor with stride rate less than 140 steps per minute

• Speed between 0 and 7km/hr (GPS, footpod)

• Walking Sensor ID (sensor has unique ID)

• Postural Incline is Upright (one or more of accelerometer, gyro, magnetometer) Running :

· Accelerometer Decelerations (greater than a set threshold) greater than 140 per minute

• Stride Rate sensor with stride rate greater than 140 steps per minute

• Speed between 7 and 22km/hr (GPS, footpod)

• Running Sensor ID (sensor has unique ID)

· Postural Incline is Upright (one or more of accelerometer, gyro, magnetometer)

Cycling :

• Cycling Sensor ID (sensor has unique ID)

· Postural Incline is leaning forward (one or more of accelerometer, gyro, magnetometer)

• User is following roads, and stops at intersections (GPS)

• Speed is greater than 20km/hr (GPS, Cycle speed sensor)

• Wind Speed is greater than 20km/hr (Anemometer, Pitot tube)

· Power Sensor or sports equipment inclinometer present

Rowing : • Rowing Sensor ID (sensor has unique ID)

• Postural Incline - user is seated (one or more of accelerometer, gyro, magnetometer)

• User is facing backwards to direction of movement (magnetometer)

• Accelerometer decelerations are between 0 and 45 per minute

• Impeller or rowing stroke rate sensor is present

Swimming :

· Swimming Sensor ID (sensor has unique ID)

• Postural Incline - user is lying flat or nearly flat (one or more of accelerometer, gyro, magnetometer)

· Accelerometer decelerations consistent with swimming stroke rate

• User is immersed in water (two sensors use water to complete circuit)

• Swimming stroke rate sensor is present

Kayaking :

• Kayaking Sensor ID (sensor has unique ID)

· Motion pattern is consistent with Kayaking (one or more of accelerometer, gyro, magnetometer)

• Accelerometer decelerations consistent with kayaking stroke rate

· Impeller or kayaking stroke rate sensor is present

Skating or Cross Country Skiing :

• Skating or Cross Country Skiing Sensor ID (sensor has unique ID)

• Motion pattern is consistent with Skating or Cross Country Skiing (one or more of accelerometer, gyro, magnetometer)

· Speed is consistent with Skating or Cross Country Skiing (GPS)

• Accelerometer decelerations consistent with skating or cross country skiing limb turnover rate

· Temperature, Time of year and location could also be used for Cross Country

Skiing

Sitting : • Upper Body Postural incline is upright (one or more of accelerometer, gyro, magnetometer)

• Lower body (femur) postural incline is near horizontal (one or more of accelerometer, gyro, magnetometer) Standing :

• Upper and lower body postural incline is vertical (one or more of accelerometer, gyro, magnetometer)

Lying Down :

• Upper and lower body postural incline is horizontal (one or more of accelerometer, gyro, magnetometer)

Travelling (motorised) :

• Upper Body Postural incline is upright (one or more of accelerometer, gyro, magnetometer)

• Lower body (femur) postural incline is near horizontal (one or more of accelerometer, gyro, magnetometer)

• Speed is above 20km/hr (GPS, Speed sensor)

• User is not in proximity of work or home (GPS)

· Motorized equipment sensor ID (sensor has unique ID)

Other sensors may also be used . Some may require more than one sensor fixed to more than one pa rt of the user's body. Postural incline for example may involve multiple sensors whose data is fused to generate a 'position' of the user. If the user's posture is upright and their thigh is at right angles to their upper body, it can be inferred that the user is sitting.

The parameters outlined above make up activity parameters used to describe an Activity or Activity Type and can be combined with still other parameters like heart rate, power, speed, respiration rate, slope, incline, gradient, change in altitude and many more to further improve accuracy of activity identification.

Data for Activity Types occurs as a plurality of measurements with respective time stamps which are associated to at least one parameter occurring over the duration, distance or period of the activity which is referred to as a first time interval. This can also occu r for Activities and Cardiovascular/Cardiac measures but these can both equally rely on a single parameter. 3.2 Activity Type Identification:

a. Minimum Activity Type Identification :

Activity Types are described by more than one parameter simultaneously conforming to a set of zones or thresholds that describes an Activity Type. An Activity Type of exercise involves an Activity Identification Engine that classifies activities within walking, running, cycling, horse training and activity status monitoring categories. For example, the running category is classified with easy, rolling hills, hills, long climbs, hill efforts, up tempo, anaerobic threshold, sprint and overspeed activities. Any combination of parameters such as speed, heart rate, power, respiration rate, heart rate variability, turnover, distance per turnover, vertical meters ascended, slope, gradient and incline can be used to depict a particular classification.

Two important measures for Activity Types are Effort and Resistance measures. These measure the user's cardiovascular and cardiac and muscular resistance effort. Muscular effort in most activities involves parameters such as terrain, distance per limb turnover (e.g. distance per stroke, stride length) or alternatively the limb turnover (e.g. stride rate, pedal cadence) for a given cardiovascular and cardiac effort (e.g. speed, power, heart rate).

Effort parameters include speed, heart rate, power, respiration rate and heart rate variability.

Muscular and Alternative Effort Parameters:

In the case of a cyclist, with a power meter, power output can be compared to heart rate. If heart rate specific to the load is dropping, then the user is getting fitter. If heart rate is higher for the power output, the user is less fit or fatigued.

Biomechanical Parameters:

Optimal heart rates can be determined in terms of stride rate. As stride rate increases heart rate increases and the heart rate to stride ratio increases as the body becomes more and more inefficient at producing speed for an increase in stride rate.

Postural Status:

Heart rate variability requires the user to be at rest, their resting position to have occurred for long enough that their physiology accurately reflects the activity, their breathing to be slow and to closely match breathing on previous measurement occasions and the posture to be upright. Finally, it is preferred that values taken also occur at approximately the same time of the day each time. To achieve this automatically, the system must be able to detect that each of these situations is occurring and stable to then take the measurement. Another cardiovascular and cardiac example is when a user is engaged in doing some speed training . For example, they may have to run at 12km/hr for 2 minutes. When a user conducts this form of training, they accelerate to 12km/hr and it takes their hea rt rate lmin to rise to correctly reflect their effort. At the end of the 2 minutes, they slow back down but it takes another l min for heart rate to drop to reflect the easier effort. To analyse this data from a speed perspective, you collect data as soon as the user is running at 12km/hr. The problem with this is heart rate is still rising for the whole of the first one minute of the two-minute speed effort. So 50% or one out of two minutes of the speed training has inaccurate data because the heart rate was still rising . Any estimates of heart rate during the speed training will be underestimated due to the one minute of lower heart rates that were measured while heart rate was still rising . The stabilisation system must delete the first minute of the speed training because heart rate had not stabilised to accurately reflect the effort till the end of the first minute of the speed training. Ca rdiovascular and Cardiac effects can include: Effort Scenarios :

Understanding heart rate, heart rate variability, oxygen uptake, respiration, heart function including ECG, blood pressure, oxygen saturation and elements of blood glucose and cholesterol are all best understood when contextualised with other factors.

All these areas, if automatically determined, require some form of understanding of outside factors that contribute to the measure. These include the muscular effort, the user's posture, whether they were likely to be awake or asleep and what the surrounding environment was.

If the user is exercising intensely, heart rate will be elevated, HRV will be very uniform, oxygen uptake will be high, and in cases where heart disease is present, heart function may become more erratic than a user's resting values, systolic blood pressure will go up, and diastolic blood pressure may remain the sa me, increase or decrease. Long periods of exercise may cause blood glucose to become decreased . Similarly, many health measures are taken when the user is at rest. But what is rest? The user in some cases is best to be lying down, in other cases sitting up and in still other cases standing . This is also time dependent. A resting heart rate is best determined as soon as a user wa kes in the morning while still lying down. Hea rt rate variability is often recommended just after the user has woken but when they are standing or sitting upright and inactive for a period of somewhere between one and three minutes.

To automatically determine many of these ca rdiovascular and cardiac values, a system must be able to not only detect the data being primarily sensed but they must also be able to detect the situation in context to accurately classify the data and know when it is best to take a measurement.

A stabilisation period of up to 6 minutes may be required to measure accurate

cardiovascular and cardiac data although often periods of 3 to 4 minutes will suffice. The system may also learn the correct period of time by repeatedly determining the adaption time and then applying the average time. Further the system may measure only when data plateaus indicating stabilisation. b. Activity Type Parameters Activity Parameters can be combinations of at least two or more of the following pa rameter groupings being Effort Parameters, Resistance Pa rameters, Biomechanical Pa rameters, Postural Parameters, Sleep Parameters and Movement Parameters.

Effort Parameters:

Ca rdiovascular and Cardiac Data Parameters:

1. Hea rt Rate

2. Hea rt Rate Variability (AVNN, SDNN, SD1, SD2, HF, LF, RMSSD, pN N50, Total Power)

3. Oxygen Uptake

4. Respiration rate

5. Oxygen Saturation (Blood, Muscle or Skeletal)

6. Electroca rdiograph waveform

7. Blood Pressure (directly measured or inferred)

Physica l Data :

Work and Alternative Effort Parameters:

1. Power Output/Energy Expenditure

2. Force/ Acceleration

3. Electromyography (muscle contraction, recruitment & use) 4. Weight lifted or carried (including speed of movement & acceleration)

Speed :

1. Speed/Velocity

2. Pace

Resistance Parameters :

Terrain :

1. Terrain based on Altitude (barometer, GPS, DEM) including slope, gradient and incline

2. Wind Drag

Limb Turnover and Distance per Limb Turnover

1. Stride rate, cadence, stroke rate

2. Stride length, distance per pedal stroke, distance per stroke

Biomechanical Parameters :

1. Vertical Oscillation (running, wa lking, cross country skiing, skating)

2. Foot strike impact

3. Foot strike time on the ground

4. Foot strike patterns (pronation, supination)

5. Limb Turnover (stride rate, cadence, stroke rate)

6. Dista nce per Limb Turnover (distance per pedal turn or stroke, stride length)

Postural Parameters:

1. Postural Status - Leaning

2. Postural Status - Slouching

3. Postural Status - Bending over

4. Postural Status - lying on back

5. Postural Status - lying on front

6. Postural Status - lying on right side

7. Postural Status - lying on left side

8. Postural Status - standing

Sleep Parameters:

Sleep Parameters: (including accelerometer & EEG measures)

1. Awake lying down

2. Awake standing up

3. Awake sitting up

4. Awake walking

5. REM sleep

6. Light Sleep 7. Deep Sleep

8. Sleep phases 1, 2, 3 and 4

Movement Parameters :

Multi-axis Movement Pa rameters:

1. Vertical impact

2. Horizontal impact

3. Arm horizontal punching

4. Arm above head, vertical punch

5. Arm above head down laterally to waist

6. Arm above head, down frontally to waist

7. Arm wind milling forwa rd/back

8. Arm bend at elbow straight to shoulder

9. Knee bend, knees together

10. Knee bend, legs wide

11. Lateral leg swing

12. Frontal leg swing

13. Heel to buttock leg curl

Biomedical Parameters:

1. Body temperature

2. Blood glucose

3. Blood cholesterol

4. EEG measurements

5. Hydration levels (perspiration quantity, rate) Environmental Parameters :

1. Altitude (ba rometer, GPS, DEM)

2. Temperature

3. Humidity

4. Wind Speed

5. Air Pressure (barometer)

All derivations of the above parameters are included and this also includes measured changes in the above parameters,

Activity Type data occurs as a plurality of measurements with respective time stamps which a re associated to at least one activity parameter occurring over the duration, distance or period of the activity which is referred to as a first time interval. c. Calibration of Effort (Effort Index)

Heart rate, speed and power thresholds and or zones that represent a Cardiovascular Effort Index need to be established for cardiovascular effort with a minimum of user work to complete.

There a re many ways a nd tests used to define these thresholds or zones for heart rate, speed and power. Different methods include using a maximum value tested or obtained from within training or activity, using the Anaerobic or Aerobic Threshold value, or using averages based on the activity or exercise of the user, using heart rate variability to establish cardiovascular stress, using respiration rate, perceived exertion ( PE), lactate thresholds, ventilatory thresholds, critical power and many more.

Anaerobic Threshold is a term that has poor standardisation in sports science literature. In this case, Anaerobic Threshold implies the maximum effort as user can sustain for 20 minutes to one hour. For completeness of explanation, anaerobic threshold may in this case be taken to mean Onset of Blood Lactate Accumulation, Lactate Turn point, Maximum Lactate Steady State, Function Threshold Power and other terms applied to the same concept.

Ca rdiovascular Effort usually uses speed, power or heart rate but could also include respiration rate and heart rate variability measures. To ascertain effort by measuring speed, power or heart rate they must be individually calibrated to the user. This is because a heart rate of 160 beats per minute represents different effort levels for different people. Likewise, a speed of 12km/hr or a power output of 250 watts also represent different effort levels for different people.

The above monitored effort parameters and in particular the threshold criteria are only exemplary and reflect possible embodiments of the invention. They are not intended to be limiting. It is preferred in fact to have variations on the threshold criteria (and zones) for each individual as the system may be calibrated to their specific ability and needs.

Set out below is an example of how effort zones can be calibrated. Initial Calibration

Exercise, activity or training zones/criteria may be calibrated to the individual so the zones conform to match correctly what the user experiences. The traditional calculations (e.g. 220- age in years and the Karvonen formula) and then percentages set against them which are used to determine the zones a re only correct in 60% of individuals so another form of a more individualised assessment is preferably performed during a user's activity. One way to achieve this assessment is to establish what the user's Anaerobic Threshold is in a method that is safe for the user and not too complicated or invasive to the user's activity.

Anaerobic Threshold (AT) is a well-known metric in exercise physiology that implies the maximum effort that a particular individual can exercise at for a pa rticular period of time (e.g. 20 minutes to 1 hour) depending on their fitness. This can be at a heart rate of 170- 180 beats per minute for one individual with a high heart rate and high Anaerobic Threshold or can be 140 - 150 for an older individual with a low Anaerobic Threshold for example. AT can similarly be measured with speed and power. There are preferably four systems to determine AT due to the fact that it must be compatible across a wide range of hardware platforms each using different sensor data .

Heart Rate Calibration System :

User heart rate data is collected each time the user exercises. A generated histogram records the number of incidences of a heart rate within a specific range (e.g. 170 - 175). Each range forms an 'incidence bin' that contains a count of all heart rate data that falls between the bins range. Some ranges will be empty with no data and therefore inactive. Of the remaining active incidence bins the highest change in incidences of a heart rate falling into the highest 3 histogram range bins that are activated denotes the 'Anaerobic Threshold' heart rate zone. The system can do this assessment as a calibration workout or can do this for every workout and constantly update itself.

Power Calibration System:

The user exercises and their power data is collected each time they exercise and generated into a histogram. The histogram records the number of incidences of a heart rate within a specific range (e.g. 170 - 175) . Each range forms an 'incidence bin' that contains a count of all heart rate data that falls between the bins range. Some ranges will be empty with no data and therefore inactive. The highest change in incidences of a power falling into 'histogram bins' in the top 3 histogram bins that are activated denotes the 'Anaerobic Threshold' power zone. The system can do this assessment as a calibration workout or can do this for every workout and constantly update itself. Once again AT power is not the same for everyone, it is highly individualised . This can be at a power of 240 watts for one individual or 120 watts for another for exa mple. In each case the training zones can be extrapolated through algorithms for each intensity level . Speed Calibration System :

The same system is applied as above to speed with several minor modifications (e.g . speeds are only assessed on the flat) to achieve the same goal. The same concept may be applied to respiration rate (and some heart rate derivatives, cadence or turnover and distance per turnover) .

Once the AT zone has been identified, in each case all the other activity/training zones can be extrapolated through algorithms for each intensity level.

If the AT is assessed for every workout so that it consta ntly updates, which is the preferred embodiment, there are contingencies set for accepting new data that updates the historic AT zone and therefore all other activity zones. Data that falls outside being less than 90% of the maximum historic AT value or more than 105% of the maximum historic AT value is deleted and not used to update the historic AT value which is an average of accepted historic AT values for each workout. d. Manual Activity Type Detection :

As with Activity Detection, Activity Type Detection can be recorded and potentially la belled manually as well as automatically. e. Number of Pa rameters Used

Activity Type Detection always requires more than one parameter. f. Activity Type Examples:

After effort has been calibrated to the user it is possible to set up thresholds and zones based on the effort calibration index. Activity Types are described by multiple simultaneous thresholds or zones that describe an Activity Type.

Set out below is a description of how Activity Types are described :

1. Walking, i .e. an individual moving at a speed below 8km/hr. One monitored

parameter and threshold criterion used to identify an individual walking ca n be a stride rate of less than 66 strides per minute. Alternatively, or in addition, an effort/intensity measure/ parameter more closely associated with the user's own ability may be used to classify walking . The threshold criteria for such a parameter may be a user heart rate (HR) of less than 60% of their maximum heart rate, and/or of less than 70% of their Anaerobic Threshold (AT) HR. Effort may alternatively or in addition be measured using speed and/or power, in which case the threshold criteria for walking may be less than 60% of the individual's AT speed and/or less than 60% of their AT power respectively. In addition to any combination of the above parameters and their threshold criteria, a flat terrain criterion is required by the classification system to identify a walking activity. In which case, the system may define a flat terrain for walking as an upward slope of less than 2° (or 4% gradient where consistent altitude (allowing for edge forgiveness - discussed in more detail in the Parameters section) cannot amount to more than a 6-meter altitude gain). A downward slope of as much as 8.5° ( 16% gradient) may also be regarded as a walking activity as would any uphill that fails to qualify as a hill (less than a 6 meter climb).

Easy running, i.e. jogging at 8 - 10 km/hr (for most people). One monitored parameter and threshold criterion used to identify an individual easy running can be a stride rate of greater than 70 strides per minute. Alternatively, or in addition, an effort/intensity measure/parameter more closely associated with the user's own ability may be used to classify walking. The threshold criteria for such a parameter may be a user heart rate (HR) of 65 - 75% of their maximum heart rate, and/or of 70 - 80% of their Anaerobic Threshold (AT) HR. Effort may alternatively or in addition be measured using speed and/or power, in which case the threshold criteria for easy running may be 60 - 90% of the individual's AT speed and/or 60 - 90% of their AT power respectively. In addition to any combination of the above parameters and their threshold criteria, a flat terrain criterion may be required by the classification system to identify a walking activity. In which case, the system may define a flat terrain for easy running as an upward slope of less than 2° (or 4% gradient where consistent altitude (allowing for Edge Forgiveness - discussed in more detail in the Parameters section) cannot amount to more than a 6-meter altitude gain). A downward slope of as much as - 8.5° (-16% gradient) may also be regarded as an easy running activity as would any uphill that fails to qualify as a hill (less than a 6-meter climb).

Flat terrain muscularly loaded activity (for example a big gear at a low cadence on a bike on the flat) - this classified activity is related to cycling and not

walking/running as for the above two. One monitored parameter and threshold criterion used to identify an individual performing a muscularly loaded activity can be a big gear (e.g. 52x16). This parameter may be measured by distance travelled per pedal revolution with a threshold criterion of 65-75 pedal revolutions per minute. Alternatively, or in addition, a threshold criterion of 85 - 130% of the AT distance per pedal turnover may be used. An effort/intensity

measure/ para meter more closely associated with the user's own ability may also or alternatively be used to classify a muscularly loaded activity. The threshold criteria for such a parameter may be a user heart rate (HR) of 65 - 75% of their maximum heart rate, or of -70-80% of their Anaerobic Threshold (AT) HR. Effort may alternatively or in addition be measured using speed and/or power, in which case the threshold criteria for flat terrain muscularly loaded may be 65 - 90% of the individual's AT speed and/or 65 - 90% of their AT power respectively. In addition to any combination of the above parameters and their threshold criteria, a flat terrain criterion is required by the classification system to identify a flat terrain muscularly loaded activity. The system may define a flat terrain for this activity as an upward slope of less than 2° (or 4% gradient where consistent altitude (allowing for Edge Forgiveness - discussed in more detail in the

Parameters section) cannot amount to more than a 6-meter altitude gain). A downward slope of as much as -2° (-4% gradient) may also be regarded as flat terrain for a muscularly loaded activity.

Hills - This activity occurs when an individual increases their altitude during exercise/activity. The threshold criteria required to classify an activity under Hills can be a continuous rise over time that exceeds a 6 meter vertical gained from the flat, or a continuous slope of 2° or more (more or less) for more than 70 sees the more or less' in the above refers to our 'edge forgiveness' system that will allow some out of zone/threshold values if the data falls back within zone or threshold criteria within a short period of time).

Speed - i.e. running at 12 km/hr or more (for most people). One monitored parameter and threshold criterion used to identify a speed activity can be a stride rate of greater than 70 strides per minute. Alternatively, or in addition, an effort/intensity measure/ parameter more closely associated with the user's own ability may be used to classify speed activities. The threshold criteria for such a parameter may be a user heart rate (HR) of more than 75% of their maximum heart rate, and/or of more than 80% of their Anaerobic Threshold (AT) HR. Effort may alternatively or in addition be measured using speed and/or power, in which case the threshold criteria for speed activities may be more than 90% of the individual's AT speed and/or more than 90% of their AT power respectively. In addition to any combination of the above parameters and their threshold criteria, a flat terrain criterion may be required by the classification system to identify a speed activity. In which case, the system may define a flat terrain for speed as an upward slope of less than 2° (or 4% gradient where consistent altitude (allowing for Edge Forgiveness - discussed in more detail in the Parameters section) cannot amount to more than a 6-meter altitude gain). A downward slope of as much as - 2° (-4% gradient) may also be regarded as flat terrain for a speed activity.

There may be many different ways to classify an activity. Any combination of parameters such as speed, heart rate, power, turnover, distance per turnover, R-R (HRV), vertical meters ascended, slope, gradient can be used to depict a particular classification. Furthermore, there can be many ways to define the threshold or zone for each of these using a maximum value tested or obtained from within training or activity, using the Anaerobic or Aerobic Threshold value, or using averages based on the activity or exercise of the user etc.

Classifications can simply be time based. For example, time periods of one hour, one day, one week, one month, one year and other time periods can be used for

classification. The above monitored parameters and in particular the threshold criteria are only exemplary and reflect possible embodiments of the invention. They are not intended to be limiting. It is preferred in fact to have variations on the threshold criteria (and zones) for each individual as the system may be calibrated to their specific ability and needs. 3.3 Cardiovascular and cardiac Event Identification:

Minimum Cardiovascular and Cardiac Event Detection

A Cardiovascular and Cardiac Event involves relating cardiovascular and cardiac data to other physical or external data to contextualise the status of a user. The status of the user can include effort, stress, fatigue and improved energy or performance levels and other biomedical events during the activity.

The single parameter for Cardiovascular and cardiac Event detection is heart rate, heart rate variability and its derivations like RMSSD and SD1, respiration rate (directly measured and derived from heart rate), oxygen saturation (blood, muscle, skeletal), blood pressure, and ECG anomalies.

The user's device is measuring at least one of these parameters and a Cardiovascular and cardiac Event occurs which might be:

Excessively high heart rate or change to excessively high heart rates

Excessively low heart rate or change to excessively low heart rates

Unusual heart rate compared to recent history

Inconsistent heart rate

Excessively high heart rate variability or change to excessively high heart rate variability

Excessively low heart rate variability or change to excessively low heart rate variability

Unusual heart rate variability compared to recent history

Inconsistent heart rate variability • Excessively high blood pressure or change to excessively high blood pressure

• Excessively low blood pressure or change to excessively low blood pressure

• Excessively high respiration rate or change to excessively high respiration rates

• Excessively low respiration rate or change to excessively low respiration rates · Inconsistent respiration

• ECG anomalies or change to ECG anomalies including ECG feature extractions such as the peak amplitude, area under the curve, displacement in relation to baseline of the P, Q, R, S and T waves,-the time delay between these peaks and valleys, and heart rate frequency (instantaneous and average). In each case a snapshot or recording from data from other sensors could be used including :

• Altitude

• Speed

• Heart rate

· Heart rate variability

• Blood pressure

• Oxygen saturation (blood, muscle, skeletal)

• Respiration rate

• ECG wave form

· Temperature

• Humidity

The above factors could be measured over time with a metric based on this like mean, median or other statistical values and could also be combined with other preceding data like cumulative vertical meters ascended, past sleep durations, past sleep quality durations, activity intensity and activity durations above or below a particular intensity threshold.

Automatic or Manual Process for Identification of Activity, Activity Types and

Cardiovascular and Cardiac Events:

The data to identify an Activity, Activity Type or Cardiovascular and Cardiac Event may be received and trawled automatically or alternatively the system is arranged to enable a user to manually time stamp a block of data by pushing a time, distance or location stamp or lap split button on a device and the time stamp block for each monitored parameter is trawled and compared against one or more threshold criteria. A time stamp may be based on time, distance or location.

Parameters that may be recorded along with a Cardiovascular and Cardiac Event: External data parameters that may be recorded, sampled or received simultaneously, or for a period immediately before the Cardiovascular/Cardiac Event or for a period immediately after the Cardiovascular/Cardiac Event include other Cardiovacular/caridac Parameters, Resistance parameters, work and alternative effort parameters, speed parameters, limb turnover and distance per limb turnover parameters, biomechanical parameters, postural parameters, sleep parameters, terrain parameters, environmental parameters, and multi axial movement parameters used as at least a second parameter to combine with and contextualise cardiovascular/cardiac status. Work/Alternative Effort parameters, Speed parameters, and Limb Turnover and Distance per Turnover parameters include power output, lifting a weight, generating force, distance per turnover or changes in power output, weight, force, and distance per turnover. These also include speed or change in speed, pace or change in pace, energy expenditure or change in energy expenditure and energy intake or change in energy, body weight and carried weight or changes in body weight or carried weight, acceleration or changes in acceleration and muscle contraction via electromyography or changes in muscle contractions. This includes identified periods of low work or speed and no work or speed. Derivations of these parameters are also included. The biomedical parameters include body temperature or change in body temperature, blood glucose or changes in blood glucose, blood cholesterol or changes in blood cholesterol and EEG or changes in EEG. Also included are hydration levels and changes in hydration levels. Derivations of these parameters are also included. Biomechanical parameters include vertical oscillation during walking or running, foot strike impact, time on the ground, limb turnover, distance per limb turnover, and foot strike patterns included measured changes in these parameters. Derivations of these parameters are also included. Postural status parameters include standing, sitting, and lying. Extra values include leaning, slouching, bending over, lying on back, front or side. This may also be linked to indications of inactivity in one of the types of postural status. Derivations of these parameters are also included. Terrain parameters include altitude or a change in altitude, slope or change in slope, gradient or change in gradient, incline or change in incline, user location or a change in user location, location of a target object or change in location of a target object, heading direction, direction the user is facing. Derivations of these parameters are also included. Environmental parameters include ambient temperature, relative humidity, barometric pressure, heat index, local wind speed, local wind direction, local rain, local altitude or changes in ambient temperature, relative humidity, ba rometric pressure, heat index, local wind speed, loca l wind direction, local rain, local altitude. Derivations of these pa rameters are also included .

Sleep parameters may include awake lying down, awake sitting up, awake standing up, awake walking, light sleep, deep sleep, REM sleep, PSG or Phases 1, 2, 3 and 4. It also involves changes in awake lying down, awake sitting up, awake standing up, awake wa lking, light sleep, deep sleep, REM sleep, or Phases 1, 2, 3 and 4. A number of these are based on data from more than one sensor. Derivations of these pa rameters are also included .

Alternate ca rdiovascular and cardiac parameters able to be included in combination from Ca rdiovascular and cardiac Event parameters include heart rate or change in heart rate, heart rate variability or change in heart rate variability, respiration or change in respiration, ventilation or changes in ventilation, oxygen uptake or change in oxygen upta ke, and oxygen saturation or changes in oxygen saturation . Inferred data and derivations of these parameters are also included .

Multi axial movement parameters a re combinations or sequences of multi axial movement used to predict a body or limb movement. They may also deal with indications of inactivity. Derivations of these pa rameters are also included . All the data may be automatically or manually linked to an external event such as a medical event, type of exercise, or type of activity in daily life.

A Cardiovascular and Cardiac Event may include heart attacks, strokes, angina, blood pressure, electrocardiograph arrhythmias, oxygen saturation levels (blood, muscle, skeletal), respiration rate and heart ectopic's and other forms of biomed ical status.

Ca rdiovascular and Cardiac Events must be recorded over a time period of more than 10 seconds. For example, multiple heart ectopics must be present, blood pressure must be consistently high for a minimum time period. This ensures that there are no mistakes in the data measures.

Data may not be recorded continuously and may involve periods of sampling between periods of non-recording or classification of activity. Cardiovascular and Cardiac Event Data occurs as a plurality of time stamped measurements and is referred to as the second time interval. The occurrence in time, occurrence in elapsed time or the duration the Cardiovascular and Cardiac Event occurs which is referred to as the second time interval may not be the same as the occurrence in time, occurrence in elapsed time or the duration of an Activity or Activity Type which may or may not be associated with it which is the first time interval.

3.4 Data Handling:

Preferably the processor is further arranged to group consecutive data points classified under the same parameter stabilisation identification to define an instance of the stable cardiovascular and cardiac data and/or physical data, the number of consecutive data points being indicative of a duration of the instance of the effort activity.

Preferably the processor is arranged to process the cardiovascular and cardiac data and/or physical data upon or after receiving the data for activity or inactivity.

The data may be received in time stamped blocks and the processor may be arranged to utilize the one or more parameter stabilisation identifications to process one or more of the time stamped blocks of data and identify a period of parameter stability during each of the one or more blocks.

The cardiovascular and cardiac and/or physical data sensors may be configured to automatically activate and measure data and potentially deactivate upon measurement completion to conserve device battery life when sensors for physical and external data meet one or more pre-determined or machine learned thresholds or configurations. Alternatively, the processor can power down to a low power mode rather than deactivating and still detect periods of data stabilisation where more sensors are activated. Further to identification of periods of data stability, measured cardiovascular/cardiac and physical parameters can be combined with at least one other measured external data parameter to identify and classify a type of activity or inactivity associated with the period of data stability. An activity classification system involves relating cardiovascular/cardiac and physical data to other physical or external data to contextualise the status of a user during the activity. The status of the user can include effort, stress, fatigue and improved energy or performance levels and other biomedical events during the activity. Preferably the step of utilizing the classification system further comprises grouping consecutive data points classified under the same activity to define an instance of the activity during a period of activity or inactivity, the number of consecutive data points being indicative of the duration of the instance of the activity.

The data is received during the activity session and the step of utilizing the stabilisation system is performed simultaneously during the measured session. This may also occur for the Activity Identification system.

3.5 Filtering:

Raw data from sensors is often affected by inaccuracies. GPS data can be highly unstable particularly when the user doesn't have a clear view of the sky in say a forest or in a city where there are many high rise buildings. Heart rate can be affected by dry skin so the sensor contact is broken and by other nearby electrical activity. Sensors like photocells (PPG) and straps used to determine respiration can have data inaccuracies once movement becomes more extreme. The data must often be filtered. Various methods include smoothing, averaging, using a median, high and low pass filters and Kalman filters. Fundamentally the data must be filtered to a point where large erroneous swings or spikes in data have been removed from the data stream. This can occur in real time or post activity. This is common and is currently known in the state of the art.

Filtering involves 'cleaning' data that has too much 'noise' if left in a raw state. Filtering can include among other techniques, smoothing and high and low pass filters. This means aberrant data is removed from the raw data so that only good quality data remains.

For example, minimum data filtering might be smoothing of data using averages or medians to reduce the effects of sudden changes in data due to inaccuracies in sensor measurements.

3.6 Stabilization:

Biological systems are dynamic and incur an adaption phase and stabilization phase in response to new activities. In short, stabilisation is used to allow a human user or animal to settle into a new activity before measurements of the activity are taken. This is needed because a user's physiology will often take time to adapt to the activity before it truly reflects the requirements of the activity. A simple example of this is heart rate when a user moves from walking to running. The change in velocity is virtually instantaneous but the heart rate lags behind taking between one and six minutes to settle at the values that truly reflect the user's effort. For this reason, stabilisation of data is important in the process of obtaining accurate data on an activity. The adaption phase occurs as the system works to adapt to the new form of activity. Often this does not accurately represent the requirements of the new activity. For example, as a human or animal moves from a higher to lower intensity or vice versa, their cardiovascular/cardiac system is slower to react. During the stabilization phase the body's processes have now stabilised to accurately reflect the requirements of the new activity. For example, as intensity increases, power and speed change immediately but the cardiovascular/cardiac system parameters like respiration, heart rate and heart rate variability are slower to react and may take up to six minutes to truly stabilise at the new activity level in a way that the data truly reflects the new activities requirements and is uniform.

This can be taken still further where heart rate is at its lowest in the early hours of the morning even though the person sleeping has been lying in bed for six hours prior to this. To take this still further, the heart rate values can also be affected at this time of the night depending on whether the person sleeping is engaged in light or deep sleep at the time.

Once an activity is detected, it often takes time for physiological processes to adapt to the situation, so that the physiology truly reflects the physiological reaction to the activity.

The primary drivers for this analysis are relationships between cardiovascular/cardiac function, behaviour and effort, muscular effort, posture, sleep and the environmental factors. It is very important to automatically detect these differences in a user's activities and ensure that the data used for analysis is accurate enough to ensure high confidence in the interpreted results. a. Stabilization Parameters: Each parameter used in Parameter Stabilisation involves Cardiovascular/Cardiac data and/or Physical Data. Physical Data means an action that a human or animal is initiating with at least one of the following of muscles, limbs and or posture.

Other data such as Environmental Data may also be included.

Minimum Cardiovascular/Cardiac parameter measures are:

• Heart Rate (including determination by Photoplesmography or PPG)

• Respiration (direct or indirect through ECG QRS identification)

• Blood Pressure (Resting and Exercise)

· Heart Rate Variability (HRV, R-R, includes PPG)

• Oxygen Saturation (blood, muscle, skeletal)

• Electrocardiograph waveform

Minimum Physical Data :

• Power output (direct or indirect)

· Electromyography

• Turnover (stride rate, cadence, stroke rate)

• Distance per turnover (stride length, distance per pedal turn or stroke)

• Speed/Velocity

• Pace

· Postural incline

• Degree of Activity (motion)

• Incline, gradient, slope or change in altitude

Each parameter mentioned occurs as a plurality of measurements with respective time stamps for Activity Types but may only rely on one or more parameters for activities and Cardiovascular/Cardiac Events. b. Relationships Between Different Types of Data

Cardiovascular and Cardiac data or Physical Data parameters are compared to a lower threshold, upper threshold, threshold range or zone and data that meets threshold or zone criteria is regarded as stable. All data that meets the threshold or zone criteria and occurs either entirely or predominantly above or below the threshold or within the zone occurs as a plurality of time stamped stable data.

First Time Interval :

A stable data time interval may not be the same and is most unlikely to be the same as the Activity, Activity Type or Cardiovascular/Cardiac Event data time interval. This means that the stable data time interval is very unlikely to occur for the full duration of the first time interval. (The period, time or elapsed time where an Activity, Activity Type or Ca rdiovascular/Cardiac Event occurs.)

Second Time Interval :

A Stable Data time interval is unlikely to have the same time interval as all the

Ca rdiovascular/Cardiac Data or Activity and Activity Type Data recorded because they contain data that is both stable and unstable. This means it is unlikely that the stable data time interval is related entirely to the second time interval . (The period, time or elapsed time when all the Cardiovascular and cardiac or Activity data occurs.)

Third Time Interval :

The stable Cardiovascular/Cardiac or Activity Data will be a subset of the second time interval data and occurs as a third time interval composed entirely of parametric stable, context stable or cardiovascular and cardiac stable data . Other parameter data may be collected in conj unction with stable cardiovascula r and cardiac or Activity Data which is characterised by the third time interval and occurs during the third time interval. c. Manually Set Stabilization Thresholds and Zones :

Preferably, an upper or lower threshold or zone for each para meter is used . Data may occu r outside thresholds for an appropriate maximum time period and still be accepted as a qualified segment. Stabilization thresholds and minimum or maximum time stabilization periods can be configured through a user interface or a processor can be configured to adjust the threshold automatically.

d. Automatically Set Stabilization Periods:

A period of time or dista nce of stabilised data q ualifies the data for use in analysis. Data stabilisation systems can be automatically set by the Parameter Stabilisation Engine where va rious stabilisation periods are set based on ;

· Historic periods that show greater stability for a parameter

• Rules that suggest a stability range based on the variability of the data e. Qua lified Period of Stabilization

A minimum stabilization period is used to specify the minimum period of time that Parameter Stability must occur for the Parameter Stability Engine to accept that received data is stable. This is because data may become stable for brief amounts of time like 3 seconds or 15 seconds which does not adequately reflect purposely stable data and reflects more coincidences in data stability during non-stable fluctuations. Preferably the stabilised data occurs where one or more streams of data must remain uniform and not exceed one or more thresholds or zones for a minimum qualifying period . This might be 1 minutes 30 seconds for a user who has been similarly active for more than 10-20 minutes. It may take 4 to 6minutes for a user starting from a resting status. Fitter people often take longer to stabilise than less fit people. The stabilization period could be set alternatively as a distance or some other period. A user interface can be configured to obtain from the user, adjustments to the duration or qualifying duration of the stable duration (third time interval) for each Cardiovascular/Cardiac and Physical Data pa rameter or a processor can be configured to adj ust the duration or qualifying duration (third time interval) for each Ca rdiovascular/Cardiac and Physical Data parameter. f. Range of Data for Acceptable Stabilization

Different parameters have different ranges dependent on their stability. Here is a preferred range for stability for each pa rameter:

• Hea rt rate: +/- 5 beats per minute

• Respiration : +/- 1 breath per minute

• Blood Pressure: Systolic: +/- lOmm/hg Diastolic +/- 5 mm/hg

• Power: +/- 25 watts

· Turnover: Stride rate +/- 1 stride/min, cadence +/- 3 rpm, stroke rate +/- 1 stroke/ mi n

• Dista nce per Turnover: Running +/- 2cm

• Speed : Running +/- 1.5km/hr

• Pace: +/- 15s/km Each stability threshold can be configured by the user or updated through a machine learning algorithm. g. Multi Pa rameter Stabilization :

In many situations, more than one parameter can be used for Stability. For example power and cadence can be used for Stability at the same time to achieve greater accuracy of heart data measurement. In this case, cadence may need to have reached and be within a stabilised zone or above or below a threshold and so to must power. This ensures that any comparisons between heart rate and power are as accurate as possible. As with heart rate, blood pressures take time to stabilise. This may also take between 3 and 6 minutes in most cases at a constant load . Determining exercise blood pressures is very useful in that a user's resting blood pressure can be completely normal but the exercise blood pressure shows an elevated diastolic pressure indicating problems with blood pressures under a workload. To automatically obtain accurate blood pressure data, the system must stabilise for a time period before measuring the systolic and diastolic blood pressure values. h. Real Time Analysis and Post Workout Analysis

Preferably the step of utilizing the parameter stabilisation isystem is performed upon or after receiving the activity or data that characterises inactivity for the entire measured session. i. Automatic or Manual Process for Identification of Periods of Parameter Stability

The data to identify the period of stability may be received and trawled automatically or alternatively the system is arranged to enable a user to manually time stamp a block of data by pushing a time, distance or location stamp or lap split button on a device and the time stamp block for each monitored parameter is trawled and compared against one or more threshold criteria. A time stamp may be based on time, distance or location. j. Parameter Stability or Context Stability Alert

Once a Cardiovascular/Cardiac parameter or a Physical Data parameter meets threshold or zone criteria creating Parameter Stability or a group of Cardiovascular/Cardiac or Physical Data parameters simultaneously meets threshold or zone criteria creating Context Stability, an alert is generated which is associated to stable

Cardiovascular/Cardiac data or Physical Data. In conjunction with the Stability Alert all data measured during the stable period or third time interval which includes data not only from the Cardiovascular/Cardiac data and Physical Data stability parameters but all data being measured at the time is received, recorded or sampled from all sensors and parameters so that a segment of stable data using all available parameter and data streams is recorded.

3.7 Data Analysis and Insights:

Once the data has been stabilised and a Stability Alert is generated this initiates calculations, algorithms and statistical analysis that can be applied to the data obtained to draw out insights. 3.8 Feedback, Schedule Adjustments and Metrics:

Once the analysis of stabilised data occurs another form of Stability Alert can occur where advice and schedule or exercise/activity plan adjustments can be output to the user in a number of forms. These include: a. Auditory Advice Output:

The Inference Engine may supply 'advice' in an auditory manner. This might be to advise the user that the reason for their fatigue is linked to a lack of good quality sleep measured through the amount of motion while a user is asleep and going to bed too late measured by the time in the evening that the user is in a lying position with low levels of motion for more than 3 hours. This information around sleep habits being linked to fatigue could be supplied through a speaker or headphones. b. Auditory Signal Output:

The Inference or Insights Engine could generate a signal that has an attached meaning to the user. For example, a low pitched 'beep' might tell the user they are tired and a high pitched 'beep' might indicate good recovery and a 'fresh' status. c. Dynamic Updating of an Activity or Exercise Plan Output:

The Inference or Insights Engine can update an Activity Plan or an Exercise Plan based on inferences made through collection of Observation data. For example, lack of good quality sleep, going to bed too late and fatigue could cause the Inference Engine to adjust an Exercise Workout Plan the following day to be easier to accommodate the low energy levels. d. Graphical or Metric Output:

Fatigue detected by the Inference or Insights Engine could be output graphically by using a 'fuel tank; graphic showing that the level of the 'fuel tank' is low or by using the colour red to characterise fatigue. A metric could be provided that has a high score when the user is fresh and recovered and a low score when the user is fatigued. e. Text Output:

Information based on an Inference or Insights Alert can be output in text. The Inference or Insights Engine may output "You are fatigued due to poor quality sleep over the last few nights and going to be late. I have adjusted the workout for tomorrow to be easier and suggest that you do it in the afternoon so you can sleep in." based on sleep quality values, sleep time values and fatigue measures. f. Schedule Adjustments: A training plan or exercise plan, exercise workout, activity schedule, work schedule or appointment schedule can be dynamically updated based on the data received. g. Metrics:

Metrics that are determined through the analysis process can be retained for future data comparisons or output to a coach, trainer or person for further manual analysis.

Cardiovascular effort, cardiac anomalies and Physical data and its relation to; heart rate, heart rate variability, oxygen uptake, heart function including ECG, oxygen saturation, blood pressure, blood glucose can be output as:

· Auditory Advice Output

• Auditory Signal Output

• Dynamic Updating of an Activity or Exercise Plan Output

• Graphical or Metric Output

• Text Output It is also possible that an audio visual output could be generated. 3.9 Definitions of Terms:

In this specification Activity Data or Physical Data can mean any physical action that involves muscle use or limb movement or postural incline performed by an individual or group of individuals over a period of time or distance (or both) which may or may not involve movement, such as lying/sitting down and running/cycling. The term is intended to cover general activities such as running as well as specific activities such as running uphill at a certain pace. An activity session means a period of time where an individual performs one or more activities. Exercise and exercise sessions (or workout) are intended to be covered by the terms activity and activity sessions respectively. Activity period refers to the period within an activity session in which an activity is performed. Activity may include inactivity such is sleeping, sitting, lying down and situations that have low levels of movement or no movement. The terms Activity, Activity Type or Cardiovascular and Cardiac Event can be described by one or more sensor parameters measuring activity or physical data where each parameter exceeds a detection threshold or multiple parameters exceed and a detection threshold at a point simultaneously or with periodic alternate sampling thereby detecting or classifying the activity.

In this case, cardiovascular and cardiac are defined as having to do with both the heart, lungs and status of the blood vessels.

Postural incline is the status of a user's body or limbs in relation to gravity - meaning upright, lying down, or parts of limbs in relation to other parts of limbs - meaning upper leg in relation to their lower leg or parts of limbs in relation to the thorax/abdomen and chest, head or feet.

Physical data can mean any form of data that involves user Activity other than

Cardiovascular or Cardiac data. Snapshot means a short period of data recording.

Feedback means information that causes a user to gain new insights or information that causes the user to change aspects of future behaviour.

Training plan means a group of one or more exercises or activities for a single workout or daily schedule but can also mean a sequential series of exercises or activities over a number of calendar days. Training plan and Training program are defined in the same way.

Contextual data is other surrounding data recorded at the same time as a key parameter. Contextual data is at least in some way different in that is measures a different aspect of the user's activity or what the user is experiencing. Data may not be precisely

simultaneous but it is preferred.

A key parameter is the target parameter to be analysed, filtered or stabilised within one or more other parameters that are being measured.

The Data Accuracy Engine is a description of the overall system of Activity, Activity Type and Cardiovascular/Cardiac Event Identification, Stabilisation, Data Analysis, Insights and Feedback, Schedule Adjustments and Metrics.

The term "stabilized" means situations where one or more streams of data do not exceed one or more thresholds meaning that data is very uniform. One or more parameters is used for the stabilization process. An upper or lower threshold for one or more parameters is used although in some cases a single threshold is used.

4.0 Definitions for Sensor types:

Memory

Preferably the memory component has stored therein any one or more Activity, Activity Type or Cardiovascular and Cardiac Event classification configurations including walking classification, running classification, cycling classification, horse training classification and activity status monitoring classification categories. For example the running category classification is classified with easy, rolling hills, hills, long climbs, hill efforts up tempo, anaerobic threshold, sprint and overspeed activities.

More preferably the memory component has stored therein one or more of a weight loss activity classification, activity status monitoring classification or general activity monitoring classification, running classification, cycling classification, swimming classification, rowing classification, kayaking classification and team sports classification such as soccer classification, rugby union classification and league classification, ice and field hockey classification , American football classification , basketball classification, baseball classification and Softball classification , water polo classification, equestrian classification, handball classification, netball classification, lacrosse classification, skating classification and cross country skiing classification.

The memory component has activity classifications stored for indoor exercise equipment such as treadmills, rowing machines, elliptical trainers, and stationary cycling.

Preferably the system further comprises one or more activity monitoring devices, each arranged to obtain data indicative of parameters monitored during activity, inactivity or an exercise session. The classification, stabilization identification and/or processing may occur on-board one or more monitoring devices, on a personal computer or the device is arranged to transmit data indicative of the monitored parameters to the classification module on a remotely located module or server. Preferably the system further comprises:

A central station for accommodating the classification module, and

A receiver for receiving data indicative of multiple parameters monitored during activity, inactivity or an exercise session from the one or more monitoring devices. Alternatively the parameter stabilisation identification and activity classification module are housed within each monitoring device.

5.0 System Requirements

It will be appreciated that the system of the invention may be implemented on any suitable hardware system, platform or architecture. The hardwa re system may be provided on-board a device used by the user or on a remote server for example, and preferably comprises at least a processor for running the classification system and in pa rticular the algorithms, at least one memory component for storing at least the algorithms and the threshold criteria, and interface circuitry for communicating with external components that either directly or indirectly provide sensor output data . It will be appreciated that the processor may be any form of programmable hardware device, whether a CPU, Digital Signal Processor, Field-Prog rammable Gate Array, Microcontroller, Application-Specific Integrated Circuit, or the like.

There a re 3 possible configurations for housing the classification system.

The data is processed 'on board' a measurement device (i .e. the classification system is within the measurement/monitoring device),

Data is processed via manual (controlled by user) or automatic transfer (upload and download) of data via a communications network (e.g . telecommunications, wifi etc) to a remote server that contains the classification system,

or manual or automatic transfer of data to a home computer that either contains the system or that transfers (upload and download) the data to a remote server that contains the system.

They system may house the infrastructure for the classification and allow a person, trainer or coach to input the one or more parameters and/or the one or more associated thresholds that define an activity.

The invention is also intended to cover a method of analysing an exercise session as employed by the system described above. The foregoing description of the invention includes preferred forms thereof. Modifications may be made thereto without departing from the scope of the invention, as defined by the accompanying claims.

Claims

1. A method of detecting stability within an activity performed by a user, the method comprising :

receiving activity data indicative of the activity performed by the user during a first time interval, the activity data comprising a plurality of measurements and respective timestamps associated to at least one activity parameter monitored during the first time interval;

receiving cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and cardiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval;

a processor comparing at least some of the cardiovascular and cardiac data with at least one threshold range; and

on the processor detecting a threshold set of cardiovascular and cardiac data lying within the at least one threshold range within a third time interval :

generating a stability alert associated to the cardiovascular and cardiac data; and

generating a stability alert associated to the activity data having respective timestamps not earlier than the timestamps associated to the threshold set of cardiovascular and cardiac data.

2. The method as claimed in claim 1 wherein a lower bound of the first time interval is the same as a lower bound of the second time interval.

3. The method as claimed in claim 1 or claim 2 wherein an upper bound of the first time interval is the same as an upper bound of the second time interval.

4. The method as claimed in any one of the preceding claims wherein a lower bound of the third time interval is later than a lower bound of the second time interval.

5. The method as claimed in any one of the preceding claims wherein the at least one threshold range is defined by a lower threshold value and an upper threshold value, or respective lower threshold and upper threshold values.

6. The method as claimed in any one of claims 1 to 4 wherein the at least one threshold range is defined by a target value and a tolerance value, or respective target and tolerance values.

7. The method as claimed in any one of the preceding claims wherein the processor is configured to adjust the at least one threshold range.

8. The method as claimed in any one of the preceding claims wherein a user interface is configured to obtain from a user adjustments to the at least one threshold range.

9. The method as claimed in any one of the preceding claims wherein the processor is configured to adjust the duration of the third time interval .

10. The method as claimed in any one of the preceding claims wherein a user interface is configured to obtain from a user adjustment to the duration of the third time interval .

11. The method as claimed in any one of the preceding claims wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval .

12. The method as claimed in any one of claims 1 to 10 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval.

13. The method as claimed in any one of claims 1 to 10 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprise consecutive values within the third time interval .

14. The method as claimed in any one of the preceding claims wherein the cardiovascular and cardiac data is measured by the at least one cardiovascular and cardiac parameter selected from heart rate, electrocardiograph, oxygen saturation, respiration, ventilation, oxygen uptake, and blood pressure.

15. The method as claimed in any one of claims 1 to 13 wherein the cardiovascular and cardiac data comprises neurocardiogenic data measured by the at least one cardiovascular and cardiac parameter selected from hea rt rate va riability, AVNN, SDNN, SD1, SD2, HF, LF, rRMSSD, pNN50, and total power.

16. The method as claimed in any one of the preceding claims wherein the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity parameters monitored during the first time interval.

17. The method as claimed in any one of the preceding claims wherein the

cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of cardiovascular and cardiac pa ra meters monitored during the second time interval .

18. A system configured to detect stability within an activity performed by a user, the system comprising :

at least one computer-readable medium; and

at least one processor, the at least one processor programmed to :

receive activity data indicative of the activity performed by the user during a first time interval, the activity data comprising a plurality of measurements and respective timestamps associated to at least one activity pa rameter monitored during the first time interval;

receive cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and ca rdiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval ;

compare at least some of the cardiovascular and cardiac data with at least one threshold range; and

on detecting a threshold set of cardiovascular a nd cardiac data lying within the at least one threshold range within a third time interval :

generate a stability alert associated to the cardiovascular and cardiac data ; and

generate a stability alert associated to the activity data having respective timestamps not earlier than the timestamps associated to the threshold set of cardiovascular and cardiac data.

19. The system as claimed in claim 18 wherein a lower bound of the first time interval is the same as a lower bound of the second time interval .

20. The system as claimed in claim 18 or claim 19 wherein an upper bound of the first time interval is the same as an upper bound of the second time interval .

21. The system as claimed in any one of claims 18 to 20 wherein a lower bound of the third time interval is later than a lower bound of the second time interval .

22. The system as claimed in any one of claims 18 to 21 wherein the at least one threshold range is defined by a lower threshold value and an upper threshold value, or respective lower threshold and upper threshold values.

23. The system as claimed in any one of claims 18 to 21 wherein the at least one threshold range is defined by a target value and a tolerance value, or respective target and tolerance values.

24. The system as claimed in any one of claims 18 to 23 wherein the processor is configured to adjust the at least one threshold range.

25. The system as claimed in any one of claims 18 to 24 wherein a user interface is configured to obtain from a user adj ustments to the at least one threshold range.

26. The system as claimed in any one of claims 18 to 25 wherein the processor is configured to adjust the duration of the third time interval.

27. The system as claimed in any one of claims 18 to 26 wherein a user interface is configured to obtain from a user adj ustments to the duration of the third time interval .

28. The system as claimed in any one of claims 18 to 27 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval.

29. The system as claimed in any one of claims 18 to 27 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval.

30. The system as claimed in any one of claims 18 to 27 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprise consecutive values within the third time interval .

31. The system as claimed in any one of claims 18 to 30 wherein the cardiovascular and cardiac data is measured by the at least one cardiovascular and cardiac parameter selected from heart rate, electrocardiograph, oxygen saturation, respiration, ventilation, oxygen uptake, and blood pressure.

32. The system as claimed in any one of claims 18 to 30 wherein the cardiovascular and cardiac data comprises neurocardiogenic data measured by the at least one cardiovascular and cardiac parameter selected from hea rt rate va riability, AVNN, SDNN, SD1, SD2, HF, LF, rRMSSD, pNN50, and total power.

33. The system as claimed in any one of claims 18 to 32 wherein the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity parameters monitored during the first time interval.

34. The system as claimed in any one of claims 18 to 33 wherein the cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of cardiovascular and cardiac parameters monitored during the second time interval.

35. A computer-readable medium having stored thereon computer-executable instructions that, when executed by at least one processor, cause the at least one processor to perform a method of detecting stability within an activity performed by a user, the method comprising :

receiving activity data indicative of the activity performed by the user during a first time interval, the activity data comprising a plurality of measurements and respective timestamps associated to at least one activity pa rameter monitored during the first time interval;

receiving cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and cardiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval ;

comparing at least some of the cardiovascular and cardiac data with at least one threshold range; and

on detecting a threshold set of ca rdiovascular a nd cardiac data lying within the at least one threshold range within a third time interval :

generating a stability alert associated to the cardiovascular and cardiac data ; and

36. The computer-readable medium of claim 35 wherein a lower bound of the first time interval is the same as a lower bound of the second time interval .

37. The computer-readable medium of claim 35 or claim 36 wherein an upper bound of the first time interval is the same as an upper bound of the second time interval.

38. The computer-readable medium of any one of claims 35 to 37 wherein a lower bound of the third time interval is later than a lower bound of the second time interval .

39. The computer-readable medium of any one of claims 35 to 38 wherein the at least one threshold range is defined by a lower threshold value and an upper threshold value, or respective lower threshold and upper threshold values.

40. The computer-readable medium of any one of claims 35 to 38 wherein the at least one threshold range is defined by a target value and a tolerance value, or respective target and tolerance values.

41. The computer-readable medium of any one of claims 35 to 40 wherein the processor is configured to adjust the at least one threshold range.

42. The computer-readable medium of any one of claims 35 to 41 wherein a user interface is configured to obtain from a user adjustments to the at least one threshold range.

43. The computer-readable medium of any one of claims 35 to 42 wherein the processor is configured to adjust the duration of the third time interval.

44. The computer-readable medium of any one of claims 35 to 43 wherein a user interface is configured to obtain from a user adjustments to the duration of the third time interval .

45. The computer-readable medium of any one of claims 35 to 44 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval.

46. The computer-readable medium of any one of claims 35 to 44 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval .

47. The computer-readable medium of any one of claims 35 to 44 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprise consecutive values within the third time interval .

48. The computer-readable medium of any one of claims 35 to 47 wherein the cardiovascular and cardiac data is measured by the at least one cardiovascular and cardiac parameter selected from heart rate, electrocardiograph, oxygen saturation, respiration, ventilation, oxygen uptake, and blood pressure.

49. The computer-readable medium of any one of claims 35 to 47 wherein the cardiovascular and cardiac data comprises neuroca rdiogenic data measured by the at least one cardiovascular and cardiac parameter selected from heart rate variability, AVNN, SDNN, SD1, SD2, HF, LF, rRMSSD, pNN50, and total power.

50. The computer-readable medium of any one of claims 35 to 49 wherein the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity parameters monitored during the first time interval.

51. The computer-readable medium of any one of claims 35 to 50 wherein the cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of cardiovascular and cardiac pa ra meters monitored during the second time interval .

52. A method of detecting stability within an activity performed by a user, the method comprising :

a processor comparing at least some of the activity data with at least one threshold range; and

on the processor detecting a threshold set of activity data lying within the at least one threshold range within a third time interval :

generating a stability alert associated to the activity data; and generating a stability alert associated to the cardiovascular and cardiac data having respective timestamps not earlier than the timestamps associated to the threshold set of activity data .

53. The method as claimed in claim 52 wherein a lower bound of the first time interval is the same as a lower bound of the second time interval .

54. The method as claimed in claim 52 or claim 53 wherein an upper bound of the first time interval is the same as an upper bound of the second time interval.

55. The method of any one of claims 52 to 54 wherein a lower bound of the third time interval is later than a lower bound of the second time interval .

56. The method of any one of claims 52 to 55 wherein the at least one threshold range is defined by a lower threshold value and an upper threshold value, or respective lower threshold and upper threshold values.

57. The method of any one of claims 52 to 55 wherein the at least one threshold range is defined by a target value and a tolerance value, or respective target and tolerance values.

58. The method of any one of claims 52 to 57 wherein the processor is configured to adjust the at least one threshold range.

59. The method of any one of claims 52 to 58 wherein a user interface is configured to obtain from a user adjustments to the at least one threshold range.

60. The method of any one of claims 52 to 59 wherein the processor is configured to adjust the duration of the third time interval .

61. The method of any one of claims 52 to 60 wherein a user interface is configured to obtain from a user adjustments to the duration of the third time interval .

62. The method of any one of claims 52 to 61 wherein the threshold set of

cardiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval.

63. The method of any one of claims 52 to 61 wherein the threshold set of

cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval.

64. The method of any one of claims 52 to 61 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprise consecutive values within the third time interval .

65. The method of any one of claims 52 to 64 wherein the cardiovascular and cardiac data is measured by the at least one ca rdiovascular and cardiac parameter selected from heart rate, electrocardiograph, oxygen saturation, respiration, ventilation, oxygen upta ke, and blood pressure.

66. The method of any one of claims 52 to 64 wherein the cardiovascular and cardiac data comprises neuroca rdiogenic data measured by the at least one cardiovascular and cardiac parameter selected from heart rate variability, AVNN, SDNN, SD1, SD2, HF, LF, rRMSSD, pNN50, and total power.

67. The method of any one of claims 52 to 66 wherein the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity pa rameters monitored during the first time interval .

68. The method of any one of claims 52 to 67 wherein the cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of cardiovascular and ca rdiac parameters monitored during the second time interval .

69. A system configured to detect stability within an activity performed by a user, the system comprising :

at least one computer-readable medium; and

at least one processor, the at least one processor programmed to :

compare at least some of the activity data with at least one threshold range; and

on detecting a threshold set of activity data lying within the at least one threshold range within a third time interval : generate a stability alert associated to the activity data ; and generate a stability alert associated to the cardiovascular and cardiac data having respective timestamps not earlier than the timestamps associated to the threshold set of activity data.

70. The system as claimed in claim 69 wherein a lower bound of the first time interval is the same as a lower bound of the second time interval .

71. The system as claimed in claim 69 or claim 70 wherein an upper bound of the first time interval is the same as an upper bound of the second time interval .

72. The system as claimed in any one of claims 69 to 71 wherein a lower bound of the third time interval is later than a lower bound of the second time interval .

73. The system as claimed in any one of claims 69 to 72 wherein the at least one threshold range is defined by a lower threshold value and an upper threshold value, or respective lower threshold and upper threshold values.

74. The system as claimed in any one of claims 69 to 72 wherein the at least one threshold range is defined by a target value and a tolerance value, or respective target and tolerance values.

75. The system as claimed in any one of claims 69 to 74 wherein the processor is configured to adjust the at least one threshold range.

76. The system as claimed in any one of claims 69 to 75 wherein a user interface is configured to obtain from a user adj ustments to the at least one threshold range.

77. The system as claimed in any one of claims 69 to 76 wherein the processor is configured to adjust the duration of the third time interval.

78. The system as claimed in any one of claims 69 to 77 wherein a user interface is configured to obtain from a user adj ustments to the duration of the third time interval .

79. The system as claimed in any one of claims 69 to 78 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval.

80. The system as claimed in any one of claims 69 to 78 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval.

81. The system as claimed in any one of claims 69 to 78 wherein the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprise consecutive values within the third time interval .

82. The system as claimed in any one of claims 69 to 81 wherein the cardiovascular and cardiac data is measured by the at least one cardiovascular and cardiac parameter selected from heart rate, electrocardiograph, oxygen saturation, respiration, ventilation, oxygen uptake, and blood pressure.

83. The system as claimed in any one of claims 69 to 81 wherein the cardiovascular and cardiac data comprises neurocardiogenic data measured by the at least one cardiovascular and cardiac parameter selected from hea rt rate va riability, AVNN, SDNN, SD1, SD2, HF, LF, rRMSSD, pNN50, and total power.

84. The system as claimed in any one of claims 69 to 83 wherein the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity parameters monitored during the first time interval.

85. The system as claimed in any one of claims 69 to 84 wherein the cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of cardiovascular and cardiac parameters monitored during the second time interval.

86. A computer-readable medium having stored thereon computer-executable instructions that, when executed by at least one processor, cause the at least one processor to perform a method of detecting stability within an activity performed by a user, the method comprising :

receiving cardiovascular and cardiac data indicative of the activity performed by the user during a second time interval, the cardiovascular and cardiac data comprising a plurality of measurements and respective timestamps associated to at least one cardiovascular and cardiac parameter monitored during the second time interval ; comparing at least some of the activity data with at least one threshold range; and

on detecting a threshold set of activity data lying within the at least one threshold range within a third time interval :

generating a stability alert associated to the activity data ; and generating a stability alert associated to the cardiovascular and cardiac data having respective timestarmps not earlier than the timestarmps associated to the threshold set of activity data.

87. The computer-readable medium as claimed in claim 86 wherein a lower bound of the first time interval is the same as a lower bound of the second time interval .

88. The computer-readable medium as claimed in claim 86 or claim 87 wherein an upper bound of the first time interval is the sa me as an upper bound of the second time interval .

89. The computer-readable medium as claimed in any one of claims 86 to 88 wherein a lower bound of the third time interval is later than a lower bound of the second time interval .

90. The computer-readable medium as claimed in any one of claims 86 to 89 wherein the at least one threshold range is defined by a lower threshold value and an upper threshold value, or respective lower threshold and upper threshold values.

91. The computer-readable medium as claimed in any one of claims 86 to 89 wherein the at least one threshold range is defined by a target value and a tolerance value, or respective target and tolerance values.

92. The computer-readable medium as claimed in any one of claims 86 to 91 wherein the processor is configured to adjust the at least one threshold range.

93. The computer-readable medium as claimed in any one of claims 86 to 92 wherein a user interface is configured to obtain from a user adj ustments to the at least one threshold range.

94. The computer-readable medium as claimed in any one of claims 86 to 93 wherein the processor is configured to adjust the duration of the third time interval .

95. The computer-readable medium as claimed in any one of claims 86 to 94 wherein a user interface is configured to obtain from a user adj ustments to the duration of the third time interval .

96. The computer-readable medium as claimed in any one of claims 86 to 95 wherein the threshold set of ca rdiovascular and cardiac data lying within the at least one threshold range comprises all the cardiovascular and cardiac data within the third time interval .

97. The computer-readable medium as claimed in any one of claims 86 to 95 wherein the threshold set of ca rdiovascular and cardiac data lying within the at least one threshold range comprises some of the cardiovascular and cardiac data within the third time interval.

98. The computer-readable medium as claimed in any one of claims 86 to 95 wherein Preferably the threshold set of cardiovascular and cardiac data lying within the at least one threshold range comprise consecutive values within the third time interval .

99. The computer-readable medium as claimed in any one of claims 86 to 98 wherein the cardiovascular and cardiac data is measured by the at least one cardiovascular and cardiac parameter selected from heart rate, electrocardiograph, oxygen saturation, respiration, ventilation, oxygen uptake, and blood pressure.

100. The computer-readable medium as claimed in any one of claims 86 to 98 wherein the cardiovascular and cardiac data comprises neuroca rdiogenic data measured by the at least one cardiovascular and cardiac parameter selected from heart rate variability, AVNN, SDNN, SD1, SD2, HF, LF, rRMSSD, pNN50, and total power.

101. The computer-readable medium as claimed in any one of claims 86 to 100 wherein the activity data comprises a plurality of measurements and respective timestamps associated to a plurality of activity parameters monitored during the first time interval.

102. The computer-readable medium as claimed in any one of claims 86 to 101 wherein the cardiovascular and cardiac data comprises a plurality of measurements and respective timestamps associated to a plurality of cardiovascular and cardiac parameters monitored during the second time interval.

103. The method as claimed in any one of claims 1 to 17 further comprising generating stable activity data at least partly from the activity data to which the stability alert is associated . 104. The system as claimed in any one of claims 18 to 34 wherein the processor is further configured to generate stable activity data at least partly from the activity data to which the stability alert is associated .

105. The computer readable-medium as claimed in any one of claims 35 to 51 wherein the method further comprises generating stable activity data at least pa rtly from the activity data to which the stability alert is associated.

106. The method as claimed in any one of claims 52 to 68 further comprising generating stable cardiovascular and ca rdiac data at least partly from the cardiovascular and cardiac data to which the stability alert is associated .

104. The system as claimed in any one of claims 69 to 85 wherein the processor is further configured to generate stable cardiovascular and cardiac data at least partly from the cardiovascular and cardiac data to which the stability alert is associated .

105. The computer readable-medium as claimed in any one of claims 86 to 103 wherein the method further comprises generating stable cardiovascular and cardiac data at least partly from the cardiovascular and cardiac data to which the sta bility alert is associated .