WO2009126997A1

WO2009126997A1 - Hierarchical activity classification method and apparatus

Info

Publication number: WO2009126997A1
Application number: PCT/AU2009/000459
Authority: WO
Inventors: Niranjan Parameshwar Bidargaddi; Antti Ilmari Sarela; Mohanraj Krishnamoorthy Karunanithi
Original assignee: Commonwealth Scientific And Industrial Research Organisation
Priority date: 2008-04-18
Filing date: 2009-04-14
Publication date: 2009-10-22

Abstract

A method and apparatus for displaying information, in particular in a health care monitoring context, relating to a hierarchical activity classification of a plurality of input time series signals. The method comprise the steps of: selecting a condition for defining a hierarchical activity classification; classifying one or more time periods across each said input time series signal, wherein the selected said condition is satisfied during each said one or more time periods; calculating one or more hierarchical activity results, wherein each said hierarchical activity result is indicative of an output measure derived from one or more said time series signals over the classified said one or more time periods; and displaying said one or more hierarchical activity results.

Description

HIERARCHICAL ACTIVITY CLASSIFICATION METHOD AND APPARATUS

FIELD OF THE INVENTION

[0001] The present invention relates to the display of information, in particular in a health care monitoring context.

[0002] The invention has been developed primarily for monitoring, classifying and displaying clinical significant information obtained from health care monitors and will be described hereinafter with reference to this application. However, it will be appreciated that the invention is not limited to this particular field of use.

BACKGROUND OF THE INVENTION [0003] Any discussion of the prior art throughout the specification should in no way be considered as an admission that such prior art is widely known or forms part of the common general knowledge in the field.

[0004] Known methods for displaying clinical significant information obtained from health care monitors typically use single time series graphs to display the physiological signals collected with ambulatory monitors. These graphs traditionally display the measured signals in two-dimensional (x-axis / y-axis) plots, bar graphs or by using other similar graphical methods. An activity classification result can be similarly displayed in pie charts or bar graphs.

[0005] A commercial pedometer, such as those made by Omron HealthCare - Japan, may use activity classification rules and present the results with a bar graph on a computer display. For example walking may be classified into either aerobic or other miscellaneous types of steps.

[0006] Another commercial activity measurement system, such as those made by MiniSun - USA, may provide more information but typically fails to suitably present the clinically relevant information. [0007] There is a need in the art for a method and apparatus that can analyse and combine 'raw' health care signals and present results in a clinically meaningful way, which also provides additional information regarding patient behaviour.

SUMMARY OF THE INVENTION [0008] It is an object of the present invention to overcome or ameliorate at least one of the disadvantages of the prior art, or to provide a useful alternative.

[0009] It is an object of the invention in its preferred form to provide a method and apparatus for hierarchical activity classification.

[0010] In accordance with an aspect of the present invention, there is provided a method for hierarchical activity classification of a plurality of input time series signals, the method comprising the steps of: (a) selecting a condition for defining a hierarchical activity classification; (b) classifying one or more time periods across each the input time series signal, wherein the selected the condition is satisfied during each the one or more time periods; (c) calculating one or more hierarchical activity results, wherein each the hierarchical activity result is indicative of an output measure derived from one or more the time series signals over the classified the one or more time periods; and (d) displaying the one or more hierarchical activity results.

[0011] Preferably, the method further comprises the steps of: (e) providing a plurality of further input time series signals, wherein each the further input time series can be indicative of respective one of the previous the input time series signals over the previously classified the one or more time periods; and (f) repeating steps (a) through (d) substituting the further input time series signals as the plurality of input time series signals for displaying a further the hierarchical activity results.

[0012] Preferably, the method also further comprises the steps of: (g) recursively repeating steps (e) and (f) to a predefined depth for displaying a further hierarchical activity results.

[0013] The output measure preferably can be selected from the group including: a time series measure and a numerical measure. Each of the time series signals preferably can be selected from the group including: a physical activity measurement signals and a physiological measurement signals. The selected condition preferably can be selected from the group including: a binary condition applied to an identifiable activity derived from one or more the time series signals; a binary condition applied to values of one or more the time series signal; and a binary condition applied to a calculated value derived from one or more the time series signal. The hierarchical activity result preferably can include a graphical display indicative of one or more of the output measure. The hierarchical activity result preferably can include a graphical display indicative of a plurality of the output measure displayed on a single graph. The hierarchical activity result preferably can include a numerical display of a calculated measure indicative of one or more of the output measure.

[0014] In accordance with a further aspect of the present invention, there is provided a apparatus for hierarchical activity classification of a plurality of input time series signals, the apparatus comprising: an input module adapted to receive a plurality of input time series signals and data indicative of a selected condition to define a hierarchical activity classification; a process module adapted to classify one or more time periods across each input time series signal such that the selected the condition is satisfied during each one or more time periods, the process module further adapted to calculate one or more hierarchical activity results such that each hierarchical activity result is indicative of an output measure derived from one or more time series signals over the classified one or more time periods; and a display module adapted to display the one or more hierarchical activity results. Preferably, the display module can be adapted to provide the one or more hierarchical activity results via a web portal and the process module can be a distributed process module.

[0015] In accordance with a further aspect of the present invention, there is provided a computer-readable carrier medium carrying a set of instructions that when executed by one or more processors cause the one or more processors to carry out a method for hierarchical activity classification of a plurality of input time series signals, the method comprising: (a) selecting a condition for defining a hierarchical activity classification; (b) classifying one or more time periods across each the input time series signal, wherein the selected the condition is satisfied during each the one or more time periods; (c) calculating one or more hierarchical activity results, wherein each the hierarchical activity result is indicative of an output measure derived from one or more the time series signals over the classified the one or more time periods; and (d) displaying the one or more hierarchical activity results.

[0016] In accordance with a further aspect of the present invention, there is provided a computer-readable carrier medium carrying a set of instructions that when executed by one or more processors cause the one or more processors to carry out a method as described herein.

[0017] In accordance with a further aspect of the present invention, there is provided a computer program product stored on a computer readable medium, the computer program product adapted to provide a hierarchical activity classification of a plurality of input time series signals, the computer program product comprising: a computer readable program means for selecting a condition for defining a hierarchical activity classification; a computer readable program means for classifying one or more time periods across each said input time series signal, wherein the selected said condition is satisfied during each said one or more time periods; a computer readable program means for calculating one or more hierarchical activity results, wherein each said hierarchical activity result is indicative of an output measure derived from one or more said time series signals over the classified said one or more time periods; and a computer readable program means for displaying said one or more hierarchical activity results.

[0018] In accordance with a further aspect of the present invention, there is provided a computer program product stored on a computer readable medium, the computer program product adapted to provide a hierarchical activity classification of a plurality of input time series signals, the computer program product comprising a computer readable program means for performing a method as described herein.

[0019] In accordance with a further aspect of the present invention, there is provided computer hardware including one or more processors configured to perform a method a method as described herein. BRIEF DESCRIPTION OF THE DRAWINGS ^

[0020] A preferred embodiment of the invention will now be described, by way of example only, with reference to the accompanying drawings in which:

FIG. 1 is an example flowchart of a method for hierarchical activity classification of a plurality of input time series signals;

FIG. 2 is an example schematic diagram of an apparatus adapted to implement a method for hierarchical activity classification of a plurality of input time series signals;

FIG. 3 is an example schematic diagram of a distributed apparatus adapted to implement a method for hierarchical activity classification of a plurality of input time series signals; and

FIG. 4 is an example display of hierarchical activity results.

PREFERRED EMBODIMENT OF THE INVENTION

[0021] An embodiment provides a method of analysing and combining 'raw' health care signals and presenting results in a clinically meaningful way, which provides additional information regarding patient behaviour via a related user interface.

[0022] Ambulatory and home-care monitors are commonly used for measuring movement activity and other physiological signals. For example, raw activities signals indicative of daily living can be measured with a waist worn 3-Dimensional accelerometer and applied to classification algorithms to extract daily activities from the measured raw signal. By way of example, other raw physiological signals such as single lead ECG can also be monitored and applied to algorithms that result in calculating heart rate and respiratory rate from the raw signal.

[0023] In an embodiment, a method is disclosed for organizing and displaying significant information obtained from the results of activity classification and the other measured physiological signal calculations. The resulting display provided to a graphical user interface can efficiently depict the status and development of physical condition of a patient. The patient can be living in a home setting. [0024] A hierarchical structure is applied to the measured and analysed activity information, which is provided to a user interface method for displaying the physiological signals in relation to the required activities.

[0025] In an embodiment, by way of example only, aspects of the method can include: (a) Hierarchical activity classification, where the resulting activity classes form a multi-level structure that can be expanded and collapsed according to the level of detail that is of interest.

(b) Vital signs and other physiological measures are combined with different levels of activities to create new clinical information. For example, the respiratory rate after vigorous exercise can be included as an important measure to assess the condition of a chronic obstructive pulmonary disease (COPD) patient.

(c) Activity classification results and related vital signs are displayed graphically. For example, this can include a colour bar on a 24-hour time axis where different colours depict different activities. The graphical display may be further combined with another physiological signal.

(d) Detailed levels in an activity classification structure are displayed below, but in a similar format to, an upper level. For example, a full display of all activity levels may form a vertical stack of colour bars. A required amount of detail in the structure may be selected by a user.

(e) Trends in activity duration and vital signs variation can be shown in the same view along with behavioural patterns.

(f) A minimal number of colours (say only 2) can be used in the representation.

[0026] It would be appreciated that advantages of the present embodiment can include:

> Only the relevant information of interest to the clinicians can be displayed while hiding any unnecessary data. This can be achieved by display hierarchical levels.

> Combining of two signals can provide increased information content for a clinician to better understanding of the status and development of a patient's physical condition. By simultaneously combining two measures it is possible to create new knowledge related to a patient's condition. [0027] A method of assessing a patient's health status and physical condition can involve evaluating cardiovascular and respiratory exercise performance by using physiological tests and scoring systems. These tests are usually performed in a laboratory setting in a care facility.

[0028] In an embodiment," ambulatory measurement devices and software systems can be used to collect health information from patients in a home health care setting, where patients with chronic diseases live at home. As this need not be performed in a laboratory setting, it can also provide a more precise result - which reflects the condition of a patient under normal conditions - and improves assessment quality.

[0029] Ambulatory monitoring in a home care setting is relatively new and typically involves use of simple time series graphs to display measured physiological signals. These measured signals are typically displayed graphically in traditional two- dimensional (x-axis / y-axis) plots, bar graphs or other similar graphical methods.

[0030] Current ambulatory monitoring systems typically collect and display huge amount of data, which needs to be analysed to identify relevant portion of clinical information from the collected data. This relevant portion of clinical information may also be related to other signals or post-analysis results. It would be appreciated that care workers in the community care field are typically not trained for performing complex data analysis and do not have the time to spend interpreting the data provided by monitoring devices.

[0031] An embodiment provides a method of presenting complex data, for example from ambulatory monitoring systems, by isolating significant clinical information and using a hierarchical activity classification to extract different levels and states of a person's behaviour. An activity levels and types of activity along with a corresponding physiological data can be selected in a user interface that will display results from the time periods of the selected activities. By way of example only, a physiotherapist can be interested in a patient's respiratory rate data that is only associated with periods of high or moderate levels of exercise. By way of example only, a sleep laboratory can be interested only in the respiratory rate data and oxygen saturation data during periods of sleep for diagnose of sleep apnoea. [0032] It would be appreciated that, by way of example only, displaying measured physiological signals that relate only to periods of selected conditions or activities (including further subsets at each level), a clinician can isolate relevant information without distraction from irrelevant data. Using this hierarchical representation of analysed conditions or activities can also provide advantages though the association of multiple clinical data measurements. For example, if the data shows an increase in average energy expenditure, a physiotherapist can find the source of this increase by dividing out conditions or activities at each level. Trends in both duration and in vital signs variation can be displayed in the same view. Behavioural information can also be inferred by reviewing different hierarchies.

[0033] Referring to FIG. 1, a flowchart 100 is shown for an example embodiment of a method for hierarchical activity classification of a plurality of input time series signals. This method comprises the steps of:

(a) selecting a condition for defining a hierarchical activity classification 110; (b) classifying one or more time periods across each input time series signal 120, wherein the selected condition is satisfied during each one or more time periods;

(c) calculating one or more hierarchical activity results 130, wherein each hierarchical activity result is indicative of an output measure derived from one or more time series signals over the classified one or more time periods; and

(d) displaying the one or more hierarchical activity results 140.

[0034] This hierarchical activity classification can be extended by applying a further method for hierarchical activity classification to the already classified signals, i.e. by applying the previous method to one or more time periods across each input time series signal. This typically involves the selection of a different condition to further identify sub-classifications within the already classified signals. By way of example only, the previously described method can be extended using the steps of:

(e) providing a plurality of further input time series signals, wherein each further input time series is indicative of respective one of the previous input time series signals over the previously classified one or more time periods; and (f) repeating steps (a) through (d) substituting further input time series signals as the plurality of input time series signals for displaying further hierarchical activity results.

[0035] This hierarchical activity classification can be extended even further by applying this approach in a recursive manner, i.e. applying the recently classified signals as input to the next iteration to further identify sub-classifications. Again this typically involves the selection of a different condition to further identify sub-classifications within the already classified signals. By way of example only, the previously described method can be recursively applied using the step of: (g) recursively repeating steps (e) and (f) to a predefined depth for displaying a further hierarchical activity results.

[0036] The input time series signals can include measured physiological signals, detailed time based activity signals which identifying an activity or condition over a period of time. These activity signals can be calculated from one or more measured physiological signals or provided directly as an input time series signal. An input time series signal is typically selected from the group including a physical activity signal and a physiological measurement signal.

[0037] In an embodiment, the output measure can be derived from one or more time series signals over the classified one or more time periods. By way of example only, the output measure is selected from the group including a time series measure and a numerical measure.

[0038] In an embodiment, the hierarchical activity result includes a graphical display indicative of one or more output measure. The hierarchical activity result can also include a graphical display indicative of a plurality of output measures displayed on a single graph. The hierarchical activity result can also include a numerical display of a calculated measure indicative of one or more output measure.

[0039] An output measure can be derived from measured signals other than physical activity signals. For example, the heart rate measurement can be used to classify exercise events. When displaying one or more hierarchical activity results, the results (indicative of more than one physiological signal) can be simultaneously displayed in connection with the activity classification. For example, respiratory rate and heart rate can be displayed together for each hierarchical activity classification. Further, this method can calculate and display numerical values that describe status or development of a physiological signal in connection with a classification. For example, average heart rate during walking with over 6km/h speed can be calculated and displayed.

[0040] The selected condition defines the classification for the hierarchical layer. This condition is typically binary and enables the output classification time periods to be represented in two colours. It would be appreciated that ternary (and higher) conditions are possible leading to a plurality of hierarchical paths in which to display. Using a binary condition allows the selection of one or more time periods across each input time series signal that satisfy one classification. The condition is typically selected from the group including: a binary condition applied to an identifiable activity derived from one or more time series signals; a binary condition applied to values of one or more time series signal; and a binary condition applied to a calculated value derived from one or more time series signal.

[0041] FIG. 2 shows an example schematic diagram of an apparatus 200 adapted to implement a method for hierarchical activity classification of a plurality of input time series signals. This apparatus 200 includes:

(a) an input module 210 for receiving a plurality of input time series signals and data indicative of a selected condition to define a hierarchical activity classification;

(b) a process module 220 for (i) classifying one or more time periods across each input time series signal such that the selected condition is satisfied during each one or more time periods; (ii) calculating one or more hierarchical activity results such that each hierarchical activity result is indicative of an output measure derived from one or more time series signals over the classified one or more time periods;

(c) a display module for displaying one or more hierarchical activity results.

[0042] It would be appreciated that time series signals can be produced by a number of clinical and other data logging devices. For example, patients undergoing cardiac rehabilitation can wear a small device that measures and records movement activity and ECG signals as measured time series signals and transmits these signals to a receiving device as raw or partially processed measured time series signals. One or more intermediate hub devices can facilitate this transmission. Software adapted to provide algorithms and user interface modules can extract and calculate different physical activities and physiological measures from the received time series signals. The calculated different physical activities and physiological measures, including the received time series signals, can be displayed as a hierarchical activity classification result using method described herein.

[0043] FIG. 3 shows an example schematic diagram of a distributed system or apparatus 300 adapted to implement a method for hierarchical activity classification of a plurality of input time series signals. In this system, a person (or patient) being monitored 310 has a device 320 for monitoring physical activities and/or physiological measures. This device records one or more time series signals that are transmitted to a processing device 320. In this example, the time series signals are transmitted from the recording device 320 to a processing device 330 via a data network 340. This data network comprises a hub 341 for receiving the signals via a wireless link 342 and forwarding the signals onto a wired network 343, 344 and 345. The processing device 320 receives the time series signals via a network input module and has a further input module 331 for receiving data indicative of a selected condition to define a hierarchical activity classification.

[0044] The processing device 320 is adapted to (i) classify one or more time periods across each input time series signal such that the selected condition is satisfied during each one or more time periods; (ii) calculating one or more hierarchical activity results such that each hierarchical activity result is indicative of an output measure derived from one or more time series signals over the classified one or more time periods. A display module 322 is adapted to display one or more hierarchical activity results.

[0045] It would be appreciated that software can be embedded in a measurement device or a home hub for implementing the algorithms and user interface. Further the processing and hierarchical display of results can be distributed across a plurality of devices. For example, an algorithm can be implemented in a measurement device and/or hub, and a user interface adapted for hierarchical activity classification can be implemented on a computer. A measurement device that provides activity signals may use any sensor sensitive to body movements and can be used on wrist, chest, or upper arm etc. The display can be calculated on a networked computer and presented via a web page or web portal.

[0046] In an embodiment, by way of example only, a computer-readable carrier medium carrying a set of instructions that when executed by one or more processors cause the one or more processors to carry out a method for hierarchical activity classification of a plurality of input time series signals, the method comprising:

(a) receiving a plurality of input time series signals;

(b) selecting a condition for defining a hierarchical activity classification; (c) classifying one or more time periods across each input time series signal, wherein the selected condition is satisfied during each one or more time periods;

(d) calculating one or more hierarchical activity results, wherein each hierarchical activity result is indicative of an output measure derived from one or more time series signals over the classified one or more time periods; and

(e) displaying one or more hierarchical activity results.

[0047] It would be appreciated that this same method can be used in other applications where activities, performance or physiological signals need to be measured and analysed. For example, the method is suitable for obesity management, elderly care, or sports.

[0048] Referring to FIG. 4, a user interface 400 is shown an embodiment, by way of example only, that presents a hierarchical activity classification result.

[0049] In this example embodiment, conditions (or activity types) that a user is interested in are selected from the corresponding "Level" menus 410, 412, 414 and 416. It would be appreciated that these graphs are displayed in a hierarchical order wherein the lower level graph is always a subset of the selected activity type in the graph at a higher level. The "Vital signs" 420 menu can be used to select a signal that is displayed in the graphs. In this example, the area under the selected signal curve that corresponds to the time and duration of the selected activity type is filled, for example 430. The "Activities (%)" 440 bar graphs, for example 442, show the proportion of the higher level activity consisting of the selected activity at the lower level. Summary values such as an average of a selected measurement signal, for example average heart rate 450, can also be displayed. This value is calculated for only the duration of the selected activity.

[0050] It would be appreciated that a user can conclude complex information from the simple display. For example, this patient spends about 60% of time performing Dynamic Activities (i.e. the patient is moving) 460 and about 40% of time being Static (without moving significantly) 461. Of the dynamic activities, about 75% exceed a 3MET level 462, which is indicative of a high amount of exercise. Of the dynamic activities that exceeded the 3MET level, about 40% is classified as walking 463. Of the dynamic activities that exceeded the 3MET level and are classified as walking, about 65% is at a walking speed of over 6km/h 464. As this hierarchical display differentiates between two states at each level, complex hierarchical information can be displayed using only two colours.

[0051] This example user interface also displays other physiological measures associated with periods of time associated with a condition (or activity type) of each level. It is shown that the total average heart rate is 80 beats/min 465 over both static and dynamic activity periods, which does not specifically convey this patient's condition. A more suitable measurement average heart rate calculated over periods of dynamic activities that exceeded the 3MET level, which for this example the average heart rate is calculated as 165 beats/min 466. From this measurement a clinician can assess this patient's heart rate response to the high intensity exercise.

[0052] This example user interface also displays trend information. Trend lines 467 and 468 shows that this patient's average heart rate is lower during day 2 than during day 1. These trends, when viewed over longer periods of time of weeks or months, can assist in assessing the development of a patient's condition.

[0053] It would be farther appreciated that this example user interface can display trends in both duration and in vital signs variation in the same view. Behavioural information can also be inferred by reviewing different hierarchies. For example, if trends in hierarchical level 2 shows increase in high intensity activity duration and hierarchical level 3 shows decrease in the duration for walk of high intensity then it indicates that the patient has been participating in other activities. Another example would be where hierarchical level 3 shows increases in heart rate for high intensity walk, which can indicate a patient's mobility was deteriorating. It would be difficult for a clinician to infer these results by reviewing only the top-level results.

[0054] This example user interface method combines physiological signal and hierarchical activity information to produce complex information in the form of a graphical view that a clinician can more easily and quickly analyse.

[0055] It would be appreciated that these embodiments can, by way of example only, be used for products associated with community care, chronic disease management, elderly care, physiotherapy, rehabilitation, personal wellness, or sports medicine. These embodiments can, by way of example only, be used in public care districts, private practices, and home care agencies that provide community care services.

Interpretation

[0056] It would be appreciated that, some of the embodiments are described herein as a method or combination of elements of a method that can be implemented by a processor of a computer system or by other means of carrying out the function. Thus, a processor with the necessary instructions for carrying out such a method or element of a method forms a means for carrying out the method or element of a method. Furthermore, an element described herein of an apparatus embodiment is an example of a means for carrying out the function performed by the element for the purpose of carrying out the invention.

[0057] In alternative embodiments, the one or more processors operate as a standalone device or may be connected, e.g., networked to other processor(s), in a networked deployment, the one or more processors may operate in the capacity of a server or a client machine in server-client network environment, or as a peer machine in a peer-to- peer or distributed network environment.

[0058] Thus, one embodiment of each of the methods described herein is in the form of a computer-readable carrier medium carrying a set of instructions, e.g., a computer program that are for execution on one or more processors.

[0059] Unless specifically stated otherwise, as apparent from the following discussions, it is appreciated that throughout the specification discussions utilizing terms such as "processing", "computing", "calculating", "determining" or the like, can refer to the action and/or processes of a computer or computing system, or similar electronic computing device, that manipulate and/or transform data represented as physical, such as electronic, quantities into other data similarly represented as physical quantities.

[0060] In a similar manner, the term "processor" may refer to any device or portion of a device that processes electronic data, e.g., from registers and/or memory to transform that electronic data into other electronic data that, e.g., may be stored in registers and/or memory. A "computer" or a "computing machine" or a "computing platform" may include one or more processors.

[0061] The methodologies described herein are, in one embodiment, performable by one or more processors that accept computer-readable (also called machine-readable) code containing a set of instructions that when executed by one or more of the processors carry out at least one of the methods described herein. Any processor capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken is included.

[0062] Unless the context clearly requires otherwise, throughout the description and the claims, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is to say, in the sense of "including, but not limited to".

[0063] As used herein, unless otherwise specified the use of the ordinal adjectives "first", "second", "third", etc., to describe a common object, merely indicate that different instances of like objects are being referred to, and are not intended to imply that the objects so described must be in a given sequence, either temporally, spatially, in ranking, or in any other manner.

[0064] Reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment, but may refer to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner, as would be apparent to one of ordinary skill in the art from this disclosure, in one or more embodiments.

[0065] Similarly it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

[0066] Furthermore, while some embodiments described herein include some but not other features included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention, and form different embodiments, as would be understood by those in the art. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0067] In the description provided herein, numerous specific details are set forth.

However, it is understood that embodiments of the invention may be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description. Although the invention has been described with reference to specific examples, it will be appreciated by those skilled in the art that the invention may be embodied in many other forms.

Claims

THE CLAIMS DEFINING THE INVENTION ARE AS FOLLOWS:

1. A method for hierarchical activity classification of a plurality of input time series signals, said method comprising the steps of:

(a) selecting a condition for defining a hierarchical activity classification; (b) classifying one or more time periods across each said input time series signal, wherein the selected said condition is satisfied during each said one or more time periods;

(c) calculating one or more hierarchical activity results, wherein each said hierarchical activity result is indicative of an output measure derived from one or more said time series signals over the classified said one or more time periods; and

(d) displaying said one or more hierarchical activity results.

2. A method as claimed in claim 1, said method further comprising the steps of:

(e) providing a plurality of further input time series signals, wherein each said further input time series is indicative of respective one of the previous said input time series signals over the previously classified said one or more time periods; and

(f) repeating steps (a) through (d) substituting said further input time series signals as said plurality of input time series signals for displaying a further said hierarchical activity results.

3. A method as claimed in claim 2, said method further comprising the steps of:

(g) recursively repeating steps (e) and (f) to a predefined depth for displaying a further hierarchical activity results.

4. A method as claimed in any previous claim wherein said output measure is selected from the group including: a time series measure; and a numerical measure.

5. A method as claimed in any previous claim wherein each of said time series signals is selected from the group including: a physical activity measurement signals; and a physiological measurement signals.

6. A method as claimed in any previous claim wherein the selected said condition is selected from the group including: a binary condition applied to an identifiable activity derived from one or more said time series signals; a binary condition applied to values of one or more said time series signal; and a binary condition applied to a calculated value derived from one or more said time series signal.

7. A method as claimed in any previous claim wherein said hierarchical activity result includes a graphical display indicative of one or more of said output measure.

8. A method as claimed in claim 7 wherein said hierarchical activity result includes a graphical display indicative of a plurality of said output measure displayed on a single graph.

9. A method as claimed in any previous claim wherein said hierarchical activity result includes a numerical display of a calculated measure indicative of one or more of said output measure.

10. A method for hierarchical activity classification of a plurality of input time series signals substantially as herein described with reference to any one of the embodiments of the invention illustrated in the accompanying drawings and/or examples.

11. An apparatus for hierarchical activity classification of a plurality of input time series signals, said apparatus adapted to perform a method as claimed in any previous claim.

12. An apparatus for hierarchical activity classification of a plurality of input time series signals, said apparatus comprising: an input module adapted to receive a plurality of input time series signals and data indicative of a selected condition to define a hierarchical activity classification; a process module adapted to classify one or more time periods across each input time series signal such that the selected said condition is satisfied during each one or more time periods, said process module further adapted to calculate one or more hierarchical activity results such that each hierarchical activity result is indicative of an output measure derived from one or more time series signals over the classified one or more time periods; and a display module adapted to display said one or more hierarchical activity results.

13. An apparatus as claimed in claim 12, wherein said display module is adapted to provide said one or more hierarchical activity results via a web portal.

14. An apparatus as claimed in claim 12 or claim 13, wherein said a process module is a distributed process module.

15. An apparatus for hierarchical activity classification of a plurality of input time series signals substantially as herein described with reference to any one of the embodiments of the invention illustrated in the accompanying drawings and/or examples.

16. A computer-readable carrier medium carrying a set of instructions that when executed by one or more processors cause the one or more processors to carry out a method for hierarchical activity classification of a plurality of input time series signals, said method comprising: (a) selecting a condition for defining a hierarchical activity classification;

(b) classifying one or more time periods across each said input time series signal, wherein the selected said condition is satisfied during each said one or more time periods;

(d) displaying said one or more hierarchical activity results.

17. A computer-readable carrier medium carrying a set of instructions that when executed by one or more processors cause the one or more processors to carry out a method for hierarchical activity classification of a plurality of input time series signals substantially as herein described with reference to any one of the embodiments of the invention illustrated in the accompanying drawings and/or examples.

18. A computer program product stored on a computer readable medium, the computer program product adapted to provide a hierarchical activity classification of a plurality of input time series signals, the computer program product comprising: a computer readable program means for selecting a condition for defining a hierarchical activity classification; a computer readable program means for classifying one or more time periods across each said input time series signal, wherein the selected said condition is satisfied during each said one or more time periods; a computer readable program means for calculating one or more hierarchical activity results, wherein each said hierarchical activity result is indicative of an output measure derived from one or more said time series signals over the classified said one or more time periods; and a computer readable program means for displaying said one or more hierarchical activity results.

19. A computer program product stored on a computer readable medium, the computer program product adapted to provide a hierarchical activity classification of a plurality of input time series signals, the computer program product comprising a computer readable program means for performing a method according to any on or claims 1 to 10.

20. Computer hardware including one or more processors configured to perform a method according to any one of claims 1 to 10.