GB2494538A - Human stress detection system - Google Patents
Human stress detection system Download PDFInfo
- Publication number
- GB2494538A GB2494538A GB201216063A GB201216063A GB2494538A GB 2494538 A GB2494538 A GB 2494538A GB 201216063 A GB201216063 A GB 201216063A GB 201216063 A GB201216063 A GB 201216063A GB 2494538 A GB2494538 A GB 2494538A
- Authority
- GB
- United Kingdom
- Prior art keywords
- stress
- accelerometers
- artificial neural
- neural network
- person
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4884—Other medical applications inducing physiological or psychological stress, e.g. applications for stress testing
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Psychiatry (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Physiology (AREA)
- Educational Technology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Geophysics And Detection Of Objects (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention concerns a human stress detection system. Said system comprises a plurality of accelerometers 14, 16, 17 designed to be attached to the body of a person 11 and a processing unit 18 configured to detect a level of stress of said person 11on the basis of the accelerations measured by said accelerometers 14, 16, 17. In particular accelerometer 14 is located on the head and accelerometers 16 and 17 are located on the back and/or shoulders. The signals are processed to obtain data indicative of vibrations of the head with respect to the shoulders and/or back.
Description
HUMAN STRESS DETECTION SYSTEM
TECHNICAL FIELD OF INVENTION
The present invention relates to a system and a method for S detecting human stress.
In general, the present invention can be advantageously, but not exclusively, exploited to detect and monitor the levels ot stress of workers who perform tasks that require high levels of concentration and that, in consequence, can induce a high level of stress.
In particular, the present invention can be advantageously, hut not exclusively, exploited to detect and monitor the level of stress in subjects such as pilots of unmanned air vehicles, aircraft and helicopters, drivers of simple notor vehicles, rescue vehicles and trucks, machinery dperators, controllers of workstations dedicated to plant safety, athletes or sports enthusiasts in general, workers, specialized technicians, etc. In addition, the present invention can also be exploited in market research, company personnel selection and as a lie detector in police interrogations.
STATE OF THE ART
As is known, at present, in orér to déLect and monitor the stress of an individual, or a person, various physiological parameters are measured, such as, for example, blood pressure, heartbeat and heart rate, skin perspiration, breathing frequency and intensity, presence of cortiso] in saliva, pupil diameter and skin temperature.
For example, international patent application W02010107788.
describes a method for monitoring the stress of a person that includes: acquiring measurements *of one or more physiological parameter(s) of the persOn taken in a gIven period of tine; storing the acquired measurements; determining an average value of the stored measurements; and comparing measurements taken with the average value to identify any differences between said measurements and said average value so as to monitor and assess possible changes in the level of stress of the person.
In particular, according to international patent application Vo2oloio778B, the measurements of the physiological parameter can comprise: electrocardiogram results, arterial pressure measurements, breath pressure measurements, nervous activity measurements, galvanic skin response (also known as skin conductance) measurements and body temperature measurements.
The applicant has noted that known systems and methods for detecting and monitoring the stress of an individual, such as those described in international patent application W020l0l07788 for example, are somewhat invasive or, in any case, do not allow the subject to have freedom of movement as, in order to measure the abcve-stated physiological parameters, sensors with wires or cables that restrict the subject are used, or because they require the subject or certain parts of the subject's body to stay in specific positions whilst taking the measurements in order for Ehese tEe rneasurements of said physiological parameters to be taken correctly.
OBJECT AND SUMMARY OF TIlE INVENTION
The object of the present invention is therefore that of providing a system and method for detecting a level of stress of an individual that, in general, mitigate the previously described drawbacks, at least in part, and that, in particular, are not invasive and, in use, do not impose limitations in movement and/or posture of the monitored individual.
The above-stated object is achieved by the present invention insofar as it relates to a human stress detection system, a processor and a software program product, as defined in the appended claims.
In particular, the above-stated object is achieved by the present invention insofar as it relates to a human stress, detection system that comprises: a plurality of accelerometers designeed to be attached to the body of a person; and a processing unit configured to detect a level of stress of said person on the basis of accelerations measured by said accelerometers.
BRIEF DESCRIPTION OF DRAWINGS
For a better understanding of the present invention, some prefrred embodiments, provided by way of non-limitative example, will now be illustrated with reference to the attached drawings (not to scale), where: Figure 1 shows an embodiment of the presen invention; * -Figure 2 schematically shows the operations carried out in a training phase by a processing unit of a human stress detection system according to a preferred embodiment of the present invention; - * Figure 3 shows the performancedf a classifier of the human stress detection system according to said preferred embodiment of the present invention; and * Figure 4 schematically show5 the operations carried out in an operational phase by the procesing unit of the human stress detection system according to said preferred embodiment of the present invention. - * DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS OF THE INVENTION The following description is provided to enable an expert in
the field to embody and use the invention. Various
modifications to the embodiments presented will be immediately evident to experts in the field and the generic principles divulged herein could be applied to other embodiments and applications without, however, leaving the scope of protection of the present invention.
Therefore, the present invention should not be intended as limited to just the embodiments described and shown herein,.
but be conceded the broadest scope of protection consistent with the principles and characteristics described herein and defined in the appended claims.
A human stress detection system according to a preferred embodiment of the present invention comprises: a plurality of accelerometers, or rather sensors designed to detect and measure accelerations, that, in use, are attached to the body of a person so as to be positioned near to the head of the petson and near to the shoulders and/or the back and/or the neck of the person; and a processing unit that, in use, is connected to said accelerometers in a wired or wireless manner, i.e. with or without wires, to acquire signals indicative of accelerations measured by said accelerometers and is configured to detect a level of stress of the person on the basis of the acquired signals.
preferably, the accelerometers are triaxial accelerometers, i.e. sensors designed to detect and measure accelerations in three mutually orthogonal directions.
Conveniently, the accelerometers comprise: a first accelerometer that can be applied, directly or via a support, to any part of the head of the monitored subject; for example, said fit accelerometer could be positioned on a safety helmet, a hat, a helmet, headphones, an earphone or spectacle-frames worn, in use, by the monitored subject, or on any other support attached, in use, to the head the monitored subject; and one or more second accelerometers that can be applied, directly or via one or more supports, on the shoulders and/or the back and/or the *neck of the monitored subject; for example, said second accelerometer(s) could be located on a T-shirt worn, in use, by the monitored subject so as to be positioned, in use, near to the shoulders and/or the back.
and/or the neck of the monitored subject.
The accelerometers can also be applied to the monitored subject's body using adhesive tape, elastic bands or other means -Different types of wired or wireless links can be used to connect the processing unit to the accelerometers. In particular, the processing unit can be conveniently connected to the accelerometers: by wires; or by any radio communication technology, for example, by Bluetooth technology or the so-called Near Field Communication (I'JFC) technology or any mobile phone technology, and/or by a wireless network of the LAN (Local Area Network), WAN (Wide Area Network) , PAN (Personal Area Network) or BAN (Body Area Ietwork) type.
Depending on the type of link employed to connect the processing unit to the accelerometers, said processing unit can be remotely connected to the accelerometers and consequently be far away from the monitored subject, or it can be placed close to the monitored subject, or even attached to the monitored subject's body; for example, said processing unit could be conveniently placed on a belt or overalls worn, in use, by the monitored subject or on any other support attached, in use, to the monitored subject's body.
Figure 1 shows an embodiment of the previously described human stress detection system.
In particular, Figure 1 schematically shows an individual ii who is working at a computer (for simplicity, only a screen 12 and a keyboard 13 of said computer are shown in rigure 1) and whose stress is detected and monitored in real time by a system made according to an embodiment of the present, invention that comprises: a first accelerometer 14 placed on headphones 15 worn by the individual 11; * a second accelerometer 16 and a third accelerometer 17 placed on the back of the individual 11; and * a processing unit 18 that is placed on a belt 19 worn by the individual 11, is wired or wireless connected to the accelerometers 14, 16 and 17, and is configured to acquire from said accelerometers 14, 16 and 17 data indicative of the accelerations measured by said accelerometers 14, 16 and 17 and to detect a level of stress of the individual 11 in real time on the basis of the acquired data.
In order to describe the aforesaid preferred embodiment of the present invention in greater detail, the operation of the processing unit will now be described.
In particular, the processing unit is configured to: * process the signals acquired from the accelerometers so as to eliminate possible acceleration values indicative of movements by the monitored subject not related to stress, for example, indicative of voluntary movements by the monitored subject, in this way obtaining data indicative of vibrations of the head of the monitored subject with respect to the shoulders and/or the back and/or the neck of the monitored subject; and * detect a level of stress of the monitored subject in real time on the basis of said data indicative of vibrations -_7 of the head with respect to the shoulders and/or the back and/or the neck..
In detail the processing unit comprises a classifier trained S to detect a level of stress of the monitored subject on the basis of the data indicative of the vibrations of the head with respect to the shoulders and/or the back and/or the neck.
Preferably, said classifier comprises a monolithic artificial neural network, or an artificial noural network ensemble, trained so as to have a transfer function capable of correlating the data indicative of said vibrations with the state of stress felt by the monitored subject.
In particular, the transfer function of the monolithic artificial neural network or artificial neural network ensemble is determined via a preliminary phase known as "training", in which inputs and outputs of said monolithic artificial neural network or said artificial neural network ensemble are set.
In detail, the monolithic artificial neural network or artificial neural network ensemble is trained by subjecting each person who is destined to use the system forming the subject of the present invention to a controlled stimulation, one or more times in their life, during hich: * the accelerometers are applied to the head and shoulders and/or the back and/or the neck of said person; * said person is subjected to predetermined stress conditions; and, for each predefined stress condition to which said person is subjected, a corresponding level of stress of said person is detected, for example, using: any known stress detection system for an individual based on the measurement qf physiological parameters.
Furthermore, in order to train the monolithic artificial neural network or artificial neural network ensemble, the processing unit performs the operations illustrated in the flowchart shown in Figure 2, namely: * an acquisition operation in which the processing unit acquires the detected levels of stress and signals indicative of the corresponding accelerations measured by the accelerometers during the controlled stimulation (block 21 shown in Figure 2); * a synchronization operation in which the raw signals acquired from the accelerometers are synchronized, or rather temporally correlated, with the correponding detected levels of stress (block 22 shown in Figure 2); * a normalization operation in which the acceleration levels contained in the signals acquired from the accelerometers are normalized with respect to one or more indicatttte average values of one or more voluntary movements of the person, the information content of which is, in this way, cancelled (block 23 shown in Figure 2); * a segmentation operation in which the significant sampling windows for stress analysis are separated in a coherent manner (block 24 shown in Figure 2) * a spectral analysis operation in which a Fourier transformation is applied to the segmented signals so as to extract the frequency content of the vibrations of the head with respect to the shoulders and/or the back and/or the neck (block 25 shown in Figure 2); * an extraction of characteristics and data assembly bperation in which the frequency data is converted into the final format accepted by the monolithic artificial neural network or by the artificial neural network ensemble; in particular, for each sampling instant, the frequency data *is converted into a corresponding identification value of a * vibration (block 26 shown in Figure 2); and * * a training operation of the monolithic artificial nOural network or artificial neural network ensemble in which the vibration identification values are supplied as input to the monolithic artificial neural network or the artificial neuralnetwork ensemble to be trained, while the corresponding detected levels of stress are set, instant by instant, from the output (block 27 shown in Figure 2) In this way, the definition of the transfer function of the classifier, i.e. the monolithic artificial neural network or, th artificial neural network ensemble, is reached through a series of successive approximations. This transfer function will then be used during the actual operational phase regarding the same monitored subject.
The effectiveness in training the classifier, in particular the monolithic artificial neural network or the artificial neural network ensemble, can be conveniently assessed by means of two parameters, called precision if and recall p, which are respectively defined as: 2P and TP+FP
TP
TP+FN' where TP is the number of true positive cases, i.e. it represents the number of cases in which levels of stress are correctly detected by the classifier, in particular by the monolithic artificial neural network or the artificial neural network ensemble; * FP is the number Df false positive cases, i.e. it represents the number of cases in which levels of stress are eroneously detected by the classifier, in particular by the monolithic artificial neural network or the artificial neural network ensemble; and.
* FN is the number of false negative cases, i.e. it -10 -represents the number of cases in which levels of stress are not detected by the classifier, in particular by the monolithic artificial neural network or the artificial neural network ensemble.
In detail, the precision r *and recall p parameters respectively indicate the capacity of the previously trained classifier (in particular of the monolithic artificial neural, network or the artificial neural network ensemble) to distinguish a real stress condition from a false alarm andthe capacity to keep missing alarms at a low level.
The closer the precision ir and recall p parameters are to a value of one, the more reliable the classifier is in detecting stress conditions.
In connection with this, Figure 3 shows a graph representing the levels of precision if and recall p reached by the present invention in the case where the classifier employed is implemented via a monolithic artificial neural network (in Figure 3, this classifier is indicated as classifier 1) and in the case where the classifier employed is implemented via an artificial neural network ensemble (in Figure 3, this classifier is indicated as classifier 2) -In particular, the levels of prcision r and recall p shown in Figure 3 are related to two different stress thresholds, specifically to two intermediate stress levels on an overall scale comprising 5 stress levels (in Figure 3 these intermediate stress levels are respectively indicated as level 2 and level 3) As can be noted from Figure 3, the levels of precision r and recall p reached. by the present inventiof' are very high. This demonstrates that, independently of the specific ithplementation of the classifier, the system according to the present invention is able to detect the stress of a subject under analysIs with high levels of accuracy and reliability.
Finally, in the operational phase, the processing unit performs the operations illustrated in the flowchart shown in Figure 4, namely: an acquisition Operation in which the processing unit acquires signals from the accelerometers indicative the respectively measured accelerations (block 41 shown in Figure 4); a normalization operation in which the acceleration levels contained in the signalS acquired from the accelerometers are normalized with respect to one or more indicative average values of one or more voluntary movements of the person, the information content of which is, in this way, cancelled (block 42.shown in Figure 4); a segmentation operatfon in which the significant sampling windows for stress analysis are separated in a coherent manner (block 43 shown in Figure 4) a spectral analysis operation in which a Fourier transformation is applied to the segmented signals so as to extract the frequency content of the vibrations of the head with respect to the shoulders and/or the back and/or the neck (block 44 shown in Figure 4); an extraction of characteristics and data assembly operation in which the frequency data i converted into the final format accepted by the monolithic artificial neural network or by the artificial neural network ensemble; in particular, for each sampling instant, the frequency data is 3O cOnverted into a corresponding identification value of a vibration (block 45 shown in Figure 4); and * a detection operation in whihh the vibration identification values *are supplied as input to the previously trained monolithic artificial neural network or artificial neura] network ensemble and, for each sampling instant, said monolithic artificial neural network or said artifIcial neural -12 -network ensele detect a possible corresponding level of stress of the monitored subject on the basis of the corresponding identification value of a vibration (block 46 shown in Figure 4) The advantages of the present invention can be immediately
appreciated from the foregoing description.
In particular, the present inventaon possesses the following technical advantages: * stress detection is precise and effective (accuracy and reliability) * detection is immediate, or rather it takes place in real time; cost of the system is low (inexpensiveness) * the measurement is not disturbed by the presence of the accelerometers (non-invasive character) the subject under analysis has total freedom of movement and is not restricted (transportability); * the system can be specially calibrated for each person and for each specific application environment (adaptability) and * the system's alarm levels can be changed to adapt them to the stress levels that are recognized as being acceptable in the environment in which the system is used (flexibility) It is important to underline that the present invention can be advantageously exploited in all applications where stress detection is difficult with invasive traditional techniques and/o.r ones that use sensors that restrict the subject with wires or electric cables and/or that require the subject to be monitored or certain parts of the subject's body be kept in specific positions whilst taking the rneasurementsin order for these the measurements to be taken correctly. ln fact, unlike the* traditional techniques, the system forming the subject of the present invention does not limit the movements of the -13'-monitored subject in any way and any movements, made by the subject do, not compromise taking correct measurements.
Furthermore since the accelerometers are surface accelerometer sensors and, preferably, the connections between the accelerometers and the processing unit are wireless:, the presence of the system forming the subject of the present invention does not affect the measurements to be taken in any way.' In conclusion, the present invention can be advantageously, but not exclusively, exploited for detecting and monitoring the level of stress of: * workers who perform tasks that require high levels of concentration and that, in consequence, can induce a high level of stress; * pilots of unmanned air vehicles, aircraft and helicopters, and drivers of simple motor vehicles, rescue vehicles and trucks; * machinery operators; controllers of workstations dedicated to plant safety; * athletes or sports enthusiasts in general; * workers; * specialized technicians; * etc. Finally, it is' clear that various modifiations can be applied to the present.invention without leaving the scope of protection of the invention defined in the appended claims. ,
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| IT000796A ITTO20110796A1 (en) | 2011-09-07 | 2011-09-07 | HUMAN STRESS DETECTION SYSTEM |
Publications (3)
| Publication Number | Publication Date |
|---|---|
| GB201216063D0 GB201216063D0 (en) | 2012-10-24 |
| GB2494538A true GB2494538A (en) | 2013-03-13 |
| GB2494538A8 GB2494538A8 (en) | 2013-05-15 |
Family
ID=44899200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| GB201216063A Withdrawn GB2494538A (en) | 2011-09-07 | 2012-09-07 | Human stress detection system |
Country Status (2)
| Country | Link |
|---|---|
| GB (1) | GB2494538A (en) |
| IT (1) | ITTO20110796A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104000604A (en) * | 2014-05-14 | 2014-08-27 | 李起武 | Toy lie detector |
| CN104000613A (en) * | 2014-05-14 | 2014-08-27 | 李起武 | Toy lie detector |
| CN104000612A (en) * | 2014-05-14 | 2014-08-27 | 李起武 | Toy lie detector |
| GB2545764A (en) * | 2016-06-21 | 2017-06-28 | Flashy Ltd | A communication system and a method of communication |
| CN110192872A (en) * | 2019-04-16 | 2019-09-03 | 华为技术有限公司 | Stress appraisal calibration method, device and storage medium |
| WO2020039428A1 (en) * | 2018-08-19 | 2020-02-27 | Sensority Ltd. | Machine classification of significant psychophysiological response |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2742161C1 (en) * | 2020-04-24 | 2021-02-02 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Тульский государственный университет" (ТулГУ) | Method for diagnosing stress resistance |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006082565A1 (en) * | 2005-02-07 | 2006-08-10 | Koninklijke Philips Electronics N.V. | Device for determining a stress level of a person and providing feedback on the basis of the stress level as determined |
| WO2008055078A2 (en) * | 2006-10-27 | 2008-05-08 | Vivometrics, Inc. | Identification of emotional states using physiological responses |
| US20110105862A1 (en) * | 2008-04-28 | 2011-05-05 | Universite Du Sud Toulon-Var | Device for acquiring and processing physiological data of an animal or of a human in the course of a physical or mental activity |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SE0202948D0 (en) * | 2002-10-04 | 2002-10-04 | Bergfalk & Knagenhjelm Ab | Ways of detecting activity patterns that indicate mental illness, and corresponding arrangements |
| US20090149778A1 (en) * | 2004-11-23 | 2009-06-11 | Koninklijke Philips Electronics, N.V. | Depression detection system |
| US20100280336A1 (en) * | 2009-04-30 | 2010-11-04 | Medtronic, Inc. | Anxiety disorder monitoring |
-
2011
- 2011-09-07 IT IT000796A patent/ITTO20110796A1/en unknown
-
2012
- 2012-09-07 GB GB201216063A patent/GB2494538A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006082565A1 (en) * | 2005-02-07 | 2006-08-10 | Koninklijke Philips Electronics N.V. | Device for determining a stress level of a person and providing feedback on the basis of the stress level as determined |
| WO2008055078A2 (en) * | 2006-10-27 | 2008-05-08 | Vivometrics, Inc. | Identification of emotional states using physiological responses |
| US20110105862A1 (en) * | 2008-04-28 | 2011-05-05 | Universite Du Sud Toulon-Var | Device for acquiring and processing physiological data of an animal or of a human in the course of a physical or mental activity |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104000604A (en) * | 2014-05-14 | 2014-08-27 | 李起武 | Toy lie detector |
| CN104000613A (en) * | 2014-05-14 | 2014-08-27 | 李起武 | Toy lie detector |
| CN104000612A (en) * | 2014-05-14 | 2014-08-27 | 李起武 | Toy lie detector |
| GB2545764A (en) * | 2016-06-21 | 2017-06-28 | Flashy Ltd | A communication system and a method of communication |
| GB2545764B (en) * | 2016-06-21 | 2022-04-06 | Flashy Ltd | A communication system and a method of communication |
| WO2020039428A1 (en) * | 2018-08-19 | 2020-02-27 | Sensority Ltd. | Machine classification of significant psychophysiological response |
| CN110192872A (en) * | 2019-04-16 | 2019-09-03 | 华为技术有限公司 | Stress appraisal calibration method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| ITTO20110796A1 (en) | 2013-03-08 |
| GB2494538A8 (en) | 2013-05-15 |
| GB201216063D0 (en) | 2012-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| GB2494538A (en) | Human stress detection system | |
| US8529448B2 (en) | Computerized systems and methods for stability—theoretic prediction and prevention of falls | |
| EP3065628B1 (en) | Biomechanical activity monitoring | |
| CN107490999B (en) | Systems, methods, and apparatus for sensing environmental conditions and alerting a user | |
| US20200285873A1 (en) | Wearable authentication device | |
| US20080319281A1 (en) | Device for Detecting and Warning of Medical Condition | |
| JP2009525107A (en) | Gait analysis | |
| US20190261910A1 (en) | Information processing apparatus, information processing method, and program | |
| CN109770863A (en) | Suitable for personnel's safety supervision bracelet under high temperature and humidity place | |
| US20190183404A1 (en) | Method of indicating the probability of psychogenic non-epileptic seizures | |
| US11699524B2 (en) | System for continuous detection and monitoring of symptoms of Parkinson's disease | |
| WO2017190965A1 (en) | A method and apparatus for verifying whether to change a determined wearing status of a device | |
| WO2021046968A1 (en) | Wearable device-based doctor health monitoring system | |
| WO2016092159A1 (en) | Device and method for determining a state of consciousness | |
| US20200210689A1 (en) | A system and a method for analyzing a behavior or an activity of an object | |
| KR20200066290A (en) | Method and device for detecting stress using ECG function between beats | |
| US20220280051A1 (en) | In-ear wearable device | |
| CN108882883A (en) | Parasympathetic autonomic nerves system is measured to while sympathetic autonomic nerves system to independent activities, related and analysis method and system | |
| KR102451630B1 (en) | Impairment detection with environmental considerations | |
| KR20170142227A (en) | Method for Monitoring of Sleeping State using Bio Signals | |
| US20230094452A1 (en) | Measuring physiological characteristics | |
| Adamec et al. | Statistical characterization of actigraphy data during sleep and wakefulness states | |
| Cavuoto et al. | A Data-Driven Approach to Identifying Physical Fatigue | |
| GB2600104A (en) | Method and system for determining a recovery score for a subject | |
| CN116236175A (en) | Wearable device and respiratory tract infection evaluation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WAP | Application withdrawn, taken to be withdrawn or refused ** after publication under section 16(1) |