CN109717831B - Non-interference type nervous system disease auxiliary detection system based on touch gestures - Google Patents
Non-interference type nervous system disease auxiliary detection system based on touch gestures Download PDFInfo
- Publication number
- CN109717831B CN109717831B CN201811416118.7A CN201811416118A CN109717831B CN 109717831 B CN109717831 B CN 109717831B CN 201811416118 A CN201811416118 A CN 201811416118A CN 109717831 B CN109717831 B CN 109717831B
- Authority
- CN
- China
- Prior art keywords
- finger
- module
- nervous system
- touch screen
- variance
- 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.)
- Active
Links
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a non-interference type nervous system disease auxiliary detection system based on touch gestures, which belongs to the field of digital medical treatment, and mainly comprises the steps of collecting gesture operation data by utilizing touch screen actions of a subject to be diagnosed in a touch screen process based on a trained nervous system disease diagnosis model K, judging through the nervous system disease diagnosis model, quantitatively analyzing and mining more information of diseases, and being applied to early disease diagnosis, prevention and rehabilitation state monitoring to achieve the effect of preventing diseases in the bud.
Description
Technical Field
The invention belongs to the field of digital medical treatment, and particularly relates to a non-interference type nervous system disease auxiliary detection system based on touch gestures.
Background
With the rapid development of the scientific and technological level and the continuous improvement of the physical life, the average normal life of people is longer and longer, and the aging condition of the population is more and more serious, so that the care of the physical and mental health of the middle-aged and old people is necessary. Common diseases which seriously disturb the physical and mental health of middle-aged and elderly people include nervous system diseases such as Alzheimer's disease, Parkinson's disease, cerebrovascular disease and the like, and the diseases can cause damage to the functions of limb movements and the like of patients (reference document: Tangjie, Zeyan, Linbi mapping, strength and balance training influence the motor and posture control functions of the Parkinson's disease patients [ J ] nerve damage and function reconstruction, 2017,12(3):266 and 268.).
There are several medical approaches to detect nervous system function, among which the UPDRS rating scale is mainly used to determine the nervous system function of a patient by inquiring and observing the physical condition of the patient by the attending physician (refer to the following references: Neumann, Wolf Julian, et al, "nervous Synchronized cultured nervous Activity With Motor Imperial in Patents With Parkinson's disease," motion Disorderers 31.11(2016):1748-1751.), but this rating method mainly depends on the subjective judgment of the physician on the patient.
There are many methods for disease diagnosis and physiological state detection based on mobile devices and wearable devices in recent years. For example, a neural function evaluation multi-channel model for performing online test by using pen-type interaction can evaluate the cognitive and motor functions of a patient to a certain extent (reference documents: Huangjin, Chengyeng, Liujie, Tianfeng, Daizhong, Wang hong Ann. neural function evaluation multi-channel interaction model in a mobile environment. software bulletin, 2016,27(Sup.2): 156. 171). Tremor was assessed by subjects arcing with a pen on a cell phone application (ref: surangsrirate, Decho, et. "Tremor assessment using a screw analysis in time-frequency domain." Proceedings of IEEE heastcon IEEE,2013: 1-6.). For example, a real-time gait feedback program is designed, which can detect the gait state of the patient and remind the Parkinson's disease person by audio frequency, so as to better cooperate with the rehabilitation therapy (refer to Casassima, Filippo, et al, "week audio-feedback system for the rehabilitation in subjects with Parkinson's disease," ACM Conference on Peractive and Ubiotus Computing addition Publication ACM,2013: 275-. Cao et al used Kinect to perform gait tests on subjects to compare Parkinson's, hemiplegic and healthy adults (references: Cao, Ya, et al, "Kinect-based gaps analyses of Patents with Parkinson's disease, Patents with Stroke with chemistry, and health adults," Cns Neuroscience & Therapeutics 23.5(2017): 447.). Min et al have devised a system for recording the noise, lights, acceleration, screen on/off, and sleep log information around the phone to assess the quality of sleep (Min, J.K., Doryab, A., Wiese, J., Amini, S., Zimmerman, J., & Hong, J.I. (2014.) Toss 'n' turn: smart phone as sheet and sheet quality detector Sigchi Conference on Human Factors Computing Systems (pp.477-486.) when the user sleeps at night.
Some of the methods presented above require the subject to participate in some specific tasks or to use specialized equipment and sensors, and the subject may not be accustomed to some procedures and products. Smart phones are also becoming more common, and the touch screen of the smart phone can acquire coordinates, touch screen pressure and area clicked by a patient, and the acceleration sensor of the smart phone can detect the motion state of the smart phone. Arroyo-Gallego et al analyzed the motor function impairment of Parkinson's patients by typing them on a Mobile phone screen for a key press interval of 5 minutes (reference: Arroyo-Gallego, T, et al. "Detection of MotorImpatientin Parkinson's Disease video Mobile touch Screen typing." IEEETransactions on biological Engineering PP.99(2017):1-1.), but this experiment only analyzed the key press interval and did not add more information including pressure, acceleration sensors, etc. to the analysis.
Disclosure of Invention
The invention aims to provide a non-interference type nervous system disease auxiliary detection system based on touch gestures, which is characterized in that gesture operation data are collected by utilizing touch screen actions of a subject to be diagnosed in a touch screen process, judgment is carried out through a nervous system disease diagnosis model, more information of diseases is analyzed and mined quantitatively, and the system can be applied to early diagnosis, prevention and rehabilitation state monitoring of the diseases to achieve the effect of preventing the diseases in the bud.
In order to achieve the purpose, the specific technical scheme of the invention is as follows:
a non-interference type nervous system disease auxiliary detection system based on touch gestures comprises a data acquisition module and a data processing and analyzing module:
the data acquisition module comprises: the module detects the bottom state of a screen, acquires the global operation gesture event information of a subject in the process of using the mobile phone, and respectively collects three gestures through three sub-modules:
(1) the system comprises a clicking module, a display module and a display module, wherein the clicking module is used for generating a 9-dimensional vector Xt at a time t, a touch screen state, an X coordinate, a y coordinate, a touch screen pressure p, a touch screen area S and a numerical value of an acceleration sensor < v1, v2, v3> every time a subject clicks a touch screen key or a touch screen button by using a clicking gesture, and forming a sequence S0< X0, X1, X2,. multidot.,. Xm >, X0 which represents data collected at the 1 st moment according to a sampling rate (such as 10ms), and analogizing the sequence, wherein the value of m is changed according to the operation time;
(2) the single-finger sliding module is used for generating a 9-dimensional vector Xt < time t, a touch screen state, an X coordinate, a y coordinate, a touch screen pressure p, a touch screen area S and a value of an acceleration sensor < v1, v2 and v3> at the screen contact time t when a subject slides on a screen by using a single-finger sliding gesture, enabling all single-finger sliding actions to form a sequence S1< X0, X1, X2,. multidot.Xm >, X0 representing data collected at the 1 st time according to a sampling rate (such as 10ms), and repeating the steps until the value of m changes according to the time of the single-finger sliding operation;
(3) the multi-finger sliding module is used for generating a 5+4n (n is 2,3, …,10) -dimensional vector Xt according to the moment t of the touch screen and the number n of fingers on the touch screen when the subject slides on the screen by using a multi-finger sliding gesture, wherein the gesture refers to that each time the multi-finger slides on the screen to contact with the screen, and the multi-finger sliding gesture generates<Time t, touch screen state, acceleration sensor value<v1,v2,v3>N × x coordinate, n × y coordinate, n × touch screen pressure p, n × touch screen area s>(ii) a For example, when n is 2, X is 13-dimensional, i.e.<Time t, touch screen state, acceleration sensor value<v1,v2,v3>，x1Coordinate, y1Coordinates, touch screen pressure p1Area of touch screen s1，x2Coordinate, y2Coordinates, touch screen pressure p2Area of touch screen s2>(ii) a All multi-finger sliding motion forms a sequence S2 containing multiple Xts according to the sampling rate (such as 10ms)<X0,X1,X2,..,Xm>X0 represents the data collected at time 1, and so on, the value of m varies depending on the time of the multi-finger sliding operation.
II, a data processing and analyzing module: the module comprises three sub-modules of data preprocessing, feature extraction and model training:
(1) the data preprocessing module is used for preprocessing the acquired original data < S0, S1 and S2> to obtain < T0, T1 and T2 >;
(2) the characteristic extraction module is used for extracting the characteristics of the data < T0, T1 and T2> to obtain characteristics < B0, B1 and B2 >;
(3) the nervous system function evaluation module comprises a trained nervous system disease diagnosis model K, and the nervous system function evaluation module inputs the characteristics < B0, B1, B2> into the nervous system disease diagnosis model K so as to evaluate the nervous system function of the subject.
Further, the click gesture includes a click operation of tapping an input method and clicking an application button to edit a text on a screen.
Furthermore, the single-finger sliding gesture mainly comprises single-finger sliding operations of sliding the screen left and right, unlocking the graph and the like on the screen.
Further, the multi-finger sliding gesture mainly includes multi-finger simultaneous touch screen operations of zooming a picture, rotating the picture, and the like on the screen.
Further, the preprocessing performed by the data preprocessing module includes:
resampling the original data < S0, S1, S2> such that the interval time between sampling points is equal to T;
the sliding data in the original data < S0, S1, S2> is smoothed to reduce the degree of gesture shaking.
Further, the features extracted by the feature extraction module include:
for a tap gesture, the main extracted features B0 include: key time interval, key time variance, press-and-raise offset mean, press-and-raise offset variance, pressure mean, pressure variance, mobile phone acceleration mean, mobile phone acceleration variance, and mobile phone acceleration frequency domain mean;
for single-finger swipe gestures, the main extracted features B1 include: the average value of the sliding speed, the variance of the sliding speed, the average value of the pressure, the variance of the pressure, the average value of the acceleration of the mobile phone, the variance of the acceleration of the mobile phone and the average value of the acceleration frequency domain of the mobile phone;
for multi-finger swipe gestures, the main extracted features B2 include: the mobile phone acceleration detection method comprises the following steps of multi-finger deflection angle speed mean, multi-finger deflection angle speed variance, multi-finger relative speed mean, multi-finger relative speed variance, finger i pressure mean, finger i pressure variance, finger i speed mean, finger i speed variance, mobile phone acceleration mean, mobile phone acceleration variance and mobile phone acceleration frequency domain mean, wherein i is 1, 2.
Furthermore, the system also comprises a nervous system function medical examination module which is used for evaluating the testee according to a medical nervous system function evaluation scale, the evaluation process does not depend on the original data < S0, S1 and S2>, but the medical evaluation is carried out on the testee according to the clinical observation and medical instruments of doctors, and the evaluation result is analyzed to obtain a nervous system function score Q; and the nervous system function evaluation module trains a nervous system disease diagnosis model K by adopting a mathematical modeling and machine learning method according to the characteristics < B0, B1 and B2> and the nervous system function score Q. When the model is used for diagnosing a new subject after the training of the model is completed, the scoring of the nervous system function medical examination module can be avoided, and the medical examination process is simplified.
Further, the medical examination module for nervous system function adopts a medical standard nervous system scoring mechanism, and after standard and comprehensive medical clinical examination of the subject, the examination result is divided into different grades, for example, the grade is divided into 0-5, 0 represents that the nervous system function is healthy, and 5 represents that the nervous system function is seriously damaged, so that the nervous system function score Q is obtained.
Further, the medical neurological function assessment scale includes the UPDRS unified parkinson's disease assessment scale and the montreal cognitive assessment scale for MOCA cognitive function assessment.
Further, the model training process is based on a certain amount of nervous system disease patients (such as Parkinson disease patients and cerebral small vessel disease patients) and healthy people under the same physiological conditions to carry out experimental verification of the model.
Further, the data acquisition module is supported on a mobile phone, a tablet and a touch screen device capable of acquiring clicking, single-finger sliding and multi-finger sliding gestures.
And the result output module is used for outputting the result evaluated by the model K and has at least one function of displaying on a display screen, printing, sending a short message, generating a bar code or a two-dimensional code.
Compared with the prior art, the invention has the advantages and positive effects as follows:
1) the invention realizes the automation of data acquisition, analysis and diagnosis in the process of evaluating and analyzing the function of the nervous system, reduces the time and labor required by the traditional test, and has simple and convenient use.
2) The detection of the present invention is non-interfering. The non-interference means that the behavior habit of the user is not changed in the using process, the user can operate the touch screen device driven by the daily behavior habit, the user does not need to study specially, the behavior characteristic of the touch screen device used by the user in a daily normal mode is kept consistent, and therefore interference caused by unfamiliarity of the user with the touch screen device can be eliminated.
3) The evaluation index of the nervous system function of the user is quantified, the nervous system function status of the user is graded, the problem of qualitative or semi-quantitative analysis of the nervous system function by the traditional disease monitoring tool is solved, and the quantitative analysis is realized.
4) The system can enable a user to give auxiliary functions of early warning, diagnosis and rehabilitation treatment in the aspect of nervous system diseases. Reminding the patient to intervene in the treatment as soon as the early symptoms of the disease begin, and achieving the best treatment effect. Meanwhile, in the rehabilitation process, the patient can monitor the disease condition change in real time by using the invention.
Drawings
Fig. 1 is a schematic diagram illustrating a non-interfering neurological disease auxiliary detection principle based on touch gestures.
Fig. 2 is a schematic structural diagram of a non-interfering neurological disease auxiliary detection system based on touch gestures according to an embodiment.
Detailed Description
The present invention will be described in detail with reference to the following embodiments, which are intended to explain the purpose, features, and advantages of the invention.
The embodiment discloses a non-interference type nervous system disease auxiliary detection system based on a touch gesture, the principle of which is shown in fig. 1, gesture operation data (including clicking, single-finger sliding and multi-finger sliding) of a subject are collected, nervous system medical examination is carried out, data preprocessing, feature extraction and model construction are carried out, the model is used for carrying out diagnosis and evaluation on the nervous system function of the subject, and the purpose of carrying out non-interference type nervous system disease auxiliary detection on the subject is achieved.
The structure of the system is shown in fig. 2, and is specifically explained as follows:
1) and the gesture operations of clicking, single-finger sliding, multi-finger sliding and the like in the touch screen process of the subject are recorded through a clicking module, a single-finger sliding module and a multi-finger sliding module of the data acquisition module.
2) The data preprocessing module of the data processing and analyzing module is used for preprocessing the original data as follows:
2.1) resampling the original data, and the algorithm is as follows:
a) and manually setting a proper sampling frequency, wherein the sampling time interval is T, and initializing a resampling point set R and an initializing point time interval set D.
b) The first original sampling point SPoint0Added to the set of resample points R.
c) Calculating the SPoint between two adjacent points of the set of the original sampling points SPointsi,SPointi-1The time interval between t _ gap, t _ gap is added to D.
d) If T _ gap < T, increase i by 1, and jump back to step c)
e) Otherwise, a new point SPoint is generatedjNeed to be SPointjThe time between the last resample point and the last is approximately equal to T, the point is sampledjAdded to the set of resampled points R and inserted into the points SPointiBefore, jump back to step c).
2.2) smoothing the original data: three successive points, SPoids, are taken from the set of original sampling points, SPoidsi-1,SPointi,SPointi+1Calculating the average value of the three points, and recording as yjThereby generating a new point SPointjWill SPointjAdded to the set of smoothed sample points, spiints.
3) The feature extraction module of the data processing and analyzing module is used for extracting features, and the method mainly comprises the following aspects:
3.1) for tap gestures, the main extracted features B0 include: key time interval, key time variance, press-and-lift offset mean, press-and-lift offset variance, pressure mean, pressure variance, cell phone acceleration mean, cell phone acceleration variance, cell phone acceleration frequency domain mean.
3.2) for single-finger swipe gestures, the main extracted features B1 include: the average value of the sliding speed, the variance of the sliding speed, the mean value of the pressure, the variance of the pressure, the average value of the acceleration of the mobile phone, the variance of the acceleration of the mobile phone and the average value of the acceleration frequency domain of the mobile phone.
3.3) for multi-finger swipe gestures, the main extracted features B2 include: the mobile phone acceleration detection method comprises the following steps of multi-finger deflection angle speed mean, multi-finger deflection angle speed variance, multi-finger relative speed mean, multi-finger relative speed variance, finger i pressure mean, finger i pressure variance, finger i speed mean, finger i speed variance, mobile phone acceleration mean, mobile phone acceleration variance and mobile phone acceleration frequency domain mean, wherein i is 1, 2.
The characteristics < B0, B1, B2> can be obtained from the above.
4) Through a nervous system function medical examination module, a subject is medically evaluated by a doctor through clinical observation and medical instruments, and a nervous system function score Q is obtained through analysis and serves as a label.
5) Training the model by a nervous system function evaluation module of the data processing analysis module:
and (3) taking the characteristics < B0, B1 and B2> and < B0, B1, B2 and Q > obtained by Q as the data part of a training set, constructing a mathematical model by using mathematical modeling, carrying out model training by using a machine learning method, and training a nervous system disease diagnosis model K. The model training process is based on a certain number of Parkinson's patients and healthy people under the same physiological conditions.
After the model K is trained, the system can be used for diagnosing and evaluating the functions of the nervous system of a new subject according to the trained model, gesture action data of the new subject are collected through the data collection module according to the process, the gesture action data are tested through the data processing and analyzing module, the data of the subject are analyzed, the model K trained through the nervous system function evaluation module is used for diagnosing and evaluating, and the quantitative evaluation result of the functions of the nervous system of the subject is given.
6) And outputting the evaluation result through a result output module, such as displaying through a display screen, printing, sending a short message, generating a bar code or a two-dimensional code and the like.
The click module, the single-finger sliding module and the multi-finger sliding module of the embodiment are supported by a mobile phone, a tablet and any other touch screen equipment which can acquire the three gestures and is used by a subject.
The non-intrusive neurological disease auxiliary detection system based on touch gestures is described in detail above with reference to embodiments, but the specific implementation form of the present invention is not limited to this. Various obvious changes and modifications can be made by one skilled in the art without departing from the spirit and principles of the process of the invention. The protection scope of the present invention shall be subject to the claims.
Claims (10)
1. A non-interference type nervous system disease auxiliary detection system based on touch gestures comprises a data acquisition module and a data processing and analyzing module, wherein the data processing and analyzing module comprises a feature extraction module and a nervous system function evaluation module; the system is characterized in that the data acquisition module comprises a click module, a single-finger sliding module and a multi-finger sliding module; the data processing and analyzing module also comprises a data preprocessing module; wherein the content of the first and second substances,
the clicking module is used for generating a 9-dimensional vector Xt at a clicking moment t, a touch screen state, an X coordinate, a y coordinate, a touch screen pressure p, a touch screen area S and a numerical value of an acceleration sensor < v1, v2, v3> during the process that a subject clicks an input method or a key of a screen by using a clicking gesture, and enabling all clicking actions to form a sequence S0< X0, X1, X2., Xm > containing a plurality of Xts according to a sampling rate;
the single-finger sliding module is used for generating a 9-dimensional vector Xt at the moment t of screen contact, the touch screen state, the X coordinate, the y coordinate, the touch screen pressure p, the touch screen area S and the value of an acceleration sensor < v1, v2, v3> when a subject slides on a screen by using a single-finger sliding gesture, and enabling all single-finger sliding actions to form a sequence S1< X0, X1, X2,.., Xm > containing a plurality of Xts according to the sampling rate;
the multi-finger sliding module is used for generating a 5+4 n-dimensional vector Xt < time t, a touch screen state, a numerical value < v1, v2, v3> of an acceleration sensor, an n × X coordinate, an n × y coordinate, n × touch screen pressure p, n × touch screen area S > according to the time t of a touch screen and the number n of fingers of the touch screen when a subject slides on the screen by using a multi-finger sliding gesture, wherein n is 2,3, …,10, and all multi-finger sliding actions form a sequence S2< X0, X1, X2,. Xm > containing a plurality of Xts according to a sampling rate;
the data preprocessing module is used for preprocessing the acquired original data < S0, S1 and S2> to obtain < T0, T1 and T2 >;
the characteristic extraction module is used for carrying out characteristic extraction on the data < T0, T1 and T2> to obtain characteristics < B0, B1 and B2 >;
the nervous system function evaluation module comprises a trained nervous system disease diagnosis model K, and the nervous system function evaluation module inputs the characteristics < B0, B1, B2> into the nervous system disease diagnosis model K so as to evaluate the nervous system function of the subject.
2. The system of claim 1, wherein the single-finger slide gesture comprises a single-finger left-right screen slide on the screen, graphical unlock operation gesture.
3. The system of claim 1, wherein the multi-finger swipe gesture comprises a multi-finger simultaneous manipulation gesture that zooms in a picture, rotates a picture on a screen.
4. The system of claim 1, wherein the pre-processing by the data pre-processing module comprises:
resampling the original data < S0, S1, S2> such that the interval time between sampling points is equal to T;
the sliding data in the original data < S0, S1, S2> is smoothed to reduce the degree of gesture shaking.
5. The system of claim 1, wherein the features extracted by the feature extraction module comprise:
for a tap gesture, the extracted features B0 include: key time interval, key time variance, press-and-raise offset mean, press-and-raise offset variance, pressure mean, pressure variance, mobile phone acceleration mean, mobile phone acceleration variance, and mobile phone acceleration frequency domain mean;
for a single-finger swipe gesture, the extracted feature B1 includes: the average value of the sliding speed, the variance of the sliding speed, the average value of the pressure, the variance of the pressure, the average value of the acceleration of the mobile phone, the variance of the acceleration of the mobile phone and the average value of the acceleration frequency domain of the mobile phone;
for a multi-finger swipe gesture, the extracted feature B2 includes: the mobile phone acceleration detection method comprises the following steps of multi-finger deflection angle speed mean, multi-finger deflection angle speed variance, multi-finger relative speed mean, multi-finger relative speed variance, finger i pressure mean, finger i pressure variance, finger i speed mean, finger i speed variance, mobile phone acceleration mean, mobile phone acceleration variance and mobile phone acceleration frequency domain mean, wherein i is 1, 2.
6. The system of claim 1, further comprising a neurological medical examination module for performing a medical clinical examination on the subject using a medically standard neurological scoring mechanism according to a medical neurological assessment scale to obtain a neurological score Q; and training a nervous system disease diagnosis model K by the nervous system function evaluation module according to the characteristics < B0, B1 and B2> and the nervous system function score Q.
7. The system of claim 6, wherein the medical neurological assessment scale comprises the UPDRS unified Parkinson's disease assessment scale and the Montreal cognitive assessment scale for MOCA cognitive function assessment.
8. The system of claim 6, wherein the model K training process for diagnosing neurological disease is based on experimental validation of a certain number of patients with neurological disease and healthy persons under equivalent physiological conditions.
9. The system of claim 1, wherein the data collection module is supported on a cell phone, tablet, and touch screen device capable of collecting click, single-finger swipe, multi-finger swipe gestures.
10. The system of claim 1, further comprising a result output module for outputting a result evaluated by the neurological disease diagnosis model K, wherein the result output module has at least one of a function of displaying on a display screen, printing, sending a short message, generating a barcode or a two-dimensional code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811416118.7A CN109717831B (en) | 2018-11-26 | 2018-11-26 | Non-interference type nervous system disease auxiliary detection system based on touch gestures |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811416118.7A CN109717831B (en) | 2018-11-26 | 2018-11-26 | Non-interference type nervous system disease auxiliary detection system based on touch gestures |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109717831A CN109717831A (en) | 2019-05-07 |
| CN109717831B true CN109717831B (en) | 2020-06-30 |
Family
ID=66295144
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811416118.7A Active CN109717831B (en) | 2018-11-26 | 2018-11-26 | Non-interference type nervous system disease auxiliary detection system based on touch gestures |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109717831B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111329444A (en) * | 2020-02-14 | 2020-06-26 | 桂林医学院附属医院 | Parkinson's disease condition monitoring system based on virtual keyboard |
| CN112244882B (en) * | 2020-10-30 | 2023-06-02 | 北京中科心研科技有限公司 | Disease early warning method and device based on multi-mode physiological data |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015148732A1 (en) * | 2014-03-25 | 2015-10-01 | Massachusetts Institute Of Technology | Apparatus and method for motor function characterization |
| CN106901689B (en) * | 2015-12-23 | 2020-04-10 | 中国科学院软件研究所 | Cognitive and motor function detection system based on physical interaction and data processing method |
| CN107066778A (en) * | 2016-10-03 | 2017-08-18 | 朴植 | The Nounou intelligent guarding systems accompanied for health care for the aged |
| CN107273677A (en) * | 2017-06-08 | 2017-10-20 | 中国科学院软件研究所 | A kind of multi-channel nerve function quantitative evaluation system |
-
2018
- 2018-11-26 CN CN201811416118.7A patent/CN109717831B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109717831A (en) | 2019-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11468288B2 (en) | Method of and system for evaluating consumption of visual information displayed to a user by analyzing user's eye tracking and bioresponse data | |
| US20230240534A1 (en) | Apparatus and method for user evaluation | |
| US9155487B2 (en) | Method and apparatus for biometric analysis using EEG and EMG signals | |
| EP2568881B1 (en) | Apparatus for use in diagnosing and/or treating neurological disorder | |
| KR101854812B1 (en) | Psychiatric symptoms rating scale system using multiple contents and bio-signal analysis | |
| US20200375500A1 (en) | Systems and methods for detection and correction of abnormal movements | |
| Sahyoun et al. | ParkNosis: Diagnosing Parkinson's disease using mobile phones | |
| Sigcha et al. | Deep learning and wearable sensors for the diagnosis and monitoring of Parkinson’s disease: a systematic review | |
| CN109715049A (en) | For the multi-modal physiological stimulation of traumatic brain injury and the agreement and signature of assessment | |
| CN109717831B (en) | Non-interference type nervous system disease auxiliary detection system based on touch gestures | |
| Skaramagkas et al. | Multi-modal Deep Learning Diagnosis of Parkinson’s Disease-A Systematic Review | |
| CN108962397B (en) | Pen and voice-based cooperative task nervous system disease auxiliary diagnosis system | |
| CN108962379B (en) | Mobile phone auxiliary detection system for cranial nerve system diseases | |
| Antunes et al. | A morphology-based feature set for automated Amyotrophic Lateral Sclerosis diagnosis on surface electromyography | |
| KR20020082828A (en) | Real-time integrated sensibility assessments method and system thereof | |
| Carrino et al. | Gesture segmentation and recognition with an EMG-based intimate approach-an accuracy and usability study | |
| CN113921131A (en) | Method for recognizing handwriting of neurodegenerative patient through digital writing | |
| Allebawi et al. | A new online Arabic handwriting dataset for analyzing Parkinson’s disease | |
| Saraguro et al. | Analysis of hand movements in patients with Parkinson’s Disease using Kinect | |
| WO2017044092A1 (en) | A system and method for passive remote monitoring of patients' fine motor behavior | |
| Antony et al. | A review on efficient EEG pattern recognition using machine learning and deep learning methods and its application | |
| Kaur et al. | Physiological and Inertial Features based Dataset for Falls and Activities: PIF v2 | |
| Yang et al. | Application of Human-Computer Interaction Technology in Ancillary Diagnosis of Nervous System Diseases: Current Situation and Prospect | |
| Hubers et al. | Artificial intelligence-based classification of motor unit action potentials in real-world needle EMG recordings | |
| Signals-Based et al. | Check for updates |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |