CN110179470A - Motor function of stroke patients and fatigue state comprehensive estimation method - Google Patents
Motor function of stroke patients and fatigue state comprehensive estimation method Download PDFInfo
- Publication number
- CN110179470A CN110179470A CN201910301495.4A CN201910301495A CN110179470A CN 110179470 A CN110179470 A CN 110179470A CN 201910301495 A CN201910301495 A CN 201910301495A CN 110179470 A CN110179470 A CN 110179470A
- Authority
- CN
- China
- Prior art keywords
- stage
- sub
- motion
- complex network
- node
- 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.)
- Pending
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
- A61B5/1113—Local tracking of patients, e.g. in a hospital or private home
- A61B5/1114—Tracking parts of the body
-
- 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
- A61B5/103—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
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
- A61B5/1122—Determining geometric values, e.g. centre of rotation or angular range of movement of movement trajectories
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Dentistry (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Physiology (AREA)
- Medical Informatics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Geometry (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention relates to a kind of motor function of stroke patients and fatigue state comprehensive estimation methods, including limbs to perceive signal acquisition: by entire motion process equipartition at multiple sub-stages；Construct the complex network of each sub-stage: in each sub-stage, using each period of motion as the node of its complex network, with the presence or absence of even side between node, according to the similarity degree determination between the collected limbs perceptual signal of institute of corresponding two periods of motion；Complex network evolution Feature is extracted, complex network evolution Feature is the evolution difference value of the complex network for portraying index and adjacent sub-stage of the complex network of calculated each sub-stage portrayed between index；Using the complex network evolution Feature of extraction, motor function of stroke patients assessment models are established based on artificial intelligence approach.The motor function of patients with cerebral apoplexy can not only be quantitatively evaluated in the present invention, moreover it is possible to which fatigue state when completing designated movement task is quantitatively evaluated.
Description
Technical field
The present invention relates to motor function of stroke patients evaluation areas, in particular to a kind of brain to be developed based on complex network
Apoplexy patient motor function and fatigue state comprehensive estimation method.
Background technique
With the aggravation of China human mortality aging process, the disease incidence of cerebral apoplexy is in rising trend.Since China's rehabilitation is cured
Development is started late, clinical resources it is in short supply and exist distribution unbalance, cause many patients with cerebral apoplexy after discharge without
Method obtains timely, scientific rehabilitation, brings heavy stress and huge financial burden to society and family.
The development of wearable device technology, the extremity motor function for assessing patients with cerebral apoplexy for long-range, quantitative, individuation mention
Possible approach has been supplied, has had many scholars both at home and abroad and research is unfolded, and achieve great successes.In sensor selecting party
Face, using it is most be micro-inertia sensor (including accelerometer, gyroscope, magnetometer etc.).The research of early stage uses mostly
Uniaxial acceleration transducer, but subsequent correlative study is found, uniaxial acceleration transducer can not completely portray brain soldier
The extremity motor function of middle patient, therefore, many researchs begin to use 3-axis acceleration sensor and acceleration transducer
Multi-source fusion is carried out with other sensors (gyroscope, magnetometer etc.), to realize more subtly assessment and analysis.Currently,
Nine axis inertial sensor units (including 3-axis acceleration sensor, three-axis gyroscope and three axle magnetometer) are substantially public
Think the standard scheme of movement capture.In terms of the number of sensors for needing to wear, when using three-axis sensor, need to wear
Number of sensors the case where being considerably less than using uniaxially or biaxially sensor.In terms of the wearing position of sensor, due to
Different research groups position of interest is also not quite similar, and from finger, wrist, forearm, upper arm, closes to back, hip
There are relevant report in the positions such as section, knee, ankle-joint.
However, it is complete to require nothing more than patients with cerebral apoplexy when the motor function to patients with cerebral apoplexy is assessed for current research
At primary or a small number of psychomotor tasks specified several times, and traditional clinical rehabilitation measuring scale is also single evaluation, i.e., only
Consider whether patients with cerebral apoplexy has the ability for completing required movement, and has ignored patients with cerebral apoplexy and persistently complete more number
Endurance and fatigue state when required movement task.
Therefore, it is necessary to design a kind of new method, realize comprehensive to motor function of stroke patients and fatigue state progress
Close assessment.
Summary of the invention
The object of the present invention is to provide a kind of motor function of stroke patients and fatigue state comprehensive estimation method, the assessments
The motor function of patients with cerebral apoplexy can not only be quantitatively evaluated in method, moreover it is possible to fatigue when to completion designated movement task
State is quantitatively evaluated.
Realize the object of the invention technical solution be: the present invention the following steps are included:
S1, signal acquisition: patients with cerebral apoplexy is repeated several times in the motion capture device by that can acquire limbs perceptual signal
Limbs perceptual signal when completing required movement task is acquired；
S2, motion process separate: completing a required movement task is a period of motion, the quantity according to the period of motion
M, by entire motion process equipartition at n sub-stage；The period of motion number of each sub-stage isWherein n >=2；
The complex network of S3, each sub-stage of building: in each sub-stage, using each period of motion as its complex network
Node, with the presence or absence of even side between node, according to corresponding two periods of motion phase between collected limbs perceptual signal
It is determined like degree；When similarity degree is more than given threshold value, then there is even side in two periods of motion corresponding node, otherwise not
In the presence of even side；Wherein, limbs perceptual signal when given threshold value is generally by by acquisition normal person's completion same movement
It determines；
S4, extract to complex network evolution Feature: complex network evolution Feature is calculated each sub-stage
The evolution difference value of the complex network for portraying index and adjacent sub-stage of complex network portrayed between index；
S5, assessment models are established: using the complex network evolution Feature extracted, establishing cerebral apoplexy based on artificial intelligence approach
Patient motion functional assessment model.
Above-mentioned motion capture device is wearable inertial sensor；The inertial sensor includes 3 axis accelerometers, 3
Axis gyroscope and 3 axis magnetometers.
Quantity M >=30 of the above-mentioned period of motion.
Above-mentioned index of portraying includes average degree, average path length and average cluster coefficient；The evolution difference value includes
Average degree difference, average path length difference and average cluster coefficient differentials.
Artificial intelligence approach described in above-mentioned steps S5 is artificial neural network or support vector machines or convolutional Neural net
Network.
In above-mentioned steps S3 two periods of motion similarity degree between collected limbs perceptual signal judgment basis
The matching degree of two period of motion inertial sensor signals or the difference or the difference of two periodic motion time of amplitude peak
Value.
7, motor function of stroke patients according to claim 4 and fatigue state comprehensive estimation method, feature
It is: adjacency matrix A=(a is obtained according to complex networkij)L×L, which is L rank square matrix, the member on the i-th row jth column
Plain aijIt indicates the similarity degree between i-th of node and j-th of node, is defined as follows:
The calculation formula that index is portrayed in the step S4 is as follows:
Average degree:
Average path length:
Average cluster coefficient:
Wherein, dijIt indicates the distance between node i and node j, is defined as connecting on the shortest path of the two nodes
The number on side；kiIndicate the degree of node i, i.e., the number for other nodes for directly thering is side to connect with node i；EiIndicate node i
kiThe number of edges of physical presence between a neighbors.
Average degree difference is that the average degree of latter sub-stage subtracts the average degree of previous sub-stage in institute step S4；Average road
Electrical path length difference is that the average path length of latter sub-stage subtracts the average path length of previous sub-stage；Average cluster system
Number difference is that the average cluster coefficient of latter sub-stage subtracts the average cluster coefficient of previous sub-stage.
The present invention has the effect of positive: the present invention combines wearable movement capturing technology, Complex Networks Theory and artificial
Intelligent method is analyzed by patients with cerebral apoplexy being repeated several times evolution of motion process when completing designated movement task, real
Now to the overall merit of its motor function and fatigue state.It is compared with the traditional method, method of the invention not only may be implemented pair
The motor function of patients with cerebral apoplexy is quantitatively evaluated, i.e., whether patients with cerebral apoplexy has the ability for completing designated movement task
And how complete quality.Importantly, method of the invention, which can also be realized, completes designated movement task to patients with cerebral apoplexy
When fatigue state be quantitatively evaluated, i.e., whether have a tired generation, and the degree that fatigue occurs how.
Detailed description of the invention
In order that the present invention can be more clearly and readily understood, right below according to specific embodiment and in conjunction with attached drawing
The present invention is described in further detail, wherein
Fig. 1 is flow diagram of the invention；
Fig. 2 is motion capture device wearing position schematic diagram in the embodiment of the present invention；
Fig. 3 is the original letter of acceleration transducer for completing to record during Bobath shakes hands 30 times in the embodiment of the present invention
Number；
Fig. 4 is the complex network figure of 10 action cycles of initial phase building in the embodiment of the present invention；
Fig. 5 is the complex network figure of 10 action cycles of transition stage building in the embodiment of the present invention；
Fig. 6 is the complex network figure of 10 action cycles of end stage building in the embodiment of the present invention；
Fig. 7 is the Integrated Evaluation Model estimated performance figure established in the embodiment of the present invention.
Specific embodiment
Below in conjunction with Figure of description, technical solution is clearly and completely described, it is clear that described implementation
Example is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to what the present invention protected
Range.
As shown in Figure 1, a kind of motor function of stroke patients to be developed based on complex network of the present invention and fatigue
State comprehensive estimation method, includes the following steps:
S1, signal acquisition.The wearable motion capture device of embedded 9 axis inertial sensor units is fixed or worn first
In the initial position that concrete application requires, then using patients with cerebral apoplexy in host computer data acquisition software acquisition a period of time
The original signal of 9 axis inertial sensors when completing designated movement task is repeated several times.It should be pointed out that in institute of the present invention
In the method for proposition, signal acquisition process does not limit the type of inertial sensor unit and data acquisition software, and sampling frequency
The size of rate.As long as limbs perceptual signal when can collect patients with cerebral apoplexy multiplicating completion designated movement task is i.e.
It can.
S2, motion process separate.In order to analyse in depth fortune when completion designated movement task is repeated several times in patients with cerebral apoplexy
Dynamic evolutionary process, needs to be separated collected original signal.According to the quantity of the period of motion, by entire motion process
Equipartition is at three sub-stages (initial phase, transition stage and end stage).Assuming that patients with cerebral apoplexy be repeatedly performed it is specified
The number of motor task is 3*L, then the signal of the 1~L period of motion is as initial phase, the L+1~2*L movement week
The signal of phase is as transition stage, and the signal of the 2*L+1~3*L period of motion is as end stage.In specific implementation case
In example, unlimited allocate of sub-stage segregation method of the step is divided, and uneven division methods can also.The sub-stage of separation
Not limited to is three fixed, is more than or equal to 2.The number that patients with cerebral apoplexy is repeatedly performed designated movement task is not limited to son
The integral multiple (for example, 3 integral multiples) of phase data, when condition is not satisfied, makees truncated position to collected original signal
Reason gets the maximum integer times of sub-stage data.Without loss of generality, it is assumed that patients with cerebral apoplexy is repeatedly performed designated movement task
Number be M (cannot be divided exactly by 3), then the period of motion number intercepted isWherein symbolIt indicates to be rounded fortune downwards
It calculates.
The complex network of S3, each sub-stage of building: in each sub-stage, using each period of motion as complex network
Node is determined with the presence or absence of even side according to the similarity degree between corresponding two periods of motion inertial sensor signal between node.
One specific network can be abstracted as the figure G=(V, E) being made of point set V and side collection E.Assuming that sub-stage has L movement week
Phase then shares L node, believes with the presence or absence of even side according to corresponding two period of motion inertial sensors between node in point set V
Similarity degree between number determines that the judgement of similarity degree can be according to the matching journey of two period of motion inertial sensor signals
Degree, the difference of amplitude peak or difference of two periodic motion time etc..If similarity degree is more than given threshold value, two
There is even side between period corresponding node, otherwise there is no even sides.Wherein threshold value is completed identical generally by acquisition normal person
What limbs perceptual signal when movement determined.
S4, complex network evolution Feature is extracted: calculates adjacent sub-stage complex network and portrays drilling between index
Change between difference, including initial phase and transition stage, between transition stage and end stage.Firstly, according to every sub- rank
The adjacency matrix of section complex network calculates the index of portraying of sub-stage complex network, including but not limited to average degree, average
Path length and average cluster coefficient etc..Adjacency matrix A=(aij)L×LIt is a L rank square matrix, the element on the i-th row jth column
aijIt indicates the similarity degree between i-th of node (period of motion) and j-th of node (period of motion), is defined as follows:
The above-mentioned calculation formula for portraying index is as follows:
Average degree:
Average path length:
Average cluster coefficient:
Wherein, dijIt indicates the distance between node i and node j, is defined as connecting on the shortest path of the two nodes
The number on side；kiIndicate the degree of node i, i.e., the number for other nodes for directly thering is side to connect with node i；EiIndicate node i
kiThe number of edges of physical presence between a neighbors.
Then, it calculates adjacent sub-stage complex network and portrays evolution difference value between index, i.e. initial phase and transition
Indicator difference value Δ<k>is portrayed between stage1,ΔS1,ΔC1Index error is portrayed between transition stage and end stage
Different value Δ<k>2,ΔS2,ΔC2。
S5, assessment models are established: using the complex network evolution Feature extracted, establishing cerebral apoplexy based on artificial intelligence approach
Patient motion function and fatigue state Integrated Evaluation Model.The input of model includes: to extract from each sub-stage complex network
Portray index and adjacent sub-stage complex network portrays evolution difference value between index；The output of model is clinical doctor
The raw evaluation result and degree of fatigue score provided according to traditional scale.The foundation of Integrated Evaluation Model is based on artificial intelligence side
Method realization, including but not limited to artificial neural network, support vector machines, convolutional neural networks etc..
Specific embodiment is carried out to the present invention below to analyze:
It is analyzed by taking Bobath dohandshake action as an example.The motion process that Bobath shakes hands are as follows: sitting position, both hands intersect
It is put in above-knee, stretches elbow, transfer after lifting maintenance 3-5 second on shoulder over the top of the head to initial position.Before data acquisition, first by two inertia
Sensor is worn on the forearm and upper arm of patient's hemiplegia side respectively, as shown in Figure 2.
Fig. 3 describes the patients with cerebral apoplexy limbs that three axis accelerometer is recorded when being repeatedly performed 30 Bobath and shaking hands
Perception data, wherein 1-10 times is initial phase, and 11-20 times is transition stage, and 21-30 times is end stage.
Fig. 4, Fig. 5 and Fig. 6 respectively describe three complex webs constructed by initial phase, transition stage and end stage
Network.It therefrom can visually see, with the increase of times of exercise, the degree of similarity between each action cycle gradually drops
Low, i.e. the degree of fatigue of patients with cerebral apoplexy gradually increases.
What the following table 1 listed three sub-stage complex networks in detail portrays index and complex network evolution Feature parameter value.
1 three sub-stage complex networks of table portray index and complex network evolution Feature parameter value
The sub-stage complex network extracted in upper table is portrayed index and complex network evolution Feature parameter as synthesis to comment
The input of cover half type, totally 15.The assessment score that clinician is provided using Fugl-Meyer is as the output of model, benefit
Model is established with BP neural network.BP neural network is a three-decker, only includes a hidden layer, hidden layer neuron
Number is 30.Maximum frequency of training 1000 times, learning objective 1e-3, learning rate 0.1.The estimated performance of model such as Fig. 5 institute
Show, the coefficient of determination R of model2Up to 0.839, show that the Fugl-Meyer score of prediction must divide it with what clinician provided
Between it is very close.Meanwhile complex network evolution Feature can intuitively reflect that completion is being repeated several times in patients with cerebral apoplexy
The increasingly severe trend of the fatigue state showed when Bobath dohandshake action.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
It describes in detail bright, it should be understood that the above is only a specific embodiment of the present invention, is not intended to restrict the invention,
All within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should be included in of the invention
Within protection scope.
Claims (7)
1. a kind of motor function of stroke patients and fatigue state comprehensive estimation method；Characterized by the following steps:
S1, signal acquisition: patients with cerebral apoplexy, which is repeated several times, in the motion capture device by that can acquire limbs perceptual signal completes
Limbs perceptual signal when required movement task is acquired；
S2, motion process separate: completing a required movement task is a period of motion, will according to the quantity M of the period of motion
Entire motion process equipartition is at n sub-stage；The period of motion number of each sub-stage isWherein n >=2；
The complex network of S3, each sub-stage of building: in each sub-stage, using each period of motion as the section of its complex network
Point, with the presence or absence of even side between node, according to corresponding two periods of motion similar journey between collected limbs perceptual signal
Degree determines；When similarity degree is more than given threshold value, then there is even side in two periods of motion corresponding node, and otherwise there is no connect
Side；
S4, extract to complex network evolution Feature: complex network evolution Feature is the complexity of calculated each sub-stage
The evolution difference value of the complex network for portraying index and adjacent sub-stage of network portrayed between index；
S5, assessment models are established: using the complex network evolution Feature extracted, establishing patients with cerebral apoplexy based on artificial intelligence approach
Motor function assessment models.
2. motor function of stroke patients according to claim 1 and fatigue state comprehensive estimation method, it is characterised in that:
The motion capture device is wearable inertial sensor；The inertial sensor includes 3 axis accelerometers, 3 axis gyroscopes
With 3 axis magnetometers.
3. motor function of stroke patients according to claim 1 and fatigue state comprehensive estimation method, it is characterised in that:
Quantity M >=30 of the period of motion.
4. motor function of stroke patients according to claim 1 and fatigue state comprehensive estimation method, it is characterised in that:
The index of portraying includes average degree, average path length and average cluster coefficient；The evolution difference value includes that average degree is poor
Value, average path length difference and average cluster coefficient differentials.
5. motor function of stroke patients according to claim 1 and fatigue state comprehensive estimation method, it is characterised in that:
Artificial intelligence approach described in the step S5 is artificial neural network or support vector machines or convolutional neural networks.
6. motor function of stroke patients according to claim 1 and fatigue state comprehensive estimation method, it is characterised in that:
In the step S3 two periods of motion similarity degree between collected limbs perceptual signal judgment basis two movements
The matching degree of period inertial sensor signal or the difference of amplitude peak or the difference of two periodic motion time.
7. motor function of stroke patients according to claim 4 and fatigue state comprehensive estimation method, it is characterised in that:
Adjacency matrix A=(a is obtained according to complex networkij)L×L, which is L rank square matrix, the element a on the i-th row jth columnijTable
Show the similarity degree between i-th of node and j-th of node, be defined as follows:
The calculation formula that index is portrayed in the step S4 is as follows:
Average degree:
Average path length:
Average cluster coefficient:
Wherein, dijIt indicates the distance between node i and node j, is defined as connecting the side on the shortest path of the two nodes
Number；kiIndicate the degree of node i, i.e., the number for other nodes for directly thering is side to connect with node i；EiIndicate the k of node iiA neighbour
The number of edges of physical presence between node.
Average degree difference is that the average degree of latter sub-stage subtracts the average degree of previous sub-stage in institute step S4；Average path is long
Degree difference is that the average path length of latter sub-stage subtracts the average path length of previous sub-stage；Average cluster coefficient difference
The average cluster coefficient of previous sub-stage is subtracted for the average cluster coefficient of latter sub-stage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910301495.4A CN110179470A (en) | 2019-04-16 | 2019-04-16 | Motor function of stroke patients and fatigue state comprehensive estimation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910301495.4A CN110179470A (en) | 2019-04-16 | 2019-04-16 | Motor function of stroke patients and fatigue state comprehensive estimation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110179470A true CN110179470A (en) | 2019-08-30 |
Family
ID=67714552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910301495.4A Pending CN110179470A (en) | 2019-04-16 | 2019-04-16 | Motor function of stroke patients and fatigue state comprehensive estimation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110179470A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110755084A (en) * | 2019-10-29 | 2020-02-07 | 南京茂森电子技术有限公司 | Motion function evaluation method and device based on active and passive staged actions |
| CN110782991A (en) * | 2019-10-23 | 2020-02-11 | 吉林大学 | Real-time evaluation method for assisting rehabilitation exercise of heart disease patient |
| TWI745812B (en) * | 2019-12-25 | 2021-11-11 | 財團法人工業技術研究院 | Intelligent real-time exercise fatigue detection system and method, and intelligent real-time exercise fatigue detection device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107626040A (en) * | 2017-10-24 | 2018-01-26 | 杭州易脑复苏科技有限公司 | It is a kind of based on the rehabilitation system and method that can interact virtual reality and nerve electric stimulation |
| CN108309318A (en) * | 2018-01-30 | 2018-07-24 | 苏州大学 | Cerebral function state evaluation device based on brain hemoglobin information |
-
2019
- 2019-04-16 CN CN201910301495.4A patent/CN110179470A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107626040A (en) * | 2017-10-24 | 2018-01-26 | 杭州易脑复苏科技有限公司 | It is a kind of based on the rehabilitation system and method that can interact virtual reality and nerve electric stimulation |
| CN108309318A (en) * | 2018-01-30 | 2018-07-24 | 苏州大学 | Cerebral function state evaluation device based on brain hemoglobin information |
Non-Patent Citations (1)
| Title |
|---|
| LI-QUAN GUO 等: "Wearable rehabilitation assessment system based on complex network", 《2017 2ND INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY (INCIT)》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110782991A (en) * | 2019-10-23 | 2020-02-11 | 吉林大学 | Real-time evaluation method for assisting rehabilitation exercise of heart disease patient |
| CN110755084A (en) * | 2019-10-29 | 2020-02-07 | 南京茂森电子技术有限公司 | Motion function evaluation method and device based on active and passive staged actions |
| CN110755084B (en) * | 2019-10-29 | 2023-06-23 | 南京茂森电子技术有限公司 | Motion function assessment method and device based on active-passive and staged actions |
| TWI745812B (en) * | 2019-12-25 | 2021-11-11 | 財團法人工業技術研究院 | Intelligent real-time exercise fatigue detection system and method, and intelligent real-time exercise fatigue detection device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Duan et al. | Classification of multichannel surface-electromyography signals based on convolutional neural networks | |
| CN107397649B (en) | Upper limb exoskeleton movement intention identification method based on radial basis function neural network | |
| CN110179470A (en) | Motor function of stroke patients and fatigue state comprehensive estimation method | |
| CN110236550B (en) | Human gait prediction device based on multi-mode deep learning | |
| CN109635820B (en) | Construction method of Parkinson's disease bradykinesia video detection model based on deep neural network | |
| CN107378944A (en) | A kind of multi-dimensional surface electromyographic signal prosthetic hand control method based on PCA | |
| CN106156524A (en) | A kind of online gait planning system and method for Intelligent lower limb power assisting device | |
| CN110503077A (en) | A kind of real-time body's action-analysing method of view-based access control model | |
| CN111274998B (en) | Parkinson's disease finger knocking action recognition method and system, storage medium and terminal | |
| CN107616898B (en) | Upper limb wearable rehabilitation robot based on daily actions and rehabilitation evaluation method | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| CN110659677A (en) | Human body falling detection method based on movable sensor combination equipment | |
| CN109846487A (en) | Thigh measuring method for athletic posture and device based on MIMU/sEMG fusion | |
| CN104586402B (en) | A kind of feature extracting method of physical activity | |
| CN110827987A (en) | Myoelectricity continuous prediction method and system for wrist joint torque in multi-grabbing mode | |
| Qi et al. | sEMG-based recognition of composite motion with convolutional neural network | |
| CN106178427A (en) | A kind of hands functional training based on the mutual virtual reality of many people and assessment system | |
| Yuan et al. | Adaptive recognition of motion posture in sports video based on evolution equation | |
| CN113642432A (en) | Method for identifying human body posture by convolutional neural network based on covariance matrix transformation | |
| CN110675936B (en) | Fitness compensation assessment method and system based on OpenPose and binocular vision | |
| CN107961013A (en) | Portable upper extremity exercise coordination detection system | |
| Kubota et al. | Human motion tracking and feature extraction for cognitive rehabilitation in informationally structured space | |
| CN115904086A (en) | Sign language identification method based on wearable calculation | |
| Ni et al. | Sports dance action recognition system oriented to human motion monitoring and sensing | |
| CN115222882A (en) | Model construction method and device based on human motion video and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190830 |