CN109984763A - Method based on artificial neural network intelligent predicting human synovial torque - Google Patents
Method based on artificial neural network intelligent predicting human synovial torque Download PDFInfo
- Publication number
- CN109984763A CN109984763A CN201910283322.4A CN201910283322A CN109984763A CN 109984763 A CN109984763 A CN 109984763A CN 201910283322 A CN201910283322 A CN 201910283322A CN 109984763 A CN109984763 A CN 109984763A
- Authority
- CN
- China
- Prior art keywords
- data
- artificial neural
- neural network
- input
- human synovial
- 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
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/22—Ergometry; Measuring muscular strength or the force of a muscular blow
- A61B5/221—Ergometry, e.g. by using bicycle type apparatus
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
-
- 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
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Dentistry (AREA)
- Geometry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physical Education & Sports Medicine (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Rehabilitation Tools (AREA)
Abstract
The present invention relates to a kind of methods based on artificial neural network intelligent predicting human synovial torque, comprising the following steps: step S1: acquiring human synovial multiple degrees of freedom angle-data to be measured and electromyography signal data；Step S2: obtained multiple degrees of freedom angle-data and electromyography signal data are subjected to denoising, and are normalized；Step S3: using after normalization multiple degrees of freedom angle-data and electromyography signal data as the input of elastomeric network, training elastomeric network, variable relevant to output is filtered out according to the zero of input variable coefficient number statistical value in elastomeric network learning process, the variable data after obtaining rarefaction；Step S4: one artificial neural network of building；Step S5: using the variable data after rarefaction as the input of artificial neural network, human synovial torque to be measured is obtained.The present invention can provide foundation for the research of real-time gait analysis and exoskeleton robot control during athletic rehabilitation.
Description
Technical field
The present invention relates to a kind of methods based on artificial neural network intelligent predicting human synovial torque.
Background technique
Human synovial torque is a very important parameter in biomethanics, but existing joint moment prediction technique is past
Toward the kinematics and dynamics data for needing to input human body, and the measurement of these data is extremely complex, and required equipment is also very high
It is expensive, it cannot be used in unconfined environment.Then people begin one's study the joint moment prediction side based on artificial neural network
Method obtains joint moment by inputting some data for being easier measurement, can reduce the complexity of its measurement in this way
And measurement cost, so that joint moment is quickly and easily measured.But currently based on the prediction technique of artificial neural network
There is also some drawbacks, that is, there are many variable for needing to input, and predict process or more complicated, it is necessary in specific experimental situation
In measure.So how the input variable of optimization neural network, be the critical issue of current research, and in surroundings
The necessary condition of the middle real-time joint moment of prediction.
Summary of the invention
In view of this, the purpose of the present invention is to provide one kind to be based on artificial neural network intelligent predicting human synovial torque
Method, real-time joint moment can be obtained under the conditions of daily, can be real-time gait analysis and dermoskeleton during athletic rehabilitation
The research of bone robot control provides foundation.
To achieve the above object, the present invention adopts the following technical scheme:
A method of based on artificial neural network intelligent predicting human synovial torque, which comprises the following steps:
Step S1: human synovial multiple degrees of freedom angle-data to be measured and electromyography signal data are acquired；
Step S2: obtained multiple degrees of freedom angle-data and electromyography signal data are subjected to denoising, and place is normalized
Reason；
Step S3: using after normalization multiple degrees of freedom angle-data and electromyography signal data as the input of elastomeric network, training
Elastomeric network filters out change relevant to output according to the zero of input variable coefficient number statistical value in elastomeric network learning process
Amount, the variable data after obtaining rarefaction；Step S4: one artificial neural network of building；
Step S5: using the variable data after rarefaction as the input of artificial neural network, human synovial torque to be measured is obtained.
Further, the elastomeric network specifically:
(1)
X is input variable in formula, and y is output variable, and β is input variable coefficient;
The variation coefficient unrelated with output is reduced to zero in learning process by elastomeric network, and whether variable is related to output,
The statistical value of zero number depending on input variable coefficient, expression formula are as follows:
(2)
In formulaFor the input variable coefficient of i-th of subject, m-th of input variable,For the input of m-th of input variable
Variation coefficient.
Further, the artificial neural network is Three Tiered Network Architecture, including a hidden layer, M hidden neuron.
Compared with the prior art, the invention has the following beneficial effects:
The present invention can obtain real-time joint moment under the conditions of daily, can analyze for real-time gait during athletic rehabilitation and outer
The research of bone robot control provides foundation.
Detailed description of the invention
Fig. 1 is the method for the present invention flow chart;
Fig. 2 is that artificial neural network structure schemes in one embodiment of the invention.
Specific embodiment
The present invention will be further described with reference to the accompanying drawings and embodiments.
Fig. 1 is please referred to, the present invention provides a kind of method based on artificial neural network intelligent predicting human synovial torque,
It is characterized in that, comprising the following steps:
Step S1: human synovial multiple degrees of freedom angle-data to be measured and electromyography signal data are acquired；
Step S2: obtained multiple degrees of freedom angle-data and electromyography signal data are subjected to denoising, and place is normalized
Reason；
Step S3: using after normalization multiple degrees of freedom angle-data and electromyography signal data as the input of elastomeric network, training
Elastomeric network filters out change relevant to output according to the zero of input variable coefficient number statistical value in elastomeric network learning process
Amount, the variable data after obtaining rarefaction；Step S4: one artificial neural network of building；
Step S5: using the variable data after rarefaction as the input of artificial neural network, human synovial torque to be measured is obtained.
In the present embodiment, the elastomeric network specifically:
(1)
X is input variable in formula, and y is output variable, and β is input variable coefficient;
The variation coefficient unrelated with output is reduced to zero in learning process by elastomeric network, and whether variable is related to output,
The statistical value of zero number depending on input variable coefficient, expression formula are as follows:
(2)
In formulaFor the input variable coefficient of i-th of subject, m-th of input variable,For the input of m-th of input variable
Variation coefficient.
Referring to Fig. 2, in the present embodiment, the artificial neural network is Three Tiered Network Architecture, including a hidden layer, M
A hidden neuron.
The foregoing is merely presently preferred embodiments of the present invention, all equivalent changes done according to scope of the present invention patent with
Modification, is all covered by the present invention.
Claims (3)
1. a kind of method based on artificial neural network intelligent predicting human synovial torque, which comprises the following steps:
Step S1: human synovial multiple degrees of freedom angle-data to be measured and electromyography signal data are acquired；
Step S2: obtained multiple degrees of freedom angle-data and electromyography signal data are subjected to denoising, and place is normalized
Reason；
Step S3: using after normalization multiple degrees of freedom angle-data and electromyography signal data as the input of elastomeric network, training
Elastomeric network filters out change relevant to output according to the zero of input variable coefficient number statistical value in elastomeric network learning process
Amount, the variable data after obtaining rarefaction；Step S4: one artificial neural network of building；
Step S5: using the variable data after rarefaction as the input of artificial neural network, human synovial torque to be measured is obtained.
2. the method according to claim 1 based on artificial neural network intelligent predicting human synovial torque, feature exist
In: the elastomeric network specifically:
(1)
X is input variable in formula, and y is output variable, and β is input variable coefficient;
The variation coefficient unrelated with output is reduced to zero in learning process by elastomeric network, and whether variable is related to output,
The statistical value of zero number depending on input variable coefficient, expression formula are as follows:
(2)
In formulaFor the input variable coefficient of i-th of subject, m-th of input variable,Become for the input of m-th of input variable
Coefficient of discharge.
3. the method according to claim 1 based on artificial neural network intelligent predicting human synovial torque, feature exist
In: the artificial neural network is Three Tiered Network Architecture, including a hidden layer, M hidden neuron.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910283322.4A CN109984763A (en) | 2019-04-10 | 2019-04-10 | Method based on artificial neural network intelligent predicting human synovial torque |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910283322.4A CN109984763A (en) | 2019-04-10 | 2019-04-10 | Method based on artificial neural network intelligent predicting human synovial torque |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109984763A true CN109984763A (en) | 2019-07-09 |
Family
ID=67132739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910283322.4A Pending CN109984763A (en) | 2019-04-10 | 2019-04-10 | Method based on artificial neural network intelligent predicting human synovial torque |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109984763A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110638449A (en) * | 2019-09-30 | 2020-01-03 | 福州大学 | Muscle quantitative analysis method based on mechanical work |
| CN110710984A (en) * | 2019-10-18 | 2020-01-21 | 福州大学 | Ankle moment prediction method of recursion cerebellum model based on surface electromyogram signal |
| CN111079927A (en) * | 2019-12-12 | 2020-04-28 | 福州大学 | Patella pain detection system based on extreme learning machine |
| CN111590544A (en) * | 2020-04-10 | 2020-08-28 | 南方科技大学 | Method and device for determining output force of exoskeleton |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080009771A1 (en) * | 2006-03-29 | 2008-01-10 | Joel Perry | Exoskeleton |
| CN109044352A (en) * | 2018-06-22 | 2018-12-21 | 福州大学 | A kind of method of the artificial intelligence input variable of determining prediction human synovial torque |
| CN109259739A (en) * | 2018-11-16 | 2019-01-25 | 西安交通大学 | A kind of myoelectricity estimation method of wrist joint motoring torque |
| CN109276245A (en) * | 2018-11-01 | 2019-01-29 | 重庆中科云丛科技有限公司 | A kind of surface electromyogram signal characteristic processing and joint angles prediction technique and system |
| CN109559826A (en) * | 2019-01-30 | 2019-04-02 | 福州大学 | A kind of knee joint torque estimation method based on surface myoelectric and motor message |
-
2019
- 2019-04-10 CN CN201910283322.4A patent/CN109984763A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080009771A1 (en) * | 2006-03-29 | 2008-01-10 | Joel Perry | Exoskeleton |
| CN109044352A (en) * | 2018-06-22 | 2018-12-21 | 福州大学 | A kind of method of the artificial intelligence input variable of determining prediction human synovial torque |
| CN109276245A (en) * | 2018-11-01 | 2019-01-29 | 重庆中科云丛科技有限公司 | A kind of surface electromyogram signal characteristic processing and joint angles prediction technique and system |
| CN109259739A (en) * | 2018-11-16 | 2019-01-25 | 西安交通大学 | A kind of myoelectricity estimation method of wrist joint motoring torque |
| CN109559826A (en) * | 2019-01-30 | 2019-04-02 | 福州大学 | A kind of knee joint torque estimation method based on surface myoelectric and motor message |
Non-Patent Citations (1)
| Title |
|---|
| BAOPING XIONG 等: "Intelligent Prediction of Human LowerExtremity Joint Moment: An Artificial Neural Network Approach", 《SPECIAL SECTION ON DATA-ENABLED INTELLIGENCE FOR DIGITAL HEALTH》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110638449A (en) * | 2019-09-30 | 2020-01-03 | 福州大学 | Muscle quantitative analysis method based on mechanical work |
| CN110638449B (en) * | 2019-09-30 | 2021-05-18 | 福州大学 | Muscle quantitative analysis method based on mechanical work |
| CN110710984A (en) * | 2019-10-18 | 2020-01-21 | 福州大学 | Ankle moment prediction method of recursion cerebellum model based on surface electromyogram signal |
| CN110710984B (en) * | 2019-10-18 | 2021-11-02 | 福州大学 | Ankle moment prediction method of recursion cerebellum model based on surface electromyogram signal |
| CN111079927A (en) * | 2019-12-12 | 2020-04-28 | 福州大学 | Patella pain detection system based on extreme learning machine |
| CN111079927B (en) * | 2019-12-12 | 2022-07-08 | 福州大学 | Patella pain detection system based on extreme learning machine |
| CN111590544A (en) * | 2020-04-10 | 2020-08-28 | 南方科技大学 | Method and device for determining output force of exoskeleton |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109984763A (en) | Method based on artificial neural network intelligent predicting human synovial torque | |
| CN107397649B (en) | Upper limb exoskeleton movement intention identification method based on radial basis function neural network | |
| Ibrahimy et al. | Design and optimization of Levenberg-Marquardt based neural network classifier for EMG signals to identify hand motions | |
| CN106156524B (en) | A kind of online gait planning method of Intelligent lower limb power assisting device | |
| CN105841961A (en) | Bearing fault diagnosis method based on Morlet wavelet transformation and convolutional neural network | |
| CN110232412B (en) | Human gait prediction method based on multi-mode deep learning | |
| CN110826453A (en) | Behavior identification method by extracting coordinates of human body joint points | |
| CN107273685A (en) | A kind of data analysing method of multi-modal big data for clinical disease | |
| CN111207875B (en) | Electromyographic signal-torque matching method based on multi-granularity parallel CNN model | |
| Stapornchaisit et al. | Finger angle estimation from array EMG system using linear regression model with independent component analysis | |
| CN110710984B (en) | Ankle moment prediction method of recursion cerebellum model based on surface electromyogram signal | |
| Cui et al. | Recognition of upper limb action intention based on IMU | |
| Chen et al. | Assembly torque data regression using sEMG and inertial signals | |
| Ibrahimy et al. | Design and performance analysis of artificial neural network for hand motion detection from EMG signals | |
| CN110032987B (en) | Surface electromyographic signal classification method based on cerebellar neural network model | |
| Sohane et al. | A single platform for classification and prediction using a hybrid bioinspired and deep neural network (PSO-LSTM) | |
| CN111772669A (en) | Elbow joint contraction muscle force estimation method based on adaptive long-time and short-time memory network | |
| Su et al. | Ankle joint torque prediction based on surface Electromyographic and angular velocity signals | |
| CN115147768B (en) | Fall risk assessment method and system | |
| CN111950460A (en) | Muscle strength self-adaptive stroke patient hand rehabilitation training action recognition method | |
| CN116543455A (en) | Method, equipment and medium for establishing parkinsonism gait damage assessment model and using same | |
| CN105046193A (en) | Human motion identification method based on fusion sparse expression matrixes | |
| Veer et al. | Analysis and recognition of operations using SEMG from upper arm muscles | |
| Kumar et al. | Development of an adjustable pulse measurement system for determining the precise position for recording high wrist pulse signals | |
| CN111079927B (en) | Patella pain detection system based on extreme learning machine |
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 |
Application publication date: 20190709 |
|
| RJ01 | Rejection of invention patent application after publication |