CN107273798A - A kind of gesture identification method based on surface electromyogram signal - Google Patents

A kind of gesture identification method based on surface electromyogram signal Download PDF

Info

Publication number
CN107273798A
CN107273798A CN201710327893.4A CN201710327893A CN107273798A CN 107273798 A CN107273798 A CN 107273798A CN 201710327893 A CN201710327893 A CN 201710327893A CN 107273798 A CN107273798 A CN 107273798A
Authority
CN
China
Prior art keywords
sample
method based
identification method
surface electromyogram
gesture identification
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
Application number
CN201710327893.4A
Other languages
Chinese (zh)
Inventor
庄聪聪
李远清
周平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by South China University of Technology SCUT filed Critical South China University of Technology SCUT
Priority to CN201710327893.4A priority Critical patent/CN107273798A/en
Publication of CN107273798A publication Critical patent/CN107273798A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/107—Static hand or arm
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

The invention discloses a kind of gesture identification method based on surface electromyogram signal, including step：1) prepare before testing；2) subject, which makes, clenches fist, exrending boxing, bent wrist, stretches wrist, hold cylinder, pinch the scraps of paper, OK, stretch forefinger this eight classes gesture motion, gathers primary signal；3) initial data input 50HZ trappers are filtered with 50 150HZ bandpass filters；4) active segment of each gesture motion is extracted, rest section is cast out；5) active segment adding window is split, obtains window sample；6) the myoelectricity feature in calculation window；7) dimension-reduction treatment is carried out to the myoelectricity feature tried to achieve using PCA；8) sample after dimensionality reduction is divided into training set and test set, SVM classifier is trained, test sample is classified afterwards, calculate classification accuracy rate.The present invention disclosure satisfy that the requirement that Mechatronic control system is controlled in real time, and effectively improve discrimination.

Description

A kind of gesture identification method based on surface electromyogram signal
Technical field
The present invention relates to the technical field of surface electromyogram signal gesture identification, refer in particular to a kind of based on surface electromyogram signal Gesture identification method, can be applied to control artificial limb and other man-machine interaction situations.
Background technology
Any one action of human body is all mutually coordinated, the common completion under the domination of nervous system by multiple muscle groups 's.It is not only able to reflect that joint stretches in the wrong in the muscle activity information of response muscle group skin surface capture by surface myoelectric sensor State and stretch Qu Qiangdu, moreover it is possible to which the information such as the shape of limbs and position in reflection action complete process, is to perceive human action Important way.Different gesture motions, can produce different surface electromyogram signals (SEMG), by dividing surface electromyogram signal Analysis, it can be determined that go out specific pattern.Gesture motion is recognized in particular with surface electromyogram signal, driving, which is done evil through another person, makes phase Gesture motion is answered, disabled person is helped, extensive concern is obtained and studies.
Although domestic and foreign scholars are made that many achievements, simultaneously there is also it is many problem of.Surface electromyogram signal Research be, in order to reach higher action recognition rate, faster recognition speed, therefore to explore that a kind of discrimination is higher to be known simultaneously Other speed is fast, and the algorithm that disclosure satisfy that requirement of real-time is the emphasis and difficult point of the gesture identification of surface electromyogram signal.
The content of the invention
Present invention aims to overcome that the deficiencies in the prior art and shortcoming, it is proposed that a kind of hand based on surface electromyogram signal Gesture recognition methods, high to surface electromyogram signal multiclass gesture motion discrimination, whole signal processing is simple, disclosure satisfy that machine The requirement that electric control system is controlled in real time.
To achieve the above object, technical scheme provided by the present invention is：A kind of gesture based on surface electromyogram signal is known Other method, comprises the following steps：
1) prepare before testing
1.1) subjects skin is cleared up, the hair at respective muscle is removed, alcohol wipe subject interface is dipped with cotton swab Skin；
1.2) electrode paste on subject's musculus flexor digitorum sublimis, long flexor muscle of thumb, musculus extensor digitorum, four pieces of muscle of musculus flexor carpi ulnaris, Mix up equipment；
1.3) posture for allowing subject to loosen is sitting on chair, and arm is naturally drooped, and informs subject's action norm, And experiment flow；
2) subject, which makes, clenches fist, exrending boxing, bent wrist, stretches wrist, hold cylinder, pinch the scraps of paper, OK, stretch forefinger this eight classes gesture and move Make, gather primary signal；
3) initial data input 50HZ trappers are filtered with 50-150HZ bandpass filters；
4) active segment of each gesture motion is extracted, rest section is cast out；
5) active segment adding window is split, obtains window sample；
6) the myoelectricity feature in calculation window；
7) dimension-reduction treatment is carried out to the myoelectricity feature tried to achieve using PCA；
8) sample after dimensionality reduction is divided into training set and test set, SVM classifier is trained, afterwards to test sample Classified, calculate classification accuracy rate.
In step 3) in, in the primary signal of acquisition contain substantial amounts of noise information, before analysis will after filtering, SEMG signal energies are concentrated in the range of 50 to 500HZ, and are concentrated mainly in the range of 50 to 150HZ, are fallen into using 50HZ Ripple device filters out Hz noise, and 50 filter out interference to 150HZ bandpass filters.
In step 4) in, the extraction process of the active segment is as follows：
The instantaneous energy of SEMG signal sequences is handled using rolling average method, the 2% of selection signal maximum is used as threshold Value, starting point is defined as the 64ms signals of rolling average signal more than threshold value and afterwards also above threshold value, and end point is defined as moving It is dynamic that average signal is just below threshold value and later 64ms signals are below threshold value；According to obtained beginning and end, cast out data long Degree does not reach the data segment of requirement, determines the multichannel SEMG activities section corresponding to each gesture sample.
In step 5) in, the length of the sliding window is 250ms, and overlap ratio is 50%.
In step 6) in, selection standard is poor, absolute mean ratio, 4 rank AR coefficients are characterized, wherein, the standard deviation, definitely Average ratio, the calculation formula of 4 rank AR coefficients difference are as follows：
Standard deviation：
Absolute mean ratio：
4 rank AR coefficients：
In formula, N is window size；akFor AR coefficients, k=1,2,3,4；WiFor white noise residual error.
In step 7) in, original sample data is projected in a new space, the principal component of data is retained Come, neglect and data are described with unessential composition, the vector space that principal component dimension is constituted is as lower dimensional space, by higher-dimension To this spatially, its detailed process is as follows for data projection：
7.1) input data set Dh*m, centralization is carried out to all samples；
7.2) sample covariance matrix is calculated；
7.3) Eigenvalues Decomposition is done to covariance matrix；
7.4) the corresponding characteristic vector constitutive characteristic vector matrix W of n eigenvalue of maximum before choosingm*n；
7.5) D=W is exportedm*n*Dh*m；
After conversion, each row are down to n dimensions by h dimensions, here according to contribution rate, n=4.
In step 8) in, sample is divided into training set and test set, classified using SVM bis-, grader is trained with training set, Final classification results are determined by way of ballot.
The present invention compared with prior art, has the following advantages that and beneficial effect：
1st, the feature of PCA dimension-reduction treatment signal extractions has been used, computation complexity is reduced.
2nd, using SVM classifier, discrimination is high.
3rd, whole signal processing is simple, and processing speed is fast, and disclosure satisfy that requirement of real-time, discrimination is high simultaneously.
Embodiment
With reference to specific embodiment, the invention will be further described.
Now using recognize clench fist, exrending boxing, bent wrist, stretch wrist, hold cylinder, pinch the scraps of paper, OK, stretch the class gesture motion of forefinger eight as Example, with reference to technical scheme proposed by the present invention, provides detailed operating procedure and specific recognition result, its process is as follows：
1) prepare before testing
1.1) subjects skin is cleared up, the hair at respective muscle is removed, alcohol wipe subject interface is dipped with cotton swab Skin；
1.2) electrode paste on subject's musculus flexor digitorum sublimis, long flexor muscle of thumb, musculus extensor digitorum, four pieces of muscle of musculus flexor carpi ulnaris, Mix up equipment；
1.3) posture for allowing subject to loosen is sitting on chair, and arm is naturally drooped, and informs subject's action norm, And experiment flow.
2) subject, which makes, clenches fist, exrending boxing, bent wrist, stretches wrist, hold cylinder, pinch the scraps of paper, OK, stretch forefinger this eight classes gesture and move Make, per class gesture duration 5s, respectively do 21 groups, finish one group of rest 1min, prevent muscular fatigue, using DELSYS Table top types Myoelectricity Acquisition Instrument gathers signal, and sample rate is 1KHZ.
3) substantial amounts of noise information is contained in the primary signal obtained, before analysis will after filtering, SEMG signal energy Amount is concentrated in the range of 50 to 500HZ, and is concentrated mainly in the range of 50 to 150HZ, and work is filtered out using 50HZ trappers Frequency is disturbed, and 50 filter out interference to 150HZ bandpass filters.
4) instantaneous energy of SEMG signal sequences, 2% conduct of selection signal maximum are handled using rolling average method Threshold value, starting point is defined as the 64ms signals of rolling average signal more than threshold value and afterwards also above threshold value, and end point is defined as Rolling average signal is just below threshold value and later 64ms signals are below threshold value；According to obtained beginning and end, cast out data Length does not reach the data segment of requirement, determines the multichannel SEMG activities section corresponding to each gesture sample.
5) active segment adding window is split by the way of overlapping window, obtains window sample, sliding window length is 250ms, Overlap ratio is 50%, according to this dividing method, and 210 samples are obtained in an action one.
6) the myoelectricity feature in calculation window：Selection standard is poor, absolute mean ratio, 4 rank AR coefficients are characterized, wherein described Standard deviation, absolute mean ratio, 4 rank AR coefficient formulas difference are as follows：
Standard deviation：
Absolute mean ratio：
4 rank AR coefficients：
In formula, N is window size, and N=250, a are chosen herek(k=1,2,3,4) is AR coefficients, WiFor white noise residual error.
7) dimension-reduction treatment is carried out to myoelectricity feature, dimension-reduction treatment, specific mistake is carried out to the myoelectricity feature tried to achieve using PCA Journey is as follows：
7.1) input data set Dh*m, centralization is carried out to all samples；
7.2) sample covariance matrix is calculated；
7.3) Eigenvalues Decomposition is done to covariance matrix；
7.4) the corresponding characteristic vector constitutive characteristic vector matrix W of n eigenvalue of maximum before choosingm*n；
7.5) D=W is exportedm*n*Dh*m；
After conversion, each row are down to n dimensions by h dimensions, here according to contribution rate, n=7.
8) sample after dimensionality reduction is divided into training set and test set, each action has 105 training samples, 105 tests Sample, is classified using SVM bis-, is trained grader with training set, final classification results is determined by way of ballot, and count Discrimination is calculated, average recognition rate can reach more than 97%.
In summary, after using above scheme, algorithm complex reduction disclosure satisfy that the requirement handled in real time, recognize Rate also effectively improves, with real value, is worthy to be popularized.
Embodiment described above is only the preferred embodiments of the invention, and the practical range of the present invention is not limited with this, therefore The change that all shape, principles according to the present invention are made, all should cover within the scope of the present invention.

Claims (7)

1. a kind of gesture identification method based on surface electromyogram signal, it is characterised in that comprise the following steps：
1) prepare before testing
1.1) subjects skin is cleared up, the hair at respective muscle is removed, alcohol wipe subject interface's skin is dipped with cotton swab；
1.2) electrode paste is mixed up on subject's musculus flexor digitorum sublimis, long flexor muscle of thumb, musculus extensor digitorum, four pieces of muscle of musculus flexor carpi ulnaris Equipment；
1.3) posture for allowing subject to loosen is sitting on chair, and arm is naturally drooped, and informs subject's action norm, and real Test flow；
2) subject, which makes, clenches fist, exrending boxing, bent wrist, stretches wrist, hold cylinder, pinch the scraps of paper, OK, stretch forefinger this eight classes gesture motion, adopts Collect primary signal；
3) initial data input 50HZ trappers are filtered with 50-150HZ bandpass filters；
4) active segment of each gesture motion is extracted, rest section is cast out；
5) active segment adding window is split, obtains window sample；
6) the myoelectricity feature in calculation window；
7) dimension-reduction treatment is carried out to the myoelectricity feature tried to achieve using PCA；
8) sample after dimensionality reduction is divided into training set and test set, SVM classifier is trained, test sample is carried out afterwards Classification, calculates classification accuracy rate.
2. a kind of gesture identification method based on surface electromyogram signal according to claim 1, it is characterised in that：In step 3) in, substantial amounts of noise information is contained in the primary signal of acquisition, before analysis will after filtering, SEMG signal energies are concentrated In the range of 50 to 500HZ, and it is concentrated mainly in the range of 50 to 150HZ, Hz noise is filtered out using 50HZ trappers, 50 filter out interference to 150HZ bandpass filters.
3. a kind of gesture identification method based on surface electromyogram signal according to claim 1, it is characterised in that：In step 4) in, the extraction process of the active segment is as follows：
Handle the instantaneous energy of SEMG signal sequences using rolling average method, selection signal maximum 2% as threshold value, rise Initial point is defined as the 64ms signals of rolling average signal more than threshold value and afterwards also above threshold value, and end point is defined as rolling average Signal is just below threshold value and later 64ms signals are below threshold value；According to obtained beginning and end, cast out data length up to not To desired data segment, the multichannel SEMG activities section corresponding to each gesture sample is determined.
4. a kind of gesture identification method based on surface electromyogram signal according to claim 1, it is characterised in that：In step 5) in, the length of the sliding window is 250ms, and overlap ratio is 50%.
5. a kind of gesture identification method based on surface electromyogram signal according to claim 1, it is characterised in that：In step 6) in, selection standard is poor, absolute mean ratio, 4 rank AR coefficients are characterized, wherein, the standard deviation, absolute mean ratio, 4 rank AR systems Several calculation formula difference is as follows：
Standard deviation：
Absolute mean ratio：
4 rank AR coefficients：
In formula, N is window size；akFor AR coefficients, k=1,2,3,4；WiFor white noise residual error.
6. a kind of gesture identification method based on surface electromyogram signal according to claim 1, it is characterised in that：In step 7) in, original sample data is projected in a new space, the principal component of data is remained, neglected to data Unessential composition is described, high dimensional data is projected to this by the vector space that principal component dimension is constituted as lower dimensional space Spatially, its detailed process is as follows：
7.1) input data set Dh*m, centralization is carried out to all samples；
7.2) sample covariance matrix is calculated；
7.3) Eigenvalues Decomposition is done to covariance matrix；
7.4) the corresponding characteristic vector constitutive characteristic vector matrix W of n eigenvalue of maximum before choosingm*n；
7.5) D=W is exportedm*n*Dh*m；
After conversion, each row are down to n dimensions by h dimensions, here according to contribution rate, n=4.
7. a kind of gesture identification method based on surface electromyogram signal according to claim 1, it is characterised in that：In step 8) in, sample is divided into training set and test set, classified using SVM bis-, grader is trained with training set, by way of ballot Determine final classification results.
CN201710327893.4A 2017-05-11 2017-05-11 A kind of gesture identification method based on surface electromyogram signal Pending CN107273798A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710327893.4A CN107273798A (en) 2017-05-11 2017-05-11 A kind of gesture identification method based on surface electromyogram signal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710327893.4A CN107273798A (en) 2017-05-11 2017-05-11 A kind of gesture identification method based on surface electromyogram signal

Publications (1)

Publication Number Publication Date
CN107273798A true CN107273798A (en) 2017-10-20

Family

ID=60074176

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710327893.4A Pending CN107273798A (en) 2017-05-11 2017-05-11 A kind of gesture identification method based on surface electromyogram signal

Country Status (1)

Country Link
CN (1) CN107273798A (en)

Cited By (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107861628A (en) * 2017-12-19 2018-03-30 许昌学院 A kind of hand gestures identifying system based on human body surface myoelectric signal
CN108268844A (en) * 2018-01-17 2018-07-10 上海术理智能科技有限公司 Movement recognition method and device based on surface electromyogram signal
CN108564105A (en) * 2018-02-28 2018-09-21 浙江工业大学 A kind of online gesture identification method for myoelectricity individual difference problem
CN108606882A (en) * 2018-03-23 2018-10-02 合肥工业大学 Intelligent wheelchair control system based on myoelectricity and acceleration self adaptive control
CN108703824A (en) * 2018-03-15 2018-10-26 哈工大机器人（合肥）国际创新研究院 A kind of bionic hand control system and control method based on myoelectricity bracelet
CN109033976A (en) * 2018-06-27 2018-12-18 北京中科天合科技有限公司 Over-sampling processing method and system
CN109271031A (en) * 2018-09-27 2019-01-25 中国科学院深圳先进技术研究院 A kind of haptic signal detection method, device, system, equipment and storage medium
CN109446957A (en) * 2018-10-18 2019-03-08 广州云从人工智能技术有限公司 One kind being based on EMG signal recognition methods
CN109800733A (en) * 2019-01-30 2019-05-24 中国科学技术大学 Data processing method and device, electronic equipment
CN110298286A (en) * 2019-06-24 2019-10-01 中国科学院深圳先进技术研究院 Virtual reality recovery training method and system based on surface myoelectric and depth image
CN110618754A (en) * 2019-08-30 2019-12-27 电子科技大学 Surface electromyogram signal-based gesture recognition method and gesture recognition armband
CN110639169A (en) * 2019-09-25 2020-01-03 燕山大学 CPM lower limb rehabilitation training method and system based on game and electromyographic signals
CN110664404A (en) * 2019-09-30 2020-01-10 华南理工大学 Trunk compensation detection and elimination system based on surface electromyogram signals
CN110826625A (en) * 2019-11-06 2020-02-21 南昌大学 Finger gesture classification method based on surface electromyographic signals
CN111603162A (en) * 2020-05-07 2020-09-01 北京海益同展信息科技有限公司 Electromyographic signal processing method and device, intelligent wearable device and storage medium
CN111651046A (en) * 2020-06-05 2020-09-11 上海交通大学 Gesture intention recognition system without hand action
CN111714123A (en) * 2020-07-22 2020-09-29 华南理工大学 System and method for detecting human body waist and back surface electromyographic signals
CN111783719A (en) * 2020-07-13 2020-10-16 中国科学技术大学 Myoelectric control method and device
CN111844032A (en) * 2020-07-15 2020-10-30 北京海益同展信息科技有限公司 Electromyographic signal processing and exoskeleton robot control method and device
CN111985270A (en) * 2019-05-22 2020-11-24 中国科学院沈阳自动化研究所 sEMG signal optimal channel selection method based on gradient lifting tree
CN112932508A (en) * 2021-01-29 2021-06-11 电子科技大学 Finger activity recognition system based on arm electromyography network
CN113625882A (en) * 2021-10-12 2021-11-09 四川大学 Myoelectric gesture recognition method based on sparse multichannel correlation characteristics
CN113901881A (en) * 2021-09-14 2022-01-07 燕山大学 Automatic myoelectric data labeling method
CN114098768A (en) * 2021-11-25 2022-03-01 哈尔滨工业大学 Cross-individual surface electromyographic signal gesture recognition method based on dynamic threshold and easy TL
CN115114962A (en) * 2022-07-19 2022-09-27 歌尔股份有限公司 Control method and device based on surface electromyogram signal and wearable device
EP4005473A4 (en) * 2019-09-03 2023-07-26 Jingdong Technology Information Technology Co., Ltd. Motion speed analysis method and apparatus, and wearable device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103440498A (en) * 2013-08-20 2013-12-11 华南理工大学 Surface electromyogram signal identification method based on LDA algorithm
CN106383579A (en) * 2016-09-14 2017-02-08 西安电子科技大学 EMG and FSR-based refined gesture recognition system and method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103440498A (en) * 2013-08-20 2013-12-11 华南理工大学 Surface electromyogram signal identification method based on LDA algorithm
CN106383579A (en) * 2016-09-14 2017-02-08 西安电子科技大学 EMG and FSR-based refined gesture recognition system and method

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
XIAOLONG ZHAI ; BETH JELFS ; ROSA H. M. CHAN ; CHUNG TIN: "Short latency hand movement classification based on surface EMG spectrogram with PCA", 《2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)》 *
张旭: "基于表面肌电信号的人体动作识别与交互", 《中国博士学位论文全文数据库 医药卫生科技辑》 *
张生军: "《基于视觉的无标记手势识别》", 30 June 2016 *
徐建武，闫汝蕴: "《膝关节运动损伤康复学》", 31 March 2014 *
高允领: "基于表面肌电信号的人手抓取动作模式识别技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107861628A (en) * 2017-12-19 2018-03-30 许昌学院 A kind of hand gestures identifying system based on human body surface myoelectric signal
CN108268844A (en) * 2018-01-17 2018-07-10 上海术理智能科技有限公司 Movement recognition method and device based on surface electromyogram signal
CN108564105A (en) * 2018-02-28 2018-09-21 浙江工业大学 A kind of online gesture identification method for myoelectricity individual difference problem
CN108703824A (en) * 2018-03-15 2018-10-26 哈工大机器人（合肥）国际创新研究院 A kind of bionic hand control system and control method based on myoelectricity bracelet
CN108606882B (en) * 2018-03-23 2019-09-10 合肥工业大学 Intelligent wheelchair control system based on myoelectricity and acceleration self adaptive control
CN108606882A (en) * 2018-03-23 2018-10-02 合肥工业大学 Intelligent wheelchair control system based on myoelectricity and acceleration self adaptive control
CN109033976A (en) * 2018-06-27 2018-12-18 北京中科天合科技有限公司 Over-sampling processing method and system
CN109033976B (en) * 2018-06-27 2022-05-20 北京中科天合科技有限公司 Abnormal muscle detection method and system
CN109271031A (en) * 2018-09-27 2019-01-25 中国科学院深圳先进技术研究院 A kind of haptic signal detection method, device, system, equipment and storage medium
CN109446957A (en) * 2018-10-18 2019-03-08 广州云从人工智能技术有限公司 One kind being based on EMG signal recognition methods
CN109800733A (en) * 2019-01-30 2019-05-24 中国科学技术大学 Data processing method and device, electronic equipment
CN111985270A (en) * 2019-05-22 2020-11-24 中国科学院沈阳自动化研究所 sEMG signal optimal channel selection method based on gradient lifting tree
CN111985270B (en) * 2019-05-22 2024-01-05 中国科学院沈阳自动化研究所 sEMG signal optimal channel selection method based on gradient lifting tree
CN110298286A (en) * 2019-06-24 2019-10-01 中国科学院深圳先进技术研究院 Virtual reality recovery training method and system based on surface myoelectric and depth image
CN110298286B (en) * 2019-06-24 2021-04-30 中国科学院深圳先进技术研究院 Virtual reality rehabilitation training method and system based on surface myoelectricity and depth image
CN110618754A (en) * 2019-08-30 2019-12-27 电子科技大学 Surface electromyogram signal-based gesture recognition method and gesture recognition armband
EP4005473A4 (en) * 2019-09-03 2023-07-26 Jingdong Technology Information Technology Co., Ltd. Motion speed analysis method and apparatus, and wearable device
CN110639169A (en) * 2019-09-25 2020-01-03 燕山大学 CPM lower limb rehabilitation training method and system based on game and electromyographic signals
CN110664404A (en) * 2019-09-30 2020-01-10 华南理工大学 Trunk compensation detection and elimination system based on surface electromyogram signals
CN110664404B (en) * 2019-09-30 2021-10-26 华南理工大学 Trunk compensation detection and elimination system based on surface electromyogram signals
CN110826625A (en) * 2019-11-06 2020-02-21 南昌大学 Finger gesture classification method based on surface electromyographic signals
CN110826625B (en) * 2019-11-06 2022-04-12 南昌大学 Finger gesture classification method based on surface electromyographic signals
CN111603162A (en) * 2020-05-07 2020-09-01 北京海益同展信息科技有限公司 Electromyographic signal processing method and device, intelligent wearable device and storage medium
CN111651046A (en) * 2020-06-05 2020-09-11 上海交通大学 Gesture intention recognition system without hand action
CN111783719A (en) * 2020-07-13 2020-10-16 中国科学技术大学 Myoelectric control method and device
CN111844032B (en) * 2020-07-15 2022-04-12 京东科技信息技术有限公司 Electromyographic signal processing and exoskeleton robot control method and device
CN111844032A (en) * 2020-07-15 2020-10-30 北京海益同展信息科技有限公司 Electromyographic signal processing and exoskeleton robot control method and device
CN111714123A (en) * 2020-07-22 2020-09-29 华南理工大学 System and method for detecting human body waist and back surface electromyographic signals
CN112932508A (en) * 2021-01-29 2021-06-11 电子科技大学 Finger activity recognition system based on arm electromyography network
CN113901881A (en) * 2021-09-14 2022-01-07 燕山大学 Automatic myoelectric data labeling method
CN113901881B (en) * 2021-09-14 2024-05-03 燕山大学 Myoelectricity data automatic labeling method
CN113625882A (en) * 2021-10-12 2021-11-09 四川大学 Myoelectric gesture recognition method based on sparse multichannel correlation characteristics
CN114098768A (en) * 2021-11-25 2022-03-01 哈尔滨工业大学 Cross-individual surface electromyographic signal gesture recognition method based on dynamic threshold and easy TL
CN114098768B (en) * 2021-11-25 2024-05-03 哈尔滨工业大学 Cross-individual surface electromyographic signal gesture recognition method based on dynamic threshold and EasyTL
CN115114962A (en) * 2022-07-19 2022-09-27 歌尔股份有限公司 Control method and device based on surface electromyogram signal and wearable device

Similar Documents

Publication Publication Date Title
CN107273798A (en) A kind of gesture identification method based on surface electromyogram signal
CN110238863B (en) Lower limb rehabilitation robot control method and system based on electroencephalogram-electromyogram signals
CN108681396B (en) Human-computer interaction system and method based on brain-myoelectricity bimodal neural signals
CN103440498A (en) Surface electromyogram signal identification method based on LDA algorithm
Oh et al. Classification of hand gestures based on multi-channel EMG by scale Average wavelet transform and convolutional neural network
Phinyomark et al. Wavelet-based denoising algorithm for robust EMG pattern recognition
CN113143676B (en) Control method of external limb finger based on brain-muscle-electricity cooperation
Liang et al. Identification of gesture based on combination of raw sEMG and sEMG envelope using supervised learning and univariate feature selection
Naik A comparison of ICA algorithms in surface EMG signal processing
CN108874149B (en) Method for continuously estimating human body joint angle based on surface electromyogram signal
CN104997582B (en) Device and method for controlling intelligent artificial limb based on eye and lower jaw electromyographic signals
Xiong et al. An user-independent gesture recognition method based on sEMG decomposition
Abougharbia et al. A novel BCI system based on hybrid features for classifying motor imagery tasks
Yeon et al. Rejecting impulse artifacts from surface emg signals using real-time cumulative histogram filtering
Fu et al. Identification of finger movements from forearm surface EMG using an augmented probabilistic neural network
CN113642528B (en) Hand movement intention classification method based on convolutional neural network
Bo et al. Hand gesture recognition using semg signals based on cnn
CN113476799B (en) Hand training and evaluation method based on myoelectricity and inertia information
Song et al. Recognition of motion of human upper limb using semg in real time: Towards bilateral rehabilitation
Qi et al. Recognition of composite motions based on sEMG via deep learning
CN114098768A (en) Cross-individual surface electromyographic signal gesture recognition method based on dynamic threshold and easy TL
Mohamed Towards improved EEG interpretation in a sensorimotor BCI for the control of a prosthetic or orthotic hand
CN114343679A (en) Surface electromyogram signal upper limb action recognition method and system based on transfer learning
Lu et al. Channel-distribution hybrid deep learning for sEMG-based gesture recognition
CN110680315A (en) Electroencephalogram and electromyogram signal monitoring method based on asymmetric multi-fractal detrending correlation analysis

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: 20171020