CN109498009A - Human body daily behavior myoelectricity feature selection approach based on feature class separability index - Google Patents
Human body daily behavior myoelectricity feature selection approach based on feature class separability index Download PDFInfo
- Publication number
- CN109498009A CN109498009A CN201811606406.9A CN201811606406A CN109498009A CN 109498009 A CN109498009 A CN 109498009A CN 201811606406 A CN201811606406 A CN 201811606406A CN 109498009 A CN109498009 A CN 109498009A
- Authority
- CN
- China
- Prior art keywords
- feature
- myoelectricity
- class
- emg
- movement
- 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
- 238000013459 approach Methods 0.000 title claims description 6
- 238000002567 electromyography Methods 0.000 claims abstract description 47
- 230000003068 static effect Effects 0.000 claims abstract description 32
- 230000005021 gait Effects 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000006243 chemical reaction Methods 0.000 claims description 17
- 239000000203 mixture Substances 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 210000003314 quadriceps muscle Anatomy 0.000 claims description 4
- 238000001228 spectrum Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 6
- 210000003141 lower extremity Anatomy 0.000 abstract description 2
- 239000002699 waste material Substances 0.000 abstract description 2
- 230000007704 transition Effects 0.000 abstract 1
- 230000006399 behavior Effects 0.000 description 11
- 238000000605 extraction Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 230000003387 muscular Effects 0.000 description 2
- 101000739754 Homo sapiens Semenogelin-1 Proteins 0.000 description 1
- 102100037550 Semenogelin-1 Human genes 0.000 description 1
- 230000036982 action potential Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003183 myoelectrical effect Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- 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
- A61B5/103—Measuring 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 or mobility of a limb
- A61B5/1116—Determining posture transitions
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Measuring 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 or mobility of a limb
- A61B5/1116—Determining posture transitions
- A61B5/1117—Fall detection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Measuring 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 or mobility of a limb
- A61B5/1123—Discriminating type of movement, e.g. walking or running
-
- 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
-
- 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
-
- 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)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Signal Processing (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
本发明公开了一种基于特征类可分性指标的人体日常行为肌电特征选择方法。首先，采集了人体下肢活动中四路表面肌电信号，然后计算了10种提取每路肌电信号的10个肌电特征形成肌电特征池，对静态动作、步态动作、静态转换动作的三大类分别计算10个肌电信号特征各自的特征类可分性指标，从肌电特征池中选择特征类可分性指标高于0.6的肌电特征组成静态动作肌电特征组，特征类可分性指标高于0.5的肌电特征组成步态动作肌电特征组，特征类可分性指标高于0.2的肌电特征组成静态转换动作肌电特征组。根据特征类可分性指标可以最大限度的利用各个特征，不会造成特征信息的浪费或冗余，大大降低了算法的复杂度，使分类效果更好。
The invention discloses a method for selecting electromyography characteristics of human daily behavior based on the characteristic class separability index. First, four channels of surface EMG signals were collected during human lower extremity activities, and then 10 EMG features extracted from each channel of EMG signals were calculated to form an EMG feature pool. The three major categories were calculated for each feature class separability index of the 10 EMG features, and the EMG features with the feature class separability index higher than 0.6 were selected from the EMG feature pool to form a static action EMG feature group. The EMG features with the separability index higher than 0.5 constituted the gait action EMG feature group, and the EMG features with the feature class separability index higher than 0.2 constituted the static transition action EMG feature group. According to the feature class separability index, each feature can be used to the maximum extent without waste or redundancy of feature information, which greatly reduces the complexity of the algorithm and makes the classification effect better.
Description
Technical field
The invention belongs to feature extraction fields, are related to a kind of human body daily behavior myoelectricity based on feature class separability index
Feature selection approach.
Background technique
EMG is the superposition of moving cell action potential over time and space in numerous muscle fibres.SEMG is superficial muscular
Comprehensive effect of the electric discharge behavior in skin surface on EMG and nerve cord.It can be divided into commonly used in the feature extracting method of EMG signal
Time domain approach, frequency domain method, time-frequency domain method.Time Domain Analysis is most species, the most common method, this is because time domain
Method is only based on signal amplitude, and algorithm is simple, and the complexity of feature extraction is small.Arief et al. [33] divides from time domain
Average absolute value (Mean Absolute Value, MAV), variance (Variance, VAR), Wilson's amplitude are analysed
(Willison Amplitude, WAMP), waveform length (Waveform Length, WL) and zero passage points (Zero
Crossing, ZC), it is intended to finding can make that feature complexity is minimum, dimension is less, the optimal method of separability, grind to be subsequent
Offer technical support is provided.Frequency domain method is mainly to be obtained by power spectral density, such as average frequency, median frequency etc..In EMG
In, frequency domain character is commonly used in the detection of muscular fatigue.Such as Song Haiyan is by extracting frequency of average power (Mean Power
Frequency, MPF), it show that its characteristic value is consistent with the subjective assessment of human-body fatigue, can be used for predicting fatigue.Time-frequency domain method
It is the combined method of time and frequency, the change frequency information at different time position can be characterized, provided largely about analysis
The non-stationary information of signal.Wavelet transformation (Wavelet Transform, WT) is the common method in time-frequency domain, is suitable for table
Show the short pulse in high-frequency signal or the long-time signal of speed variation.Wavelet package transforms (Wavelet Packet
Transform, WPT) be WT extension, can effectively eliminate high-frequency noise.However, WT is still very poor in high band, WPT lacks
Translation invariant property.Therefore, Xing et al. proposes a kind of new solution, using wavelet packet component energy construction feature to
Amount.Activity consciousness, especially daily routines monitoring and fall detection, as a basic subdomains of behavior perception, to needs
The daily routines of the elderly and weak person of help play an important role.If active health can be carried out according to patient muscle's motion intention
Refreshment is practiced, and the rehabilitation efficacy of patient can be improved.
Summary of the invention
In view of the deficiencies of the prior art, the present invention proposes a kind of human body daily behaviors based on feature class separability index
Myoelectricity feature selection approach.
The present invention studies the feature extraction of surface electromyogram signal and feature selecting, it is therefore an objective to determine surface myoelectric
Best features of the signal in number of storage tanks produced per day monitoring and fall detection.Firstly, acquire human body lower limbs activity in gastrocnemius,
Then this four road surfaces electromyography signal of tibialis anterior, vastus medials, musculus vastus lateralis calculates being averaged for 10 kinds of every road electromyography signals of extraction
Amplitude, variance, Wilson's amplitude, autoregressive coefficient, median frequency, frequency of average power, wavelet energy coefficient, wavelet-packet energy
Coefficient, fuzzy entropy, totally 10 myoelectricity features form myoelectricity feature pool to arrangement entropy, dynamic to static state movement, gait movement, static conversion
The three categories of work calculate separately respective feature class separability index (the Feature Class of 10 electromyography signal features
Separability index), select feature class separability index quiet higher than 0.6 myoelectricity feature composition from myoelectricity feature pool
State acts myoelectricity feature group, and myoelectricity feature composition gait of the feature class separability index higher than 0.5 acts myoelectricity feature group, feature
Myoelectricity feature composition static conversion of the class separability index higher than 0.2 acts myoelectricity feature group.
In order to achieve the goal above, the method for the present invention mainly comprises the steps that
It is total that step (1) acquires human body gastrocnemius, tibialis anterior, vastus medials, musculus vastus lateralis when human body does daily behavior movement
4 tunnel electromyography signals；Daily behavior movement includes static movement, gait movement, static conversion movement, static state movement includes station, sit,
It squats, lie；Gait movement includes that level land is walked, goes upstairs, goes downstairs, runs；Static conversion movement include station-seat, seat-stand, stand-
It squats, crouching-is stood, sat-lie, lie-and sits；
Step (2) extracts every road electromyography signal x that sample number is NiAverage amplitude MA,
Variance VAR,Wilson's amplitude WAMP,U (x) indicates rank
Jump function, and T is threshold value；Autoregressive coefficient AR；Median frequency MF,fiAnd hiRespectively frequency and frequency spectrum is strong
Degree；Frequency of average power MPF,P(fi) be basic point signal power spectrum；Wavelet energy coefficient EWT,FjIt is the coefficient of wavelet energy, K is jth layer decomposition coefficient, Wj,kIt is the kth of jth layer decomposition coefficient
A coefficient；Wavelet-packet energy coefficient EWP；Fuzzy entropy FE,WhereinM defines the dimension of data, DijIt is the similarity of two samples, r is DijMiddle finger
The width of number function, referred to as average similarity；Entropy PE is arranged,N refers to sample points, totally 10
A myoelectricity feature forms myoelectricity feature pool；
Step (3) refers to the static respective feature class separability of 10 electromyography signal features for acting calculating step 2 extraction
Mark selects myoelectricity feature composition static movement myoelectricity feature group of the feature class separability index J higher than 0.6；
Step (4) acts the respective feature class separability of 10 electromyography signal features that calculating step 2 is extracted to gait and refers to
Mark selects myoelectricity feature composition gait of the feature class separability index index J higher than 0.5 to act myoelectricity feature group；
Step (5), which acts the respective feature class of 10 electromyography signal features that calculating step 2 is extracted to static conversion, to be divided
Property index, select feature class separability index index J higher than 0.2 myoelectricity feature composition static conversion act myoelectricity feature group；
The feature class separability index of the electromyography signal feature specifically calculates as follows:
Equipped with electromyography signal training sample feature vector x1,x2,...xK, wherein KiIt is a to belong to classification ωi, i.e. KiFor the i-th class
Sample number, be denoted as Xi=x1 i,x2 i,...xKi i, i=1,2,3...C, C are total class number, and K is total number of samples,
Remember ωiThe myoelectricity mean vector of class is mi, have
The mean vector for remembering all class myoelectricity features is m, is had
Discrete matrix S between the respective class of electromyography signal featureBWith discrete matrix S in classW, formula is as follows:
Then tr (S is calculatedB),tr(Sw) respectively indicate matrix SBAnd SwMark, feature class separability index J obtains by following formula
It arrives:
The present invention has a characteristic that compared with the feature selecting algorithm of existing many electromyography signals
Since the present invention is extracted 10 kinds of features, if all using this 10 kinds of features to the movement of every class, it is multiple to will lead to algorithm
Miscellaneous degree increases significantly, and increases operation time.It can be utilized to greatest extent using this method of feature class separability index
Each feature not will cause the waste or redundancy of characteristic information, reduces dimension, greatly reduces the complexity of algorithm, make to classify
Effect is more preferable.
Detailed description of the invention
Fig. 1 is implementation flow chart of the invention；
Fig. 2 is the initial surface electromyography signal figure of 4 road signals of some daily behaviors；
Fig. 3 is the feature class separability index value of 15 kinds of features；
Fig. 4 is feature class separability index value and the calculating time of 15 kinds of features.
Specific embodiment
Elaborate with reference to the accompanying drawing to the embodiment of the present invention: the present embodiment before being with technical solution of the present invention
It puts and is implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to down
The embodiment stated.
As shown in Figure 1, the present embodiment includes the following steps:
Step 1 acquires human body gastrocnemius, tibialis anterior, vastus medials, musculus vastus lateralis totally 4 when human body does daily behavior movement
Road electromyography signal；Daily behavior movement includes static movement, gait movement, static conversion movement, static state movement includes station, sit,
It squats, lie；Gait movement includes that level land is walked, goes upstairs, goes downstairs, runs；Static conversion movement include station-seat, seat-stand, stand-
It squats, crouching-is stood, sat-lie, lie-and sits.As shown in Figure 2, it is shown that the original electromyography signal of several behavior acts.
Step 2 extracts the average amplitude MA of every road electromyography signal, variance VAR, Wilson's amplitude WAMP, autoregressive coefficient
AR, median frequency MF, frequency of average power MPF, wavelet energy coefficient EWT, wavelet-packet energy coefficient EWP, fuzzy entropy FE, arrangement
Entropy PE, totally 10 myoelectricity features form myoelectricity feature pool；
Step 3 calculates separately the 10 of step 2 extraction to the three categories of static movement, gait movement, static conversion movement
Discrete matrix S between the class of a electromyography signal featureBWith discrete matrix S in classW, then calculate separately feature class separability index
Step 4 selects myoelectricity feature composition of the feature class separability index J higher than 0.6 static dynamic from myoelectricity feature pool
Make myoelectricity feature group, myoelectricity feature composition gait of the feature class separability index J higher than 0.5 acts myoelectricity feature group, feature class
Myoelectricity feature composition static conversion of the separability index J higher than 0.2 acts myoelectricity feature group.
Fig. 3 shows the feature class separability index value of the EMG feature set of 15 seed types of three experiment bodies.Higher spy
Sign class separability index means corresponding characteristic high separation.WAMP feature is come previous position, followed by MA, EWT
And EWP.IAV, ARCU and FE feature are worst.Fig. 3 also shows do not have in the feature class separability index value of electromyogram feature
There is significant individual difference.Spearman coefficient of rank correlation average value shows spearman between individual close to 0.98 between subject
Grade difference is little.This result shows that, even for a small number of subjects, the main result of this research is still complete, for every
A individual subjects, sample size are very big.In addition, in terms of the inherent feature of electromyography signal, handicapped person and without between handicapped person
It is not significantly different.
Fig. 4 shows the feature class separability index value of every kind of characteristic type and calculates time, the spy of every kind of characteristic type
It is all average for levying class separability index value and calculating time.The result shows that can divide well although some characteristic types have
Property, but the separability value of some characteristic types (such as EWT and EWP) is got well than many other features, but it is very long to calculate the time.
10 kinds of features of table act static conversion, the separability index of gait movement and the ADLs comprising tumble movement
Different characteristic extracting mode, which acts on different types of movement, might have the classifying quality of great disparity.In addition, single
Feature, the one side feature of electromyography signal can only be utilized, such as single MA only apply to the difference in magnitude feature of EMG.For energy
The information sufficiently provided with electromyography signal, this project propose: in conjunction with identifying the different classes of middle higher feature of separability index,
Consider dimension factor simultaneously, forms suitable feature set.The higher MA of separability index in static conversion movement is such as combined,
WAMP, FE, EWT composition characteristic group, and it is called the feature set suitable for static conversion classification, it is abbreviated as Static-Convert
Feature group；It is suitable for the feature of gait classification in conjunction with separability index higher VAR, WAMP, EWP, MA composition in gait movement
Collection, is abbreviated as Gait-Move feature group；In conjunction with the higher MA of feature class separability index value, WAMP, VAR and EWT group in ADLs
At the feature set for being suitable for classifying to ADLs, it is abbreviated as ADL-Act feature group.
Claims (1)
1. the human body daily behavior myoelectricity feature selection approach based on feature class separability index, which is characterized in that this method packet
Include following steps:
Step (1) acquires human body gastrocnemius, tibialis anterior, vastus medials, musculus vastus lateralis totally 4 tunnel when human body does daily behavior movement
Electromyography signal；Daily behavior movement includes static movement, gait movement, static conversion movement, static state movement includes station, sit, squat,
It lies；Gait movement includes that level land is walked, goes upstairs, goes downstairs, runs；Static conversion movement include station-seat, seat-stand, stand-crouching,
Crouching-is stood, sat, and-lie, lie-sits；
Step (2) extracts every road electromyography signal x that sample number is NiAverage amplitude MA,Variance
VAR,Wilson's amplitude WAMP,U (x) indicates step letter
Number, T is threshold value；Autoregressive coefficient AR；Median frequency MF,fiAnd hiRespectively frequency and spectrum intensity；
Frequency of average power MPF,P(fi) be basic point signal power spectrum；Wavelet energy coefficient EWT,FjIt is the coefficient of wavelet energy, K is jth layer decomposition coefficient, Wj,kIt is the kth of jth layer decomposition coefficient
A coefficient；Wavelet-packet energy coefficient EWP；Fuzzy entropy FE,WhereinM defines the dimension of data, DijIt is the similarity of two samples, r is DijMiddle finger
The width of number function, referred to as average similarity；Entropy PE is arranged,N refers to sample points, totally 10
A myoelectricity feature forms myoelectricity feature pool；
Step (3) calculates static movement the respective feature class separability index of 10 electromyography signal features that step 2 is extracted,
Select myoelectricity feature composition static movement myoelectricity feature group of the feature class separability index J higher than 0.6；
Step (4) acts the respective feature class separability index of 10 electromyography signal features for calculating step 2 and extracting to gait,
Myoelectricity feature composition gait of the feature class separability index index J higher than 0.5 is selected to act myoelectricity feature group；
Step (5) acts the respective feature class separability of 10 electromyography signal features that calculating step 2 is extracted to static conversion and refers to
Mark selects myoelectricity feature composition static conversion of the feature class separability index index J higher than 0.2 to act myoelectricity feature group；
The feature class separability index of the electromyography signal feature specifically calculates as follows:
Equipped with electromyography signal training sample feature vector x1,x2,...xK, wherein KiIt is a to belong to classification ωi, i.e. KiFor the sample of the i-th class
This number is denoted asC is total class number, and K is total number of samples,
Remember ωiThe myoelectricity mean vector of class is mi, have
The mean vector for remembering all class myoelectricity features is m, is had
Discrete matrix S between the respective class of electromyography signal featureBWith discrete matrix S in classW, formula is as follows:
Then tr (S is calculatedB),tr(Sw) respectively indicate matrix SBAnd SwMark, feature class separability index J obtains by following formula:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811606406.9A CN109498009A (en) | 2018-12-26 | 2018-12-26 | Human body daily behavior myoelectricity feature selection approach based on feature class separability index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811606406.9A CN109498009A (en) | 2018-12-26 | 2018-12-26 | Human body daily behavior myoelectricity feature selection approach based on feature class separability index |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109498009A true CN109498009A (en) | 2019-03-22 |
Family
ID=65754841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811606406.9A Pending CN109498009A (en) | 2018-12-26 | 2018-12-26 | Human body daily behavior myoelectricity feature selection approach based on feature class separability index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109498009A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116135493A (en) * | 2021-11-16 | 2023-05-19 | 广州视源电子科技股份有限公司 | Performance test method and device of wearable equipment and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5390679A (en) * | 1993-06-03 | 1995-02-21 | Eli Lilly And Company | Continuous cardiac output derived from the arterial pressure waveform using pattern recognition |
| CN107440716A (en) * | 2017-07-26 | 2017-12-08 | 电子科技大学 | Human body lower limbs athletic performance classification discrimination method based on single channel electromyographic signal |
| CN108354627A (en) * | 2018-04-04 | 2018-08-03 | 东北大学 | A kind of Ultrasound beamforming method improving frame frequency |
-
2018
- 2018-12-26 CN CN201811606406.9A patent/CN109498009A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5390679A (en) * | 1993-06-03 | 1995-02-21 | Eli Lilly And Company | Continuous cardiac output derived from the arterial pressure waveform using pattern recognition |
| CN107440716A (en) * | 2017-07-26 | 2017-12-08 | 电子科技大学 | Human body lower limbs athletic performance classification discrimination method based on single channel electromyographic signal |
| CN108354627A (en) * | 2018-04-04 | 2018-08-03 | 东北大学 | A kind of Ultrasound beamforming method improving frame frequency |
Non-Patent Citations (2)
| Title |
|---|
| 周宇轩: "基于通信原理与肌电信号控制的上肢运动功能重建系统设计与实验研究", 《中国博士学位论文全文数据库医药卫生科技辑》 * |
| 席旭刚，等: "融合表面肌电和加速度信号的下肢运动模式识别研究", 《电子学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116135493A (en) * | 2021-11-16 | 2023-05-19 | 广州视源电子科技股份有限公司 | Performance test method and device of wearable equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Doulah et al. | Wavelet domain feature extraction scheme based on dominant motor unit action potential of EMG signal for neuromuscular disease classification | |
| Phinyomark et al. | Fractal analysis features for weak and single-channel upper-limb EMG signals | |
| CN104127181B (en) | Electromyographic signal tumble detection method based on WKFDA | |
| CN105997064B (en) | A kind of discrimination method for human body lower limbs surface electromyogram signal | |
| Nazarpour et al. | Application of higher order statistics to surface electromyogram signal classification | |
| Phinyomark et al. | Investigating long-term effects of feature extraction methods for continuous EMG pattern classification | |
| CN102961203A (en) | Method for identifying surface electromyography (sEMG) on basis of empirical mode decomposition (EMD) sample entropy | |
| CN107440716A (en) | Human body lower limbs athletic performance classification discrimination method based on single channel electromyographic signal | |
| Baspinar et al. | Performance comparison of artificial neural network and Gaussian mixture model in classifying hand motions by using sEMG signals | |
| CN103610466A (en) | EMG fall identification method based on EMD permutation entropy | |
| Amanpreet | Machine learning-based novel approach to classify the shoulder motion of upper limb amputees | |
| Paz et al. | Effects of different antagonist protocols on repetition performance and muscle activation | |
| Ahmed et al. | EMG Signal classification for detecting neuromuscular disorders | |
| CN108280464A (en) | The brain electrical feature extracting method of DWT and EMD fusion approximate entropies | |
| Wang et al. | Accelerometry based classification of gait patterns using empirical mode decomposition | |
| Xiong et al. | An unsupervised compressed sensing algorithm for multi-channel neural recording and spike sorting | |
| Phinyomark et al. | EMG amplitude estimators based on probability distribution for muscle–computer interface | |
| CN112541415A (en) | Brain muscle function network movement fatigue detection method based on symbol transfer entropy and graph theory | |
| CN114533089A (en) | Lower limb action recognition and classification method based on surface electromyographic signals | |
| CN106127191A (en) | Brain electricity sorting technique based on WAVELET PACKET DECOMPOSITION and logistic regression | |
| Acharya et al. | Classification of normal, neuropathic, and myopathic electromyograph signals using nonlinear dynamics method | |
| Rong et al. | Classification of surface EMGs using wavelet packet energy analysis and a genetic algorithm-based support vector machine | |
| CN109498009A (en) | Human body daily behavior myoelectricity feature selection approach based on feature class separability index | |
| Dzitac et al. | Identification of ERD using fuzzy inference systems for brain-computer interface | |
| CN115137375A (en) | Surface electromyographic signal classification method based on double branch network |
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: 20190322 |
|
| RJ01 | Rejection of invention patent application after publication |