Method for identifying surface electromyography (sEMG) on basis of empirical mode decomposition (EMD) sample entropy

A technology of myoelectric signal and recognition method, applied in the field of pattern recognition, which can solve the problems of real-time control of myoelectric prosthetic hand and weak anti-noise ability

Active Publication Date: 2013-03-13
HANGZHOU DIANZI UNIV
4 Cites 31 Cited by

AI-Extracted Technical Summary

Problems solved by technology

These nonlinear algorithms have solved the feature extraction problem of myoelectric signal very well. However, these feature extraction methods re...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Method used

(1) collect the myoelectric signal of human upper limb. The subjects performed 80 groups of 4 kinds of forearm movements, wrist up, wrist down, fist stretching and fist clenching, with a total of 320 sets of data. The extensor carpi ulnaris and flexor carpi ulnaris of the upper limbs were selected as the source of surface electromyography signals . Before the experiment, alcohol was used to wipe and decontaminate the extensor carpi ulnaris and flexor carpi ulnaris of the subjects to enhance the signal picking ability, and the MyoTrace 400 electromyographic signal acquisi...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Abstract

The invention provides a method for identifying surface electromyography (sEMG) on the basis of empirical mode decomposition (EMD) sample entropy. The method comprises the following steps: acquiring the corresponding sEMG from the related muscle tissue; performing EMD by using an actuating signal of the sEMG determined by energy threshold; adaptively selecting a plurality of intrinsic mode function (IMF) components comprising electromyographic signal effective information according to a frequency availability method; superposing the IMF components to serve as effective electromyographic signals and evaluating the sample entropy; and inputting the sample entropy serving as feature vector into a clustering classifier based on a spindle kernel clustering algorithm to realize identification on an upper limb multi-locomotion mode of the electromyographic signal. The sample entropy can disclose the complexity of the sEMG from a short time sequence, represents the tiny change condition of the electromyographic signal well, has high antijamming capability, simple algorithm and high calculation speed, and is particularly suitable for real-time processing of the electromyographic signal.

Application Domain

Technology Topic

Machine learningElectromyography +8

Image

  • Method for identifying surface electromyography (sEMG) on basis of empirical mode decomposition (EMD) sample entropy
  • Method for identifying surface electromyography (sEMG) on basis of empirical mode decomposition (EMD) sample entropy
  • Method for identifying surface electromyography (sEMG) on basis of empirical mode decomposition (EMD) sample entropy

Examples

  • Experimental program(1)

Example Embodiment

[0056] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings: this embodiment is implemented on the premise of the technical solution of the present invention, and detailed implementation modes and specific operation procedures are given.
[0057] Such as figure 1 As shown, this embodiment includes the following steps:
[0058] Step one is to obtain the sample data of the human upper limb EMG signal, specifically: first pick up the human upper limb EMG signal through the EMG signal acquisition instrument, and then use the energy threshold to determine the action signal of the EMG signal.
[0059] (1) Collect the EMG signal of the human upper limbs. The subjects performed 80 sets of four hand and forearm movements, namely, wrist upturn, wrist down, fist extension, and fist making. A total of 320 sets of data were performed. The upper extensor carpi ulnaris and flexor carpi ulnaris were selected as the surface EMG signal sources. . Before the experiment, the subjects’ extensor carpi ulnaris and flexor carpi ulnaris were rubbed and smeared with alcohol to enhance the signal pickup ability. The MyoTrace 400 EMG signal collector was used to pick up the extensor carpi ulnaris and The surface EMG signal corresponding to the flexor carpi ulnaris.
[0060] (2) Use energy threshold to determine the starting position and ending position of the action as the action EMG signal.
[0061] Step 2: Perform empirical mode decomposition on the sEMG motion signal obtained in Step 1, and then adaptively select several IMF components containing effective information of the EMG signal according to the frequency validity method and superimpose them as EMG signals.
[0062] Perform EMD decomposition of the action signal and decompose it into the sum of multiple stable intrinsic modal functions. According to the effective information statistics method based on instantaneous frequency, several IMF components containing effective information of the EMG signal are adaptively selected as the summation Action signal. This example selects the current frequency validity The first five IMF components at the time are superimposed as the EMG signal.
[0063] Step 3: Perform feature extraction on the EMG signal obtained in Step 2, and obtain the sample entropy as the EMG signal feature.
[0064] Find the sample entropy of the EMG signal by taking different with Value to calculate the sample entropy value of the EMG signal. A large number of experiments have proved that when When unchanged, When changing from 0.1 to 0.25, the sample entropy has a decreasing trend, but the change is very small and has little effect on feature extraction. In this example, take the embedding dimension =2, similarity tolerance =0.2, the effect of feature extraction is ideal.
[0065] Table 1 shows the statistical data of 80 groups of EMG signals on each of the subjects’ extensor carpi ulnaris and flexor carpi ulnaris muscles, using two methods to directly obtain sample entropy and EMD sample entropy of the motion signal
[0066] Table 1 Statistical characteristics of sample entropy and EMD sample entropy of 4 kinds of action EMG signals
[0067]
[0068] figure 2 In order to directly obtain the entropy of the sample from the action signal, take the sample entropy of the flexor muscle as the abscissa and the sample entropy of the extensor muscle as the ordinate to establish the characteristic distribution result of the rectangular coordinate system; image 3 To use the characteristic distribution result of the EMD sample entropy method.
[0069] Step 4: Use the sample entropy obtained in step 3 as a feature vector to input the clustering classifier based on the spindle kernel clustering algorithm to obtain the recognition result.
[0070] This example uses the kernel clustering algorithm, and the kernel function takes the spindle kernel function. The input of the classifier is the sample entropy of the signal of the extensor carpi ulnaris muscle and the supraflexor carpi ulnaris muscle. The sample entropy of the flexors and extensors of each set of actions is formed into a feature vector ,among them Is the first The sample entropy of the group flexor signal, Is the first The sample entropy value of the group extensor signal. Select 40 sets of 160 sets of surface EMG signals of each type of motion signal collected as the training set, obtain the EMD sample entropy to obtain the feature vector, use the spindle core clustering algorithm to obtain the spindle core function of each specific action, and then calculate the remaining The 160 sets of data below are used as the test set and sent to the spindle core clustering classifier for recognition. If the recognition result is consistent with the test target, it means that the test action is classified correctly, otherwise it is classified incorrectly.
[0071] Table 2 shows the result of pattern recognition by directly calculating the sample entropy and EMD sample entropy of the action signal as the feature vector, and inputting the cluster classifier based on the spindle kernel clustering algorithm. Table 3 compares the EMD sample entropy of the action signal as the feature vector, using the clustering classifier based on K-means and the Mahalanobis distance classifier based on the distance measure and the clustering classifier based on the spindle kernel clustering algorithm. Pattern recognition result.
[0072] Table 2 Hand movement recognition results of the two feature extraction methods
[0073] Feature extraction method On the turn Flip down Show fist make a fist Average recognition rate Sample entropy 37 34 33 35 86.7% EMD sample entropy 40 37 36 39 95%
[0074] Table 3 Recognition results obtained by inputting feature vectors extracted by the feature extraction method of the present invention into different classifiers
[0075] Pattern classifier On the turn Flip down Show fist make a fist Average recognition rate K-mean 82% 77% 77% 82% 79.5% Mahalanobis distance 90% 80% 83% 85% 84.5% Spindle kernel clustering 100% 92.5% 90% 97.5% 95%
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Similar technology patents

Classification and recommendation of technical efficacy words

  • Simple algorithm
  • Strong anti-interference ability

Ice layer thickness sensor and its detecting method

InactiveCN1560560AStrong anti-interference abilityMechanical thickness measurementsElectrical/magnetic thickness measurementsContactorIntermediate space
Owner:TAIYUAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products