Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Daily behavior recognition method based on myoelectric wavelet coherence and support vector machine

A technology of support vector machine and wavelet coherence, applied in the field of pattern recognition, to achieve high recognition rate and reliability

Inactive Publication Date: 2019-04-05
HANGZHOU DIANZI UNIV
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there are few researches on daily behavior recognition based on the coherence analysis of surface electromyography signals, and there is a relatively broad research space

Method used

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

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Daily behavior recognition method based on myoelectric wavelet coherence and support vector machine
  • Daily behavior recognition method based on myoelectric wavelet coherence and support vector machine
  • Daily behavior recognition method based on myoelectric wavelet coherence and support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] like figure 1 As shown, this embodiment includes the following steps:

[0032] Step 1: Acquire the sample data of the two EMG signals x(t) and y(t), and collect the EMG signals of the relevant muscles of the human body through the EMG signal acquisition instrument, specifically: through the DELSYS Trigno Wireless System EMG signal acquisition instrument Collect the EMG signals of the relevant muscles during the movement of the lower limbs of the human body. The experimental actions taken are standing, walking, running, climbing stairs, descending stairs and falling. The relevant muscles collected are gastrocnemius, tibialis anterior, rectus femoris and semitendinosus. figure 2 (a)-(f) are EMG signals of relevant muscles under different daily activities. Then use an improved wavelet threshold denoising method for preprocessing.

[0033]

[0034] in d i and are the wavelet coefficients before and after thresholding, and N is a normal number.

[0035] Step 2, c...

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 Login to View More

Abstract

The invention discloses a daily behavior recognition method based on myoelectric wavelet coherence and a support vector machine. Myoelectric signals of human body relevant muscles are collected through a myoelectric signal collection instrument; sample data of two paths of myoelectric signals is obtained; pretreatment is performed by using a modified wavelet threshold value noise reducing method;the wavelet coherence coefficient of the two paths of myoelectric signals is calculated. The obtained wavelet coherence coefficient is used as a feature vector to be input into the support vector machine for classification recognition; different daily behaviors are successfully recognized; higher recognition rate is realized. A method of combining the myoelectric features of the wavelet coherencewith the support vector machine is used; higher recognition rate and reliability is realized on the human body daily behavior recognition. Experiment results show that the method provided by the invention reaches the average sensitivity of 96.17 on going upstairs, going downstairs, standing, walking, running and falling; the average specificity degree reaches 92.29; the values are higher than those of a conventional method.

Description

technical field [0001] The invention belongs to the field of pattern recognition, and relates to a pattern recognition method of electromyographic signals, in particular to a daily behavior recognition method based on electromyographic wavelet coherence and support vector machines. Background technique [0002] At present, the recognition of daily behavior is receiving increasing attention, which is the basis of behavior monitoring and fall detection. Wearable sensors are the most widely used method in behavior detection, with the characteristics of easy operation and strong environmental compatibility. Wearable sensors include motion and electrophysiological sensors, such as accelerometer sensors, inertial sensors, gyroscopes, and surface electromyography (sEMG) sensors. Among them, the sEMG sensor can directly reflect the electrophysiological responses of various human activities, has a short calculation time, and can distinguish passive behavior from active behavior. It ...

Claims

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

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): A61B5/0488A61B5/11A61B5/00
CPCA61B5/1116A61B5/1117A61B5/1123A61B5/7203A61B5/7235A61B5/7264A61B5/316A61B5/389
Inventor 席旭刚杨晨石鹏袁长敏罗志增张启忠佘青山
Owner HANGZHOU DIANZI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com