Multiple features fusion system for motion recognition

Jiang Hua, Zhaojie Ju, Disi Chen, Dalin Zhou, Haoyi Zhao, Du Jiang, Gongfa Li*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

105 Downloads (Pure)


Surface EMG signal is a signal source that can reflect the movement state of human muscles accurately. However, there are still problems such as low recognition rate in practical applications. It is necessary to study how they can be exploited effectively for a more accurate extraction. The paper combines two time domain features and nonlinear feature to get the feature vector for subsequent pattern recognition. The paper chooses the generalized regression neural network (GRNN) as the classifier for hand motion pattern recognition. The proposed method in this paper not only realizes the feature extraction of signals, but also ensures the high classification accuracy. The feature, RMS-SampEn-WL, obtains the highest recognition rate above 97% compared with the two time features. The new sEMG feature is effective and suitable for hand motion pattern recognition. Finally, we hope to establish a robust recognition system based on sEMG.

Original languageEnglish
Title of host publicationIntelligent Robotics and Applications
Subtitle of host publication12th International Conference, ICIRA 2019, Proceedings, Part IV
EditorsHaibin Yu, Jinguo Liu, Lianqing Liu, Zhaojie Ju, Yuwang Liu, Dalin Zhou
Number of pages11
ISBN (Electronic)978-3-030-27538-9
ISBN (Print)978-3-030-27537-2
Publication statusPublished - 3 Aug 2019
Event12th International Conference on Intelligent Robotics and Applications - Shenyang, China
Duration: 8 Aug 201911 Aug 2019

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameLecture Notes in Artificial Intelligence
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference12th International Conference on Intelligent Robotics and Applications
Abbreviated titleICIRA 2019


  • GRNN classifier
  • RMS-SampEn-WL
  • Surface EMG signal


Dive into the research topics of 'Multiple features fusion system for motion recognition'. Together they form a unique fingerprint.

Cite this