Skip to main navigation Skip to search Skip to main content

A wearable capacitive sensing system with phase-dependent classifier for locomotion mode recognition

  • Enhao Zheng
  • , Baojun Chen
  • , Qining Wang
  • , Kunlin Wei
  • , Long Wang
  • Peking University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

Locomotion mode recognition is one of the most important aspects for the control of motion rehabilitation systems, e.g. lower-limb prostheses and exoskeletons. In this paper, we propose a capacitance based sensing system for recognizing human locomotion modes. The proposed system includes two rings as sensing front-ends of body capacitance, two sensing circuits for processing the signals and the gait event detection system. The deformation of muscles can be reflected by the changes of capacitance signals. To validate the developed prototype, nine locomotion modes are monitored and ten channels of capacitance signals are collected for locomotion mode recognition. With the combination of capacitive sensing approach and phase-dependent classification method, satisfactory recognition results are obtained.

Original languageEnglish
Title of host publication2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012
Pages1747-1752
Number of pages6
DOIs
StatePublished - 2012
Externally publishedYes
Event2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012 - Rome, Italy
Duration: 24 Jun 201227 Jun 2012

Publication series

NameProceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics
ISSN (Print)2155-1774

Conference

Conference2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012
Country/TerritoryItaly
CityRome
Period24/06/1227/06/12

Fingerprint

Dive into the research topics of 'A wearable capacitive sensing system with phase-dependent classifier for locomotion mode recognition'. Together they form a unique fingerprint.

Cite this