Classification of finger extension and flexion of EMG and Cyberglove data with modified ICA weight matrix

Ganesh R. Naik, Amit Acharyya, Hung T. Nguyen

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

22 Citations (Scopus)

Abstract

This paper reports the classification of finger flexion and extension of surface Electromyography (EMG) and Cyberglove data using the modified Independent Component Analysis (ICA) weight matrix. The finger flexion and extension data are processed through Principal Component Analysis (PCA), and next separated using modified ICA for each individual with customized weight matrix. The extension and flexion features of sEMG and Cyberglove (extracted from modified ICA) were classified using Linear Discriminant Analysis (LDA) with near 90% classification accuracy. The applications of this study include Human Computer Interface (HCI), virtual reality and neural prosthetics.

Original languageEnglish
Title of host publication2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Place of PublicationChicago, IL
PublisherInstitute of Electrical and Electronics Engineers
Pages3829-3832
Number of pages4
ISBN (Electronic)9781424479290
DOIs
Publication statusPublished - 2014
Externally publishedYes
Event2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 - Chicago, United States
Duration: 26 Aug 201430 Aug 2014

Publication series

Name2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014

Conference

Conference2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
Country/TerritoryUnited States
CityChicago
Period26/08/1430/08/14

Keywords

  • Thumb
  • Electromyography
  • Principal component analysis
  • Sensors
  • Feature extraction
  • Surface treatment

Fingerprint

Dive into the research topics of 'Classification of finger extension and flexion of EMG and Cyberglove data with modified ICA weight matrix'. Together they form a unique fingerprint.

Cite this