表面筋電位を用いた多クラスSVMによる手指の実時間動作認識システムに関する検討

• 二股 大央

  東海大学大学院工学研究科

• 永田 健太郎

  早稲田大学人間総合研究センター

• 曲谷 一成

  東海大学工学部

書誌事項

タイトル別名

• The Evaluation of the Realtime Hand Motion Recognition System That Analyzes Forearm SEMG Using Multiclass SVM
• ヒョウメンキン デンイ オ モチイタ タクラス SVM ニ ヨル テサシ ノ ジツジカン ドウサ ニンシキ システム ニ カンスル ケントウ

抄録

Electromyogram (EMG) is a kind of biological signal that is generated because of excitement of muscle according to the motor instruction from a brain. We have been experimentally developing the real-time hand motion recognition system by using 4 channels forearm SEMG signals. In our system, in order to classify measured SEMG SVM (Support Vector Machine) that has higher discriminability is used. Usually SVM is used as a non-linear classifier. However, In the conventional system that we developed, we used a canonical discriminant analysis (CDA) method. CDA method is based on linear discriminant function, and it has shown good experimental results. So, we think linear SVM also has good separate performance. Than before, these discussions are not enough. Therefore, we developed real-time hand motion recognition system that uses linear SVM or non-linear SVM as a discriminant function, and we have compared the discriminant ability between linear SVM, non-linear SVM. In this report, we will describe about the results of this experiment.

収録刊行物

• 計測自動制御学会論文集

  計測自動制御学会論文集 50 (1), 37-43, 2014

  公益社団法人 計測自動制御学会

キーワード

• electromyogram
• EMG
• support vector machine
• SVM
• pattern recognition

詳細情報

• CRID: 1390001204503930112
• NII論文ID: 130004855691
• NII書誌ID: AN00072392
• DOI: 10.9746/sicetr.50.37
• ISSN: 18838189
• ISSN: 04534654
• NDL書誌ID: 025155534
• Web Site: http://id.ndl.go.jp/bib/025155534
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I025155534
• Web Site: https://www.jstage.jst.go.jp/article/sicetr/50/1/50_37/_pdf
• 本文言語コード: ja
• データソース種別:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可