Recognition of wrist motion pattern by EMG

Tadahiro Oyama, Yuji Matsumura, Stephen Karungaru, Yasue Mitsukura, Minoru Fukumi

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

9 Citations (Scopus)

Abstract

Recently, studies of artificial arms and pointing devices using ElectroMyoGram(EMG) have been actively done. However, the individual variation of EMG is large, and its repeatability is low. Furthermore, EMG is usually measured from a part with comparatively big muscular fibers such as arms and shoulders. Therefore, if we can recognize wrist operations using EMG which was measured from the wrist, the range of application will extend furthermore. In this study, we aim toward the development of a device of wristwatch type that consolidates operational interface of various equipments. In particular, as an early stage, we propose a wrist motion recognition system. First, we execute the Fourier transform to the signal for feature extraction. Next, we experiment it by using neural networks after the dimensional reduction by using Simple-PCA and Simple-FLDA to reduce the number of inputs to NN. It was confirmed that the present approach was one of the techniques which were effective in the wrist recognition experiment.

Original languageEnglish
Title of host publication2006 SICE-ICASE International Joint Conference
Pages599-603
Number of pages5
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event2006 SICE-ICASE International Joint Conference - Busan, Korea, Republic of
Duration: 2006 Oct 182006 Oct 21

Other

Other2006 SICE-ICASE International Joint Conference
CountryKorea, Republic of
CityBusan
Period06/10/1806/10/21

Fingerprint

Feature extraction
Fourier transforms
Experiments
Neural networks
Fibers

Keywords

  • EMQ Simple-PCA
  • Neural network
  • Online-tuning
  • Simple-FLDA

ASJC Scopus subject areas

  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Oyama, T., Matsumura, Y., Karungaru, S., Mitsukura, Y., & Fukumi, M. (2006). Recognition of wrist motion pattern by EMG. In 2006 SICE-ICASE International Joint Conference (pp. 599-603). [4108901] https://doi.org/10.1109/SICE.2006.315705

Recognition of wrist motion pattern by EMG. / Oyama, Tadahiro; Matsumura, Yuji; Karungaru, Stephen; Mitsukura, Yasue; Fukumi, Minoru.

2006 SICE-ICASE International Joint Conference. 2006. p. 599-603 4108901.

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

Oyama, T, Matsumura, Y, Karungaru, S, Mitsukura, Y & Fukumi, M 2006, Recognition of wrist motion pattern by EMG. in 2006 SICE-ICASE International Joint Conference., 4108901, pp. 599-603, 2006 SICE-ICASE International Joint Conference, Busan, Korea, Republic of, 06/10/18. https://doi.org/10.1109/SICE.2006.315705
Oyama T, Matsumura Y, Karungaru S, Mitsukura Y, Fukumi M. Recognition of wrist motion pattern by EMG. In 2006 SICE-ICASE International Joint Conference. 2006. p. 599-603. 4108901 https://doi.org/10.1109/SICE.2006.315705
Oyama, Tadahiro ; Matsumura, Yuji ; Karungaru, Stephen ; Mitsukura, Yasue ; Fukumi, Minoru. / Recognition of wrist motion pattern by EMG. 2006 SICE-ICASE International Joint Conference. 2006. pp. 599-603
@inproceedings{a70d545828c6492195bffd0367b74796,
title = "Recognition of wrist motion pattern by EMG",
abstract = "Recently, studies of artificial arms and pointing devices using ElectroMyoGram(EMG) have been actively done. However, the individual variation of EMG is large, and its repeatability is low. Furthermore, EMG is usually measured from a part with comparatively big muscular fibers such as arms and shoulders. Therefore, if we can recognize wrist operations using EMG which was measured from the wrist, the range of application will extend furthermore. In this study, we aim toward the development of a device of wristwatch type that consolidates operational interface of various equipments. In particular, as an early stage, we propose a wrist motion recognition system. First, we execute the Fourier transform to the signal for feature extraction. Next, we experiment it by using neural networks after the dimensional reduction by using Simple-PCA and Simple-FLDA to reduce the number of inputs to NN. It was confirmed that the present approach was one of the techniques which were effective in the wrist recognition experiment.",
keywords = "EMQ Simple-PCA, Neural network, Online-tuning, Simple-FLDA",
author = "Tadahiro Oyama and Yuji Matsumura and Stephen Karungaru and Yasue Mitsukura and Minoru Fukumi",
year = "2006",
doi = "10.1109/SICE.2006.315705",
language = "English",
isbn = "8995003855",
pages = "599--603",
booktitle = "2006 SICE-ICASE International Joint Conference",

}

TY - GEN

T1 - Recognition of wrist motion pattern by EMG

AU - Oyama, Tadahiro

AU - Matsumura, Yuji

AU - Karungaru, Stephen

AU - Mitsukura, Yasue

AU - Fukumi, Minoru

PY - 2006

Y1 - 2006

N2 - Recently, studies of artificial arms and pointing devices using ElectroMyoGram(EMG) have been actively done. However, the individual variation of EMG is large, and its repeatability is low. Furthermore, EMG is usually measured from a part with comparatively big muscular fibers such as arms and shoulders. Therefore, if we can recognize wrist operations using EMG which was measured from the wrist, the range of application will extend furthermore. In this study, we aim toward the development of a device of wristwatch type that consolidates operational interface of various equipments. In particular, as an early stage, we propose a wrist motion recognition system. First, we execute the Fourier transform to the signal for feature extraction. Next, we experiment it by using neural networks after the dimensional reduction by using Simple-PCA and Simple-FLDA to reduce the number of inputs to NN. It was confirmed that the present approach was one of the techniques which were effective in the wrist recognition experiment.

AB - Recently, studies of artificial arms and pointing devices using ElectroMyoGram(EMG) have been actively done. However, the individual variation of EMG is large, and its repeatability is low. Furthermore, EMG is usually measured from a part with comparatively big muscular fibers such as arms and shoulders. Therefore, if we can recognize wrist operations using EMG which was measured from the wrist, the range of application will extend furthermore. In this study, we aim toward the development of a device of wristwatch type that consolidates operational interface of various equipments. In particular, as an early stage, we propose a wrist motion recognition system. First, we execute the Fourier transform to the signal for feature extraction. Next, we experiment it by using neural networks after the dimensional reduction by using Simple-PCA and Simple-FLDA to reduce the number of inputs to NN. It was confirmed that the present approach was one of the techniques which were effective in the wrist recognition experiment.

KW - EMQ Simple-PCA

KW - Neural network

KW - Online-tuning

KW - Simple-FLDA

UR - http://www.scopus.com/inward/record.url?scp=34250703709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250703709&partnerID=8YFLogxK

U2 - 10.1109/SICE.2006.315705

DO - 10.1109/SICE.2006.315705

M3 - Conference contribution

AN - SCOPUS:34250703709

SN - 8995003855

SN - 9788995003855

SP - 599

EP - 603

BT - 2006 SICE-ICASE International Joint Conference

ER -