Multi modal gesture identification for HCI using surface EMG

Ganesh R. Naik; Dinesh K. Kumar; Sridhar P. Arjunan

doi:10.1145/1457199.1457219

Multi modal gesture identification for HCI using surface EMG

Ganesh R. Naik, Dinesh K. Kumar, Sridhar P. Arjunan

Western Sydney University

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

9 Citations (Scopus)

Abstract

![CDATA[Gesture and Speech comprise the most important modalities of human interaction. There has been a considerable amount of research attempts at incorporating these modalities for natural HCI. This involves challenge ranging from the low level signal processing of multi-modal input to the high level interpretation of natural speech and gesture in HCI. This paper proposes novel methods to recognize the hand gestures and unvoiced utterances using surface Electromyogram (sEMG) signals originating from different muscles. The focus of this work is to establish a simple, yet robust system that can be integrated to identify subtle complex hand gestures and unvoiced speech commands for control of prosthesis and other computer assisted devices. The proposed multi-modal system is able to identify the hand gestures and silent utterances using Independent Component Analysis (ICA) and Integral RMS (IRMS) of sEMG respectively. Training of the sEMG features was done using a designed ANN architecture and the results reported with overall recognition accuracy of 90.33%.]]

Original language	English
Title of host publication	MindTrek '08: Proceedings of the 12th International Conference on Entertainment and Media in the Ubiquitous Era, 7-9 October 2008, Tampere, Finland
Publisher	Association for Computing Machinery
Pages	90-94
Number of pages	5
ISBN (Print)	9781605581972
DOIs	https://doi.org/10.1145/1457199.1457219
Publication status	Published - 2008
Event	International MindTrek Conference - Duration: 7 Oct 2008 → …

Conference

Conference	International MindTrek Conference
Period	7/10/08 → …

Keywords

electromyography
human information processing
independent component analysis
multimodal user interfaces (computer systems)
muscles
speech perception

Access to Document

10.1145/1457199.1457219

Cite this

@inproceedings{e7068417bdbc4638910539f3811c78e9,

title = "Multi modal gesture identification for HCI using surface EMG",

abstract = "![CDATA[Gesture and Speech comprise the most important modalities of human interaction. There has been a considerable amount of research attempts at incorporating these modalities for natural HCI. This involves challenge ranging from the low level signal processing of multi-modal input to the high level interpretation of natural speech and gesture in HCI. This paper proposes novel methods to recognize the hand gestures and unvoiced utterances using surface Electromyogram (sEMG) signals originating from different muscles. The focus of this work is to establish a simple, yet robust system that can be integrated to identify subtle complex hand gestures and unvoiced speech commands for control of prosthesis and other computer assisted devices. The proposed multi-modal system is able to identify the hand gestures and silent utterances using Independent Component Analysis (ICA) and Integral RMS (IRMS) of sEMG respectively. Training of the sEMG features was done using a designed ANN architecture and the results reported with overall recognition accuracy of 90.33%.]]",

keywords = "electromyography, human information processing, independent component analysis, multimodal user interfaces (computer systems), muscles, speech perception",

author = "Naik, {Ganesh R.} and Kumar, {Dinesh K.} and Arjunan, {Sridhar P.}",

year = "2008",

doi = "10.1145/1457199.1457219",

language = "English",

isbn = "9781605581972",

pages = "90--94",

booktitle = "MindTrek '08: Proceedings of the 12th International Conference on Entertainment and Media in the Ubiquitous Era, 7-9 October 2008, Tampere, Finland",

publisher = "Association for Computing Machinery",

note = "International MindTrek Conference ; Conference date: 07-10-2008",

}

Naik, GR, Kumar, DK & Arjunan, SP 2008, Multi modal gesture identification for HCI using surface EMG. in MindTrek '08: Proceedings of the 12th International Conference on Entertainment and Media in the Ubiquitous Era, 7-9 October 2008, Tampere, Finland. Association for Computing Machinery, pp. 90-94, International MindTrek Conference, 7/10/08. https://doi.org/10.1145/1457199.1457219

Multi modal gesture identification for HCI using surface EMG. / Naik, Ganesh R.; Kumar, Dinesh K.; Arjunan, Sridhar P.
MindTrek '08: Proceedings of the 12th International Conference on Entertainment and Media in the Ubiquitous Era, 7-9 October 2008, Tampere, Finland. Association for Computing Machinery, 2008. p. 90-94.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Multi modal gesture identification for HCI using surface EMG

AU - Naik, Ganesh R.

AU - Kumar, Dinesh K.

AU - Arjunan, Sridhar P.

PY - 2008

Y1 - 2008

N2 - ![CDATA[Gesture and Speech comprise the most important modalities of human interaction. There has been a considerable amount of research attempts at incorporating these modalities for natural HCI. This involves challenge ranging from the low level signal processing of multi-modal input to the high level interpretation of natural speech and gesture in HCI. This paper proposes novel methods to recognize the hand gestures and unvoiced utterances using surface Electromyogram (sEMG) signals originating from different muscles. The focus of this work is to establish a simple, yet robust system that can be integrated to identify subtle complex hand gestures and unvoiced speech commands for control of prosthesis and other computer assisted devices. The proposed multi-modal system is able to identify the hand gestures and silent utterances using Independent Component Analysis (ICA) and Integral RMS (IRMS) of sEMG respectively. Training of the sEMG features was done using a designed ANN architecture and the results reported with overall recognition accuracy of 90.33%.]]

AB - ![CDATA[Gesture and Speech comprise the most important modalities of human interaction. There has been a considerable amount of research attempts at incorporating these modalities for natural HCI. This involves challenge ranging from the low level signal processing of multi-modal input to the high level interpretation of natural speech and gesture in HCI. This paper proposes novel methods to recognize the hand gestures and unvoiced utterances using surface Electromyogram (sEMG) signals originating from different muscles. The focus of this work is to establish a simple, yet robust system that can be integrated to identify subtle complex hand gestures and unvoiced speech commands for control of prosthesis and other computer assisted devices. The proposed multi-modal system is able to identify the hand gestures and silent utterances using Independent Component Analysis (ICA) and Integral RMS (IRMS) of sEMG respectively. Training of the sEMG features was done using a designed ANN architecture and the results reported with overall recognition accuracy of 90.33%.]]

KW - electromyography

KW - human information processing

KW - independent component analysis

KW - multimodal user interfaces (computer systems)

KW - muscles

KW - speech perception

UR - http://handle.westernsydney.edu.au:8081/1959.7/uws:44534

U2 - 10.1145/1457199.1457219

DO - 10.1145/1457199.1457219

M3 - Conference Paper

SN - 9781605581972

SP - 90

EP - 94

BT - MindTrek '08: Proceedings of the 12th International Conference on Entertainment and Media in the Ubiquitous Era, 7-9 October 2008, Tampere, Finland

PB - Association for Computing Machinery

T2 - International MindTrek Conference

Y2 - 7 October 2008

ER -

Multi modal gesture identification for HCI using surface EMG

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this