Segmentation by Data Point Classification Applied to Forearm Surface EMG

Jonathan Lin; Ali-Akbar Samadani; Dana Kulić

Smart City 360°. First EAI International Summit, Smart City 360°, Bratislava, Slovakia and Toronto, Canada, October 13-16, 2015. Revised Selected Papers

Research Article

Segmentation by Data Point Classification Applied to Forearm Surface EMG

Download

343 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-319-33681-7_13,
    author={Jonathan Lin and Ali-Akbar Samadani and Dana Kulić},
    title={Segmentation by Data Point Classification Applied to Forearm Surface EMG},
    proceedings={Smart City 360°. First EAI International Summit, Smart City 360°, Bratislava, Slovakia and Toronto, Canada, October 13-16, 2015. Revised Selected Papers},
    proceedings_a={SMARTCITY360},
    year={2016},
    month={6},
    keywords={Motion segmentation Surface electromyography Classifiers Pattern recognition},
    doi={10.1007/978-3-319-33681-7_13}
}

Jonathan Lin
Ali-Akbar Samadani
Dana Kulić
Year: 2016
Segmentation by Data Point Classification Applied to Forearm Surface EMG
SMARTCITY360
Springer
DOI: 10.1007/978-3-319-33681-7_13

Jonathan Lin¹^,*, Ali-Akbar Samadani²^,*, Dana Kulić¹^,*

1: University of Waterloo
2: University of Toronto

*Contact email: jf2lin@uwaterloo.ca, ali.samadani@utoronto.ca, dkulic@uwaterloo.ca

Abstract

Recent advances in wearable technologies have led to the development of new modalities for human-machine interaction such as gesture-based interaction via surface electromyograph (EMG). An important challenge when performing EMG gesture recognition is to temporally segment the individual gestures from continuously recorded time-series data. This paper proposes an approach for EMG data segmentation, by formulating the segmentation problem as a classification task, where a classifier is used to label each data point as either a segment point or a non-segment point. The proposed EMG segmentation approach is used to recognize 9 hand gestures from forearm EMG data of 10 participants and a balanced accuracy of 83 % is achieved.

Keywords: Motion segmentation Surface electromyography Classifiers Pattern recognition

Published: 2016-06-29
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-319-33681-7_13