Real Time on Sensor Gait Phase Detection with 0.5KB Deep Learning Model

Yian Chen; Jien De Sui; Tian Sheuan Chang

doi:10.1109/ICCE-Taiwan49838.2020.9258180

Real Time on Sensor Gait Phase Detection with 0.5KB Deep Learning Model

Yian Chen, Jien De Sui, Tian Sheuan Chang

研究成果: Conference contribution › 同行評審

摘要

Gait phase detection with convolution neural network provides accurate classification but demands high computational cost, which inhibits real time low power on-sensor processing. This paper presents a segmentation based gait phase detection with a width and depth downscaled U-Net like model that only needs 0.5KB model size and 67K operations per second with 95.9% accuracy to be easily fitted into resource limited on sensor microcontroller.

原文	English
主出版物標題	2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020
發行者	Institute of Electrical and Electronics Engineers Inc.
ISBN（電子）	9781728173993
DOIs	https://doi.org/10.1109/ICCE-Taiwan49838.2020.9258180
出版狀態	Published - 28 九月 2020
事件	7th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020 - Taoyuan, Taiwan 持續時間: 28 九月 2020 → 30 九月 2020

出版系列

名字	2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020

Conference

Conference	7th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020
國家	Taiwan
城市	Taoyuan
期間	28/09/20 → 30/09/20

存取文件

10.1109/ICCE-Taiwan49838.2020.9258180

其它文件與鏈接

Link to publication in Scopus

指紋深入研究「Real Time on Sensor Gait Phase Detection with 0.5KB Deep Learning Model」主題。共同形成了獨特的指紋。

引用此

Chen, Y., Sui, J. D., & Chang, T. S. (2020). Real Time on Sensor Gait Phase Detection with 0.5KB Deep Learning Model. 於 2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020 [9258180] (2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCE-Taiwan49838.2020.9258180

@inproceedings{ba74a7850a0e4086959d80a627e50284,

title = "Real Time on Sensor Gait Phase Detection with 0.5KB Deep Learning Model",

abstract = "Gait phase detection with convolution neural network provides accurate classification but demands high computational cost, which inhibits real time low power on-sensor processing. This paper presents a segmentation based gait phase detection with a width and depth downscaled U-Net like model that only needs 0.5KB model size and 67K operations per second with 95.9% accuracy to be easily fitted into resource limited on sensor microcontroller.",

author = "Yian Chen and Sui, {Jien De} and Chang, {Tian Sheuan}",

year = "2020",

month = sep,

day = "28",

doi = "10.1109/ICCE-Taiwan49838.2020.9258180",

language = "English",

series = "2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020",

address = "United States",

}

Chen, Y, Sui, JD & Chang, TS 2020, Real Time on Sensor Gait Phase Detection with 0.5KB Deep Learning Model. 於 2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020., 9258180, 2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020, Institute of Electrical and Electronics Engineers Inc., 7th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020, Taoyuan, Taiwan, 28/09/20. https://doi.org/10.1109/ICCE-Taiwan49838.2020.9258180

Real Time on Sensor Gait Phase Detection with 0.5KB Deep Learning Model. / Chen, Yian; Sui, Jien De; Chang, Tian Sheuan.

2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9258180 (2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020).

研究成果: Conference contribution › 同行評審

TY - GEN

T1 - Real Time on Sensor Gait Phase Detection with 0.5KB Deep Learning Model

AU - Chen, Yian

AU - Sui, Jien De

AU - Chang, Tian Sheuan

PY - 2020/9/28

Y1 - 2020/9/28

N2 - Gait phase detection with convolution neural network provides accurate classification but demands high computational cost, which inhibits real time low power on-sensor processing. This paper presents a segmentation based gait phase detection with a width and depth downscaled U-Net like model that only needs 0.5KB model size and 67K operations per second with 95.9% accuracy to be easily fitted into resource limited on sensor microcontroller.

AB - Gait phase detection with convolution neural network provides accurate classification but demands high computational cost, which inhibits real time low power on-sensor processing. This paper presents a segmentation based gait phase detection with a width and depth downscaled U-Net like model that only needs 0.5KB model size and 67K operations per second with 95.9% accuracy to be easily fitted into resource limited on sensor microcontroller.

UR - http://www.scopus.com/inward/record.url?scp=85098460186&partnerID=8YFLogxK

U2 - 10.1109/ICCE-Taiwan49838.2020.9258180

DO - 10.1109/ICCE-Taiwan49838.2020.9258180

M3 - Conference contribution

AN - SCOPUS:85098460186

T3 - 2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020

BT - 2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 28 September 2020 through 30 September 2020

ER -

Chen Y, Sui JD, Chang TS. Real Time on Sensor Gait Phase Detection with 0.5KB Deep Learning Model. 於 2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9258180. (2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020). https://doi.org/10.1109/ICCE-Taiwan49838.2020.9258180