Towards a human airbag system using μIMU with SVM training for falling-motion recognition

Yilun Luo; Guangyi Shi; Josh Lam; Guanglie Zhang; Wen J. Li; Philip H.W. Leong; Pauline P.Y. Lui; Kwok-Sui Leung

doi:10.1109/ROBIO.2005.246342

Towards a human airbag system using μIMU with SVM training for falling-motion recognition

Yilun Luo, Guangyi Shi, Josh Lam, Guanglie Zhang, Wen J. Li^*, Philip H.W. Leong, Pauline P.Y. Lui, Kwok-Sui Leung

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

5 Citations (Scopus)

Abstract

A Micro Inertial Measurement Unit (μIMU) which is based on MEMS accelerometers and gyro sensors is developed for real-time recognition of human body motions, specifically falling-down motions caused by slippage. A μIMU measures three-dimensional angular rates and accelerations. With an integrated microcontroller, the overall size of our μIMU is less than 26mm*20mm*20mm. We present our progress on using this μIMU based on Support Vector Machine (SVM) training to recognize falling-motions. The digital sample rate of the micro controller is 200Hz which ensures rapid reaction to short falling time and also gives a sufficient data information for SVM recognition. Experimental results show that our system can achieve a lateral falling-motion recognition rate of 100% using selected eigenvector sets generated from 200 experimental sets. Our goal is to implement this system to a human airbag system designed to protect hip fractures of the elderly. © 2005 IEEE.

Original language	English
Title of host publication	2005 IEEE International Conference on Robotics and Biomimetics, ROBIO
Publisher	IEEE
Pages	634-639
ISBN (Print)	0780393155, 9780780393158
DOIs	https://doi.org/10.1109/ROBIO.2005.246342
Publication status	Published - Jul 2005
Externally published	Yes
Event	2005 IEEE International Conference on Robotics and Biomimetics (ROBIO 2005) - Hong Kong, China Duration: 5 Jul 2005 → 9 Jul 2005

Conference

Conference	2005 IEEE International Conference on Robotics and Biomimetics (ROBIO 2005)
Place	China
City	Hong Kong
Period	5/07/05 → 9/07/05

Research Keywords

μIMU
Human airbag
Human motion sensing
MEMS
SVM

Access Output

10.1109/ROBIO.2005.246342

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{2eac36123d8d49d788f5b138814fa27a,

title = "Towards a human airbag system using μIMU with SVM training for falling-motion recognition",

abstract = "A Micro Inertial Measurement Unit (μIMU) which is based on MEMS accelerometers and gyro sensors is developed for real-time recognition of human body motions, specifically falling-down motions caused by slippage. A μIMU measures three-dimensional angular rates and accelerations. With an integrated microcontroller, the overall size of our μIMU is less than 26mm*20mm*20mm. We present our progress on using this μIMU based on Support Vector Machine (SVM) training to recognize falling-motions. The digital sample rate of the micro controller is 200Hz which ensures rapid reaction to short falling time and also gives a sufficient data information for SVM recognition. Experimental results show that our system can achieve a lateral falling-motion recognition rate of 100% using selected eigenvector sets generated from 200 experimental sets. Our goal is to implement this system to a human airbag system designed to protect hip fractures of the elderly. {\textcopyright} 2005 IEEE.",

keywords = "μIMU, Human airbag, Human motion sensing, MEMS, SVM",

author = "Yilun Luo and Guangyi Shi and Josh Lam and Guanglie Zhang and Li, {Wen J.} and Leong, {Philip H.W.} and Lui, {Pauline P.Y.} and Kwok-Sui Leung",

year = "2005",

month = jul,

doi = "10.1109/ROBIO.2005.246342",

language = "English",

isbn = "0780393155",

pages = "634--639",

booktitle = "2005 IEEE International Conference on Robotics and Biomimetics, ROBIO",

publisher = "IEEE",

address = "United States",

note = "2005 IEEE International Conference on Robotics and Biomimetics (ROBIO 2005) ; Conference date: 05-07-2005 Through 09-07-2005",

}

Luo, Y, Shi, G, Lam, J, Zhang, G, Li, WJ, Leong, PHW, Lui, PPY & Leung, K-S 2005, Towards a human airbag system using μIMU with SVM training for falling-motion recognition. in 2005 IEEE International Conference on Robotics and Biomimetics, ROBIO. IEEE, pp. 634-639, 2005 IEEE International Conference on Robotics and Biomimetics (ROBIO 2005), Hong Kong, China, 5/07/05. https://doi.org/10.1109/ROBIO.2005.246342

Towards a human airbag system using μIMU with SVM training for falling-motion recognition. / Luo, Yilun; Shi, Guangyi; Lam, Josh et al.
2005 IEEE International Conference on Robotics and Biomimetics, ROBIO. IEEE, 2005. p. 634-639.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Towards a human airbag system using μIMU with SVM training for falling-motion recognition

AU - Luo, Yilun

AU - Shi, Guangyi

AU - Lam, Josh

AU - Zhang, Guanglie

AU - Li, Wen J.

AU - Leong, Philip H.W.

AU - Lui, Pauline P.Y.

AU - Leung, Kwok-Sui

PY - 2005/7

Y1 - 2005/7

N2 - A Micro Inertial Measurement Unit (μIMU) which is based on MEMS accelerometers and gyro sensors is developed for real-time recognition of human body motions, specifically falling-down motions caused by slippage. A μIMU measures three-dimensional angular rates and accelerations. With an integrated microcontroller, the overall size of our μIMU is less than 26mm*20mm*20mm. We present our progress on using this μIMU based on Support Vector Machine (SVM) training to recognize falling-motions. The digital sample rate of the micro controller is 200Hz which ensures rapid reaction to short falling time and also gives a sufficient data information for SVM recognition. Experimental results show that our system can achieve a lateral falling-motion recognition rate of 100% using selected eigenvector sets generated from 200 experimental sets. Our goal is to implement this system to a human airbag system designed to protect hip fractures of the elderly. © 2005 IEEE.

AB - A Micro Inertial Measurement Unit (μIMU) which is based on MEMS accelerometers and gyro sensors is developed for real-time recognition of human body motions, specifically falling-down motions caused by slippage. A μIMU measures three-dimensional angular rates and accelerations. With an integrated microcontroller, the overall size of our μIMU is less than 26mm*20mm*20mm. We present our progress on using this μIMU based on Support Vector Machine (SVM) training to recognize falling-motions. The digital sample rate of the micro controller is 200Hz which ensures rapid reaction to short falling time and also gives a sufficient data information for SVM recognition. Experimental results show that our system can achieve a lateral falling-motion recognition rate of 100% using selected eigenvector sets generated from 200 experimental sets. Our goal is to implement this system to a human airbag system designed to protect hip fractures of the elderly. © 2005 IEEE.

KW - μIMU

KW - Human airbag

KW - Human motion sensing

KW - MEMS

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=33947624144&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-33947624144&origin=recordpage

U2 - 10.1109/ROBIO.2005.246342

DO - 10.1109/ROBIO.2005.246342

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0780393155

SN - 9780780393158

SP - 634

EP - 639

BT - 2005 IEEE International Conference on Robotics and Biomimetics, ROBIO

PB - IEEE

T2 - 2005 IEEE International Conference on Robotics and Biomimetics (ROBIO 2005)

Y2 - 5 July 2005 through 9 July 2005

ER -

Towards a human airbag system using μIMU with SVM training for falling-motion recognition

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this