PCA/ICA-based SVM for fall recognition using MEMS motion sensing data

Guangyi Shi; Yuexian Zou; Yufeng Jin; Wen Jung Li

doi:10.1109/APCCAS.2008.4745962

PCA/ICA-based SVM for fall recognition using MEMS motion sensing data

Guangyi Shi
, Yuexian Zou^*
, Yufeng Jin
, Wen Jung Li

^*Corresponding author for this work

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

4 Citations (Scopus)

Abstract

This paper presents the progress towards a fall recognition algorithm based on MEMS motion sensing data. A Micro Inertial Measurement Unit (μIMU) that is 66 mm x 20 mm x 20 mm in size is built. This unit consists of three dimensional MEMS accelerometers, gyroscopes, and a Bluetooth module. It records human motion information, and the database of FALL and NORMAL is formed. We propose principal component analysis (PCA) for feature generation and independent component analysis (ICA) for feature extraction. Then, we use support vector machine (SVM) for training process. Experiments show that the process can classify falls and other normal motions successfully. © 2008 IEEE.

Original language	English
Title of host publication	IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS
Pages	69-72
DOIs	https://doi.org/10.1109/APCCAS.2008.4745962
Publication status	Published - 2008
Externally published	Yes
Event	2008 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS 2008) - Macao, China Duration: 30 Nov 2008 → 3 Dec 2008

Conference

Conference	2008 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS 2008)
Place	China
City	Macao
Period	30/11/08 → 3/12/08

Access Output

10.1109/APCCAS.2008.4745962

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{25a025a1777d4b3fbc96872475d7bd4b,

title = "PCA/ICA-based SVM for fall recognition using MEMS motion sensing data",

abstract = "This paper presents the progress towards a fall recognition algorithm based on MEMS motion sensing data. A Micro Inertial Measurement Unit (μIMU) that is 66 mm x 20 mm x 20 mm in size is built. This unit consists of three dimensional MEMS accelerometers, gyroscopes, and a Bluetooth module. It records human motion information, and the database of FALL and NORMAL is formed. We propose principal component analysis (PCA) for feature generation and independent component analysis (ICA) for feature extraction. Then, we use support vector machine (SVM) for training process. Experiments show that the process can classify falls and other normal motions successfully. {\textcopyright} 2008 IEEE.",

author = "Guangyi Shi and Yuexian Zou and Yufeng Jin and Li, \{Wen Jung\}",

year = "2008",

doi = "10.1109/APCCAS.2008.4745962",

language = "English",

isbn = "9781424423422",

pages = "69--72",

booktitle = "IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS",

note = "2008 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS 2008) ; Conference date: 30-11-2008 Through 03-12-2008",

}

PCA/ICA-based SVM for fall recognition using MEMS motion sensing data. / Shi, Guangyi; Zou, Yuexian; Jin, Yufeng et al.
IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS. 2008. p. 69-72 4745962.

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

TY - GEN

T1 - PCA/ICA-based SVM for fall recognition using MEMS motion sensing data

AU - Shi, Guangyi

AU - Zou, Yuexian

AU - Jin, Yufeng

AU - Li, Wen Jung

PY - 2008

Y1 - 2008

N2 - This paper presents the progress towards a fall recognition algorithm based on MEMS motion sensing data. A Micro Inertial Measurement Unit (μIMU) that is 66 mm x 20 mm x 20 mm in size is built. This unit consists of three dimensional MEMS accelerometers, gyroscopes, and a Bluetooth module. It records human motion information, and the database of FALL and NORMAL is formed. We propose principal component analysis (PCA) for feature generation and independent component analysis (ICA) for feature extraction. Then, we use support vector machine (SVM) for training process. Experiments show that the process can classify falls and other normal motions successfully. © 2008 IEEE.

AB - This paper presents the progress towards a fall recognition algorithm based on MEMS motion sensing data. A Micro Inertial Measurement Unit (μIMU) that is 66 mm x 20 mm x 20 mm in size is built. This unit consists of three dimensional MEMS accelerometers, gyroscopes, and a Bluetooth module. It records human motion information, and the database of FALL and NORMAL is formed. We propose principal component analysis (PCA) for feature generation and independent component analysis (ICA) for feature extraction. Then, we use support vector machine (SVM) for training process. Experiments show that the process can classify falls and other normal motions successfully. © 2008 IEEE.

UR - https://www.scopus.com/pages/publications/62949159573

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-62949159573&origin=recordpage

U2 - 10.1109/APCCAS.2008.4745962

DO - 10.1109/APCCAS.2008.4745962

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

SN - 9781424423422

SP - 69

EP - 72

BT - IEEE Asia-Pacific Conference on Circuits and Systems, Proceedings, APCCAS

T2 - 2008 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS 2008)

Y2 - 30 November 2008 through 3 December 2008

ER -

PCA/ICA-based SVM for fall recognition using MEMS motion sensing data

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this