State Classification with Array Sensor Using Support Vector Machine for Wireless Monitoring Systems

Jihoon HONG; Tomoaki OHTSUKI

doi:10.1587/transcom.E95.B.3088

State Classification with Array Sensor Using Support Vector Machine for Wireless Monitoring Systems

Jihoon HONG, Tomoaki OHTSUKI

Full Text Views

0

Share
Cite this

Summary :

We have previously proposed an indoor monitoring and security system with an array sensor. The array sensor has some advantages, such as low privacy concern, easy installation with low cost, and wide detection range. Our study is different from the previously proposed classification method for array sensor, which uses a threshold to classify only two states for intrusion detection: nothing and something happening. This paper describes a novel state classification method based on array signal processing with a machine learning algorithm. The proposed method uses eigenvector and eigenvalue spanning the signal subspace as features, obtained from the array sensor, and assisted by multiclass support vector machines (SVMs) to classify various states of a human being or an object. The experimental results show that our proposed method can provide high classification accuracy and robustness, which is very useful for monitoring and surveillance applications.

Publication: IEICE TRANSACTIONS on Communications Vol.E95-B No.10 pp.3088-3095

Publication Date: 2012/10/01

Publicized

Online ISSN: 1745-1345

DOI: 10.1587/transcom.E95.B.3088

Type of Manuscript: Special Section PAPER (Special Section on Medical Information Communication Technology for Disaster Recovery and Human Health Care Support)

Category

Cite this

Copy

Jihoon HONG, Tomoaki OHTSUKI, "State Classification with Array Sensor Using Support Vector Machine for Wireless Monitoring Systems" in IEICE TRANSACTIONS on Communications, vol. E95-B, no. 10, pp. 3088-3095, October 2012, doi: 10.1587/transcom.E95.B.3088.
Abstract: We have previously proposed an indoor monitoring and security system with an array sensor. The array sensor has some advantages, such as low privacy concern, easy installation with low cost, and wide detection range. Our study is different from the previously proposed classification method for array sensor, which uses a threshold to classify only two states for intrusion detection: nothing and something happening. This paper describes a novel state classification method based on array signal processing with a machine learning algorithm. The proposed method uses eigenvector and eigenvalue spanning the signal subspace as features, obtained from the array sensor, and assisted by multiclass support vector machines (SVMs) to classify various states of a human being or an object. The experimental results show that our proposed method can provide high classification accuracy and robustness, which is very useful for monitoring and surveillance applications.
URL: https://globals.ieice.org/en_transactions/communications/10.1587/transcom.E95.B.3088/_p

Copy

@ARTICLE{e95-b_10_3088,
author={Jihoon HONG, Tomoaki OHTSUKI, },
journal={IEICE TRANSACTIONS on Communications},
title={State Classification with Array Sensor Using Support Vector Machine for Wireless Monitoring Systems},
year={2012},
volume={E95-B},
number={10},
pages={3088-3095},
abstract={We have previously proposed an indoor monitoring and security system with an array sensor. The array sensor has some advantages, such as low privacy concern, easy installation with low cost, and wide detection range. Our study is different from the previously proposed classification method for array sensor, which uses a threshold to classify only two states for intrusion detection: nothing and something happening. This paper describes a novel state classification method based on array signal processing with a machine learning algorithm. The proposed method uses eigenvector and eigenvalue spanning the signal subspace as features, obtained from the array sensor, and assisted by multiclass support vector machines (SVMs) to classify various states of a human being or an object. The experimental results show that our proposed method can provide high classification accuracy and robustness, which is very useful for monitoring and surveillance applications.},
keywords={},
doi={10.1587/transcom.E95.B.3088},
ISSN={1745-1345},
month={October},}

Copy

TY - JOUR
TI - State Classification with Array Sensor Using Support Vector Machine for Wireless Monitoring Systems
T2 - IEICE TRANSACTIONS on Communications
SP - 3088
EP - 3095
AU - Jihoon HONG
AU - Tomoaki OHTSUKI
PY - 2012
DO - 10.1587/transcom.E95.B.3088
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E95-B
IS - 10
JA - IEICE TRANSACTIONS on Communications
Y1 - October 2012
AB - We have previously proposed an indoor monitoring and security system with an array sensor. The array sensor has some advantages, such as low privacy concern, easy installation with low cost, and wide detection range. Our study is different from the previously proposed classification method for array sensor, which uses a threshold to classify only two states for intrusion detection: nothing and something happening. This paper describes a novel state classification method based on array signal processing with a machine learning algorithm. The proposed method uses eigenvector and eigenvalue spanning the signal subspace as features, obtained from the array sensor, and assisted by multiclass support vector machines (SVMs) to classify various states of a human being or an object. The experimental results show that our proposed method can provide high classification accuracy and robustness, which is very useful for monitoring and surveillance applications.
ER -