State classification with array sensor using support vector machine forwireless monitoring systems

Jihoon Hong, Tomoaki Ohtsuki

Research output: Contribution to journalArticle

9 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)3088-3095
Number of pages8
JournalIEICE Transactions on Communications
VolumeE95-B
Issue number10
DOIs
Publication statusPublished - 2012 Oct

Fingerprint

Sensor arrays
Support vector machines
Monitoring
Intrusion detection
Security systems
Eigenvalues and eigenfunctions
Learning algorithms
Learning systems
Signal processing
Costs

Keywords

  • Array antenna
  • Support vector machine
  • Wireless monitoring

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Software

Cite this

State classification with array sensor using support vector machine forwireless monitoring systems. / Hong, Jihoon; Ohtsuki, Tomoaki.

In: IEICE Transactions on Communications, Vol. E95-B, No. 10, 10.2012, p. 3088-3095.

Research output: Contribution to journalArticle

@article{8e27f5c7ce5d44e380f6a2656c52b9be,
title = "State classification with array sensor using support vector machine forwireless monitoring systems",
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 = "Array antenna, Support vector machine, Wireless monitoring",
author = "Jihoon Hong and Tomoaki Ohtsuki",
year = "2012",
month = "10",
doi = "10.1587/transcom.E95.B.3088",
language = "English",
volume = "E95-B",
pages = "3088--3095",
journal = "IEICE Transactions on Communications",
issn = "0916-8516",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "10",

}

TY - JOUR

T1 - State classification with array sensor using support vector machine forwireless monitoring systems

AU - Hong, Jihoon

AU - Ohtsuki, Tomoaki

PY - 2012/10

Y1 - 2012/10

N2 - 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.

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.

KW - Array antenna

KW - Support vector machine

KW - Wireless monitoring

UR - http://www.scopus.com/inward/record.url?scp=84866952762&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866952762&partnerID=8YFLogxK

U2 - 10.1587/transcom.E95.B.3088

DO - 10.1587/transcom.E95.B.3088

M3 - Article

AN - SCOPUS:84866952762

VL - E95-B

SP - 3088

EP - 3095

JO - IEICE Transactions on Communications

JF - IEICE Transactions on Communications

SN - 0916-8516

IS - 10

ER -