A state classification method based on space-time signal processing using SVM for wireless monitoring systems

Jihoon Hong, Tomoaki Ohtsuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

In this paper we focus on improving state classification methods that can be implemented in elderly care monitoring systems. The authors group has previously proposed an indoor monitoring and security system (array sensor) that uses only one array antenna as the receiver. The clear advantages over conventional systems are improvement of privacy concern from the usage of closed-circuit television (CCTV) cameras, and elimination of installation difficulties. Our approach is different from the previous detection method which uses an array of sensors and a threshold that can classify only two states: nothing and something happening. In this paper, we present a state classification method that uses only one feature obtained from the radio wave propagation, and assisted by multiclass support vector machines (SVM) to classify the occurring states. The feature is the first eigenvector that spans the signal subspace of interest. The proposed method can be applied to not only indoor environments but also outdoor environments such as vehicle monitoring system. We performed experiments to classify seven states in an indoor setting: "No event," "Walking," "Entering into a bathtub," "Standing while showering," "Sitting while showering," "Falling down," and "Passing out;" and two states in an outdoor setting: "Normal state" and "Abnormal state." The experimental results show that we can achieve 96.5 % and 100 % classification accuracy for indoor and outdoor settings, respectively.

Original languageEnglish
Title of host publicationIEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC
Pages2229-2233
Number of pages5
DOIs
Publication statusPublished - 2011
Event2011 IEEE 22nd International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC'11 - Toronto, ON, Canada
Duration: 2011 Sep 112011 Sep 14

Other

Other2011 IEEE 22nd International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC'11
CountryCanada
CityToronto, ON
Period11/9/1111/9/14

Fingerprint

Support vector machines
Signal processing
Monitoring
Radio waves
Sensor arrays
Video cameras
Antenna arrays
Security systems
Eigenvalues and eigenfunctions
Wave propagation
Networks (circuits)
Sensors
Experiments

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Hong, J., & Ohtsuki, T. (2011). A state classification method based on space-time signal processing using SVM for wireless monitoring systems. In IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC (pp. 2229-2233). [6139913] https://doi.org/10.1109/PIMRC.2011.6139913

A state classification method based on space-time signal processing using SVM for wireless monitoring systems. / Hong, Jihoon; Ohtsuki, Tomoaki.

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC. 2011. p. 2229-2233 6139913.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hong, J & Ohtsuki, T 2011, A state classification method based on space-time signal processing using SVM for wireless monitoring systems. in IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC., 6139913, pp. 2229-2233, 2011 IEEE 22nd International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC'11, Toronto, ON, Canada, 11/9/11. https://doi.org/10.1109/PIMRC.2011.6139913
Hong J, Ohtsuki T. A state classification method based on space-time signal processing using SVM for wireless monitoring systems. In IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC. 2011. p. 2229-2233. 6139913 https://doi.org/10.1109/PIMRC.2011.6139913
Hong, Jihoon ; Ohtsuki, Tomoaki. / A state classification method based on space-time signal processing using SVM for wireless monitoring systems. IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC. 2011. pp. 2229-2233
@inproceedings{5c41453743ca474b80c7f9eb6347196a,
title = "A state classification method based on space-time signal processing using SVM for wireless monitoring systems",
abstract = "In this paper we focus on improving state classification methods that can be implemented in elderly care monitoring systems. The authors group has previously proposed an indoor monitoring and security system (array sensor) that uses only one array antenna as the receiver. The clear advantages over conventional systems are improvement of privacy concern from the usage of closed-circuit television (CCTV) cameras, and elimination of installation difficulties. Our approach is different from the previous detection method which uses an array of sensors and a threshold that can classify only two states: nothing and something happening. In this paper, we present a state classification method that uses only one feature obtained from the radio wave propagation, and assisted by multiclass support vector machines (SVM) to classify the occurring states. The feature is the first eigenvector that spans the signal subspace of interest. The proposed method can be applied to not only indoor environments but also outdoor environments such as vehicle monitoring system. We performed experiments to classify seven states in an indoor setting: {"}No event,{"} {"}Walking,{"} {"}Entering into a bathtub,{"} {"}Standing while showering,{"} {"}Sitting while showering,{"} {"}Falling down,{"} and {"}Passing out;{"} and two states in an outdoor setting: {"}Normal state{"} and {"}Abnormal state.{"} The experimental results show that we can achieve 96.5 {\%} and 100 {\%} classification accuracy for indoor and outdoor settings, respectively.",
author = "Jihoon Hong and Tomoaki Ohtsuki",
year = "2011",
doi = "10.1109/PIMRC.2011.6139913",
language = "English",
isbn = "9781457713484",
pages = "2229--2233",
booktitle = "IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC",

}

TY - GEN

T1 - A state classification method based on space-time signal processing using SVM for wireless monitoring systems

AU - Hong, Jihoon

AU - Ohtsuki, Tomoaki

PY - 2011

Y1 - 2011

N2 - In this paper we focus on improving state classification methods that can be implemented in elderly care monitoring systems. The authors group has previously proposed an indoor monitoring and security system (array sensor) that uses only one array antenna as the receiver. The clear advantages over conventional systems are improvement of privacy concern from the usage of closed-circuit television (CCTV) cameras, and elimination of installation difficulties. Our approach is different from the previous detection method which uses an array of sensors and a threshold that can classify only two states: nothing and something happening. In this paper, we present a state classification method that uses only one feature obtained from the radio wave propagation, and assisted by multiclass support vector machines (SVM) to classify the occurring states. The feature is the first eigenvector that spans the signal subspace of interest. The proposed method can be applied to not only indoor environments but also outdoor environments such as vehicle monitoring system. We performed experiments to classify seven states in an indoor setting: "No event," "Walking," "Entering into a bathtub," "Standing while showering," "Sitting while showering," "Falling down," and "Passing out;" and two states in an outdoor setting: "Normal state" and "Abnormal state." The experimental results show that we can achieve 96.5 % and 100 % classification accuracy for indoor and outdoor settings, respectively.

AB - In this paper we focus on improving state classification methods that can be implemented in elderly care monitoring systems. The authors group has previously proposed an indoor monitoring and security system (array sensor) that uses only one array antenna as the receiver. The clear advantages over conventional systems are improvement of privacy concern from the usage of closed-circuit television (CCTV) cameras, and elimination of installation difficulties. Our approach is different from the previous detection method which uses an array of sensors and a threshold that can classify only two states: nothing and something happening. In this paper, we present a state classification method that uses only one feature obtained from the radio wave propagation, and assisted by multiclass support vector machines (SVM) to classify the occurring states. The feature is the first eigenvector that spans the signal subspace of interest. The proposed method can be applied to not only indoor environments but also outdoor environments such as vehicle monitoring system. We performed experiments to classify seven states in an indoor setting: "No event," "Walking," "Entering into a bathtub," "Standing while showering," "Sitting while showering," "Falling down," and "Passing out;" and two states in an outdoor setting: "Normal state" and "Abnormal state." The experimental results show that we can achieve 96.5 % and 100 % classification accuracy for indoor and outdoor settings, respectively.

UR - http://www.scopus.com/inward/record.url?scp=84857574162&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857574162&partnerID=8YFLogxK

U2 - 10.1109/PIMRC.2011.6139913

DO - 10.1109/PIMRC.2011.6139913

M3 - Conference contribution

SN - 9781457713484

SP - 2229

EP - 2233

BT - IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC

ER -