Passive localization using array sensor with support vector machine

Jihoon Hong, Shun Kawakami, Tomoaki Ohtsuki

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

1 Citation (Scopus)

Abstract

A new method for passive localization using an array sensor system based on spatial smoothing processing (SSP) with support vector machine (SVM) is proposed. The array sensor uses only one array antenna as the receiver to observe the signal subspace spanned by eigenvector through array signal processing. The signal subspace represents the radio wave propagation of interest. Based on the eigenvector, it can detect and classify simple human activities: entering a room, standing, and moving. The advantages of the system are as follows: it guarantees privacy of users; it eliminates installation difficulties; it also offers a wide detection range. Although the conventional method can detect simple human activities, it cannot determine the position of the human being in detail. The proposed method uses multiple transmitters emitting different frequency signals to extend the dimension of the signal subspace. In addition, we separate coherent signals by using the SSP to obtain more features of radio wave propagation than the number of transmitters. The features are used as inputs to SVM to localize human position. The experimental results show that the proposed method improves the localization accuracy and the root mean square error (RMSE) compared to the previous method.

Original languageEnglish
Title of host publicationWPNC'12 - Proceedings of the 2012 9th Workshop on Positioning, Navigation and Communication
Pages169-174
Number of pages6
DOIs
Publication statusPublished - 2012
Event2012 9th Workshop on Positioning, Navigation and Communication, WPNC'12 - Dresden, Germany
Duration: 2012 Mar 152012 Mar 16

Other

Other2012 9th Workshop on Positioning, Navigation and Communication, WPNC'12
CountryGermany
CityDresden
Period12/3/1512/3/16

Fingerprint

Radio waves
Sensor arrays
Eigenvalues and eigenfunctions
Wave propagation
Support vector machines
Transmitters
Processing
Antenna arrays
Mean square error
Signal processing
radio
privacy
guarantee
recipient
human being

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Communication

Cite this

Hong, J., Kawakami, S., & Ohtsuki, T. (2012). Passive localization using array sensor with support vector machine. In WPNC'12 - Proceedings of the 2012 9th Workshop on Positioning, Navigation and Communication (pp. 169-174). [6268759] https://doi.org/10.1109/WPNC.2012.6268759

Passive localization using array sensor with support vector machine. / Hong, Jihoon; Kawakami, Shun; Ohtsuki, Tomoaki.

WPNC'12 - Proceedings of the 2012 9th Workshop on Positioning, Navigation and Communication. 2012. p. 169-174 6268759.

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

Hong, J, Kawakami, S & Ohtsuki, T 2012, Passive localization using array sensor with support vector machine. in WPNC'12 - Proceedings of the 2012 9th Workshop on Positioning, Navigation and Communication., 6268759, pp. 169-174, 2012 9th Workshop on Positioning, Navigation and Communication, WPNC'12, Dresden, Germany, 12/3/15. https://doi.org/10.1109/WPNC.2012.6268759
Hong J, Kawakami S, Ohtsuki T. Passive localization using array sensor with support vector machine. In WPNC'12 - Proceedings of the 2012 9th Workshop on Positioning, Navigation and Communication. 2012. p. 169-174. 6268759 https://doi.org/10.1109/WPNC.2012.6268759
Hong, Jihoon ; Kawakami, Shun ; Ohtsuki, Tomoaki. / Passive localization using array sensor with support vector machine. WPNC'12 - Proceedings of the 2012 9th Workshop on Positioning, Navigation and Communication. 2012. pp. 169-174
@inproceedings{9fd936365cc14078bf0209a009212b61,
title = "Passive localization using array sensor with support vector machine",
abstract = "A new method for passive localization using an array sensor system based on spatial smoothing processing (SSP) with support vector machine (SVM) is proposed. The array sensor uses only one array antenna as the receiver to observe the signal subspace spanned by eigenvector through array signal processing. The signal subspace represents the radio wave propagation of interest. Based on the eigenvector, it can detect and classify simple human activities: entering a room, standing, and moving. The advantages of the system are as follows: it guarantees privacy of users; it eliminates installation difficulties; it also offers a wide detection range. Although the conventional method can detect simple human activities, it cannot determine the position of the human being in detail. The proposed method uses multiple transmitters emitting different frequency signals to extend the dimension of the signal subspace. In addition, we separate coherent signals by using the SSP to obtain more features of radio wave propagation than the number of transmitters. The features are used as inputs to SVM to localize human position. The experimental results show that the proposed method improves the localization accuracy and the root mean square error (RMSE) compared to the previous method.",
author = "Jihoon Hong and Shun Kawakami and Tomoaki Ohtsuki",
year = "2012",
doi = "10.1109/WPNC.2012.6268759",
language = "English",
isbn = "9781467314398",
pages = "169--174",
booktitle = "WPNC'12 - Proceedings of the 2012 9th Workshop on Positioning, Navigation and Communication",

}

TY - GEN

T1 - Passive localization using array sensor with support vector machine

AU - Hong, Jihoon

AU - Kawakami, Shun

AU - Ohtsuki, Tomoaki

PY - 2012

Y1 - 2012

N2 - A new method for passive localization using an array sensor system based on spatial smoothing processing (SSP) with support vector machine (SVM) is proposed. The array sensor uses only one array antenna as the receiver to observe the signal subspace spanned by eigenvector through array signal processing. The signal subspace represents the radio wave propagation of interest. Based on the eigenvector, it can detect and classify simple human activities: entering a room, standing, and moving. The advantages of the system are as follows: it guarantees privacy of users; it eliminates installation difficulties; it also offers a wide detection range. Although the conventional method can detect simple human activities, it cannot determine the position of the human being in detail. The proposed method uses multiple transmitters emitting different frequency signals to extend the dimension of the signal subspace. In addition, we separate coherent signals by using the SSP to obtain more features of radio wave propagation than the number of transmitters. The features are used as inputs to SVM to localize human position. The experimental results show that the proposed method improves the localization accuracy and the root mean square error (RMSE) compared to the previous method.

AB - A new method for passive localization using an array sensor system based on spatial smoothing processing (SSP) with support vector machine (SVM) is proposed. The array sensor uses only one array antenna as the receiver to observe the signal subspace spanned by eigenvector through array signal processing. The signal subspace represents the radio wave propagation of interest. Based on the eigenvector, it can detect and classify simple human activities: entering a room, standing, and moving. The advantages of the system are as follows: it guarantees privacy of users; it eliminates installation difficulties; it also offers a wide detection range. Although the conventional method can detect simple human activities, it cannot determine the position of the human being in detail. The proposed method uses multiple transmitters emitting different frequency signals to extend the dimension of the signal subspace. In addition, we separate coherent signals by using the SSP to obtain more features of radio wave propagation than the number of transmitters. The features are used as inputs to SVM to localize human position. The experimental results show that the proposed method improves the localization accuracy and the root mean square error (RMSE) compared to the previous method.

UR - http://www.scopus.com/inward/record.url?scp=84866981606&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866981606&partnerID=8YFLogxK

U2 - 10.1109/WPNC.2012.6268759

DO - 10.1109/WPNC.2012.6268759

M3 - Conference contribution

AN - SCOPUS:84866981606

SN - 9781467314398

SP - 169

EP - 174

BT - WPNC'12 - Proceedings of the 2012 9th Workshop on Positioning, Navigation and Communication

ER -