Ambient intelligence sensing using array sensor

Device-free radio based approach

Jihoon Hong, Tomoaki Ohtsuki

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

14 Citations (Scopus)

Abstract

In this paper we introduce a novel device-free radio based activity recognition with localization method with various applications, such as e-Healthcare and security. Our method uses the properties of the signal subspace, which are estimated using signal eigenvectors of the covariance matrix obtained from an antenna array (array sensor) at the receiver side. To classify human activities (e.g., standing and moving) and/or positions, we apply a machine learning method with support vector machines (SVM). We compare the classification accuracy of the proposed method with signal subspace features and received signal strength (RSS). We analyze the impact of antenna deployment on classification accuracy in non-line-of-sight (NLOS) environments to prove the effectiveness of the proposed method. In addition, we compare our classification method with k-Nearest Neighbor (KNN). The experimental results show that the proposed method with signal subspace features provides accuracy improvements over the RSS-based method.

Original languageEnglish
Title of host publicationUbiComp 2013 Adjunct - Adjunct Publication of the 2013 ACM Conference on Ubiquitous Computing
Pages509-520
Number of pages12
DOIs
Publication statusPublished - 2013
Event2013 ACM Conference on Ubiquitous Computing, UbiComp 2013 - Zurich, Switzerland
Duration: 2013 Sep 82013 Sep 12

Other

Other2013 ACM Conference on Ubiquitous Computing, UbiComp 2013
CountrySwitzerland
CityZurich
Period13/9/813/9/12

Fingerprint

Sensor arrays
Covariance matrix
Antenna arrays
Eigenvalues and eigenfunctions
Support vector machines
Learning systems
Antennas
Ambient intelligence

Keywords

  • Activity recognition
  • Antenna array
  • Device-free sensing
  • Localization

ASJC Scopus subject areas

  • Software

Cite this

Hong, J., & Ohtsuki, T. (2013). Ambient intelligence sensing using array sensor: Device-free radio based approach. In UbiComp 2013 Adjunct - Adjunct Publication of the 2013 ACM Conference on Ubiquitous Computing (pp. 509-520) https://doi.org/10.1145/2494091.2497609

Ambient intelligence sensing using array sensor : Device-free radio based approach. / Hong, Jihoon; Ohtsuki, Tomoaki.

UbiComp 2013 Adjunct - Adjunct Publication of the 2013 ACM Conference on Ubiquitous Computing. 2013. p. 509-520.

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

Hong, J & Ohtsuki, T 2013, Ambient intelligence sensing using array sensor: Device-free radio based approach. in UbiComp 2013 Adjunct - Adjunct Publication of the 2013 ACM Conference on Ubiquitous Computing. pp. 509-520, 2013 ACM Conference on Ubiquitous Computing, UbiComp 2013, Zurich, Switzerland, 13/9/8. https://doi.org/10.1145/2494091.2497609
Hong J, Ohtsuki T. Ambient intelligence sensing using array sensor: Device-free radio based approach. In UbiComp 2013 Adjunct - Adjunct Publication of the 2013 ACM Conference on Ubiquitous Computing. 2013. p. 509-520 https://doi.org/10.1145/2494091.2497609
Hong, Jihoon ; Ohtsuki, Tomoaki. / Ambient intelligence sensing using array sensor : Device-free radio based approach. UbiComp 2013 Adjunct - Adjunct Publication of the 2013 ACM Conference on Ubiquitous Computing. 2013. pp. 509-520
@inproceedings{3825695b3d124afeb051e56564355a6d,
title = "Ambient intelligence sensing using array sensor: Device-free radio based approach",
abstract = "In this paper we introduce a novel device-free radio based activity recognition with localization method with various applications, such as e-Healthcare and security. Our method uses the properties of the signal subspace, which are estimated using signal eigenvectors of the covariance matrix obtained from an antenna array (array sensor) at the receiver side. To classify human activities (e.g., standing and moving) and/or positions, we apply a machine learning method with support vector machines (SVM). We compare the classification accuracy of the proposed method with signal subspace features and received signal strength (RSS). We analyze the impact of antenna deployment on classification accuracy in non-line-of-sight (NLOS) environments to prove the effectiveness of the proposed method. In addition, we compare our classification method with k-Nearest Neighbor (KNN). The experimental results show that the proposed method with signal subspace features provides accuracy improvements over the RSS-based method.",
keywords = "Activity recognition, Antenna array, Device-free sensing, Localization",
author = "Jihoon Hong and Tomoaki Ohtsuki",
year = "2013",
doi = "10.1145/2494091.2497609",
language = "English",
isbn = "9781450322157",
pages = "509--520",
booktitle = "UbiComp 2013 Adjunct - Adjunct Publication of the 2013 ACM Conference on Ubiquitous Computing",

}

TY - GEN

T1 - Ambient intelligence sensing using array sensor

T2 - Device-free radio based approach

AU - Hong, Jihoon

AU - Ohtsuki, Tomoaki

PY - 2013

Y1 - 2013

N2 - In this paper we introduce a novel device-free radio based activity recognition with localization method with various applications, such as e-Healthcare and security. Our method uses the properties of the signal subspace, which are estimated using signal eigenvectors of the covariance matrix obtained from an antenna array (array sensor) at the receiver side. To classify human activities (e.g., standing and moving) and/or positions, we apply a machine learning method with support vector machines (SVM). We compare the classification accuracy of the proposed method with signal subspace features and received signal strength (RSS). We analyze the impact of antenna deployment on classification accuracy in non-line-of-sight (NLOS) environments to prove the effectiveness of the proposed method. In addition, we compare our classification method with k-Nearest Neighbor (KNN). The experimental results show that the proposed method with signal subspace features provides accuracy improvements over the RSS-based method.

AB - In this paper we introduce a novel device-free radio based activity recognition with localization method with various applications, such as e-Healthcare and security. Our method uses the properties of the signal subspace, which are estimated using signal eigenvectors of the covariance matrix obtained from an antenna array (array sensor) at the receiver side. To classify human activities (e.g., standing and moving) and/or positions, we apply a machine learning method with support vector machines (SVM). We compare the classification accuracy of the proposed method with signal subspace features and received signal strength (RSS). We analyze the impact of antenna deployment on classification accuracy in non-line-of-sight (NLOS) environments to prove the effectiveness of the proposed method. In addition, we compare our classification method with k-Nearest Neighbor (KNN). The experimental results show that the proposed method with signal subspace features provides accuracy improvements over the RSS-based method.

KW - Activity recognition

KW - Antenna array

KW - Device-free sensing

KW - Localization

UR - http://www.scopus.com/inward/record.url?scp=84885235690&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885235690&partnerID=8YFLogxK

U2 - 10.1145/2494091.2497609

DO - 10.1145/2494091.2497609

M3 - Conference contribution

SN - 9781450322157

SP - 509

EP - 520

BT - UbiComp 2013 Adjunct - Adjunct Publication of the 2013 ACM Conference on Ubiquitous Computing

ER -