MobileRF: A robust device-free tracking system based on ahybrid neural network HMM classifier

Anindya S. Paul, Eric A. Wan, Fatema Adenwala, Erich Schafermeyer, Nick Preiser, Jeffrey Kaye, Peter Jacobs

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

18 Citations (Scopus)

Abstract

We present a device-free indoor tracking system that uses received signal strength (RSS) from radio frequency (RF) transceivers to estimate the location of a person. While many RSS-based tracking systems use a body-worn device or tag, this approach requires no such tag. The approach is based on the key principle that RF signals between wall-mounted transceivers reflect and absorb differently depending on a person's movement within their home. A hierarchical neural network hidden Markov model (NN-HMM) classifier estimates both movement patterns and stand vs. walk conditions to perform tracking accurately. The algorithm and features used are specifically robust to changes in RSS mean shifts in the environment over time allowing for greater than 90% region level classification accuracy over an extended testing period. In addition to tracking, the system also estimates the number of people in different regions. It is currently being developed to support independent living and long-term monitoring of seniors.

Original languageEnglish (US)
Title of host publicationUbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing
PublisherAssociation for Computing Machinery, Inc
Pages159-170
Number of pages12
ISBN (Print)9781450329682
DOIs
StatePublished - 2014
Event2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014 - Seattle, United States
Duration: Sep 13 2014Sep 17 2014

Other

Other2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014
CountryUnited States
CitySeattle
Period9/13/149/17/14

Fingerprint

Transceivers
Classifiers
Neural networks
Hidden Markov models
Monitoring
Testing

Keywords

  • Device-free passive localization
  • Health care
  • Indoor localization
  • Indoor tracking
  • Machine learning
  • Mobility
  • Neural network
  • Tag-free tracking

ASJC Scopus subject areas

  • Software

Cite this

Paul, A. S., Wan, E. A., Adenwala, F., Schafermeyer, E., Preiser, N., Kaye, J., & Jacobs, P. (2014). MobileRF: A robust device-free tracking system based on ahybrid neural network HMM classifier. In UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (pp. 159-170). Association for Computing Machinery, Inc. https://doi.org/10.1145/2632048.2632097

MobileRF : A robust device-free tracking system based on ahybrid neural network HMM classifier. / Paul, Anindya S.; Wan, Eric A.; Adenwala, Fatema; Schafermeyer, Erich; Preiser, Nick; Kaye, Jeffrey; Jacobs, Peter.

UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, 2014. p. 159-170.

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

Paul, AS, Wan, EA, Adenwala, F, Schafermeyer, E, Preiser, N, Kaye, J & Jacobs, P 2014, MobileRF: A robust device-free tracking system based on ahybrid neural network HMM classifier. in UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, pp. 159-170, 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014, Seattle, United States, 9/13/14. https://doi.org/10.1145/2632048.2632097
Paul AS, Wan EA, Adenwala F, Schafermeyer E, Preiser N, Kaye J et al. MobileRF: A robust device-free tracking system based on ahybrid neural network HMM classifier. In UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc. 2014. p. 159-170 https://doi.org/10.1145/2632048.2632097
Paul, Anindya S. ; Wan, Eric A. ; Adenwala, Fatema ; Schafermeyer, Erich ; Preiser, Nick ; Kaye, Jeffrey ; Jacobs, Peter. / MobileRF : A robust device-free tracking system based on ahybrid neural network HMM classifier. UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, 2014. pp. 159-170
@inproceedings{36d49294ff494e49955deface9d05b36,
title = "MobileRF: A robust device-free tracking system based on ahybrid neural network HMM classifier",
abstract = "We present a device-free indoor tracking system that uses received signal strength (RSS) from radio frequency (RF) transceivers to estimate the location of a person. While many RSS-based tracking systems use a body-worn device or tag, this approach requires no such tag. The approach is based on the key principle that RF signals between wall-mounted transceivers reflect and absorb differently depending on a person's movement within their home. A hierarchical neural network hidden Markov model (NN-HMM) classifier estimates both movement patterns and stand vs. walk conditions to perform tracking accurately. The algorithm and features used are specifically robust to changes in RSS mean shifts in the environment over time allowing for greater than 90{\%} region level classification accuracy over an extended testing period. In addition to tracking, the system also estimates the number of people in different regions. It is currently being developed to support independent living and long-term monitoring of seniors.",
keywords = "Device-free passive localization, Health care, Indoor localization, Indoor tracking, Machine learning, Mobility, Neural network, Tag-free tracking",
author = "Paul, {Anindya S.} and Wan, {Eric A.} and Fatema Adenwala and Erich Schafermeyer and Nick Preiser and Jeffrey Kaye and Peter Jacobs",
year = "2014",
doi = "10.1145/2632048.2632097",
language = "English (US)",
isbn = "9781450329682",
pages = "159--170",
booktitle = "UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - MobileRF

T2 - A robust device-free tracking system based on ahybrid neural network HMM classifier

AU - Paul, Anindya S.

AU - Wan, Eric A.

AU - Adenwala, Fatema

AU - Schafermeyer, Erich

AU - Preiser, Nick

AU - Kaye, Jeffrey

AU - Jacobs, Peter

PY - 2014

Y1 - 2014

N2 - We present a device-free indoor tracking system that uses received signal strength (RSS) from radio frequency (RF) transceivers to estimate the location of a person. While many RSS-based tracking systems use a body-worn device or tag, this approach requires no such tag. The approach is based on the key principle that RF signals between wall-mounted transceivers reflect and absorb differently depending on a person's movement within their home. A hierarchical neural network hidden Markov model (NN-HMM) classifier estimates both movement patterns and stand vs. walk conditions to perform tracking accurately. The algorithm and features used are specifically robust to changes in RSS mean shifts in the environment over time allowing for greater than 90% region level classification accuracy over an extended testing period. In addition to tracking, the system also estimates the number of people in different regions. It is currently being developed to support independent living and long-term monitoring of seniors.

AB - We present a device-free indoor tracking system that uses received signal strength (RSS) from radio frequency (RF) transceivers to estimate the location of a person. While many RSS-based tracking systems use a body-worn device or tag, this approach requires no such tag. The approach is based on the key principle that RF signals between wall-mounted transceivers reflect and absorb differently depending on a person's movement within their home. A hierarchical neural network hidden Markov model (NN-HMM) classifier estimates both movement patterns and stand vs. walk conditions to perform tracking accurately. The algorithm and features used are specifically robust to changes in RSS mean shifts in the environment over time allowing for greater than 90% region level classification accuracy over an extended testing period. In addition to tracking, the system also estimates the number of people in different regions. It is currently being developed to support independent living and long-term monitoring of seniors.

KW - Device-free passive localization

KW - Health care

KW - Indoor localization

KW - Indoor tracking

KW - Machine learning

KW - Mobility

KW - Neural network

KW - Tag-free tracking

UR - http://www.scopus.com/inward/record.url?scp=84908607399&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908607399&partnerID=8YFLogxK

U2 - 10.1145/2632048.2632097

DO - 10.1145/2632048.2632097

M3 - Conference contribution

AN - SCOPUS:84908607399

SN - 9781450329682

SP - 159

EP - 170

BT - UbiComp 2014 - Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing

PB - Association for Computing Machinery, Inc

ER -