In-home behavioral monitoring using simultaneous localization and activity detection

Mateusz M. Mittek, Jay D. Carlson, Francisco Mora-Becerra, Eric T. Psota, Lance C Perez

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

Abstract

Shifting demographics in the U.S. has created an urgent need to reform the policies, practices, and technology associated with delivering healthcare to geriatric populations. Automated monitoring systems can improve the quality of life-while reducing healthcare costs-for individuals aging in place. For these systems to be successful, both activity detection and localization are important, but most existing research focuses on only one of these technologies-and systems that do collect both data treat these data sources separately. Here, we present SLAD-Simultaneous Localization and Activity Detection-a novel framework for simultaneously processing data collected from localization and activity classification systems. Using a hidden Markov model and machine learning techniques, SLAD fuses these two sources of data in real time using a probabilistic likelihood framework, which allows activity data to refine localization, and vice-versa. To evaluate the system, a wireless sensor network was deployed to collect RSSI data and IMU data concurrently from a wrist-worn watch; the RSSI data was processed using a radial basis function neural network localization algorithm, and the resulting position likelihoods were combined with the likelihoods from an IMU activity classification algorithm. In an experiment conducted in an indoor office environment, the proposed method produces 97% localization accuracy and 85% activity classification.

Original languageEnglish (US)
Title of host publication52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015
PublisherInternational Society of Automation (ISA)
Pages292-299
Number of pages8
ISBN (Electronic)9781510801981
StatePublished - 2015
Event52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015 - Salt Lake City, United States
Duration: Apr 10 2015Apr 12 2015

Other

Other52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015
CountryUnited States
CitySalt Lake City
Period4/10/154/12/15

Fingerprint

Information Storage and Retrieval
Monitoring
Geriatrics
Technology
Independent Living
Watches
Electric fuses
Hidden Markov models
Wrist
Health Care Costs
Learning systems
Wireless sensor networks
Aging of materials
geriatrics
Quality of Life
Demography
Neural networks
Delivery of Health Care
wrist
machine learning

Keywords

  • Activity classification
  • Behavioral monitoring
  • Indoor tracking
  • RSSI localization

ASJC Scopus subject areas

  • Instrumentation
  • Bioengineering
  • Biotechnology
  • Biomedical Engineering

Cite this

Mittek, M. M., Carlson, J. D., Mora-Becerra, F., Psota, E. T., & Perez, L. C. (2015). In-home behavioral monitoring using simultaneous localization and activity detection. In 52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015 (pp. 292-299). International Society of Automation (ISA).

In-home behavioral monitoring using simultaneous localization and activity detection. / Mittek, Mateusz M.; Carlson, Jay D.; Mora-Becerra, Francisco; Psota, Eric T.; Perez, Lance C.

52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015. International Society of Automation (ISA), 2015. p. 292-299.

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

Mittek, MM, Carlson, JD, Mora-Becerra, F, Psota, ET & Perez, LC 2015, In-home behavioral monitoring using simultaneous localization and activity detection. in 52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015. International Society of Automation (ISA), pp. 292-299, 52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015, Salt Lake City, United States, 4/10/15.
Mittek MM, Carlson JD, Mora-Becerra F, Psota ET, Perez LC. In-home behavioral monitoring using simultaneous localization and activity detection. In 52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015. International Society of Automation (ISA). 2015. p. 292-299
Mittek, Mateusz M. ; Carlson, Jay D. ; Mora-Becerra, Francisco ; Psota, Eric T. ; Perez, Lance C. / In-home behavioral monitoring using simultaneous localization and activity detection. 52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015. International Society of Automation (ISA), 2015. pp. 292-299
@inproceedings{114220134aa64d879865ce5b1f7b7e3e,
title = "In-home behavioral monitoring using simultaneous localization and activity detection",
abstract = "Shifting demographics in the U.S. has created an urgent need to reform the policies, practices, and technology associated with delivering healthcare to geriatric populations. Automated monitoring systems can improve the quality of life-while reducing healthcare costs-for individuals aging in place. For these systems to be successful, both activity detection and localization are important, but most existing research focuses on only one of these technologies-and systems that do collect both data treat these data sources separately. Here, we present SLAD-Simultaneous Localization and Activity Detection-a novel framework for simultaneously processing data collected from localization and activity classification systems. Using a hidden Markov model and machine learning techniques, SLAD fuses these two sources of data in real time using a probabilistic likelihood framework, which allows activity data to refine localization, and vice-versa. To evaluate the system, a wireless sensor network was deployed to collect RSSI data and IMU data concurrently from a wrist-worn watch; the RSSI data was processed using a radial basis function neural network localization algorithm, and the resulting position likelihoods were combined with the likelihoods from an IMU activity classification algorithm. In an experiment conducted in an indoor office environment, the proposed method produces 97{\%} localization accuracy and 85{\%} activity classification.",
keywords = "Activity classification, Behavioral monitoring, Indoor tracking, RSSI localization",
author = "Mittek, {Mateusz M.} and Carlson, {Jay D.} and Francisco Mora-Becerra and Psota, {Eric T.} and Perez, {Lance C}",
year = "2015",
language = "English (US)",
pages = "292--299",
booktitle = "52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015",
publisher = "International Society of Automation (ISA)",

}

TY - GEN

T1 - In-home behavioral monitoring using simultaneous localization and activity detection

AU - Mittek, Mateusz M.

AU - Carlson, Jay D.

AU - Mora-Becerra, Francisco

AU - Psota, Eric T.

AU - Perez, Lance C

PY - 2015

Y1 - 2015

N2 - Shifting demographics in the U.S. has created an urgent need to reform the policies, practices, and technology associated with delivering healthcare to geriatric populations. Automated monitoring systems can improve the quality of life-while reducing healthcare costs-for individuals aging in place. For these systems to be successful, both activity detection and localization are important, but most existing research focuses on only one of these technologies-and systems that do collect both data treat these data sources separately. Here, we present SLAD-Simultaneous Localization and Activity Detection-a novel framework for simultaneously processing data collected from localization and activity classification systems. Using a hidden Markov model and machine learning techniques, SLAD fuses these two sources of data in real time using a probabilistic likelihood framework, which allows activity data to refine localization, and vice-versa. To evaluate the system, a wireless sensor network was deployed to collect RSSI data and IMU data concurrently from a wrist-worn watch; the RSSI data was processed using a radial basis function neural network localization algorithm, and the resulting position likelihoods were combined with the likelihoods from an IMU activity classification algorithm. In an experiment conducted in an indoor office environment, the proposed method produces 97% localization accuracy and 85% activity classification.

AB - Shifting demographics in the U.S. has created an urgent need to reform the policies, practices, and technology associated with delivering healthcare to geriatric populations. Automated monitoring systems can improve the quality of life-while reducing healthcare costs-for individuals aging in place. For these systems to be successful, both activity detection and localization are important, but most existing research focuses on only one of these technologies-and systems that do collect both data treat these data sources separately. Here, we present SLAD-Simultaneous Localization and Activity Detection-a novel framework for simultaneously processing data collected from localization and activity classification systems. Using a hidden Markov model and machine learning techniques, SLAD fuses these two sources of data in real time using a probabilistic likelihood framework, which allows activity data to refine localization, and vice-versa. To evaluate the system, a wireless sensor network was deployed to collect RSSI data and IMU data concurrently from a wrist-worn watch; the RSSI data was processed using a radial basis function neural network localization algorithm, and the resulting position likelihoods were combined with the likelihoods from an IMU activity classification algorithm. In an experiment conducted in an indoor office environment, the proposed method produces 97% localization accuracy and 85% activity classification.

KW - Activity classification

KW - Behavioral monitoring

KW - Indoor tracking

KW - RSSI localization

UR - http://www.scopus.com/inward/record.url?scp=84943408656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943408656&partnerID=8YFLogxK

M3 - Conference contribution

SP - 292

EP - 299

BT - 52nd Annual Rocky Mountain Bioengineering Symposium and 52nd International ISA Biomedical Sciences Instrumentation Symposium 2015

PB - International Society of Automation (ISA)

ER -