Physical activity discrimination improvement using accelerometers and wireless sensor network localization

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

Abstract

Automating documentation of physical activity data (e.g., duration and speed of walking or propelling a wheelchair) into the electronic medical record (EMR) offers promise for improving efficiency of documentation and understanding of best practices in the rehabilitation and home health settings. Commercially available devices which could be used to automate documentation of physical activities are either cumbersome to wear or lack the specificity required to differentiate activities. We have designed a novel system to differentiate and quantify physical activities, using inexpensive accelerometer-based biomechanical data technology and wireless sensor networks, a technology combination that has not been used in a rehabilitation setting to date. As a first step, a feasibility study was performed where 14 healthy young adults (mean age = 22.6 ± 2.5 years, mean height = 173 ± 10.0 cm, mean mass = 70.7 ± 11.3 kg) carried out eight different activities while wearing a biaxial accelerometer sensor. Activities were performed at each participant's self-selected pace during a single testing session in a controlled environment. Linear discriminant analysis was performed by extracting spectral parameters from the subjects' accelerometer patterns. It is shown that physical activity classification alone results in an average accuracy of 49.5%, but when combined with rule-based constraints using a wireless sensor network with localization capabilities in an in silico simulated room, accuracy improves to 99.3%. When fully implemented, our technology package is expected to improve goal setting, treatment interventions and patient outcomes by enhancing clinicians' understanding of patients' physical performance within a day and across the rehabilitation program.

Original languageEnglish (US)
Title of host publication50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013
Pages244-251
Number of pages8
StatePublished - Sep 9 2013
Event50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013 - Colorado Springs, CO, United States
Duration: Apr 5 2013Apr 7 2013

Publication series

Name50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013
Volume493

Conference

Conference50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013
CountryUnited States
CityColorado Springs, CO
Period4/5/134/7/13

Fingerprint

Accelerometers
Patient rehabilitation
Wireless sensor networks
Electronic medical equipment
Wheelchairs
Discriminant analysis
Wear of materials
Health
Sensors
Testing

Keywords

  • Physical activity classification
  • Rehabilitation
  • Spectral analysis
  • Wireless sensor networks

ASJC Scopus subject areas

  • Bioengineering
  • Biomedical Engineering

Cite this

Bashford, G. R., Burnfield, J., & Perez, L. C. (2013). Physical activity discrimination improvement using accelerometers and wireless sensor network localization. In 50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013 (pp. 244-251). (50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013; Vol. 493).

Physical activity discrimination improvement using accelerometers and wireless sensor network localization. / Bashford, Gregory R; Burnfield, Judith; Perez, Lance C.

50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013. 2013. p. 244-251 (50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013; Vol. 493).

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

Bashford, GR, Burnfield, J & Perez, LC 2013, Physical activity discrimination improvement using accelerometers and wireless sensor network localization. in 50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013. 50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013, vol. 493, pp. 244-251, 50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013, Colorado Springs, CO, United States, 4/5/13.
Bashford GR, Burnfield J, Perez LC. Physical activity discrimination improvement using accelerometers and wireless sensor network localization. In 50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013. 2013. p. 244-251. (50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013).
Bashford, Gregory R ; Burnfield, Judith ; Perez, Lance C. / Physical activity discrimination improvement using accelerometers and wireless sensor network localization. 50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013. 2013. pp. 244-251 (50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013).
@inproceedings{3ffba98c1f014609ac969bd7ca00ebe2,
title = "Physical activity discrimination improvement using accelerometers and wireless sensor network localization",
abstract = "Automating documentation of physical activity data (e.g., duration and speed of walking or propelling a wheelchair) into the electronic medical record (EMR) offers promise for improving efficiency of documentation and understanding of best practices in the rehabilitation and home health settings. Commercially available devices which could be used to automate documentation of physical activities are either cumbersome to wear or lack the specificity required to differentiate activities. We have designed a novel system to differentiate and quantify physical activities, using inexpensive accelerometer-based biomechanical data technology and wireless sensor networks, a technology combination that has not been used in a rehabilitation setting to date. As a first step, a feasibility study was performed where 14 healthy young adults (mean age = 22.6 ± 2.5 years, mean height = 173 ± 10.0 cm, mean mass = 70.7 ± 11.3 kg) carried out eight different activities while wearing a biaxial accelerometer sensor. Activities were performed at each participant's self-selected pace during a single testing session in a controlled environment. Linear discriminant analysis was performed by extracting spectral parameters from the subjects' accelerometer patterns. It is shown that physical activity classification alone results in an average accuracy of 49.5{\%}, but when combined with rule-based constraints using a wireless sensor network with localization capabilities in an in silico simulated room, accuracy improves to 99.3{\%}. When fully implemented, our technology package is expected to improve goal setting, treatment interventions and patient outcomes by enhancing clinicians' understanding of patients' physical performance within a day and across the rehabilitation program.",
keywords = "Physical activity classification, Rehabilitation, Spectral analysis, Wireless sensor networks",
author = "Bashford, {Gregory R} and Judith Burnfield and Perez, {Lance C}",
year = "2013",
month = "9",
day = "9",
language = "English (US)",
isbn = "9781627481663",
series = "50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013",
pages = "244--251",
booktitle = "50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013",

}

TY - GEN

T1 - Physical activity discrimination improvement using accelerometers and wireless sensor network localization

AU - Bashford, Gregory R

AU - Burnfield, Judith

AU - Perez, Lance C

PY - 2013/9/9

Y1 - 2013/9/9

N2 - Automating documentation of physical activity data (e.g., duration and speed of walking or propelling a wheelchair) into the electronic medical record (EMR) offers promise for improving efficiency of documentation and understanding of best practices in the rehabilitation and home health settings. Commercially available devices which could be used to automate documentation of physical activities are either cumbersome to wear or lack the specificity required to differentiate activities. We have designed a novel system to differentiate and quantify physical activities, using inexpensive accelerometer-based biomechanical data technology and wireless sensor networks, a technology combination that has not been used in a rehabilitation setting to date. As a first step, a feasibility study was performed where 14 healthy young adults (mean age = 22.6 ± 2.5 years, mean height = 173 ± 10.0 cm, mean mass = 70.7 ± 11.3 kg) carried out eight different activities while wearing a biaxial accelerometer sensor. Activities were performed at each participant's self-selected pace during a single testing session in a controlled environment. Linear discriminant analysis was performed by extracting spectral parameters from the subjects' accelerometer patterns. It is shown that physical activity classification alone results in an average accuracy of 49.5%, but when combined with rule-based constraints using a wireless sensor network with localization capabilities in an in silico simulated room, accuracy improves to 99.3%. When fully implemented, our technology package is expected to improve goal setting, treatment interventions and patient outcomes by enhancing clinicians' understanding of patients' physical performance within a day and across the rehabilitation program.

AB - Automating documentation of physical activity data (e.g., duration and speed of walking or propelling a wheelchair) into the electronic medical record (EMR) offers promise for improving efficiency of documentation and understanding of best practices in the rehabilitation and home health settings. Commercially available devices which could be used to automate documentation of physical activities are either cumbersome to wear or lack the specificity required to differentiate activities. We have designed a novel system to differentiate and quantify physical activities, using inexpensive accelerometer-based biomechanical data technology and wireless sensor networks, a technology combination that has not been used in a rehabilitation setting to date. As a first step, a feasibility study was performed where 14 healthy young adults (mean age = 22.6 ± 2.5 years, mean height = 173 ± 10.0 cm, mean mass = 70.7 ± 11.3 kg) carried out eight different activities while wearing a biaxial accelerometer sensor. Activities were performed at each participant's self-selected pace during a single testing session in a controlled environment. Linear discriminant analysis was performed by extracting spectral parameters from the subjects' accelerometer patterns. It is shown that physical activity classification alone results in an average accuracy of 49.5%, but when combined with rule-based constraints using a wireless sensor network with localization capabilities in an in silico simulated room, accuracy improves to 99.3%. When fully implemented, our technology package is expected to improve goal setting, treatment interventions and patient outcomes by enhancing clinicians' understanding of patients' physical performance within a day and across the rehabilitation program.

KW - Physical activity classification

KW - Rehabilitation

KW - Spectral analysis

KW - Wireless sensor networks

UR - http://www.scopus.com/inward/record.url?scp=84883409924&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883409924&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781627481663

T3 - 50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013

SP - 244

EP - 251

BT - 50th Annual Rocky Mountain Bioengineering Symposium and 50th International ISA Biomedical Sciences Instrumentation Symposium 2013

ER -