Online human activity recognition using low-power wearable devices

Ganapati Bhat, Ranadeep Deb, Vatika Vardhan Chaurasia, Holly Shill, Umit Ogras

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

1 Citation (Scopus)

Abstract

Human activity recognition (HAR) has attracted significant research interest due to its applications in health monitoring and patient rehabilitation. Recent research on HAR focuses on using smartphones due to their widespread use. However, this leads to inconvenient use, limited choice of sensors and inefficient use of resources, since smartphones are not designed for HAR. This paper presents the first HAR framework that can perform both online training and inference. The proposed framework starts with a novel technique that generates features using the fast Fourier and discrete wavelet transforms of a textile-based stretch sensor and accelerometer data. Using these features, we design a neural network classifier which is trained online using the policy gradient algorithm. Experiments on a low power IoT device (TI-CC2650 MCU) with nine users show 97.7% accuracy in identifying six activities and their transitions with less than 12.5 mW power consumption.

Original languageEnglish (US)
Title of host publication2018 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018 - Digest of Technical Papers
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781450359504
DOIs
StatePublished - Nov 5 2018
Event37th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018 - San Diego, United States
Duration: Nov 5 2018Nov 8 2018

Other

Other37th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018
CountryUnited States
CitySan Diego
Period11/5/1811/8/18

Fingerprint

Smartphones
Discrete wavelet transforms
Sensors
Accelerometers
Patient rehabilitation
Textiles
Electric power utilization
Classifiers
Health
Neural networks
Monitoring
Experiments
Internet of things

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Cite this

Bhat, G., Deb, R., Chaurasia, V. V., Shill, H., & Ogras, U. (2018). Online human activity recognition using low-power wearable devices. In 2018 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018 - Digest of Technical Papers [a72] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1145/3240765.3240833

Online human activity recognition using low-power wearable devices. / Bhat, Ganapati; Deb, Ranadeep; Chaurasia, Vatika Vardhan; Shill, Holly; Ogras, Umit.

2018 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018 - Digest of Technical Papers. Institute of Electrical and Electronics Engineers Inc., 2018. a72.

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

Bhat, G, Deb, R, Chaurasia, VV, Shill, H & Ogras, U 2018, Online human activity recognition using low-power wearable devices. in 2018 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018 - Digest of Technical Papers., a72, Institute of Electrical and Electronics Engineers Inc., 37th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018, San Diego, United States, 11/5/18. https://doi.org/10.1145/3240765.3240833
Bhat G, Deb R, Chaurasia VV, Shill H, Ogras U. Online human activity recognition using low-power wearable devices. In 2018 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018 - Digest of Technical Papers. Institute of Electrical and Electronics Engineers Inc. 2018. a72 https://doi.org/10.1145/3240765.3240833
Bhat, Ganapati ; Deb, Ranadeep ; Chaurasia, Vatika Vardhan ; Shill, Holly ; Ogras, Umit. / Online human activity recognition using low-power wearable devices. 2018 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018 - Digest of Technical Papers. Institute of Electrical and Electronics Engineers Inc., 2018.
@inproceedings{e9fb85b9e22e4c7f9b0edfdf697b5396,
title = "Online human activity recognition using low-power wearable devices",
abstract = "Human activity recognition (HAR) has attracted significant research interest due to its applications in health monitoring and patient rehabilitation. Recent research on HAR focuses on using smartphones due to their widespread use. However, this leads to inconvenient use, limited choice of sensors and inefficient use of resources, since smartphones are not designed for HAR. This paper presents the first HAR framework that can perform both online training and inference. The proposed framework starts with a novel technique that generates features using the fast Fourier and discrete wavelet transforms of a textile-based stretch sensor and accelerometer data. Using these features, we design a neural network classifier which is trained online using the policy gradient algorithm. Experiments on a low power IoT device (TI-CC2650 MCU) with nine users show 97.7{\%} accuracy in identifying six activities and their transitions with less than 12.5 mW power consumption.",
author = "Ganapati Bhat and Ranadeep Deb and Chaurasia, {Vatika Vardhan} and Holly Shill and Umit Ogras",
year = "2018",
month = "11",
day = "5",
doi = "10.1145/3240765.3240833",
language = "English (US)",
booktitle = "2018 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018 - Digest of Technical Papers",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Online human activity recognition using low-power wearable devices

AU - Bhat, Ganapati

AU - Deb, Ranadeep

AU - Chaurasia, Vatika Vardhan

AU - Shill, Holly

AU - Ogras, Umit

PY - 2018/11/5

Y1 - 2018/11/5

N2 - Human activity recognition (HAR) has attracted significant research interest due to its applications in health monitoring and patient rehabilitation. Recent research on HAR focuses on using smartphones due to their widespread use. However, this leads to inconvenient use, limited choice of sensors and inefficient use of resources, since smartphones are not designed for HAR. This paper presents the first HAR framework that can perform both online training and inference. The proposed framework starts with a novel technique that generates features using the fast Fourier and discrete wavelet transforms of a textile-based stretch sensor and accelerometer data. Using these features, we design a neural network classifier which is trained online using the policy gradient algorithm. Experiments on a low power IoT device (TI-CC2650 MCU) with nine users show 97.7% accuracy in identifying six activities and their transitions with less than 12.5 mW power consumption.

AB - Human activity recognition (HAR) has attracted significant research interest due to its applications in health monitoring and patient rehabilitation. Recent research on HAR focuses on using smartphones due to their widespread use. However, this leads to inconvenient use, limited choice of sensors and inefficient use of resources, since smartphones are not designed for HAR. This paper presents the first HAR framework that can perform both online training and inference. The proposed framework starts with a novel technique that generates features using the fast Fourier and discrete wavelet transforms of a textile-based stretch sensor and accelerometer data. Using these features, we design a neural network classifier which is trained online using the policy gradient algorithm. Experiments on a low power IoT device (TI-CC2650 MCU) with nine users show 97.7% accuracy in identifying six activities and their transitions with less than 12.5 mW power consumption.

UR - http://www.scopus.com/inward/record.url?scp=85058173279&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058173279&partnerID=8YFLogxK

U2 - 10.1145/3240765.3240833

DO - 10.1145/3240765.3240833

M3 - Conference contribution

BT - 2018 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018 - Digest of Technical Papers

PB - Institute of Electrical and Electronics Engineers Inc.

ER -