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
N1 - Publisher Copyright:
© 2018 ACM.
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
AN - SCOPUS:85058173279
T3 - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
BT - 2018 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018 - Digest of Technical Papers
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 37th IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2018
Y2 - 5 November 2018 through 8 November 2018
ER -