Next Article in Journal
An Intuitive Formulation of the Human Arm Active Endpoint Stiffness
Next Article in Special Issue
Development of Instrumented Running Prosthetic Feet for the Collection of Track Loads on Elite Athletes
Previous Article in Journal
Fault-Tolerant Network-On-Chip Router Architecture Design for Heterogeneous Computing Systems in the Context of Internet of Things
Previous Article in Special Issue
Does Curved Walking Sharpen the Assessment of Gait Disorders? An Instrumented Approach Based on Wearable Inertial Sensors
Article

w-HAR: An Activity Recognition Dataset and Framework Using Low-Power Wearable Devices

by 1,*,†,‡, 2, 3,† and 4,†,‡
1
School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA 99164, USA
2
School of Electrical, Computer, and Energy Engineering, Arizona State University, Tempe, AZ 85281, USA
3
Lonnie and Muhammad Ali Movement Disorder Center, Phoenix, AZ 85013, USA
4
Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA
*
Author to whom correspondence should be addressed.
This paper is an extended version of our paper published in: Bhat, G.; Deb, R.; Chaurasia, V.V.; Shill, H.; Ogras, U.Y. Online human activity recognition using low-power wearable devices. In Proceedings of the International Conference on Computer-Aided Design (ICCAD ’18), San Diego, CA, USA, 5–8 November 2018.
Ganapati Bhat and Umit Y. Ogras were affiliated with Arizona State University when this work was performed.
Sensors 2020, 20(18), 5356; https://doi.org/10.3390/s20185356
Received: 15 July 2020 / Revised: 30 August 2020 / Accepted: 11 September 2020 / Published: 18 September 2020
Human activity recognition (HAR) is growing in popularity due to its wide-ranging applications in patient rehabilitation and movement disorders. HAR approaches typically start with collecting sensor data for the activities under consideration and then develop algorithms using the dataset. As such, the success of algorithms for HAR depends on the availability and quality of datasets. Most of the existing work on HAR uses data from inertial sensors on wearable devices or smartphones to design HAR algorithms. However, inertial sensors exhibit high noise that makes it difficult to segment the data and classify the activities. Furthermore, existing approaches typically do not make their data available publicly, which makes it difficult or impossible to obtain comparisons of HAR approaches. To address these issues, we present wearable HAR (w-HAR) which contains labeled data of seven activities from 22 users. Our dataset’s unique aspect is the integration of data from inertial and wearable stretch sensors, thus providing two modalities of activity information. The wearable stretch sensor data allows us to create variable-length segment data and ensure that each segment contains a single activity. We also provide a HAR framework to use w-HAR to classify the activities. To this end, we first perform a design space exploration to choose a neural network architecture for activity classification. Then, we use two online learning algorithms to adapt the classifier to users whose data are not included at design time. Experiments on the w-HAR dataset show that our framework achieves 95% accuracy while the online learning algorithms improve the accuracy by as much as 40%. View Full-Text
Keywords: human activity recognition; online learning; wearable devices human activity recognition; online learning; wearable devices
Show Figures

Figure 1

MDPI and ACS Style

Bhat, G.; Tran, N.; Shill, H.; Ogras, U.Y. w-HAR: An Activity Recognition Dataset and Framework Using Low-Power Wearable Devices. Sensors 2020, 20, 5356. https://doi.org/10.3390/s20185356

AMA Style

Bhat G, Tran N, Shill H, Ogras UY. w-HAR: An Activity Recognition Dataset and Framework Using Low-Power Wearable Devices. Sensors. 2020; 20(18):5356. https://doi.org/10.3390/s20185356

Chicago/Turabian Style

Bhat, Ganapati, Nicholas Tran, Holly Shill, and Umit Y. Ogras. 2020. "w-HAR: An Activity Recognition Dataset and Framework Using Low-Power Wearable Devices" Sensors 20, no. 18: 5356. https://doi.org/10.3390/s20185356

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop