Human Activity Recognition from Wearable Sensor Data Using Self-Attention
Year: 2020
Type: book-chapter
Abstract: Human Activity Recognition from body-worn sensor data poses an inherent challenge in capturing spatial and temporal dependencies of time-series signals. In this regard, the existing recurrent or convolutional or their hybrid models for activity recognition struggle to capture spatio-temporal context from the feature space of sensor reading sequence. To address this complex problem, we propose a self-attention based neural network model that foregoes recurrent architectures and utilizes different types of attention mechanisms to generate higher dimensional feature representation used for classification. We performed extensive experiments on four popular publicly available HAR datasets: PAMAP2, Opportunity, Skoda and USC-HAD. Our model achieve significant performance improvement over recent state-of-the-art models in both benchmark test subjects and Leave-one-subject-out evaluation. We also observe that the sensor attention maps produced by our model is able capture the importance of the modality and placement of the sensors in predicting the different activity classes.
DOI: 10.3233/faia200236
Authors: Mahmud Saif, Tanjid Hasan Tonmoy M., Kumar Bhaumik Kishor, Mahbubur Rahman A.K.M., Ashraful Amin M., Shoyaib Mohammad, Asif Hossain Khan Muhammad, Ahsan Ali Amin
Institutions: University of Dhaka, Independent University, Bangladesh
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W3091367282
