Nguyen, N. and Pham, M. and Le, V. and Duongquoc, D. and Doan, V.-S. (2022) Micro-Doppler signatures based human activity classification using Dense-Inception Neural Network. In: Conference of 15th International Conference on Advanced Technologies for Communications, ATC 2022, 20 October 2022 Through 22 October 2022, Hanoi.
Full text not available from this repository. (Upload)Abstract
Falls are the leading cause of injury and death in people over 65. Timely detection and warning of the fall risks of humans, especially the elderly, while performing daily living activities are vitally necessary. Therefore, this paper proposes a Dense-Inception Neural Network (DINN) to classify falls among 11 human activities based on micro-Doppler signatures. The network's hyper-parameters are analyzed and fine-tuned through experiments with the simulated dataset from Simhumalator software to choose the most optimal network model. As a result, the proposed model with 24 filters achieves a good balance between prediction time and classification accuracy performance. Moreover, the proposed model's results remarkably outperform when compared with four other networks with the same input dataset due to the dense-inception structure. © 2022 IEEE.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Divisions: | Faculties > Faculty of Radio-Electronic Engineering Faculties > Faculty of Special Equipments |
Identification Number: | 10.1109/ATC55345.2022.9943046 |
Uncontrolled Keywords: | Activity classifications; Daily living activities; Densenet; Doppler signatures; Fall detection; Fall risk; Human activities; Micro-dopple signature; Micro-Doppler; Neural-networks, Fall detection |
Additional Information: | Conference of 15th International Conference on Advanced Technologies for Communications, ATC 2022 ; Conference Date: 20 October 2022 Through 22 October 2022; Conference Code:184412 |
URI: | http://eprints.lqdtu.edu.vn/id/eprint/10626 |