An Unsupervised Domain Adaptation-Based Device-Free Sensing Approach for Cross-Weather Target Recognition in Foliage Environments

Zhong, Yi; Bi, Tianqi; Wang, Ju; You, Minglei; Jiang, Ting

Abstract

In recent years, the emerging technique of device-free sensing (DFS) has gained popularity for foliage penetration (FOPEN) target recognition. This popularity is primarily attributed to its inherent advantage of not requiring specialized sensing equipment beyond wireless transceivers. Concerning weather variations, DFS heavily relies on labeled data for model training, which necessitates the annotation of samples for each weather environment. However, this annotation process proves impractical for real-world applications, especially under adverse weather conditions. To address this issue, this paper presents an unsupervised domain adaptation (UDA)-based cross-weather FOPEN target recognition system (CW-FTRS). Experimental results validate that the proposed method achieves an average accuracy of over 72% in unseen weather conditions using only unlabeled data samples.

Citation

Zhong, Y., Bi, T., Wang, J., You, M., & Jiang, T. (2023, May). An Unsupervised Domain Adaptation-Based Device-Free Sensing Approach for Cross-Weather Target Recognition in Foliage Environments. Presented at 12th International Conference on Communications, Signal Processing, and Systems, Singapore (and online)

• Presentation Conference Type: Edited Proceedings
• Conference Name: 12th International Conference on Communications, Signal Processing, and Systems
• Start Date: May 5, 2023
• End Date: May 7, 2023
• Acceptance Date: May 1, 2023
• Online Publication Date: Apr 18, 2024
• Publication Date: Apr 18, 2024
• Deposit Date: Jun 24, 2024
• Publisher: Springer
• Volume: 1033
• Pages: 167-175
• Series Title: Lecture Notes in Electrical Engineering
• Series ISSN: 1876-1119
• Book Title: Communications, Signal Processing, and Systems Proceedings of the 12th International Conference on Communications, Signal Processing, and Systems: Volume 2
• ISBN: 978-981-99-7555-6
• DOI: https://doi.org/10.1007/978-981-99-7502-0_18
• Public URL: https://nottingham-repository.worktribe.com/output/36294320
• Publisher URL: https://link.springer.com/chapter/10.1007/978-981-99-7502-0_18