FewSense, Towards a Scalable and Cross-Domain Wi-Fi Sensing System Using Few-Shot Learning

Yin, Guolin, Zhang, Junqing ORCID: 0000-0002-3502-2926, Shen, Guanxiong ORCID: 0000-0002-0331-4211 and Chen, Yingying ORCID: 0000-0002-3994-766X (2024) FewSense, Towards a Scalable and Cross-Domain Wi-Fi Sensing System Using Few-Shot Learning. IEEE Transactions on Mobile Computing, 23 (1). pp. 453-468.

Text
manuscript_TMC_2022_FewSense.pdf - Author Accepted Manuscript
Download (996kB) | Preview

Official URL: http://dx.doi.org/10.1109/tmc.2022.3221902

Abstract

Wi-Fi sensing can classify human activities because each activity causes unique changes to the channel state information (CSI). Existing WiFi sensing suffers from limited scalability as the system needs to be retrained whenever new classes are added, which causes overheads of data collection and retraining. Cross-domain sensing may fail because the mapping between activities and CSI variations is destroyed when a different environment or user (domain) is involved. This paper proposed a few-shot learning-based WiFi sensing system, named FewSense, which can recognise novel classes in unseen domains with only a few samples. Specifically, a feature extractor was pre-trained offline using the source domain data. When the system was applied in the target domain, a few samples were used to fine-tune the feature extractor for domain adaptation. Inference was made by computing the cosine similarity. FewSense can further boost the classification accuracy by collaboratively fusing inference from multiple receivers. We evaluated the performance of FewSense using three public datasets, i.e., SignFi, Widar, and Wiar. The results show that FewSense with five-shot learning recognised novel classes in unseen domains with an accuracy of 93.9%, 96.5%, and 82.7% on the SignFi, Widar, and Wiar datasets, respectively. Our collaborative sensing model improved system performance by an average of 29.2%.

Item Type:	Article
Depositing User:	Symplectic Admin
Date Deposited:	08 Nov 2022 15:23
Last Modified:	15 Mar 2024 14:44
DOI:	10.1109/tmc.2022.3221902
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3166054