Solving the WiFi Sensing Dilemma in Reality Leveraging Conformal Prediction
IEEE Transactions on Mobile Computing · 2026-09 · 25 (9) · 13912-13928
DOI: 10.1109/tmc.2026.3676932 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-09. Verfasst von Honglu Li und 7 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Gefördert von: National Science Foundation, National Institutes of Health.
Abstract (Originalsprache)
With the extensive deployment of smart environments and IoT devices, WiFi sensing has proven its significant convenience and contact-free sensing capabilities in supporting a wide range of applications. However, designing a ubiquitous WiFi sensing system for diverse real-world scenarios presents a substantial dilemma, as the system performance deteriorates when the testing data diverges significantly from the training data due to domain variations. To address this dilemma, existing studies need extra efforts to develop new features or even retrain the original model under environmental variations. However, these approaches have not efficiently resolved the dilemma. In this study, we conduct a comprehensive study on the domain variation problem to make WiFi sensing robust and accurate in practical applications. Our definition of domains is comprehensive and includes environmental conditions, surrounding settings, user differences, user orientations, user’s positions relative to WiFi sensors, and user participation time frames. We design a novel conformal prediction framework that quantifies the conformity (i.e., similarity) between the testing and training WiFi samples, then labels the testing samples with the most probable class(es). Unlike traditional conformal prediction which relies on data from a single domain, we develop a new statistical (Type I) approach to assess the conformity of the testing WiFi samples to individual training domains and aggregate the outcomes. To further improve the framework’s generalization, we design a (Type II) fusion approach that utilizes the inter-relationships among domains for more accurate conformity quantification. Built upon these two methods, kernel density estimation-based and SVM-based methods are developed to compute the conformity scores for new testing samples to make conformal predictions. Extensive experiments, utilizing both self-collected and publicly available datasets show that our framework can improve prediction accuracies ranging from 20.1% to 77.1% in three of the most representative WiFi-based applications across six types of domain variations.
Förderung
- National Science Foundation
- National Institutes of Health
Zitieren
APA
Li, H., Ji, Q., Shi, C., Wang, Y., Cheng, J. Q., Wang, K., Xie, M., & Chen, Y. (2026). Solving the WiFi Sensing Dilemma in Reality Leveraging Conformal Prediction. IEEE Transactions on Mobile Computing, 25(9), 13912-13928. https://doi.org/10.1109/tmc.2026.3676932
Vancouver
Li H, Ji Q, Shi C, Wang Y, Cheng JQ, Wang K, et al. Solving the WiFi Sensing Dilemma in Reality Leveraging Conformal Prediction. IEEE Transactions on Mobile Computing. 2026;25(9):13912-13928. doi:10.1109/tmc.2026.3676932
BibTeX
@article{Li2026,
author = {Li, Honglu and Ji, Qiufan and Shi, Cong and Wang, Yan and Cheng, Jerry Q. and Wang, Kailong and Xie, Minge and Chen, Yingying},
title = {Solving the WiFi Sensing Dilemma in Reality Leveraging Conformal Prediction},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {9},
pages = {13912--13928},
doi = {10.1109/tmc.2026.3676932}
}
EUVIMED