Uncertainty Aware and Scalable WiFi CSI Sensing with Large Language Models
Article
Sun, Y, Wang, X, Cao, G et al. (2026). Uncertainty Aware and Scalable WiFi CSI Sensing with Large Language Models
. IEEE Internet of Things Journal, 10.1109/JIOT.2026.3709145
Sun, Y, Wang, X, Cao, G et al. (2026). Uncertainty Aware and Scalable WiFi CSI Sensing with Large Language Models
. IEEE Internet of Things Journal, 10.1109/JIOT.2026.3709145
In this paper, we propose a robust, scalable, and interpretable WiFi Channel State Information (CSI) based sensing system that integrates functional data analysis (FDA) and large language models (LLMs) to achieve high performance on human activity and identity recognition tasks. Specifically, FDA is applied to reconstruct and extract structured features from CSI sequences, which are then processed by a lightweight LLM backbone incorporated with an uncertainty aware mechanism. To further enhance confidence calibration and feature representation, we design a composite loss function that integrates generative classification, contrastive learning, and uncertainty aware objectives. We conduct extensive experiments on multiple public CSI based sensing datasets under in dataset scenarios. The results demonstrate that our method achieves significantly higher recognition accuracy than state of the art deep learning baselines, and it is capable of producing meaningful uncertainty estimates and confidence calibration. Our system also exhibits fast convergence, good scalability with respect to backbone size, and flexibility to different subsampling strategies. Ablation studies confirm that the proposed loss functions and uncertainty awareness contribute substantially to the overall performance and robustness of the proposed system.
