WiFi-based Multi-task Sensing

TL;DR

This paper introduces Wimuse, a WiFi-based multi-task sensing model that simultaneously performs gesture recognition, indoor localization, and user identification, addressing challenges of task imbalance and discrepancy with knowledge distillation and residual adaptors.

Contribution

The paper proposes Wimuse, the first multi-task WiFi sensing model that effectively handles multiple sensing tasks with different difficulties and specific information requirements.

Findings

Achieves state-of-the-art accuracy on three public datasets.

Effectively addresses task imbalance and discrepancy issues.

Demonstrates high accuracy in all three sensing tasks.

Abstract

WiFi-based sensing has aroused immense attention over recent years. The rationale is that the signal fluctuations caused by humans carry the information of human behavior which can be extracted from the channel state information of WiFi. Still, the prior studies mainly focus on single-task sensing (STS), e.g., gesture recognition, indoor localization, user identification. Since the fluctuations caused by gestures are highly coupling with body features and the user's location, we propose a WiFi-based multi-task sensing model (Wimuse) to perform gesture recognition, indoor localization, and user identification tasks simultaneously. However, these tasks have different difficulty levels (i.e., imbalance issue) and need task-specific information (i.e., discrepancy issue). To address these issues, the knowledge distillation technique and task-specific residual adaptor are adopted in Wimuse. We first train the STS model for each task. Then, for solving the imbalance issue, the extracted common feature in Wimuse is encouraged to get close to the counterpart features of the STS models. Further, for each task, a task-specific residual adaptor is applied to extract the task-specific compensation feature which is fused with the common feature to address the discrepancy issue. We conduct comprehensive experiments on three public datasets and evaluation suggests that Wimuse achieves state-of-the-art performance with the average accuracy of 85.20%, 98.39%, and 98.725% on the joint task of gesture recognition, indoor localization, and user identification, respectively.