Neuro-Symbolic Fusion of Wi-Fi Sensing Data for Passive Radar with Inter-Modal Knowledge Transfer

TL;DR

This paper presents DeepProbHAR, a neuro-symbolic Wi-Fi sensing architecture that enhances human activity recognition by integrating domain knowledge and multi-antenna signals, achieving state-of-the-art results without extensive labelling.

Contribution

Introduction of DeepProbHAR, a neuro-symbolic framework that combines domain knowledge and multi-antenna Wi-Fi signals for improved passive human activity recognition.

Findings

DeepProbHAR achieves comparable accuracy to state-of-the-art methods.

It can differentiate simple movements like leg or arm motions.

The model generates classifiers matching labelling-intensive models.

Abstract

Wi-Fi devices, akin to passive radars, can discern human activities within indoor settings due to the human body's interaction with electromagnetic signals. Current Wi-Fi sensing applications predominantly employ data-driven learning techniques to associate the fluctuations in the physical properties of the communication channel with the human activity causing them. However, these techniques often lack the desired flexibility and transparency. This paper introduces DeepProbHAR, a neuro-symbolic architecture for Wi-Fi sensing, providing initial evidence that Wi-Fi signals can differentiate between simple movements, such as leg or arm movements, which are integral to human activities like running or walking. The neuro-symbolic approach affords gathering such evidence without needing additional specialised data collection or labelling. The training of DeepProbHAR is facilitated by declarative domain knowledge obtained from a camera feed and by fusing signals from various antennas of the Wi-Fi receivers. DeepProbHAR achieves results comparable to the state-of-the-art in human activity recognition. Moreover, as a by-product of the learning process, DeepProbHAR generates specialised classifiers for simple movements that match the accuracy of models trained on finely labelled datasets, which would be particularly costly.