GSM-CommSense-based through-the-wall sensing

TL;DR

This paper demonstrates that GSM-based communication sensing can detect environmental changes behind walls with high accuracy using machine learning, offering a novel approach for through-the-wall sensing applications.

Contribution

The paper introduces a GSM-CommSense system for through-the-wall sensing and applies statistical machine learning to achieve accurate detection of persons and objects behind walls.

Findings

Person detection accuracy: 77.458%

Weapon detection accuracy: 95.208%

Effective with limited data per GSM frame

Abstract

We have recently proposed a scheme to use the channel equalization blocks of telecommunication systems to sense changes in an environment. We call this communication-sensing, CommSense for short. After some initial positive results we tried to use our global system for mobile communication (GSM) based CommSense system for a through-the-wall sensing application. As the system was inherently highly under-determined we used statistical machine learning techniques to help us sense environmental changes in the behind-the-wall experiments. We observed that with limited amount of data per GSM frame of 577 {\mu}s a person can be detected across a wall to an accuracy of 77.458% and a person carrying a weapon can be detected to an accuracy of 95.208%. We present details of the experiments and the encouraging results that we have obtained in this article.