Group-In: Group Inference from Wireless Traces of Mobile Devices

TL;DR

Group-In is a wireless system that detects static and moving groups of people using noisy Bluetooth signals without localization, leveraging graph clustering for short-term and long-term group inference in indoor and outdoor environments.

Contribution

This work introduces novel centralized and decentralized schemes for group detection from wireless RSSI data without localization, capable of identifying both static and moving groups over different time scales.

Findings

High accuracy in short-term group detection.

Effective long-term group linkage over a month.

Robust performance in real-world office environments.

Abstract

This paper proposes Group-In, a wireless scanning system to detect static or mobile people groups in indoor or outdoor environments. Group-In collects only wireless traces from the Bluetooth-enabled mobile devices for group inference. The key problem addressed in this work is to detect not only static groups but also moving groups with a multi-phased approach based only noisy wireless Received Signal Strength Indicator (RSSIs) observed by multiple wireless scanners without localization support. We propose new centralized and decentralized schemes to process the sparse and noisy wireless data, and leverage graph-based clustering techniques for group detection from short-term and long-term aspects. Group-In provides two outcomes: 1) group detection in short time intervals such as two minutes and 2) long-term linkages such as a month. To verify the performance, we conduct two experimental studies. One consists of 27 controlled scenarios in the lab environments. The other is a real-world scenario where we place Bluetooth scanners in an office environment, and employees carry beacons for more than one month. Both the controlled and real-world experiments result in high accuracy group detection in short time intervals and sampling liberties in terms of the Jaccard index and pairwise similarity coefficient.