Privacy-preserving classifiers recognize shared mobility behaviours from WiFi network imperfect data

TL;DR

This study demonstrates that it is possible to accurately identify specific human mobility patterns from WiFi connection logs while maintaining user privacy, using simple data aggregation and machine learning techniques.

Contribution

It introduces a privacy-preserving method for recognizing shared mobility behaviors from WiFi logs without device tracking or physical layer data.

Findings

Achieved 93.7% accuracy in detecting break periods between classes.

Achieved 83.3% accuracy in recognizing end-of-class movements.

Validated feasibility under noisy, incomplete data conditions.

Abstract

This paper proves the concept that it is feasible to accurately recognize specific human mobility shared patterns, based solely on the connection logs between portable devices and WiFi Access Points (APs), while preserving user's privacy. We gathered data from the Eduroam WiFi network of Polytechnique Montreal, making omission of device tracking or physical layer data. The behaviors we chose to detect were the movements associated to the end of an academic class, and the patterns related to the small break periods between classes. Stringent conditions were self-imposed in our experiments. The data is known to have errors noise, and be susceptible to information loss. No countermeasures were adopted to mitigate any of these issues. Data pre-processing consists of basic statistics that were used in aggregating the data in time intervals. We obtained accuracy values of 93.7 % and 83.3 % (via Bagged Trees) when recognizing behaviour patterns of breaks between classes and end-of-classes, respectively.