AirTOWN: A Privacy-Preserving Mobile App for Real-time Pollution-Aware POI Suggestion
Giuseppe Fasano, Yashar Deldjoo, Tommaso Di Noia
TL;DR
AirTOWN tackles health-conscious urban navigation by delivering real-time, pollution-aware POI recommendations while preserving user privacy. It integrates AQI data from city sensor networks with Matrix Factorization-based personalization, re-ranked by a weighted fusion $S = \alpha \cdot S_{MF} + (1 - \alpha) \cdot S_{AQI}$ with $α \in [0,1]$, enabling dynamic adaptation to current air quality. The system uses a four-layer client-server architecture, interpolates AQI in sensor-sparse areas via radial basis functions, and employs Federated Averaging to train a global model without exposing user data. Demonstrations in Bari with synthetic AQI data illustrate the method’s ability to balance health considerations and user preferences, highlighting its potential impact on health-aware urban mobility. The work advances privacy-preserving, real-time, pollution-aware recommendations, with plans to extend privacy protections (e.g., differential privacy) and scale evaluations.
Abstract
This demo paper presents \airtown, a privacy-preserving mobile application that provides real-time, pollution-aware recommendations for points of interest (POIs) in urban environments. By combining real-time Air Quality Index (AQI) data with user preferences, the proposed system aims to help users make health-conscious decisions about the locations they visit. The application utilizes collaborative filtering for personalized suggestions, and federated learning for privacy protection, and integrates AQI data from sensor networks in cities such as Bari, Italy, and Cork, UK. In areas with sparse sensor coverage, interpolation techniques approximate AQI values, ensuring broad applicability. This system offers a poromsing, health-oriented POI recommendation solution that adapts dynamically to current urban air quality conditions while safeguarding user privacy.