Privacy-Aware Ambient Audio Sensing for Healthy Indoor Spaces

2025-12-13

AI Summary

This study addresses the invasive, costly, and indirect nature of current monitoring approaches for indoor airborne health risks—such as inadequate ventilation, aerosol emission, and high occupant density—by proposing a non-intrusive, real-time environmental-audio sensing paradigm. Methodologically, it pioneers the use of existing building-installed microphones to capture ambient audio, then jointly estimates three critical risk factors—ventilation efficiency, aerosol emission intensity, and spatial occupant distribution—via acoustic feature modeling, lightweight machine learning inference, and differential privacy enhancement. The approach requires no additional hardware, ensures privacy compliance, and achieves millisecond-level responsiveness. Evaluated in real-world office and classroom settings, it achieves mean estimation errors below 12% across all three factors, demonstrating high accuracy, low deployment cost, strong privacy preservation, and real-time capability. This work provides a practical, deployable technical pathway for proactive indoor air quality risk management.

Technology Category

• Machine Learning: Privacy
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Philosophy and Ethics of AI: Privacy & Security

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Indoor airborne transmission poses a significant health risk, yet current monitoring solutions are invasive, costly, or fail to address it directly. My research explores the untapped potential of ambient audio sensing to estimate key transmission risk factors such as ventilation, aerosol emissions, and occupant distribution non-invasively and in real time. I develop privacy-preserving systems that leverage existing microphones to monitor the whole spectrum of indoor air quality which can have a significant effect on an individual's health. This work lays the foundation for privacy-aware airborne risk monitoring using everyday devices.

Problem

• Estimates indoor airborne transmission risk factors non-invasively.
• Develops privacy-preserving systems using ambient audio sensing.
• Monitors indoor air quality in real-time with existing devices.

Innovation

• Uses ambient audio sensing for real-time risk estimation
• Leverages existing microphones for non-invasive air quality monitoring
• Develops privacy-preserving systems with everyday devices