Zhang Tongrui’s scientific contributions

People spend a significant portion of their time in enclosed spaces, making indoor air quality (IAQ) a critical factor for health and productivity. Artificial intelligence (AI)-driven systems that monitor air quality in real-time and utilize historical data for accurate forecasting have emerged as effective solutions to this challenge. However, these systems often raise privacy concerns, as they may inadvertently expose sensitive information about occupants’ habits and presence. Addressing these privacy challenges is essential. This research comprehensively reviews the existing literature on traditional and AI-based IAQ management, focusing on privacy-preserving techniques. The analysis reveals that while significant progress has been made in IAQ monitoring, most systems prioritize accuracy at the expense of privacy. Existing approaches often fail to adequately address the risks associated with data collection and the implications for occupant privacy. Emerging AI-driven technologies, such as federated learning and edge computing, offer promising solutions by processing data locally and minimizing privacy risks. This research introduces a novel AI-based IAQ management platform incorporating the SITA (Spatial, Identity, Temporal, and Activity) model. By leveraging customizable privacy settings, the platform enables users to safeguard sensitive information while ensuring effective IAQ management. Integrating Internet of Things (IoT) sensor networks, edge computing, and advanced privacy-preserving technologies, the proposed system delivers a robust and scalable solution that protects both privacy and health.