Bi Directional Feedback Fusion for Activity Aware Forecasting of Indoor CO2 and PM2.5

2026-03-06

AI Summary

This work addresses the challenge of modeling indoor CO₂ and PM2.5 concentrations, which are jointly influenced by environmental dynamics and human activities—particularly abrupt pollutant spikes triggered by behavior that conventional models struggle to capture. To this end, we propose a dual-stream bidirectional feedback fusion framework that integrates behavior-aware embeddings, context-adaptive modulation, and dual-timescale temporal modeling to jointly capture long-term trends and short-term peak fluctuations. A composite loss function incorporating peak-aware penalties and uncertainty regularization is designed to enhance prediction robustness and interpretability. Evaluated on real-world indoor air quality datasets, our method significantly outperforms existing approaches, achieving both high-accuracy forecasting and reliable uncertainty quantification, thereby demonstrating strong applicability in smart building systems and health monitoring scenarios.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Indoor air quality (IAQ) forecasting plays a critical role in safeguarding occupant health, ensuring thermal comfort, and supporting intelligent building control. However, predicting future concentrations of key pollutants such as carbon dioxide (CO2) and fine particulate matter (PM2.5) remains challenging due to the complex interplay between environmental factors and highly dynamic occupant behaviours. Traditional data driven models primarily rely on historical sensor trajectories and often fail to anticipate behaviour induced emission spikes or rapid concentration shifts. To address these limitations, we present a dual stream bi directional feedback fusion framework that jointly models indoor environmental evolution and action derived embeddings representing human activities. The proposed architecture integrates a context aware modulation mechanism that adaptively scales and shifts each stream based on a shared, evolving fusion state, enabling the model to selectively emphasise behavioural cues or long term environmental trends. Furthermore, we introduce dual timescale temporal modules that independently capture gradual CO2 accumulation patterns and short term PM2.5 fluctuations. A composite loss function combining weighted mean squared error, spike aware penalties, and uncertainty regularisation facilitates robust learning under volatile indoor conditions. Extensive validation on real-world IAQ datasets demonstrates that our approach significantly outperforms state of the art forecasting baselines while providing interpretable uncertainty estimates essential for practical deployment in smart buildings and health-aware monitoring systems.

Problem

• Indoor air quality
• CO2 forecasting
• PM2.5 forecasting
• human activity
• emission spikes

Innovation

• bidirectional feedback fusion
• activity-aware forecasting
• dual-timescale modeling
• context-aware modulation
• uncertainty regularization