Given the significant implications of indoor air pollution for physical and mental health, well-being and productivity, indoor air quality (IAQ) is of critical importance. CO₂ is a prevalent indoor air contaminant and represents a key determinant for IAQ characterization. This study collected sensed air pollution and climatic data from a hospital environment in Greece and employed Long Short-Term Memory (LSTM) neural network variants with progressively increased architectural complexity to predict indoor CO₂ concentration across future horizons ranging from 15 min up to 180 min. Among the examined variants, the attention-based LSTM exhibited the most consistent performance across the forecasting horizons. Incorporating additional predictors reflecting climatic conditions, air pollution and occupancy status within the hospital settings, the multivariate attention-based LSTM further enhanced its predictive performance with an MAE of 8.9 ppm, 16.7 ppm, 31.2 ppm, 38.9 and 39.5 ppm for 15 min, 30 min, 60 min, 120 min, and 180 min ahead, respectively.

Exposure to degraded indoor air quality (IAQ) conditions represents a major concern for health and well-being. PM_2.5 is among the most prevalent indoor air pollutants and constitutes a key indicator in IAQ assessment. Conventional IAQ frameworks often neglect personalization, which in turn compromises the reliability of exposure estimation and the interpretation of associated health implications. In response to this limitation, the present study introduces a human-centric framework that couples wearable sensing with deep learning, employing a low-cost wearable device to capture PM_2.5 concentrations in the immediate human vicinity and an attention-based Long-Short Term Memory (LSTM) to deliver 5-min-ahead exposure predictions. During evaluation, the proposed framework demonstrated strong and consistent performance across both stable conditions and transient spikes in PM_2.5, yielding a Mean Absolute Error (MAE) of 0.181 µg/m³. These findings highlighted the synergistic potential between wearable sensing and data-driven modeling in advancing personalized IAQ forecasting, informing proactive IAQ management strategies, and ultimately promoting healthier built environments.

Thermal comfort shapes occupant health, well-being, and productivity and influences the sustainability and energy efficiency of the built environment. The Predicted Mean Vote (PMV) is the most widely used thermal comfort index, yet four of its six input parameters—globe temperature, clothing insulation, metabolic rate, and air velocity—require specialized, costly equipment or occupant self-reporting, which has long limited its practical large-scale application. This study introduces a machine learning (ML) framework aimed at estimating these four parameters using indoor and outdoor air temperature and relative humidity as its only sensor inputs, complemented by readily available contextual information and individual activity profiles. It exploits the climatic coupling of globe temperature and air velocity to the indoor–outdoor environment and the temperature- and activity-driven behavioral patterns that govern clothing insulation and metabolic rate. The proposed framework achieved strong predictive performance, explaining 85% of the variance in actual PMV values (R² = 0.85), with a near-zero mean residual (−0.041) and a residual standard deviation of 0.286. Approximately 91% of absolute errors fell below 0.5 PMV units—a deviation unlikely to shift the assigned thermal comfort category. Mapped to thermal comfort categories, predictions reached 80% accuracy, with a macro-averaged precision of 0.81 and recall of 0.80, exhibiting the highest performance for neutral and warm conditions while performing less accurately for cool discomfort. These results suggest that standard temperature and humidity sensors, combined with basic contextual information and individual activity profiles, could support reliable PMV-based thermal comfort assessment, advancing scalable, sensor-light comfort monitoring for energy-efficient, sustainable buildings.

Exposure to poor indoor air quality (IAQ) conditions represents a major public health concern, with adverse effects on human health and well-being. The adoption of innovative technological solutions can support timely risk awareness, enable informed decision-making, and ultimately mitigate this health burden. In this context, Large Language Models (LLMs) emerge as a promising technological avenue through the Retrieval-Augmented Generation (RAG) paradigm, which extends their inherent natural language understanding capabilities with explicit access to external knowledge bases, enabling evidence-grounded reasoning and informed recommendations. The present work introduces an integrated GraphRAG-based Question Answering (QA) system that couples a domain-specific knowledge graph encoding fundamental IAQ concepts and relationships with a RAG-based natural language interface, thereby enabling explainable, context-aware, and advanced analytical reasoning over IAQ data. The evaluation results demonstrate the effectiveness of the proposed QA system across both retrieval and generation stages. The retrieval mechanism achieved a context recall of 0.914 and a precision of 0.838, while the generation mechanism attained a faithfulness score of 0.906 and an answer relevancy score of 0.891.

Recent studies have shown that common household activities produce characteristic patterns in indoor air pollutants, enabling activity inference using environmental measurements alone. However, pollutant-based approaches are usually formulated as flat multi-class classification problems, even though indoor environments are dominated by long baseline periods with no emission-generating activity, leading to false alarms and unstable predictions. This work proposes a gated hierarchical inference framework for recognizing activities from indoor air quality data. A first-stage gate detects whether a time window contains activity-induced pollutant dynamics, while a second-stage classifier conditionally identifies the specific activity only when activity relevance is detected. Multivariate time-series measurements of particulate matter, volatile organic compounds, nitrogen oxides, carbon dioxide, temperature and relative humidity were collected using a portable monitoring system during controlled household cooking and cleaning experiments. Temporal windows were processed using recurrent neural network models in both stages. By separating activity detection from activity identification, the proposed method aligns inference with the physical generation of indoor pollutant signals and improves robustness in baseline-dominated monitoring scenarios while maintaining reliable discrimination among activities. The framework supports unobtrusive activity recognition and enables applications in exposure-aware monitoring and intelligent indoor environmental management.