Interactions of spatial type, activity intensity, and season on thermal comfort and multidimensional health in older adults

Development of a D-centred thermal comfort classification model based on the ASHRAE global thermal comfort database II: an Indian case study

Thermal comfort of pregnant women in cold-region hospitals: differences by conception method

Evaluation of eco-friendly propane-based refrigerant blends for thermal comfort and refrigeration applications

Integrating LDA clustering and autoencoder-based transfer learning for thermal comfort prediction

Maintaining thermal comfort in large public waiting halls is challenging due to rapidly varying occupancy, spatial non-uniformity, and tight energy budgets. We propose an AI-enabled, occupant-centric control framework that passively estimates per-person features from synchronized RGB and thermal-infrared (TIR) streams. The framework first identifies occupancy-invariant, physically grounded features—metabolic rate, clothing insulation, action state (sit/walk) and intensity (walking speed)—and combines them with environmental drivers (air temperature, mean radiant temperature, air velocity) to inform thermal prediction. A lightweight vision pipeline (detection, tracking, optical-flow speed, and TIR torso temperature) extracts these features in real time without individual profiling. A sequence model then predicts short-horizon Predicted Mean Vote (PMV) and Predicted Percentage of Dissatisfied (PPD), and a comfort-focused regulator maps these forecasts to native HVAC setpoints (temperature and air speed) under device constraints. In a simulated waiting-hall scenario (10-40 occupants), the calibrated predictor attains PMV-TSV MAE , the controller keeps – of votes within the ASHRAE comfort band , and typically achieves within – min after density changes. These results show that coupling edge-efficient vision with sequential comfort prediction and actionable HVAC control can improve crowd-level comfort in complex public spaces while preserving privacy. • Occupant-centric. • YOLO detection. • Optical-flow motion estimation. • Sequential Mamba estimation.

Visual determinants of outdoor thermal comfort: integrating explainable AI and perceptual assessments

Incorporating urban thermal comfort into transit-oriented development (TOD) planning: Non-linear heterogeneous built environment effects

Artificial intelligence for improving thermal comfort through envelope design in residential buildings: Recent developments and future directions

Beyond proximity: optimizing waterfront design for thermal comfort through microclimatic insights and generative algorithms

• XGBoost (Extreme Gradient Boosting) model ( R 2 = 0.96 ) predicts equivalent temperature at 16 body sites • SHAP ranks key convective and radiant HVAC parameters shaping comfort • Optimal HVAC settings validated at -10 °C for two postures and three airflow modes • Validation shows at least 50% local and all upper and lower body in neutral thermal comfort • Radiant dominant HVAC reduces power by up to 240 W, guiding future EV HVAC design This paper presents an AI-based model for optimizing heating, ventilation, and air conditioning (HVAC) settings to improve thermal comfort in electric vehicles under winter conditions and to estimate the associated power consumption. Unlike conventional HVAC systems that primarily rely on convective heating, the investigated concept combines convective airflow with nine radiant heating panels to enhance comfort and energy efficiency. Equivalent temperature (ET) was employed as an objective thermal comfort metric, and an XGBoost (Extreme Gradient Boosting) model was trained to predict ET for 16 body regions, achieving a high accuracy (coefficient of determination R 2 = 0.96 ). A Random Forest model was applied to relate fan speed and damper settings to mass flow. Validation experiments confirmed that the optimized HVAC settings maintained thermal comfort, with at least 50% of local body regions and 100% of upper and lower body averages within the neutral comfort zone. The approach demonstrated potential power savings of up to 240 W compared to convection-dominant strategies. These findings highlight the potential of combining AI with hybrid HVAC concepts to improve passenger comfort and reduce energy consumption in future automated electric vehicles.

How street tree structure modulates thermal comfort during urban heat extremes: Evidence from LiDAR and micrometeorological data

Smells modulate thermal sensation: A multisensory study in office environments during winter

The effect of air deflector angle on ventilation systems in laying hen houses during summer based on CFD analysis.

Abstract This study assesses the projected impacts of climate change on human thermal comfort in mainland Portugal using high-resolution downscaling of a CMIP6 GCM (MPI-ESM-1.2-HR) with the Weather Re-search and Forecasting (WRF) model for three CMIP6 future climate scenarios (SSP2-4.5, SSP3-7.0, and SSP5-8.5). Two bioclimatic indices – the Thom Discomfort Index (TDI) and the Universal Thermal Climate Index (UTCI) – were analyzed to evaluate changes in population exposure to heat and cold stress.
Results indicate a consistent increase in heat-related discomfort across all scenarios and time periods, accompanied by a reduction in cold-related stress. By mid-century (2041–2070), both TDI and UTCI show widespread warming, particularly in spring and summer, with the strongest increases occurring in southern and interior regions. Toward the end of the century (2071–2100), the frequency and duration of high and extreme heat stress days rise substantially, especially under SSP5-8.5, while cold stress days become increasingly rare.
These findings highlight a clear shift toward hotter and more uncomfortable climatic conditions throughout Portugal, posing significant health challenges for vulnerable populations. The results underscore the im-portance of integrating thermal comfort metrics such as TDI and UTCI into climate adaptation and public health planning strategies.

Dwelling thermal comfortability varies with adaptive behaviour of community within similar climatic zone - prerequisite for consideration in residential building design.

Thermal and tactile sensations interact in shaping how we perceive our environment. These interactions rely on the activity of distinct but converging somatosensory pathways and may be altered by aging. In this study, we investigated how innocuous thermal stimulation modulates tactile sensitivity in healthy young and older adults. Mechanical detection thresholds (MDTs) were measured on the dorsal hand using a standardized protocol, while non-painful thermal stimuli were applied as follows: cold (20 °C) and warm (40 °C) either ipsilaterally or contralaterally to the testing site, and a neutral temperature (32 °C) applied only ipsilaterally. Two thermal stimulation methods were used: a localized contact thermode and a global air-based thermal chamber. Results showed that cold stimulation applied ipsilaterally to the tested hand significantly increased MDTs in both age groups, indicating reduced tactile sensitivity. This effect was consistent across stimulation methods, but stronger with the thermode and more pronounced in older adults. Neither warm nor contralateral thermal stimulation produced significant modulation, and neutral temperature had no effect, confirming the specificity of the cold-induced modulation. These findings indicate that cold input inhibits tactile sensitivity in a spatially and modality-specific manner. The absence of contralateral effects supports a segmental, rather than supraspinal, mechanism of thermo-tactile interaction. These results contribute to our understanding of age-related changes in multisensory integration and may inform the development of sensory assessment tools and therapeutic approaches tailored for older individuals.

The natural resources and local communities of Madre de Dios, Peru, face severe environmental degradation due to illegal mining, deforestation, and the expansion of agricultural activities, threatening one of the most ecologically sensitive regions of the Amazon. This research proposes a low-carbon and bioclimatic architectural design for a Sustainable Interpretation and Research Center dedicated to the conservation of the ecosystems of Manu National Park. The study is based on an analysis of the surrounding environment in terms of flora, fauna, and climate, applying bioclimatic strategies focused on sustainability and supported by specialized digital tools (Revit 2024, Canva, Global Mapper 2024, SketchUp 2024, Photoshop 2022, and Illustrator 2022). The project presents a bioclimatic architectural design that integrates constructive techniques ensuring thermal comfort in a warm-humid climate, while promoting the use of clean technologies such as photovoltaic solar systems generating 15,571.8 kWh per year and a rainwater harvesting system collecting 70,675 L annually. The infrastructure is built with bamboo and locally sourced wood, renewable materials that ensure durability and low environmental impact. In addition, the design includes the reforestation of 17.92% of the total area and 3.46% of public spaces, incorporating native species such as Brazil nut, rosewood, and capirona to reinforce local biodiversity. Overall, this research demonstrates how low-carbon construction, renewable materials, and bioclimatic design can contribute to sustainable development, environmental awareness, and the preservation of natural ecosystems in tropical regions.

High-altitude environments characterized by low air pressure, hypoxia, and strong solar radiation have a significant impact on human thermal comfort; however, existing thermal comfort theories and evaluation models are primarily developed under low-altitude climatic conditions, and their applicability in plateau regions remains limited. With the acceleration of urbanization and the increase in residential, tourism, and occupational activities in high-altitude areas, systematically reviewing the research progress on thermal comfort in such environments is of great practical significance. This study combines systematic literature retrieval and bibliometric analysis, based on the Web of Science Core Collection and China National Knowledge Infrastructure (CNKI) databases, to analyze relevant studies published since 2001. Using CiteSpace, research hotspots, collaboration networks, and evolutionary trends are visualized. The results indicate that current research hotspots mainly focus on physiological responses and thermal adaptation mechanisms under low-pressure and hypoxic conditions, thermal comfort regulation strategies for high-altitude buildings and environments, and the applicability and modification of conventional thermal comfort models. Emerging trends include multi-environmental factor coupling analysis, adaptive model development, region-specific building design approaches, and health-oriented comprehensive evaluation frameworks. The findings provide valuable references for building thermal environment design, regional revision of thermal comfort evaluation standards, and policy-making in high-altitude regions.

To address the critical need for accurate human thermal comfort prediction in winter heating environments, this study established a comprehensive thermal comfort dataset containing 2089 valid samples through experiments. On this basis, thermal comfort prediction models were constructed using three multi-class machine learning algorithms: Support Vector Classification, K-Nearest Neighbors, and Random Forest. The predictive performance of 63 different feature combinations was systematically evaluated. The results indicate that the feature subset comprising indoor air temperature, forehead temperature, cheek temperature, dorsal hand temperature, heart rate, and systolic blood pressure yields the optimal prediction performance. Among the evaluated models, the Random Forest model demonstrated superior overall performance, achieving an accuracy exceeding 90% and an AUC ranging from 96% to 99%, significantly outperforming the SVC and KNN models. Compared with the traditional Predicted Mean Vote (PMV) model, the machine learning models developed in this study showed a substantial improvement in prediction accuracy under identical conditions; notably, the Random Forest model improved accuracy by approximately 40% over the PMV model. Based on these findings, a smart heating system framework integrating environmental sensors, wearable devices, and intelligent control valves is proposed, providing a theoretical basis and technical approach for realizing personalized and energy-efficient heating control.