Comfort Model Research Articles

Machine learning-based assessment of thermal comfort for the elderly in warm environments: Combining the XGBoost algorithm and human body exergy analysis

Many elderly people rarely own or use air conditioners because of low income and economising habits, causing them to live in warm thermal environments when heat waves and hot weather occur. Living in warm conditions worsens thermal discomfort and poses health risks this group. To investigate the thermal comfort and adaptation of the elderly, a total of 38 participants were recruited for two parts of experiments in a climate chamber: Part A collected thermal sensation vote (TSV) and physiological parameters for 30 min at 28, 30, and 32 °C, and Part B presented a 20-min cooling with fans (air velocities of 0.6 and 1.4 m/s) at the same temperature. Furthermore, we constructed a thermal comfort model for the elderly based on human body exergy analysis and the GBDT, AdaBoost, and XGBoost machine-learning algorithms. The results showed that the predicted mean vote considerably overestimated the actual TSV. The TSV and mean skin temperature were decreased by 0.1–0.5 scores and 0.4–0.5 °C by the behavioural adaptation of fan cooling. The predictive results showed that the XGBoost model performed better, with R2 score, mean absolute error (MAE), and mean squared error (MSE) of 81 %, 0.10, and 0.01. Exergy transfer from evaporation (Ex-Esk), mean skin temperature (mtsk), air velocity (va), and convective exergy transfer (Ex-C) contributed more to the feature importance in the SHAP value analysis. The current study has implications for investigating physiological comfort and age-friendly environmental designs for the elderly, providing new perspectives for thermal comfort evaluations.

Exploring the effect of clothing moisture content on heat and moisture transfer from the human body using a sweating thermal manikin

Evaporative heat loss is an important component of the human body's energy balance and several developed thermal comfort models are available to assess heat and mass transfer during human sweating. However, the impact of sweat-soaked clothing due to human perspiration on heat and moisture transfer from the body remains understudied. In this study, the thermal and moisture properties of typical summer clothing were evaluated and moisture adsorption and desorption curves were obtained. The heat losses of the human body in different sweating states were compared using a sweating thermal manikin. It was found that the clothing moisture content and the clothing coverage ratio had a significant effect on the human body heat loss. As the sweating rate increases, additional resistances of the sweat moisture transfer will be added in the sweat-soaked clothing, which would adversely affect the skin temperature. The results show that the total thermal resistance of fully wetted clothing decreased by an average of almost 30% compared to dry clothing ensembles. To account for such differences, the clothing thermal and evaporative resistance, along with the temperature and vapor pressure at varying moisture contents were evaluated and predicted with empirical equations. This enables integrating a dynamic heat and moisture transfer model for the sweat-soaked clothing into a prevailing thermo-physiological model. Accounting for real clothing physical parameters is vital when evaluating thermal comfort in hot and humid weather conditions.

Urban heat islands’ effects on the thermo-energy performance of buildings according to their socio-economic factors

Urban areas experience the urban heat island (UHI) effect, which affects the thermal comfort and energy consumption of buildings. These consequences could vary depending on the socio-economic status of the neighbourhoods. Few studies have investigated how UHI affects socio-economically contrasting districts in thermal comfort and energy performance. Therefore, the primary goal of this research is to evaluate and compare the energy efficiency and thermal comfort conditions of residential buildings in the same city (Temuco, Chile) but located in socio-economically contrasting neighbourhoods. Urban weather files were first modelled in four urban zones using UWG software. Also, EnergyPlus building simulations were conducted to evaluate discomfort hours in adaptive comfort models and energy performance. The results showed annual average UHI intensities between 1.5 and 2.5 K. Urban–rural cooling energy load differences ranged between 12.47% and 38.92%, while heating energy load differences ranged between -20.47% and -81.95%. These distinctions depended on the urban zone, residence model analysed, or energy building standard applied. Similarly, urban-rural differences in thermal comfort times varied from 0.5% to 100%. Results illustrate that the risk of overheating could increase in socio-economically vulnerable areas. This issue could worsen if urban segregation continues to generate poor urban design in low-income districts.

An indoor thermal comfort model for group thermal comfort prediction based on K-means++ algorithm

An indoor thermal comfort model for group thermal comfort prediction based on K-means++ algorithm

Modelling of Indoor Air Quality and Thermal Comfort in Passive Buildings Subjected to External Warm Climate Conditions

Air renewal rate is an important parameter for both indoor air quality and thermal comfort. However, to improve indoor thermal comfort, the air renewal rate to be used, in general, will depend on the outdoor air temperature values. This article presents the modelling of indoor air quality and thermal comfort for occupants of a passive building subject to a climate with warm conditions. The ventilation and shading strategies implemented for the interior spaces are then considered, as well as the use of an underground space for storing cooled air. The indoor air quality is evaluated using the carbon dioxide concentration, and thermal comfort is evaluated using the Predicted Mean Vote index. The geometry of the passive building, with complex topology, is generated using a numerical model. The simulation is performed by Building Thermal Response software, considering the building’s geometry and materials, ventilation, and occupancy, among others. The building studied is a circular auditorium. The auditorium is divided into four semi-circular auditoriums and a central circular space, with vertical glazed windows and horizontal shading devices on its entire outer surface. Typical summer conditions existing in a Mediterranean-type environment were considered. In this work, two cases were simulated: in Case 1, the occupation is verified in the central space and the four semi-circular auditoriums and all spaces are considered as one; in Case 2, the occupation is verified only in each semi-circular auditorium and each one works independently. For both cases, three strategies were applied: A, without shading and geothermal devices; B, with a geothermal device and without a shading device; and C, with both shading and geothermal devices. The airflow rate contributes to improving indoor air quality throughout the day and thermal comfort for occupants, especially in the morning. The geothermal and shading devices improve the thermal comfort level, mainly in the afternoon.

Optimization of Customer Complain Handling at Grapari East Java

The operational process at GraPARI is a benchmark for PT Telkomsel's success in the service sector which will later influence customer loyalty in using the product and ultimately increase revenue. Therefore, the potential of GraPARI services must be maximized, especially in terms of complaint handling. The high quality of service can be seen from the number of customers who come, the orderly and comfortable queue model, and the quick and precise solutions from customer service for all complaints lodged by customers. This research was conducted to create a system for monitoring the most effective traffic handling of customer complaints, thereby speeding up the complaint handling process using parameters of customer quantity, customer service productivity, and ending in the back office as a case executor. From these three parameters, cases are first categorized into three channels (human error, system error, and unique requests). The calculation results show that from all these categories, the process of handling them is slow with an Out Of SLA ratio of almost 80%. After a simulation of optimization using tandem channels, the estimated optimal duration decreased as the number of servers used increased, with the traffic is reduced by 7% by using 10 additional servers in the tandem channels

Research on Summer Environmental Thermal Comfort Model of Buildings in Hot Summer and Cold Winter Area

Research on Summer Environmental Thermal Comfort Model of Buildings in Hot Summer and Cold Winter Area

Non-invasive vision-based personal comfort model using thermographic images and deep learning

An efficient method for predicting occupants' thermal comfort is crucial for developing optimal environmental control strategies while minimizing energy consumption in buildings. This paper presents a non-invasive vision-based personal comfort model that integrates thermographic images and deep learning. Unlike previous studies, the entire thermographic image of the upper body is directly used during model training, minimizing complex data processing and maximizing the use of rich skin temperature distribution. The proposed method is validated using thermographic images and corresponding thermal sensation votes (TSV) from 10 participants under different experimental conditions. Results show that the model based on a 3-point TSV scale achieves exceptional classification performance with an average accuracy of 99.51 %, outperforming existing models. The model performance using a 7-point TSV scale is slightly lower, with an average accuracy of 89.90 %. This method offers potential for integrating thermal comfort models into real-time building environmental control, optimizing occupant comfort and energy consumption.

Experimental evaluations of Berkeley thermal sensation and comfort models in electric vehicle cabin under cold outdoor conditions

As the automobile industry is transitioning toward electric vehicles, manufacturers have started implementing local warmers alongside cabin heating, ventilation, and air conditioning (HVAC) systems for effective thermal comfort management. However, optimal operating strategies need to be developed for integrating local warmers with HVAC systems. Although the Berkeley models comprising local/overall thermal sensation and comfort models offer insights in this regard, they lack follow-up assessments for occupants transitioning from very cold states. In this study, Berkeley models were evaluated using two sets of experimental data collected in a transient vehicle cabin under cold outdoor conditions: test (A) with cabin HVAC alone and test (B) with both HVAC and local warmers. The findings confirm the satisfactory performances of the Berkeley models for predicting overall sensation and comfort, with a maximum root mean-squared error (RMSE) of 0.15. The local comfort model performed poorly with the original coefficients across both datasets (maximum RMSE of 1.96). Therefore, the model coefficients were regressed for the dataset from test A and validated against the dataset from test B to achieve a maximum RMSE of 0.49. With these regressed coefficients, it was observed that moving toward a neutral overall state diminished the potential to maximize local comfort. Conversely, the local sensation model showed poor agreement (maximum RMSE of 1.9); we confirmed that accurate adaptive setpoint temperatures are a prerequisite for ensuring good predictions from the model. These findings are expected to contribute toward future efforts in using Berkeley models to formulate effective local warmer–HVAC operational strategies in electric vehicles.

A hierarchical framework for aggregating grid-interactive buildings with thermal and battery energy storage

The behind-the-meter (BTM) thermal and battery energy storage can help improve energy efficiency, reduce energy costs, and enhance energy resilience, particularly in rural areas and for disadvantaged communities. Aggregating numerous BTM energy storage systems can act as a price influencer with a significant source of load shifting and peak demand reduction. An integrated and scalable control mechanism is required to effectively utilize energy storage systems and flexible building loads to maximize the economic benefits, considering various distribution system constraints. This paper presents an innovative hierarchical coordination framework for energy storage and flexible load in buildings, considering various factors such as electricity prices, thermal comfort, and distribution system modeling and constraints. At the upper level, a distribution system operator optimizes the power flow to minimize its power procurement costs from the electricity wholesale market, while at the lower level, aggregators determine the optimal dispatch of battery and thermal energy storage systems in multiple buildings on behalf of end-users to minimize operating costs according to the power prices. These problems are solved using a game-theoretic approach through negotiations between the distribution system operator and aggregators as a bi-level decision model. Simulation case studies have been performed for a test distribution network with a number of building end-users using energy storage systems to quantify the performance of aggregators. The results demonstrate that the proposed strategy can reduce peak load for a reliable electricity distribution network while saving electricity bills for customers.

Predictive building energy management with user feedback in the loop

Retrofitting buildings with predictive control strategies can reduce their energy demand and improve thermal comfort by considering their thermal inertia and future weather conditions. A key challenge is minimizing additional infrastructure, such as sensors and actuators, while ensuring user comfort at all times. This study focuses on retrofitting with intelligent software, incorporating the users’ feedback directly into the control loop. We propose a predictive control strategy using an optimisation-based energy management system (EMS) to control thermal zones in an office building. It uses a physically motivated grey-box model to predict and adjust thermal demand, with individual zones modelled using an RC-approach and parameter estimation handled by an unscented Kalman filter (UKF). This reduces deployment effort as the parameters are learned from historical data. The objective function ensures user comfort, penalises undesirable behaviour and minimises heating and cooling costs. An internal comfort model, automatically calibrated with user feedback by another UKF, further improves system performance. The practical case study is an office building at the ”Innovation District Inffeld”. Operation of the system for one year yielded significant results compared to conventional control. Thermal comfort was improved by 12% and thermal energy consumption for heating and cooling was reduced by about 35%.

Interpretable general thermal comfort model based on physiological data from wearable bio sensors: Light Gradient Boosting Machine (LightGBM) and SHapley Additive exPlanations (SHAP)

This study aims to develop a general thermal comfort model using physiological signals obtained from wristband-type wearable biosensors. Accordingly, we constructed and evaluated supervised machine learning models by leveraging a diverse array of features extracted from physiological signals, including electrodermal activity (EDA), photoplethysmogram (PPG), and skin temperature (SKT). The model’s performance was evaluated using data collected from 18 subjects across controlled experimental settings. Further, this study employed leave one subject out cross validation (LOSOCV) instead of the traditional k-fold CV to assess the model’s generalizability to new subjects. Furthermore, SHapley Addictive exPlanation (SHAP) was incorporated to augment the interpretability and transparency of the model. The LightGBM model demonstrated a commendable test accuracy of 79.7% in distinguishing thermal preferences, namely, “want warmer,” “comfort,” and “want cooler.” These findings underscore the feasibility of employing wearable biosensors to evaluate occupants’ thermal comfort in real-world environments. This study makes a significant contribution to the literature by laying the groundwork for a broadly applicable method of continuous, objective, and noninvasive thermal comfort monitoring among building occupants. Considering previous challenges associated with personalized thermal comfort models due to individual variability, our study represents a pivotal step toward the development of a generalized thermal comfort model.

Improved understanding of thermal comfort could yield energy savings in heritage buildings

Abstract It is necessary to improve the understanding of thermal comfort to reduce energy consumption for heating and cooling in heritage buildings, which are often energy inefficient and where interventions are limited. Personal thermal comfort models based on measurements of environmental conditions and the individual’s physiological and subjective responses represent a potential solution to ensure the optimization of existing systems. Past research shows that lighting could impact thermophysiology and subjective perception of thermal conditions, but it is not clear whether the impact is sufficient to make light adaptation an appropriate solution to reduce energy consumption in heritage buildings, where people live and work. The research conducted under realistic semi-controlled conditions in an office environment of an existing building addresses this research gap. The paper presents the first partial simplified analyses and preliminary results of a wider ongoing study, mainly showing a correlation between skin temperature and air temperature and a partially promising effect of light on subjective thermal perception. Our research on the effect of light on thermal comfort does not provide definitive conclusions but rather highlights the need for further investigation in actual heritage buildings.

Assessing thermal comfort in wooden buildings: A visual perceptual analysis through physiological characterization

As the use of wood, a representative low-carbon building material, increases to reduce greenhouse gases, analysis of the impact of wood spaces on occupants is important for effective environmental planning. Therefore the study delved into the visual and perceptual warmth effects of wood through a comparative of thermal sensations in spaces featuring various finishing materials. A living space was created using concrete, wallpaper, brick, and wood, respectively, through virtual reality. A total of 30 subjects experienced the four living spaces through virtual reality, while subjective thermal sensation questionnaires and four physiological responses were measured. In a slightly cool environment based on predicted mean vote, subjects ranked the perceived warmth in the following order: wood > brick > wallpaper > concrete, with wood surpassing concrete by 3.30, in terms of visual warmth. These results support the hue-heat hypothesis that materials in the yellow–red spectrum are commonly perceived as warm. Moreover, the representative psychological impression associated with wood, such as warmth and coziness, considerably influences these perceptions. Importantly, the positive impact of the visual and perceptual thermal effects of wood, alongside the impression of space (as being comfortable, positive, and relaxed), notably enhanced thermal comfort, especially in cooler conditions. Furthermore, the subjective evaluation of the thermal environment was validated through correlation analysis involving thermal perception biomarkers and thermal comfort model. Indoor spaces with wood finishing materials were perceived as warm, and the possibility of reducing heating load and greenhouse gas emissions was suggested by improving thermal comfort during the heating season

Construction of a Model for Assessing the Comfort of Residential Indoor Environment Based on Multisensory Design

Economic development and technological progress have made people’s demand for indoor environments higher and higher, and designing safe, comfortable, and healthy indoor environments through multisensory design is worthy of serious consideration. In order to realize the assessment of indoor environment comfort under multi-sensory design, this paper carries out data assessment from three dimensions of thermal environment, light environment and air environment. Relying on the PMV model of thermal environment comfort, we analyze the trends of indoor temperature and humidity, average radiant temperature, and PMV values. Combine Weber-Fechler and lighting coefficient to study the visual comfort change of indoor light environment, and analyze the lighting illuminance of indoor light environment under different working conditions by illuminance uniformity. From the basic principle of indoor wind environment, the changes of effective temperature difference and blowing sense caused by air temperature and wind speed are investigated. The temperature difference of the south-facing room decreased between 12.14% and 15.65% before and after the heating was stopped, which is a small change. The average indoor ambient radiant temperature values at different measurement points were up to 27.59 °C, and the fluctuations of the average indoor thermal ambient PMV values were within the range of [-1.2,1.6]. When the indoor light ambient illuminance value increased from 200 lux to 600 lux, the visual comfort improvement was more significant than from 600 lux to 1000 lux. The indoor air distribution characteristic ADPI value was 100% when the air velocity was 0.15m/s and 0.25m/s. Based on the results of indoor environment comfort assessment, multisensory optimization of indoor environment comfort from heat, light and air environments is proposed to provide guidance for improving people’s satisfaction with indoor environment.

A generalized thermal comfort model using thermographic images and compact convolutional transformers: Towards scalable and adaptive occupant comfort optimization

Thermal comfort models that account for individual thermal sensations are crucial for optimizing environmental control while maintaining occupant comfort. However, the current approach of developing occupant-specific models is not scalable for new occupants whose data were not used for training, making it impractical for multi-occupant spaces and burdensome for management. To address this, we propose a thermal comfort model based on a subject-independent evaluation approach, capable of generalizing to new individuals not included during model training. This model accurately predicts thermal sensations without the need for occupant-specific models, allowing scalability and adaptability to new occupants. Furthermore, this study considers occupants with face masks, which is essential in environments where masks are required for their wellbeing and performance. The model was developed using Compact Convolutional Transformers which combines convolutional layers and transformer layers, allowing the model to capture both fine-grained local features and broader contextual relationships, making it effective for predicting thermal comfort from thermal images. The model was trained using the Leave-One-Subject-Out (LOSO) and Leave-One-Group-Out (LOGO) training approaches. The LOSO approach achieved high accuracies of 98.04 %, 98.93 %, and 98.88 % for dataset A (participants without face masks), dataset B (participants with face masks), and dataset C (a combination of both), respectively. The LOGO approach achieved accuracies of 99.92 %, 99.40 %, and 99.85 % for datasets A, B, and C, respectively, showing a slightly better prediction performance. The approach presented in this study offers a promising solution for designing accurate generalized models for real-time environmental control to meet the thermal comfort needs of occupants.

Measuring the Realisation of Well-Being Needs of Adolescents: Validation of the Social Production Function Instrument for the Level of Well-Being–Short (SPF-ILs)

Adolescent well-being is increasingly scrutinized due to its decline. This study was conducted to validate a theory-driven instrument for the measurement of well-being needs with a sample of Dutch adolescents. The short (15-item) Social Production Function Instrument for the Level of well-being (SPF-ILs) measures whether a person’s needs for stimulation, comfort, behavioural confirmation, affection and status are met. In this study, its psychometric properties for adolescents were examined. Data collected in spring 2018 (T1) and spring 2019 (T2) from 1,304 Dutch adolescents (53.0% girls) aged 11–17 (mean, 13.7 ± 1.1) years were used. The instrument’s factor structure, internal consistency, construct validity, and gender and age factorial invariance were evaluated. The results showed that the SPF-ILs is valid and reliable for the assessment of adolescents’ well-being needs realisation. Confirmatory factor analyses supported the five-factor (stimulation, comfort, behavioural confirmation, affection and status) model, showing good internal consistency (α = 0.86 at T1, 0.88 at T2), convergent/divergent validity, as well as gender and age factorial invariance. Comparison across groups revealed the expected differences in the realisation of physical (comfort and stimulation) and social (behavioural confirmation, status and affection) well-being needs between girls and boys and over time. SPF-ILs use increases our understanding of how adolescents achieve well-being via the fulfilment of well-being needs. The maintenance of adolescents’ well-being is a global challenge, and this study revealed clear differences in adolescents’ realisation of well-being needs, increasing our understanding of what interventions are needed to support such realisation.

Prediction Models of Overall Thermal Sensation and Comfort in Vehicle Cabin Based on Field Experiments

Prediction Models of Overall Thermal Sensation and Comfort in Vehicle Cabin Based on Field Experiments

Exploring the natural ventilation potential of urban climate for high-rise buildings across different climatic zones

The natural cooling capacity of the environment can effectively reduce the building energy consumption by natural ventilation (NV). For architects, developing NV strategies requires a comprehensive understanding of the distribution characteristics of urban meteorology. This study investigates the vertical characteristics of urban local-scale meteorological parameters across climatic zones. It aims to assess the climatic potential for NV of outdoor air in high-rise buildings. Firstly, using Weather Research and Forecasting (WRF) model coupled with Local Climate Zone (LCZ) data and sounding data, the vertical distribution of meteorological parameters are explored in typical urban areas across different climatic zones. Then, based on an adaptive thermal comfort model, the climatic potential is assessed for NV in high-rise buildings via the indicator of annual natural ventilation hour (NVH). Finally, the characteristics of urban meteorology is further is analyzed in terms of its impact on the natural ventilation potential (NVP) in each climatic zone. Results indicate that air temperature decreases with height from 0 to 500 m, with more pronounced temperature gradients in compact building areas. Near the ground level, Kunming (Temperate Zone) has the most NVH, reaching 4,840 h annually. However, when building height exceeds 100 m, Guangzhou (Hot Summer and Warm Winter, HSWW) becomes more suitable for NV. In cold regions, low temperatures limit NVP during winter, while high humidity constrains it in Temperate and HSWW zones. Overall, the annual NVP in high-rise building areas exceeds that of low-rise building areas. These distribution characteristics of NVP are anticipated to promote the utilization of natural resources for sustainable urban development.

Machine learning approach for predicting personal thermal comfort in air conditioning offices in Malaysia

The existing machine learning based models for personal thermal comfort have traditionally focused on physiological and psychological variations among occupants, and the spatial parameters have been largely overlooked. Field measurements are conducted to collect data and synthesise the collective findings for optimal spatial positioning based on a 24 °C setpoint. The objective of the present study is to investigate and compare the prediction performance made by the machine learning models for personal indoor thermal comfort in air-conditioned office environments using non-spatial parameters (NSP) and spatial parameters (SP). The data was collected from the respondents at four different occupants. A comprehensive data set of NSP and SP is comprised of machine learning models in predicting different thermal comfort situations are Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM), K-Nearest Neighbours (KNN), Naive Bayes (NB), and Neural Networks (NN). Results indicate a substantial improvement in the accuracy prediction with the Random Forest algorithm outperforming others, enhancing overall accuracy by 38.6 % with spatial parameters for thermal sensation vote (TSV). However, the SVM algorithm improves 50 % accuracy by considering SP input for thermal comfort (TC). Spatial parameters, including the distance between windows and air conditioning units, emerge as critical factors influencing thermal comfort.