Machine learning thermal comfort prediction models based on occupant demographic characteristics

• Published in: Journal of thermal biology Vol. 123; p. 103884
• Main Authors: Kocaman, Ezgi, Kuru Erdem, Merve, Calis, Gulben
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01-07-2024
• Subjects: Adolescent; Adult; Aged; Algorithms; Demographic characteristics; Female; Humans; Machine Learning; Male; Middle Aged; Prediction model; Thermal satisfaction; Thermal sensation; Thermosensing; Young Adult; Demographic characteristics; Thermal satisfaction; Thermal sensation; Prediction model; Machine learning
• ISSN: 0306-4565
• DOI: 10.1016/j.jtherbio.2024.103884

This study aims to investigate the predictive occupant demographic characteristics of thermal sensation (TS) and thermal satisfaction (TSa) as well as to find the most effective machine learning (ML) algorithms for predicting TS and TSa. To achieve this, a survey campaign was carried out in three mixed-mode buildings to develop TS and TSa prediction models by using six ML algorithms (Logistic Regression, Naïve Bayes, Decision Tree (DT), Random Forest (RF), K-Nearest Neighborhood (KNN) and Support Vector Machine). The prediction models were developed based on six demographic characteristics (gender, age, thermal history, education level, income, occupation). The results show that gender, age, and thermal history are significant predictors of both TS and TSa. Education level, income, and occupation were not significant predictors of TS, but were significant predictors of TSa. The study also found that RF and KNN are the most effective ML algorithms for predicting TS, while DT and RF are the most effective ML algorithms for predicting TSa. The study found that the accuracy of TS prediction models ranges from 83% to 99%, with neutral being the most correctly classified scale. The accuracy of TSa prediction models ranges from 84% to 97%, with dissatisfaction being the most common misclassification.
•Thermal sensation is influenced by gender, age and thermal history.•Thermal satisfaction is influenced by gender, age, thermal history, education level and monthly income.•RF is the most effective ML algorithm for predicting thermal sensation.•DT and RF are the most effective ML algorithms for predicting thermal satisfaction.