Predicting the Thermal Comfort of Rickshaw Pullers in Outdoor Settings Using Machine Learning Approach

DOI

10.2991/978-94-6239-668-5_91How to use a DOI?

Keywords

Thermal Comfort; Machine Learning; Urban Area; Thermal Stress; Seasonal Variation

Abstract

Ensuring thermal comfort is crucial for rickshaw pullers, particularly in densely populated urban areas like Dhaka, Bangladesh, where extreme environmental conditions can negatively impact their health and productivity [1]. These workers are exposed to high temperatures, humidity, and pollution levels for prolonged periods, making them highly vulnerable to thermal stress [2-3]. As outdoor workers, they face challenges in managing their comfort, which directly affects their performance and well-being [4-5]. This study employs machine learning (ML) techniques to predict the thermal comfort of rickshaw pullers in urban settings, providing valuable insights for enhancing outdoor working conditions. A total of 600 data samples were collected through field surveys and environmental monitoring, capturing variables such as temperature, humidity, CO2 levels, lighting intensity, and physiological factors like body mass index (BMI) and weight. The study utilized three ML classifiers Random Forest (RF), Decision Tree (DT), and XGBoost (XGB) and evaluated their performance using metrics such as accuracy, Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). SHapley Additive exPlanations (SHAP) analysis was applied to interpret feature importance and improve model transparency. All models achieved an accuracy of over 70%, with SHAP analysis revealing that temperature, weather quality, BMI, and weight were the most influential factors affecting thermal comfort. These findings highlight the potential of interpretable ML models to offer actionable insights that can improve outdoor working conditions. Future research should expand the dataset to include seasonal variations and additional features, which could refine predictive models and inform adaptive design strategies for outdoor environments.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Humayun Kabir
AU  - Md. Hasan
AU  - Md. Arif Hasan
AU  - Abdullah-Al-Mamun
AU  - Abdullah Al Masud
PY  - 2026
DA  - 2026/05/14
TI  - Predicting the Thermal Comfort of Rickshaw Pullers in Outdoor Settings Using Machine Learning Approach
BT  - Proceedings of the International Conference on Current Problems in Engineering and Applied Sciences (ICCPEAS 2025)
PB  - Atlantis Press
SP  - 867
EP  - 876
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-668-5_91
DO  - 10.2991/978-94-6239-668-5_91
ID  - Kabir2026
ER  -