Predicting Indoor Air Quality in University Laboratories Using Classification-Based Machine Learning Models

DOI

10.2991/978-94-6239-668-5_93How to use a DOI?

Keywords

Indoor Air Quality; University Laboratories; Machine Learning; Built-Environment

Abstract

. Indoor air quality (IAQ) in university laboratories plays a crucial role in safeguarding the health, comfort, and performance of teachers, students, and other staff, especially in densely populated cities such as Dhaka, Bangladesh. Forecasting IAQ in laboratories is challenging due to frequent changes in occupancy, ventilation, and activities. Many existing IAQ models assume steady-state conditions and may therefore be unsuitable for realistic, dynamic laboratory environments. To address this gap, this study aims to predict IAQ in university laboratories using machine learning (ML) models and analyze the key factors that significantly influence it. A dataset of 732 samples was collected from various laboratory types during the summer (June 2025-August 2025). The dataset includes both qualitative and quantitative parameters. Qualitative data were obtained from surveys on lighting satisfaction, perceived air quality, etc., along with demographic information (age, gender, study level, etc.). Smart meters were used to measure quantitative features like temperature, humidity, CO₂ concentration, occupant density, floor area, and more. Data were preprocessed by handling missing values, removing outliers, and rescaling features. Three ML models, Decision Tree (DT), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost), were developed. Their performance was evaluated using accuracy, Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). Cross-validation was applied for hyperparameter tuning, and SHapley Additive Explanations (SHAP) were used to interpret feature importance. All models demonstrated accuracies exceeding 75%, highlighting their strong ability to predict accurately. SHAP analysis highlighted CO₂ concentration, humidity, ventilation distance, occupant density, and age as the most influential features. The study demonstrates the potential of ML for real-time IAQ forecasting and control. Future research should explore seasonal variations, include more variables, and validate findings in different regions.

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  - Md. Jakaria
AU  - Md. Fardin Al Shafik
AU  - Devesis Mondal Dipta
AU  - Mohammad Nyme Uddin
AU  - Md Al Hossain Mukib
AU  - Md. Naziur Rahman
AU  - Takrim Uddin Ahmed Jengi
PY  - 2026
DA  - 2026/05/14
TI  - Predicting Indoor Air Quality in University Laboratories Using Classification-Based Machine Learning Models
BT  - Proceedings of the International Conference on Current Problems in Engineering and Applied Sciences (ICCPEAS 2025)
PB  - Atlantis Press
SP  - 883
EP  - 892
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-668-5_93
DO  - 10.2991/978-94-6239-668-5_93
ID  - Jakaria2026
ER  -