Feature Ranking for Predicting Occupant Visual Comfort in Hospital Lobby Using Artificial Neural Networks (ANNs)

DOI

10.2991/978-94-6239-668-5_90How to use a DOI?

Keywords

Feature ranking; Hospital lobby; Artificial Neural Network (ANN); Visual Comfort; Sustainable Environment

Abstract

Maintaining appropriate visual levels in hospital spaces is vital for occupant comfort and adaptive healthcare environments, particularly in dense urban areas such as Dhaka, Bangladesh, which strongly influence indoor performance and user perception. Existing research has primarily focused on energy efficiency and lighting comfort in specific hospital zones such as wards and intensive care units (ICUs), while hospital lobby spaces are often overlooked despite their significant impact on lighting comfort and overall indoor environmental quality (IEQ). To address this research gap, this study employs Artificial Neural Networks (ANNs) to identify and rank the most influential features affecting occupant visual comfort in an artificially ventilated hospital lobby in Dhaka, Bangladesh. The research was conducted through a questionnaire-based field survey, resulting in 400 valid data samples with 32 key features representing human, environmental, and indoor-related variables. These features include demographic characteristics (i.e., gender, age, visitor type, etc.), environmental features (i.e., temperature, humidity, CO₂ concentration, etc.), indoor landscape factors (i.e., surface materials, sitting direction, etc.), and building attributes such as room orientation and window direction. The dataset was divided into 80% for training and 20% for testing, and hyperparameter tuning was performed. Feature importance and ranking were evaluated using Principal Component Analysis (PCA), Random Forest (RF), Recursive Feature Elimination (RFE), and Lasso Regularization (LR), revealing sitting direction, lighting level, number of windows, and lobby location as dominant predictors, while sitting orientation, number of lights, window state, and floor level also influence visual comfort. The findings support improved health outcomes, energy efficiency, and sustainability.

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  - Ramisa Anjum
AU  - Md. Faisal Rahman Dhrubo
AU  - Md. Mashnur Hossain Pobon
AU  - Maisha Mahmud
PY  - 2026
DA  - 2026/05/14
TI  - Feature Ranking for Predicting Occupant Visual Comfort in Hospital Lobby Using Artificial Neural Networks (ANNs)
BT  - Proceedings of the International Conference on Current Problems in Engineering and Applied Sciences (ICCPEAS 2025)
PB  - Atlantis Press
SP  - 857
EP  - 866
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-668-5_90
DO  - 10.2991/978-94-6239-668-5_90
ID  - Anjum2026
ER  -