Staff View: A hybrid learning approach to model the diversity of window-opening behavior

A hybrid learning approach to model the diversity of window-opening behavior

The diverse window-opening behaviors of individuals can result in significant differences in indoor thermal environments, air quality, and energy utilization. However, the majority of existing studies focus on constructing an average window operation model, thus overlooking the diversity of behavior...

Full description

Saved in:

Bibliographic Details
Main Authors:	Liu, Yiqiao, Chong, Wen Tong, Yau, Yat Huang, Wu, Jinshun, Chang, Yufan, Cui, Tong, Chang, Li, Pan, Song
Format:	Article
Published:	Elsevier 2024
Subjects:	TA Engineering (General). Civil engineering (General) TH Building construction
Online Access:	http://eprints.um.edu.my/45188/ https://doi.org/10.1016/j.buildenv.2024.111525
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.45188
record_format	eprints
spelling	my.um.eprints.451882024-09-25T07:48:51Z http://eprints.um.edu.my/45188/ A hybrid learning approach to model the diversity of window-opening behavior Liu, Yiqiao Chong, Wen Tong Yau, Yat Huang Wu, Jinshun Chang, Yufan Cui, Tong Chang, Li Pan, Song TA Engineering (General). Civil engineering (General) TH Building construction The diverse window-opening behaviors of individuals can result in significant differences in indoor thermal environments, air quality, and energy utilization. However, the majority of existing studies focus on constructing an average window operation model, thus overlooking the diversity of behaviors. Current methods for addressing behavioral diversity face challenges with integration into building performance simulation software and are highly dependent on data scale. To address these limitations, this study proposes a novel approach that combines unsupervised learning (K-Means) and supervised learning (Light Gradient Boosting Machine, LightGBM) for modeling the diverse window-opening behaviors. Furthermore, the SHapley Additive exPlanations (SHAP) was employed to interpret the predictive model. This study yielded four key findings: 1) There were 12 different window-opening behavior patterns. Interestingly, 65 % of the residents ` window-opening behaviors were not influenced by environmental factors but were instead a matter of personal habit. 2) Using random sampling to divide the dataset may pose a risk of data leakage. The time series cross-validation method is more suitable for evaluating the performance of the window state prediction model. 3) Under the time series sampling strategy, the LightGBM model incorporating behavioral diversity improved the prediction accuracy by 1.3% - 10.4 % compared to the standalone LightGBM model. Notably, when the daily average window opening time was used as a clustering feature in the LightGBM model (Cluster(T)-LightGBM), the accuracy reached 87.1 %. 4) The SHAP feature analysis highlighted high-intensity window-opening categories, outdoor temperature, and indoor CO 2 concentration as the most pivotal predictors. Elsevier 2024-06 Article PeerReviewed Liu, Yiqiao and Chong, Wen Tong and Yau, Yat Huang and Wu, Jinshun and Chang, Yufan and Cui, Tong and Chang, Li and Pan, Song (2024) A hybrid learning approach to model the diversity of window-opening behavior. Building and Environment, 257. p. 111525. ISSN 0360-1323, DOI https://doi.org/10.1016/j.buildenv.2024.111525 <https://doi.org/10.1016/j.buildenv.2024.111525>. https://doi.org/10.1016/j.buildenv.2024.111525 10.1016/j.buildenv.2024.111525
institution	Universiti Malaya
building	UM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaya
content_source	UM Research Repository
url_provider	http://eprints.um.edu.my/
topic	TA Engineering (General). Civil engineering (General) TH Building construction
spellingShingle	TA Engineering (General). Civil engineering (General) TH Building construction Liu, Yiqiao Chong, Wen Tong Yau, Yat Huang Wu, Jinshun Chang, Yufan Cui, Tong Chang, Li Pan, Song A hybrid learning approach to model the diversity of window-opening behavior
description	The diverse window-opening behaviors of individuals can result in significant differences in indoor thermal environments, air quality, and energy utilization. However, the majority of existing studies focus on constructing an average window operation model, thus overlooking the diversity of behaviors. Current methods for addressing behavioral diversity face challenges with integration into building performance simulation software and are highly dependent on data scale. To address these limitations, this study proposes a novel approach that combines unsupervised learning (K-Means) and supervised learning (Light Gradient Boosting Machine, LightGBM) for modeling the diverse window-opening behaviors. Furthermore, the SHapley Additive exPlanations (SHAP) was employed to interpret the predictive model. This study yielded four key findings: 1) There were 12 different window-opening behavior patterns. Interestingly, 65 % of the residents ` window-opening behaviors were not influenced by environmental factors but were instead a matter of personal habit. 2) Using random sampling to divide the dataset may pose a risk of data leakage. The time series cross-validation method is more suitable for evaluating the performance of the window state prediction model. 3) Under the time series sampling strategy, the LightGBM model incorporating behavioral diversity improved the prediction accuracy by 1.3% - 10.4 % compared to the standalone LightGBM model. Notably, when the daily average window opening time was used as a clustering feature in the LightGBM model (Cluster(T)-LightGBM), the accuracy reached 87.1 %. 4) The SHAP feature analysis highlighted high-intensity window-opening categories, outdoor temperature, and indoor CO 2 concentration as the most pivotal predictors.
format	Article
author	Liu, Yiqiao Chong, Wen Tong Yau, Yat Huang Wu, Jinshun Chang, Yufan Cui, Tong Chang, Li Pan, Song
author_facet	Liu, Yiqiao Chong, Wen Tong Yau, Yat Huang Wu, Jinshun Chang, Yufan Cui, Tong Chang, Li Pan, Song
author_sort	Liu, Yiqiao
title	A hybrid learning approach to model the diversity of window-opening behavior
title_short	A hybrid learning approach to model the diversity of window-opening behavior
title_full	A hybrid learning approach to model the diversity of window-opening behavior
title_fullStr	A hybrid learning approach to model the diversity of window-opening behavior
title_full_unstemmed	A hybrid learning approach to model the diversity of window-opening behavior
title_sort	hybrid learning approach to model the diversity of window-opening behavior
publisher	Elsevier
publishDate	2024
url	http://eprints.um.edu.my/45188/ https://doi.org/10.1016/j.buildenv.2024.111525
_version_	1811682099880525824
score	13.211869

A hybrid learning approach to model the diversity of window-opening behavior

Similar Items