Predicting Outdoor Thermal Comfort in Traditional Villages: An Explainable Machine Learning Framework Integrating Model Optimization, Seasonal Variability, and Tourist-Resident Insights

首页 > 成果 > 详情

认领

导出

Link by DOI

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Jiang, Jishui;Li, Zhe;Bedra, Komi Bernard;Long, Canrong;Wu, Jiade;...

通讯作者：

Li, Z

作者机构：

[Bedra, Komi Bernard; Jiang, Jishui] Hunan City Univ, Sch Architecture & Urban Planning, Yiyang 413000, Peoples R China.

[Li, Zhe; Li, Z; Zhong, Qikang; Jiang, Jishui; Wu, Jiade] Cent South Univ, Sch Architecture & Art, Changsha 410075, Peoples R China.

[Li, Zhe; Zhong, Qikang; Jiang, Jishui; Wu, Jiade] Hunan Prov Key Lab Low Carbon Hlth Bldg, Changsha 410075, Peoples R China.

[Bedra, Komi Bernard] Key Lab Key Technol Digital Urban Rural Spatial Pl, Yiyang, Peoples R China.

[Long, Canrong] Zhejiang Univ Univ Edinburgh Inst, Haining 314400, Peoples R China.

通讯机构：

[Li, Z ] C

Cent South Univ, Sch Architecture & Art, Changsha 410075, Peoples R China.

语种：

英文

关键词：

Outdoor thermal comfort;Machine learning;Traditional village;Bayesian optimization;Shapley additive explanations

期刊：

Building and Environment

ISSN：

0360-1323

年：

2025

卷：

282

页码：

113315

DOI：

10.1016/j.buildenv.2025.113315

基金类别：

CRediT authorship contribution statement Jishui Jiang: Writing – review & editing, Writing – original draft, Investigation, Formal analysis, Data curation, Conceptualization. Zhe Li: Supervision, Resources, Project administration, acquisition. Komi Bernard Bedra: Writing – review & editing, Visualization, Validation, Software. Canrong Long: Visualization, Software, Methodology. Jiade Wu: Visualization, Validation, Investigation. Qikang Zhong: Validation, Supervision, Investigation.

机构署名：

本校为第一机构

院系归属：

建筑与城市规划学院

摘要：

This study developed explainable machine learning (ML) models to enhance outdoor thermal comfort (OTC) prediction in traditional villages, aiming to improve resident health and rural tourism. A village-specific OTC dataset was established through field experiments, and eight ML algorithms were utilized to predict thermal sensation (TSV), comfort (TCV), and acceptance (TAV) votes, with performance compared to empirical and mechanism models. Feature engineering, data resampling, and hyperparameter optimization were applied to optimize ML models, while the Shapley Additive exPlanations (SHAP) fra...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

Predicting Outdoor Thermal Comfort in Traditional Villages: An Explainable Machine Learning Framework Integrating Model Optimization, Seasonal Variability, and Tourist-Resident Insights

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问