1
Return

Multimodal fusion-based dynamic thermal comfort prediction for cross-subject generalization

delete2026-08-05
delete0
PRE
AI
X
Xiaojing Li
J
Jing Shi
J
Jiajun Xu
J
Jingsi Zhang
Y
Yi Gao
X
Xiang Zhou
罗
罗茂辉 (Maohui Luo) *
DOI：10.1016/j.buildenv.2026.115092delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• A subject-independent multimodal thermal comfort model was developed. • Only environmental temperatures and infrared images were used. • CBAM and FiLM improved thermal feature extraction and multimodal fusion. • Grad-CAM was employed to enhance model interpretability.

Journal

Building and Environment cover
Building and Environment
IF:
7.6
Papers:
1.3W
Citations:
6.6W

Organization

T
tongji university
Scholars:
7.5W
Papers: 5.8W
Citations: 98
M
Midea Corporate Research Center
Scholars:
2
Papers: 2
Citations: 0
Cited Papers

Cited Papers

Citing Papers

Citing Papers