Unsupervised Personal Thermal Comfort Prediction via Adversarial Domain Adaptation

被引：9

作者：

Das, Hari Prasanna ^{[1
]}

Schiavon, Stefano ^{[2
]}

Spanos, Costas J. ^{[1
]}

机构：

[1] Univ Calif Berkeley, Dept Elect Engn & Comp Sci, Berkeley, CA 94720 USA

[2] Univ Calif Berkeley, Ctr Built Environm, Berkeley, CA USA

来源：

BUILDSYS'21: PROCEEDINGS OF THE 2021 ACM INTERNATIONAL CONFERENCE ON SYSTEMS FOR ENERGY-EFFICIENT BUILT ENVIRONMENTS | 2021年

基金：

新加坡国家研究基金会;

关键词：

Thermal Comfort; Domain Adaptation; Transfer Learning;

D O I：

10.1145/3486611.3492231

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Personal thermal comfort models aim to predict an individual's thermal comfort response, instead of the average response of a large group. However, conducting large-scale experiments to develop such models for general occupants of a building is time and resource-intensive. At the same time, the developed models for experimental subjects do not always generalize to other building occupants. In this work, we propose a transfer learning framework, using Adversarial Domain Adaptation (ADA) to develop personal thermal comfort predictors for target occupants in an unsupervised manner. We also discuss inherent assumptions governing domain adaptation in this application and relevant future works.

引用

页码：230 / 231

页数：2