TR2018-156

A Transfer Active Learning Framework to Predict Thermal Comfort


    •  Natarajan, A., Laftchiev, E., "A Transfer Active Learning Framework to Predict Thermal Comfort", International Journal of Prognostics and Health Management Special Issue on PHM for Human Health & Performance, December 2018.
      BibTeX TR2018-156 PDF
      • @article{Natarajan2018dec,
      • author = {Natarajan, Annamalai and Laftchiev, Emil},
      • title = {A Transfer Active Learning Framework to Predict Thermal Comfort},
      • journal = {International Journal of Prognostics and Health Management Special Issue on PHM for Human Health \& Performance},
      • year = 2018,
      • month = dec,
      • url = {https://www.merl.com/publications/TR2018-156}
      • }
  • Research Areas:

    Artificial Intelligence, Data Analytics, Machine Learning

Abstract:

Personal thermal comfort is the feeling that individuals have about how hot, cold or comfortable they are. Studies have shown that thermal comfort is a key component of human performance in the work place and that personalized thermal comfort models can be learned from user labeled data that is collected from wearable devices and room sensors. These personalized thermal comfort models can then be used to optimize the thermal comfort of room occupants to maximize their performance. Unfortunately, personalized thermal comfort models can only be learned after extensive dataset collection and user labeling. This paper addresses this challenge by proposing a transfer active learning framework for thermal comfort prediction that reduces the burdensome task of collecting large labeled datasets for each new user. The framework leverages domain knowledge from prior users and an active learning strategy for new users that reduces the necessary size of the labeled dataset. When tested on a real data set collected from five users, this framework achieves a 70% reduction in the required size of the labeled dataset as compared to the fully supervised learning approach. Specifically, the framework achieves a mean error of 0.82+/- 0.05, while the supervised learning approach achieves a mean error of 0.85+/-0.04.