A Transfer Active Learning Framework to Predict Thermal Comfort



Published Jun 4, 2023
Annamalai Natarajan Emil Laftchiev


Personal thermal comfort is the feeling that individuals have about how hot, cold or comfortable they are. Studies have hown 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 dataset 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 0.822±0.05, while the supervised learning approach achieves a mean error of 0.852±0.04.

Abstract 379 | PDF Downloads 296



thermal comfort, transfer learning, active learning, office work performance

Belluck, P. (2015). Chilly at work? office formula was devised for men. New York Times.
Bonilla, E. V., Chai, K. M., & Williams, C. (2008). Multitask gaussian process prediction. In Advances in neural information processing systems (nips) (pp. 153–160).
Buller, M. J., Tharion, W. J., Cheuvront, S. N., Montain, S., Kenefick, R., Castellani, J., . . . Hoyt, R. W. (2013). Estimation of human core temperature from sequential heart rate observations. Physiological measurement, 347, 781-98.
Burbidge, R., Rowland, J. J., & King, R. D. (2007). Active learning for regression based on query by committee. In International conference on intelligent data engineering and automated learning (pp. 209–218).
Cai, W., Zhang, Y., & Zhou, J. (2013). Maximizing expected model change for active learning in regression. In International conference on data mining (icdm) (pp. 51–60). Ergonomics of the thermal environment – analytical determination and interpretation of thermal comfort using calculation of the pmv and ppd indices and local thermal comfort criteria (Tech. Rep.). (2005). ISO 7730.
Evgeniou, T., & Pontil, M. (2004). Regularized multi–task learning. In Acm sigkdd international conference on knowledge discovery and data mining (pp. 109–117).
Fanger, P. O. (1967). Calculation of thermal comfort: Introduction of a basic comfort equation. ASHRAE Transactions, 73.
Farhan, A. A., Pattipati, K., Wang, B., & Luh, P. (2015). Predicting individual thermal comfort using machine learning algorithms. In International conference on automation science and engineering (case) (pp. 708–713).
Foundation, P. S. (2010). Python language reference, version 2.7. https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.minimize.html.
Geman, S., Bienenstock, E., & Doursat, R. (2008). Neural networks and the bias/variance dilemma. Neural Networks, 4(1).
Haldi, F. (2010). Towards a unified model of occupants’ behaviour and comfort for building energy simulation (Unpublished doctoral dissertation). EPFL.
Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction. Springer.
Hedge, A., Wafa, S., & Anshu, A. (2005). Thermal effects on office productivity. In Proceedings of the human factors and ergonomics society annual meeting (Vol. 49, pp. 823–827).
Huang, C.-C. J., Yang, R., & Newman, M. W. (2015). The potential and challenges of inferring thermal comfort at home using commodity sensors. In Proceedings of the international joint conference on pervasive and ubiquitous computing (ubicomp) (pp. 1089–1100).
IJzerman, H., & Semin, G. R. (2009). The thermometer of social relations mapping social proximity on temperature. Psychological Science, 20(10), 1214-1220. Indoor environmental input parameters for design and assessment of energy performance of buildings - addressing indoor air quality, thermal environment, lighting and acoustics (Tech. Rep.). (2006). European Standards Commission.
Jiang, L., & Yao, R. (2016). Modelling personal thermal sensations using c-support vector classification (c-svc) algorithm. Building and Environment, 99, 98–106.
Laftchiev, E., & Nikovski, D. (2016). An iot system to estimate personal thermal comfort. In World forum on internet of things (wf-iot) (p. 672-677).
Lewis, D. D., & Catlett, J. (1994). Heterogeneous uncertainty sampling for supervised learning. In Machine learning proceedings (p. 148 - 156). San Francisco, CA.
Natarajan, A., Gaiser, E., Angarita, G., Malison, R., Ganesan, D., & Marlin, B. (2014). Conditional random fields for morphological analysis of wireless ecg signals. In Acm conference on bioinformatics, computational biology, and health informatics (pp. 370–379).
O‘Neill, J., Delany, S. J., & MacNamee, B. (2017). Model-free and model-based active learning for regression. In Advances in computational intelligence systems (pp. 375–386). Springer.
Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Ranjan, J., & Scott, J. (2016). Thermalsense: Determining dynamic thermal comfort preferences using thermographic imaging. In Proceedings of the international joint conference on pervasive and ubiquitous computing (ubicomp) (pp. 1212–1222).
Schlader, Z. J., Stannard, S. R., & Mündel, T. (2010). Human thermoregulatory behavior during rest and exercise - a prospective review. Physiology & behavior, 99(3), 269–275.
Schwaighofer, A., Tresp, V., & Yu, K. (2005). Learning gaussian process kernels via hierarchical bayes. In Advances in neural information processing systems (nips) (pp. 1209–1216).
Settles, B. (2010). Active learning literature survey (Tech. Rep.).
Sugiyama, M. (2006). Active learning in approximately linear regression based on conditional expectation of generalization error. Journal of Machine Learning Research, 7, 141–166. Thermal environmental conditions for human occupancy (Tech. Rep.). (2013). ASHRAE.
Wang, X., Huang, T.-K., & Schneider, J. (2014). Active transfer learning under model shift. In International conference on machine learning (icml) (pp. 1305–1313).
Technical Papers