The Squeaky wheel: Machine learning for anomaly detection in subjective thermal comfort votes

The Squeaky wheel: Machine learning for anomaly detection in subjective thermal comfort votes

TitleThe Squeaky wheel: Machine learning for anomaly detection in subjective thermal comfort votes
Publication TypeJournal Article
Year of Publication2019
AuthorsZhe Wang, Thomas Parkinson, Peixian Li, Borong Lin, Tianzhen Hong
JournalBuilding and Environment
Volume151
Pagination219 - 227
Date Published03/2019
ISSN03601323
Keywordsanomaly detection, ASHRAE global thermal comfort database, K-nearest neighbors, Multivariate Gaussian, Occupancy responsive controls, Subjective votes, thermal comfort
Abstract

Anomalous patterns in subjective votes can bias thermal comfort models built using data-driven approaches. A stochastic-based two-step framework to detect outliers in subjective thermal comfort data is proposed to address this problem. The anomaly detection technique involves defining similar conditions using a k-Nearest Neighbor (KNN) method and then quantifying the dissimilarity of the occupants' votes from their peers under similar thermal conditions through a Multivariate Gaussian approach. This framework is used to detect outliers in the ASHRAE Global Thermal Comfort Database I & II. The resulting anomaly-free dataset produced more robust comfort models avoiding dubious predictions. The proposed method has been proven to effectively distinguish outliers from inter-individual variabilities in thermal demand. The proposed anomaly detection framework could easily be applied to other applications with different variables or subjective metrics. Such a tool holds great promise for use in the development of occupancy responsive controls for automated building HVAC systems.

URLhttps://linkinghub.elsevier.com/retrieve/pii/S0360132319300861
DOI10.1016/j.buildenv.2019.01.050
Short TitleBuilding and Environment