Preliminary study of learning individual thermal complaint behavior using one-class classifier for indoor environment control

• Published in: Building and environment Vol. 72; pp. 201 - 211
• Main Authors: Zhao, Qianchuan, Zhao, Yin, Wang, Fulin, Jiang, Yi, Zhang, Fan
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.02.2014; Elsevier
• Subjects: Applied sciences; Buildings; Buildings. Public works; Commercial building; Computation methods. Tables. Charts; Exact sciences and technology; False detection rate; Human complaint; Miss detection rate; One-class classifier; Pareto-frontier; Structural analysis. Stresses; Two-stage classifier; Types of buildings; Two-stage classifier; Miss detection rate; One-class classifier; Pareto-frontier; Human complaint; False detection rate; Office building; Validation; Indoor climate; Thermal behavior; Classifier; Experimental study; Modeling; Learning; Experimental result; Individual behavior; Detection
• ISSN: 0360-1323; 1873-684X
• DOI: 10.1016/j.buildenv.2013.11.009

This paper proposes a data-driven learning method to describe the personal thermal complaint behavior in a complaint-driven environment control system. The complaint-driven system only uses personal human complaints to control the personal office environment. It avoids the user's direct control on the set-point of the room, which usually results in unreasonable and uncomfortable set-point. A two-stage classifier model is proposed, using personal thermal compliant data with respect to the transient and steady complaint behaviors. The classifier structure is developed based on the properties of human thermal perception with parameters to learn for different users. Quantitative results using experimental data show that the model has lower false negative rate than traditional data-driven classification model and acceptable false detection rate. Practical implementation and subjects' questionnaire evaluation demonstrate the satisfying performance of the model in real environment control. We also discuss the limitations and potential extensions of the model at the end of this paper. •We proposed a one-class classifier model to describe individual thermal complaints.•The model structure is based on literature and experimental observations.•Two-stage model structure deals with the transient complaint behavior.•An on-line test for the model was carried and obtained satisfying results.