Bayesian prediction model of thermally satisfied occupants considering stochasticity due to inter- and intra-individual thermal sensation variations. (15th July 2022)

• Record Type: Journal Article
• Authors: Lim, Jongyeon; Choi, Wonjun; Akashi, Yasunori; Yoshimoto, Naoki; Ooka, Ryozo
• Is Part Of: Journal of building engineering. Volume 52(2022)
• Publication Date: 2022-07-15
• Subjects: Thermal sensation vote -- Thermal satisfaction -- Thermal comfort -- Ordinal probit regression -- Bayesian inference -- Predicted mean vote (PMV); Building -- Periodicals; 690.05
• DOI: 10.1016/j.jobe.2022.104414
• Languages: English
• ISSNs: 2352-7102

Abstract

Abstract: A data-driven probabilistic model is proposed to predict the group-level thermal satisfaction of occupants subjected to a given thermal condition. This model considers the inhomogeneity of inter- and intra-individual variations in thermal sensation votes (TSVs) on the basis that individual variations in TSVs are expected to be undispersed in extreme thermal conditions and scattered in conditions closely matching thermal neutrality. Additionally, unlike conventional deterministic linear regression models, the proposed model adopts an ordinal probit regression model to treat TSVs as ordinal rather than metric variables. Model parameters are estimated by using a Bayesian inference technique to capture the stochastic characteristics of occupants' TSVs. The model's effectiveness is validated against a subset of ASHRAE Global Thermal Comfort Database II. Compared with the conventional model, the proposed model more accurately predicts the variation in TSVs and the thermal conditions in which the occupants are most satisfied. Highlights: Data-driven probabilistic method was developed to predict thermal satisfaction rate. Bayesian inference was used for model training and parameter estimation. Stochasticity due to inter-/intra-individual thermal sensation variation was considered. Unlike deterministic models, this model predicts thermal sensation dispersion caused by unmeasurable factors. Model reproduces most satisfactory thermal condition and related satisfaction rate.