PMV Dimension Reduction Utilizing Feature Selection Method: Comparison Study on Machine Learning Models

Since P.O. Fanger proposed PMV, it has been the most widely used index to estimate thermal comfort. However, in some cases, is challenging measure all six parameters within indoor spaces, which are essential for PMV estimation; a couple of parameters, such as Clo or Met, tend show large deviation accuracy. For these reasons, several studies have suggested methods but their accuracies were significantly compromised. In this vein, study way reduce dimensions prediction utilizing machine learning method, order provide fast calculations without compromising its Throughout study, influential features pinpointed using PCA, Best Subset, and Gini Importance, with each model compared others. The results showed that PCA ANN achieved highest accuracy 89.70%, combination Subset Random Forest fastest performance among all.