Investigating the Effects of Parameter Tuning on Machine Learning for Occupant Behavior Analysis in Japanese Residential Buildings

Global warming is currently progressing worldwide, and it is important to control greenhouse gas emissions from the perspective of adaptation and mitigation. Occupant behavior is highly individualized and must be analyzed to accurately determine a building's energy consumption. However, most of the resident behavior models in existing studies are based on statistical methods, and their accuracy in parameter tuning has not been examined. The accuracy of heating behavior prediction has been studied using three different methods: logistic regression, support vector machine (SVM), and deep neural network (DNN). The generalization ability of the support vector machine and the deep neural network was improved by parameter tuning. The parameter tuning of the SVM showed that the values of C and gamma affected the prediction accuracy. The prediction accuracy improved by approximately 11.9%, confirming the effectiveness of parameter tuning on the SVM. The parameter tuning of the DNN showed that the values of the layer and neuron affected prediction accuracy. Although parameter tuning also improved the prediction accuracy of the DNN, the rate of increase was lower than that of the SVM.