Recommendation of indoor luminous environment for occupants using big data analysis based on machine learning

To provide an optimal luminous environment for occupants, a personalized luminous environment can be recommended by analyzing personal lifelog data. A basic platform for collecting lifelog data was constructed based on a previous study, and the collected data were classified into three types: task, fatigue, and emotion. Twelve tasks were defined, and appropriate ranges of illuminance and correlated color temperature (CCT) were recommended for each task. In addition, fatigue was divided into four levels, and the most appropriate values of illuminance and CCT were specified within the ranges recommended for each task. In addition, the lighting colors that can alter or improve emotions were designated by selecting the first and second priorities among the five emotions. Totally, 31,680 luminous environment data were processed based on the collected lifelog data, which were divided into training and test datasets. A machine learning (ML)-based luminous environment recommendation system was constructed by applying four ML algorithms (K-nearest neighbor, decision tree, random forest, and support vector machine). The system was designed to recommend an occupant-customized luminous environment based on the task type, fatigue level, and emotion class, and showed an accuracy of approximately 92% or higher.