A real-time occupancy detection system for unoccupied, normally and abnormally occupied situation discrimination via sensor array and cloud platform in indoor environment

•A system based on sensor array and cloud platform is developed for real-time indoor environment occupied situation detection.•All-subsets regression model is used for sensor contribution evaluation and realized the sensor array size reduction.•Unoccupied, normally and abnormally occupied situation can be precisely classified by WV-ELM with a precision of 97.32%. A real-time occupancy detection system based on the sensor array and cloud platform was developed for unoccupied, normally and abnormally occupied situation discrimination in indoor environment. The system used the indoor environmental data collected by sensor array. WV-ELM algorithm was combined with the proposed system to detect the real-time occupied situation in the indoor environment. According to the actual test results, the proposed system based on light and CO2 sensors realized a detection accuracy of 97.32% with running time less than 30 s. [Display omitted] Architecture of the occupancy detection system via sensor array and cloud platform. It is significant to detect the occupancy of indoor environment from the view of saving energy. In addition, occupied situation detection can help control the density of people in room to reduce the risk of disease transmission. In preliminary, we trained nine algorithm models on the existing occupancy dataset to select the optimum algorithm. Then, all-subsets regression model is used for feature selection (sensor contribution evaluation) to optimize the size of sensor array. As a result, the voting based weighted extreme learning machine (WV-ELM) model achieved the highest prediction accuracy and the combination of light and CO2 sensors could realize a satisfied classification result. Finally, a real-time occupancy detection system based on the sensor array and cloud platform was proposed. The system used the indoor environmental data collected by the sensor array. WV-ELM model was combined with the proposed system to detect the real-time occupied situation in the indoor environment. To verify their efficiency, the system was implemented in a laboratory to collect occupancy data for one week. According to the actual test results, the proposed system realized a detection accuracy of 97.32% with running time less than 30 s.