A Statistical Process Control Chart Approach for Occupancy Estimation in Smart Buildings

Smart buildings entail several challenges including how to integrate occupants and improve their consciousness towards the energy management systems. For this purpose, occupancy estimation problem has gained increasing attention in smart buildings during the past few years and many approaches have been proposed. Greater number of these approaches has been based on supervised learning techniques. Interactive learning is a new sort of supervised learning approach used to estimate the number of occupants in buildings. This paper proposes a new solution to estimate the number of occupants based on interactive learning concept using the Multi-Layer Perceptron (MLP) regressor and statistical process control charts to avoid useless interactions with users. Statistical process control charts are deployed to ensure data analysis robustness for the purpose of deciding if an interaction with the occupant is necessary or not. Experiments in an office equipped with 30 sensors have been conducted and proved the merits of the proposed framework.