Occupancy and indoor environment quality sensing for smart buildings

Abstract

This paper presents a technique to determine the occupancy and indoor environment quality (IEQ) in buildings by enhancing physical measurements from a distributed sensor network with a statistical estimation method. The research is motivated by the increasing demand for improving energy efficiency while maintaining healthy and comfortable environment in buildings. Features representing the occupancy level and the relative changes are extracted from a suite of sensors: passive infra-red (PIR) sensors, Carbon Dioxide (CO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) concentration sensors, and relative humidity (RH) sensors, which are networked and installed in a laboratory. An Autoregressive Hidden Markov Model (ARHMM) has been developed to model the occupancy pattern, based on the measurements, given its ability to establish correlations among the observed variables. The result is compared with that obtained from the classical Hidden Markov Model (HMM) and Support Vector Machines (SVM), which indicates that the ARHMM estimation method performed better than the other two methods, with an average estimation accuracy of 80.78%.