Visible Light Based Occupancy Inference Using Ensemble Learning

As a key component of building management and security, occupancy inference through smart sensing has attracted a lot of research attention for nearly two decades. Recently, a cutting edge technique visible light sensing (VLS) that utilizes the LED luminaires as light sensors has shown its promising application potentials in occupancy inference as it piggybacks on pervasive lighting infrastructure without extra equipment deployment. Although existing inference algorithms based on the VLS data set can achieve high accuracy, the performance degrades when the occupants are moving. This paper focuses on the occupancy inference issue and presents an ensemble learning algorithm to improve the inference accuracy. We use heterogeneous learning algorithms to generate diverse learners. Consequently, we adopt forward sequential pruning to enhance the ensemble that pursues inference error minimization. We conduct extensive experiments based on the field data. The experiment results show that the proposed algorithm is able to improve inference accuracy, especially for highly dynamic occupancy data set.