Edge-Based Real-Time Occupancy Detection System through a Non-Intrusive Sensing System

Building automation and the advancement of sustainability and safety in internal spaces benefit significantly from occupancy sensing. While particular traditional Machine Learning (ML) methods have succeeded at identifying occupancy patterns for specific datasets, achieving substantial performance in other datasets is still challenging. This paper proposes an occupancy detection method using non-intrusive ambient data and a Deep Learning (DL) model. An environmental sensing board was used to gather temperature, humidity, pressure, light level, motion, sound, and Carbon Dioxide (CO2) data. The detection approach was deployed on an edge device to enable low-cost computing while increasing data security. The system was set up at a university office, which functioned as the primary case study testing location. We analyzed two Convolutional Neural Network (CNN) models to confirm the optimum alternative for edge deployment. A 2D-CNN technique was used for one day to identify occupancy in real-time. The model proved robust and reliable, with a 99.75% real-time prediction accuracy.

Automated summary

This paper proposes an occupancy detection method using non-intrusive ambient data and a Deep Learning (DL) model, which significantly benefits building automation and sustainability. The method utilizes an edge device for low-cost computing and increased data security, and achieves a 99.75% real-time prediction accuracy in testing at a university office.