Occupancy detection based on Spiking Neural Networks for green building automation systems

Abstract

Occupancies in building have effects on construction equipment operation and building energy consumption, which rely in two aspects: first, there are occupancies or not in a building zone determines whether energy consuming equipments (such as ventilation, air-conditioning equipment, lighting, and so on) turn on or not; secondly, human energy-saving awareness and behavior affect building energy efficiency. To achieve more comfortable environment and lower energy consumption, a building automation system will inevitably need personnel spatio-temporal information in a green building. However, there is lack of effective personnel information analysis tools as yet. A novel Spiking Neural Networks (SNN) multi sensor information fusion model has been proposed in this paper. SNN, the third generation of neural network models, is more closer to the essence of the organism information process than the former two generation neural network models. By mapping the relationships between sensors and corresponding neurons, a SNN information fusion model was established. The simulation results verified the effectiveness and feasibility of the proposed approach.