Optimization of Regional - Convolutional Neural Network for Electricity Conservation Using Arduino

Abstract

The demand for electrical energy in developing countries is apparently increasing thereby creating a large gap between the availability of the electrical resource and its growing demand. Globally reputed energy economists have recognized that 25% of reduction in energy consumption can be achieved by adopting efficient energy conservation techniques This paper presents one of the simplest ways of conservation techniques that enables the electric power supply only when it is actually needed. It is an automatic system that functions with the existing CCTV surveillance camera to enable/disable the electric power supply, only in the location where human is present / absent respectively. The proposed approach is demonstrated without the use of sensors, based on Regional Convolutional Neural Network (R-CNN). A new R-CNN model is constructed for CHOKEPOINT dataset and the optimization is done using Nadam technique. The results are then fed into Arduino micro controller to control the electric supply based on the presence/absence of human in the particular region.