Artificial Intelligence Helps Protect Smart Homes against Thieves

Abstract

Interaction with the environments in which humans live is increasing more and more, and Artificial Intelligence (AI) offers significant contributions to this. Although the topic of smart homes has attracted a great deal of attention from researchers, the AI-based application in this area is still in its infancy. In this study, a home security automation system, which is quite simple, but smart and AI-based, is proposed. When the home-dwellers were not at home, the home lighting system tried to be managed with AI at night, as if life was still there. The AI-based smart home physical design was done using Arduino equipment and was tried to be adapted to the real-life environment with software support. As if there was someone at home, a special dataset, which was consisted of nine inputs, one output vector and about 5500 samples was created to turn on/off the home lights in a manner suitable for night life. The home lighting system was successfully managed using an AI-based system that learns nightlife lighting habits. The proposed system performance was tested in support of commonly used machine learning classification algorithms such as Multi-layer perceptron (MLP), Linear support vector machine (L-SVM), Gaussian Naive Bayes (NB), and linear discriminant analysis (LDA). The accuracy values of MLP, L-SVM and NB algorithms were 96.69%, 94.98% and 91.23%, respectively. Our results show that a home with AI could be safer and more secure against theft.