Smart Home Monitoring House Fence Using Face Recognition Based On The IoT

Abstract

Technological developments have become very important in modern life, including the security sector. Currently, there is more and more sophisticated equipment and security systems based on the latest technology; the increasing crime rate, especially theft and robbery, encourages the need for a more effective and efficient security system. This research aims to build a prototype for smart home monitoring of home devices, namely house fences, using facial recognition based on the Internet of Things. The dataset required in this research is 11,500 facial images in 5 categories. Training of the machining learning model using a convolutional neural network was carried out several times to produce a model with the best accuracy. The test was carried out on 122 samples and produced an accuracy value of 86% and an average telegram response of 7 seconds, so that it could monitor house fences in real time.