Sistema domótico para personas con discapacidad visual mediante inteligencia artificial y reconocimiento de voz

Abstract

This research project aims to implement a prototype of a home automation system for visually impaired people through artificial intelligence and voice recognition, to improve the quality of life of visually impaired people in their homes, to fulfill this purpose was carried out an analysis of the current state of the homes of such people, through a survey of visually impaired people registered in the "School of Specialized Basic Education Cardinal Julius Doephner" in the Canton Ambato, where the lack of accessibility, access control, lighting control, control of electronic devices and security in the homes were notorious, thus establishing the use of the benefits of home automation and the main requirements they need for home management, hardware and free software that will help in the implementation of the prototype to reduce the cost. The research project developed is composed of a voice recognition system with artificial intelligence through the use of the Raspberry PI 4 computer, in which the automatic learning system was developed in TensorFlow that allows the training of neural networks for the recognition of a specific voice for the general control of the system, this will help to solve problems with better quality and low costs without the need to modify the infrastructure of the houses to be controlled.