Mobile Application for Basic Computer Troubleshooting using TensorFlow Lite

Abstract

This paper presents an application for troubleshooting computer problems using the TensorFlow and deep learning techniques. The functionality of the proposed application contains the problem lists by searching problems with text and photographs. Deep learning technique has been applied for searching information through TensorFlow Lite library. The main components of the proposed application include the classification model of computer problems and the deep learning through the TensorFlow library in order to compare the classified images, which was being learned to classify two types of images, namely, the blue screen and black screen problems. Experiments has used the 100 samples of each blue screen and black screen. The results showed that the success rate of classification of blue screen is 80%and is 90% for black screen problem.