Autism Spectrum Disorder (ASD) Detection Using Machine Learning Algorithms

Abstract Some diseases are characterized by persistent deficits in brain activity. Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder. It appears early childhood and evolves throughout life needs to be detected accelerate the treatment recovery process. These may using medical imaging techniques. In this paper, we present machine learning algorithms allowing detect peoples with ASD from normal peoples. We used data ABIDE dataset. tested 3 algorithms: Support Vector Machines (SVM), Long Short-Term Memory (LSTM) Convolutional Neural Network (CNN). The best result was obtained CNN algorithm an accuracy equal 95%.