Title: Autism spectrum disorder detection using machine learning techniques

Authors: Abdelhakim Ridouh; Fayçal Imedjdouben; Sarra Mahi

Addresses: Scientific and Technical Research Center for the Development of Arabic Language, 16011, Algiers, Algeria ' Scientific and Technical Research Center for the Development of Arabic Language, 16011, Algiers, Algeria ' Scientific and Technical Research Center for the Development of Arabic Language, 16011, Algiers, Algeria

Abstract: Autism is a developmental disorder that occurs in early childhood and affects communication and social interaction; it includes specific and recurring patterns of behaviour. There is no specific cause for autism and there is no direct treatment for it. Symptoms appear in early childhood and early diagnosis allows for a rise in the recovery rate. In this paper, we present a method to characterise, identify, and classify some ASD data by using machine learning methods such as SVM, DT, NB, and KNN. The studies are carried out on some real ASD data collected from an international database of three categories (children, adolescents, and adults). To enrich the database, we collected more samples from Algeria. The estimation of the best value of parameters for each distribution is achieved by calculating three main parameters illustrated by the confusion matrix. The results illustrate the effectiveness of the proposed method with the best precision.

Keywords: autism detection; machine learning techniques.

DOI: 10.1504/IJBRA.2024.141770

International Journal of Bioinformatics Research and Applications, 2024 Vol.20 No.5, pp.495 - 516

Received: 22 Nov 2023
Accepted: 11 Mar 2024
Published online: 01 Oct 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article