A Machine Learning Way to Classify Autism Spectrum Disorder

In recent times Autism Spectrum Disorder (ASD) is picking up its force quicker than at any other time. Distinguishing autism characteristics through screening tests over the top expensive and tedious. Screening of same a challenging task, classification must be conducted with great care. Machine Learning (ML) can perform in this problem. Most researchers have utilized ML strategy to characterize patients typical controls, among which support vector machines (SVM) are broadly utilized. Even though several studies been done utilizing various methods, these investigations didn't give complete decision about anticipating qualities regarding distinctive age groups. Accordingly, paper plans locate best technique for ASD classi-fication out SVM, K-nearest neighbor (KNN), Random Forest (RF), Naïve Bayes (NB), Stochastic gradient descent (SGD), Adaptive boosting (AdaBoost), CN2 Rule Induction using 4 datasets taken from UCI repository. The accuracy (CA) we acquired after experimentation as follows: case adult dataset SGD gives 99.7%, adolescent RF 97.2%, child 99.6%, toddler Ada-Boost 99.8%. spectrum quotients (AQs) varied sce-narios toddlers, adults, adolescents, children that include positive predic-tive value scaling purpose. AQ questions referred topics attention detail, switching, communication, imagination, social skills.