Classification of adult autistic spectrum disorder using machine learning approach

Autism spectrum disorder (ASD) is a neurological-related disorder. Patients with ASD have poor social interaction and lack of communication that lead to restricted activities. Thus, early diagnosis reliable system crucial as the symptoms may affect patient’s entire lifetime. Machine learning approaches are an effective efficient method for prediction disease. The study mainly aims achieve accuracy classification using variety machine approaches. dataset comprises 16 selected attributes inclusive 703 patients non-patients. experiments performed within simulation environment analyzed Waikato knowledge analysis (WEKA) platform. Linear support vector (SVM), k-nearest neighbours (k-NN), J48, Bagging, Stacking, AdaBoost, naïve bayes methods used compute status on subject 3, 5, 10-folds cross validation. then computed evaluate accuracy, sensitivity, specificity proposed methods. comparative result between has shown linear SVM, produce highest at 100% lowest error rate.