DefinePK

Abstract

In this study, we provide a machine learning framework for ASD early diagnosis that makes use of four remarkable featurescaling methods and eight main machine learning algorithms. The suggested design makes use of four outstanding featurescaling (FS) methods: quantile transformer (QT), power transformer (PT), normaliser, and max abs scaler (MAS). For thefeature-scaled datasets, eight trustworthy machine learning methods are utilised: AdaBoost (AB), Random forest (RF),decision Tree (DT), k-Nearest neighbours (KNN), Gaussian Naïve Bayes (GNB), Logistic Regression (LR), guide Vectorsystem (SVM), and Linear Discriminant analysis (LDA). The study utilises four standard datasets on ASD: infants, youngadults, children, and adults. Basic function selection approaches and primary type algorithms for every ASD dataset areobserved. To get the most reliable results, use the normaliser FS on younger children and the QT FS method on older adultsand teens. In order to rank the important attributes in order of importance, four feature selection techniques (FSTs) areused: information gain attribute evaluator (IGAE), gain ratio attribute evaluator (GRAE), relief F attribute evaluator (RFAE),and correlation attribute evaluator (CAE). These FSTs are used to assess the risk factors for autism spectrum disorder (ASD).Results from using the proposed paradigm for early ASD diagnosis are better than those from using current methods.