• Md. Baig Mohammad
• S.Siva Sankar Reddy
• C. Pavan Surya Prakash
• Md. Asif Shereif

Autism Spectrum Disorder (ASD) poses significant challenges to the affected individuals daily lives, making early intervention crucial for mitigating its severity. In this paper, we present a comprehensive framework aimed at evaluating various Machine Learning (ML) techniques for the early detection of ASD) with a focus on real-time prediction through a user-friendly graphical user interface (GUI).These strategies are applied to feature -scaled datasets, which are then subjected to classification using seven different and popular ML algorithms: Ada Boost (AB), Random Forest (RF), k-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), Logistic Regression (LR), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA).We conducted experiments on four standard ASD datasets representing different age groups (Toddlers, Adolescents, Children and Adults). To evaluate the classification outcomes, we employ various statistical measures such as Accuracy, Receiver Operating Curve (ROC) curve, F1 score, Specificity, Sensitivity etc. Through this analysis, the best-performing classification methods for each ASD dataset has been identified. Overall, our purposed framework Demonstrates promising results compared to existing approaches for the early detection of ASD

Autism Spectrum Disorder (ASD), Early detection, Machine learning, Classification, feature Scaling, Statistical Measures.

"A Machine Learning Framework For Early-Stage Detection Of Autism", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.h781-h784, May-2024, Available :http://www.jetir.org/papers/JETIR2405798.pdf

"A Machine Learning Framework For Early-Stage Detection Of Autism", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. pph781-h784, May-2024, Available at : http://www.jetir.org/papers/JETIR2405798.pdf