Abstract :

Autism Spectrum Disorder (ASD) Is A Complex Neurodevelopmental Condition That Affects Communication, Behavior, And Social Interaction, Typically Emerging In Early Childhood And Often Persisting Into Adulthood. Early Detection Is Essential, As Timely Intervention Can Significantly Improve Developmental Outcomes And Overall Quality Of Life. This Study Proposes A Deep Learning–based Framework For The Automated Early Detection Of ASD Using Behavioral Responses And Demographic Attributes.The AUTISM Dataset From The UCI Repository Is Used In This Research. Data Preprocessing Includes Handling Missing Values, Applying Label Encoding For Categorical Variables, And Scaling Numerical Features To Improve Consistency And Enhance Classification Accuracy. Multiple Machine Learning Algorithms—including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naïve Bayes, And Logistic Regression—were Evaluated Alongside Deep Learning Models Such As Artificial Neural Networks (ANNs) And Convolutional Neural Networks (CNNs). While Traditional Machine Learning Classifiers Achieved Moderate Accuracy, The CNN Model Outperformed All Others, Achieving 100% Accuracy On The Processed Dataset.To Further Improve Robustness And Generalization Capability, An Ensemble Framework Integrating CNNs With Conventional Machine Learning Classifiers Using A Soft-voting Mechanism Was Developed. The Optimized Model, Together With Its Data Preprocessing Pipeline, Was Deployed As An Interactive Web Application Using The Flask Framework, Allowing Users To Input Screening Information And Receive Real-time ASD Predictions. This System Provides An Accessible, Efficient, And Cost-effective Tool For Preliminary ASD Screening, Supporting Healthcare Professionals, Caregivers, And Families, Particularly In Regions With Limited Diagnostic Resources. Keywords:-Autism Spectrum Disorder (ASD), Early Detection, Deep Learning, Convolutional Neural Network (CNN), Flask Framework, Health Informatics.

Published:

14-11-2025

Issue:

Vol. 25 No. 11 (2025)

Page Nos:

110-119

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite