Early Detection and Recommendation of Autism Spectrum Disorder Using Reinforcement Learning

DOI

10.2991/978-94-6239-616-6_11How to use a DOI?

Keywords

Autism Spectrum Disorder (ASD); Machine Learning; Reinforcement Learning (RL); Early Detection; Personalized Education; RF-XG Ensemble; Feature Selection

Abstract

The reliable early diagnosis of Autism Spectrum Disorder (ASD), a complex neurodevelopmental condition, continues to present significant difficulties for healthcare and educational systems. This research performs a methodical review of contemporary machine learning (ML) techniques applied to ASD identification. It further proposes an innovative framework based on Reinforcement Learning (RL) designed to connect diagnostic outcomes with customized intervention plans. Our analysis of existing literature reveals a common shortfall: many models achieve high classification accuracy but fail to translate these results into practical, individualized educational strategies. To overcome this limitation, we introduce a unified methodology. This approach employs an RF-XG ensemble classifier for the detection phase, which attains a 98% accuracy rate by leveraging four distinct ASD datasets, the Synthetic Minority Oversampling Technique (SMOTE) for data balance, and sophisticated feature selection. The output from this diagnostic model subsequently activates an RL-based recommendation system. This engine is engineered to produce tailored teaching methodologies that align with a child’s specific behavioral characteristics and symptom intensity. Unifying a detailed survey of current research with a proven technical framework, this study offers a scalable and data-centric tool that improves diagnostic reliability while also supporting personalized educational support for children on the autism spectrum.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - R. Raju
AU  - S. Sennila
AU  - S. Priyadharshini
AU  - T. Monisha
PY  - 2026
DA  - 2026/03/31
TI  - Early Detection and Recommendation of Autism Spectrum Disorder Using Reinforcement Learning
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 130
EP  - 144
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_11
DO  - 10.2991/978-94-6239-616-6_11
ID  - Raju2026
ER  -