• Mrs. Snigdha Kesh
• Arinjoy Deb
• Injamamul Haque
• Abhay Sen

Children with autism face a developmental disorder that tends to worsen over time, characterized by challenges in communication and interaction, along with restricted behaviours. Early detection and comprehensive treatment can significantly improve the quality of life for these children, allowing them to lead fulfilling lives. However, in wealthier nations, the diagnosis of autism in children may be delayed due to the absence of specific medical tests, requiring a professional diagnosis that depends on extensive observation over time. In our study, we employed artificial intelligence (AI) technologies, using images considered irrelevant by most, to identify autism in children. We tested five different algorithms to gauge the presence of Autism Spectrum Disorder (ASD) in children: Multilayer Perceptron (MLP), Random Forest (RF), Gradient Boosting Machine (GBM), AdaBoost (AB), and Convolutional Neural Network (CNN). Our comparison of the performance of these algorithms revealed that CNN significantly surpassed traditional machine learning methods in accuracy, achieving a rate of 92.31%, thus proposing a CNN- based model for the early detection of ASD in children as the most effective approach.

Convolutional Neural Network (CNN), Autism Spectrum Disorder and Machine Learning. The platforms for applied behaviour analytics with AI augmentation's systems architecture are shown.

"Augmented Behavior Analysis for Children with Developmental Disabilities: Building Towards Precision Treatment", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.302-307, May-2024, Available :http://www.jetir.org/papers/JETIRGG06048.pdf

"Augmented Behavior Analysis for Children with Developmental Disabilities: Building Towards Precision Treatment", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. pp302-307, May-2024, Available at : http://www.jetir.org/papers/JETIRGG06048.pdf