• Saniya B Roshan
• Pratiksha P Chavan
• Subrat Bakliwal
• Rishav
• Ashwini Tuppad

Autism spectrum disorder (ASD) affects approximately one in 36 children globally. Early diagnosis is crucial for timely intervention and improved outcomes. Deep learning models have enhanced early ASD detection by boosting accuracy and efficiency. Combining neuroimaging, genetics, and behavioural data with multimodal deep learning methods can increase early diagnosis precision. It leverages a diverse dataset comprising individuals across various age groups: infants (0-3 years old), children (4-12 years old), and elderly individuals (11 years and older). The core innovation lies in the utilization of Convolutional Neural Network (CNN) based visual autistic detection algorithms tailored for each age group. Through meticulous training and evaluation, this research endeavors to deliver accurate and age-specific predictive models for ASD, contributing significantly to early intervention and personalized care strategies for individuals on the autism spectrum.

"A DEEP LEARNING APPROACH FOR PREDICTION OF AUTISM DISORDER USING MULTIMODAL DATA", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.h658-h664, June-2024, Available :http://www.jetir.org/papers/JETIR2406770.pdf

"A DEEP LEARNING APPROACH FOR PREDICTION OF AUTISM DISORDER USING MULTIMODAL DATA", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pph658-h664, June-2024, Available at : http://www.jetir.org/papers/JETIR2406770.pdf