Abstract
Hysterical conversion has similar cognition and behaviours to those in the case of ASD; it is, therefore, complex when diagnosing and classifying the condition. The majority of employed diagnostic tests are cross-sectional and fail to describe the developmental and clinical features of ASD; for this reason, they are pretty inaccurate in the diagnosis of ASD and thus cause disparities in the efficiency of the therapeutic interventions used. The present study's research contribution is a new application of deep learning that aims to analyse the spectrum of ASD with gradient-based classifications. In this case, we use a DL model trained on many traits of behaviour, cognition, and genetics because of the need to capture the idiosyncrasies of the autism spectrum. A blend of CNNs and RNNs with attention mechanisms to ensure a rich and high-dimensional representation of ASD traits is considered in this work. These representations are enhanced and diagnosed by employing the gradient-based classification algorithm to improve the categorisation for ASD and give a more detailed and accurate classification result. Suggestively pointing to the opportunities to use deep learning procedures for neurodevelopmental disorders, the results suggest that the accuracy and specificity of the diagnostic assessment for ASD are enhanced. This research creates a platform for future research that will undertake a periodic and intensive evaluation of ASD with the ultimate aim of identifying particular interventions that may help reduce the effects of ASD on the affected and enhance their standard of living.
Recommended Citation
Sar, Ayan; Mahdi, Hussain Falih; Aich, Sumit; Singh, Pranav; and Choudhury, Tanupriya
(2025)
"Comparative Study based on Continuous Analysis of Autism Spectrum Disorder Using Advanced Deep Learning with Model Interpretability Insights,"
Iraqi Journal for Computer Science and Mathematics: Vol. 6:
Iss.
3, Article 16.
DOI: https://doi.org/10.52866/2788-7421.1291
Available at:
https://ijcsm.researchcommons.org/ijcsm/vol6/iss3/16