International Research Journal of Education and Technology

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by a diverse range of symptoms affecting social interaction, communication, and behavior. This paper explores the intricate nature of ASD, detailing its subtypes and the challenges individuals face in various domains of functioning. Given the heterogeneity of ASD, there is a pressing need for effective diagnostic and intervention strategies that cater to the unique profiles of those affected. This paper investigates the application of supervised machine learning algorithms, particularly Support Vector Machine (SVM), in identifying sensory dysfunction and predicting behavioral outcomes in individuals with ASD. By leveraging labeled data on sensory processing patterns and behavioral assessments, this paper aims to develop an SVM model that accurately classifies sensory profiles and provides insights into potential therapeutic interventions. The findings underscore the significance of integrating advanced machine learning techniques into clinical practice, thereby enhancing the understanding of sensory sensitivities and informing personalized treatment strategies. Ultimately, this paper highlights the transformative potential of SVM in improving the quality of care for individuals with ASD, paving the way for future research and development in this critical area.

Keywords: ASD, SVM, Kernal functions, Neurodevelopment, ASD Child.