A Novel Methodology to Identify Autism Disorder in Earlier Stages using Artificial Intelligence Assisted Hybrid Learning Scheme

In this groundbreaking study, we introduce a novel methodology for the early identification of autism disorder, a crucial step towards more effective intervention and support. Our approach, known as the Artificial Intelligence Assisted Hybrid Learning Scheme (AIHLS), capitalizes on the synergy between cutting-edge transfer learning techniques, specifically Xception, and the XGBoost Classifier. By combining the strengths of these advanced technologies, our method offers a promising avenue for the early detection of Autism Disorder in its nascent stages. When Xception’s feature extraction capabilities are combined with the predictive prowess of XGBoost Classifier, the result is a potent framework capable of addressing complex problems in various domains. This combination offers the advantage of capturing fine-grained image features through Xception and subsequently leveraging XGBoost’s ability to make accurate predictions based on these features. This significant advancement has the capacity to transform the landscape of autism diagnosis, offering the promise of earlier and more precise assessments. Such advancements hold the potential to enhance the overall quality of life for individuals on the autism spectrum as well as their families. In comparison to conventional models, the proposed model has demonstrated an outstanding accuracy rate of 97.11%, underscoring its remarkable performance.