Accurate Autism Spectrum Disorderprediction using Support Vector Classifierbased on Federated Learning (SVCFL)

The path to an autism diagnosis can be long and difficult, and delays can have serious consequences. Artificialintelligence can completely change the way autism is diagnosed, especially when it comes to situations where it isdifficult to see the first signs of the disease. AI-based diagnostic tools may help confirm a diagnosis or highlight theneed for further testing by analyzing large volumes of data and uncovering patterns that may not be immediatelyapparent to human evaluators. After a successful and timely diagnosis, autism can be treated through artificialintelligence using various methods. In this article, by using four datasets and gathering them with the federatedlearning method and diagnosing them with the support vector classifier method, the early diagnosis of this disorderhas been discussed. In this method, we have achieved ۹۹% accuracy for predicting autism spectrum disorder andwe have achieved ۱۳% improvement in the results

کلیدواژه ها:

Autism spectrum disorder ، Support Vector Classifier ، prediction ، federated learning ، SVCAL.