نوع مقاله : مقاله پژوهشی
عنوان مقاله English
نویسندگان English
Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder that affects physical, social, and language skills. There is no specific medicine to treat ASD. To diagnose this disorder, doctors consider the child's behavior and developmental history. Autism is often difficult to diagnose because it can have a wide range of symptoms. Children with autism often have subtle facial features that distinguish them from normal children. Early diagnosis and appropriate medical intervention can significantly improve the lives of children with autism and save a lot of money. Deep neural networks (DNN) are a type of machine learning algorithm that can be used to automatically extract features from images as well as classify them. In this research, a practical solution for autism screening is proposed using images of Iranian children's faces through the use of a deep neural network based on transfer learning with 97% detection accuracy. The proposed method can also be used to improve the accuracy of clinical diagnosis.
کلیدواژهها English
