Abstract:

ASD is a common condition that affects 1 in 44 people, according to the Centres for Disease Control and Prevention (CDC). A lot of suffering occurs during this illness for both the children's parents. So early detection of disease is an immediate requirement. Many papers have been published with approaches involving image, video, emotions, face to face interaction, web browsing, social interaction and gaze and demographic studies. The use of eye-tracking technology, machine learning, and other diagnostic methods is currently used to assess early-onset ASD. Now, subjective criteria rather than objective ones are used to assess ASDs. There is evidence to support the idea that combining eye-tracking and machine learning could be a helpful tool in the early and accurate diagnosis of autism. This review paper intends to focus on all such research contributions and bring out a new methodology for early detection of ASD in children. The study reveals that video-based study has been effective with 92% accuracy

Description:

Machine Learning, ASD, Autism, Assessment, Classification, Eye Tracking, Types of Study, Eye Movement Metrics