Review of Autistic Detection Using Eye Tracking and Vocalization Based on Deep Learning

Abstract

Autism is a neuro developmental disorder usually diagnosed in childhood. Autism is identified by repetitive and restricted behaviors, and conflicts in communication. Eye tracking has long been used to research the development of ASD autism spectrum disorder as a technique, as it is a tool that tracks visual activity and tells us information such as where and for how long something is stared at by a person. Eye tracking gives a very immediate and interpretable indicator of an individual's attention, which is something that no other biomarker... will do. Effectively, in real-time, you get to know where a person allocates their attention, which tells you all about mental processing. Eye tracking is now a highly regarded method in ASD research as it enables the precise tracking of the gaze of an individual. This knowledge offers empirical insight, as a proxy for cogn. So  speech-language characteristics of vocalizations and face recognition  are  the required features . Exam pre-linguistic vocalizations for a period of time using some smart devices. Diagnosing Autistic may be challenging to diagnose since there are presently no advanced diagnostic techniques available; instead, clinicians must assess the child's behavior and development to determine a diagnosis. In addition, to correctly evaluate a youngster, repeated exams are usually required. The issue is that the analysis of vocalization specificities, newborn vocalization analysis, and the analysis of certain descriptors facial characteristics picked in various situations and for children are all problematic.The aim of this proposal is a perfect autistic detection using a classification approaches achieve with high accuracy and for subject-wise identification in a subject-independent 3-fold cross-validation scheme. At the neural level, neural activation patterns and neural adaptation to faces in face-related brain regions. In terms of functional connectivity, So amygdale seems to be more strongly connected to inferior occipital cortex and V1 in individuals with ASD. Overall, the findings indicate that neural representations of facial identity(eye movement abnormal) and expression have a similar quality in individuals with and without ASD, but some regions containing these representations are connected differently in the extended face processing network.In this research, we presented a review and presentation of the latest research that specialized in detecting autism using eye tracking and vocalization  technology, both separately.Because of the two methods of high accuracy in detecting autism, both what if they were used together. The expectable results may be an important contribution to facilitate earlier identification of autistic disease .