CPS - A Tool for Classification and Prediction of Autism with STA

Autism diagnostic procedure is a subjective, challenging and expensive procedure and relies on behavioral, historical and parental report information. In previous researches, it was investigated that whether it is possible to detect autism based on eye-movement sequences, in particular, proposed to use Scanpath Trend Analysis (STA) which is designed for identifying a trending path of a group of users on a web page based on their eye movements.

This CPS Tool first identifies the trending paths of people with autism and neurotypical people. To detect whether or not a person has autism, the similarity of the participant's path to the trending paths of people with autism and neurotypical people is calculated. If the path is more similar to the trending path of neurotypical people, the person is clasified as a neurotypical person. Otherwise, the person is clasified as a person with autism.

CPS provides a prediction, not a diagnosis for a participant. To be able to reach a successful result, this tool has some restrictions for file uploading and collecting eye-tracking data. The uploaded eye-tracking data should be in a .txt file form consisting of six attributes which are fixation index, timestamp, fixation duration, fixation x-coordinate, fixation y-coordinate and stimuli name. Click here to see an eye-tracking data file example.