DEEP LEARNING-BASED AUTISM EVALUATION ASSISTANCE SYSTEM AND METHOD

摘要

A deep learning-based autism evaluation assistance system and method. Said system comprises a data acquisition and feature extraction unit (110), a first neural network (1), a second neural network (2), a third neural network (3) and a result output unit (120), the data acquisition and feature extraction unit (110) and the result output unit (120) being respectively connected to the first neural network (1), the second neural network (2) and the third neural network (3); the data acquisition and feature extraction unit (110) being used for acquiring eye movement data of a subject watching a video, and obtaining a heat map, a focus map and a scanning path map; the first neural network (1) inputting the heat map to obtain a first classification result, the second neural network (2) inputting the focus map to obtain a second classification result, and the third neural network (3) inputting the scanning path map to obtain a third classification resu and the result output unit (120) combining the first classification result, the second classification result and the third classification result to obtain an autism detection result of the subject. The deep learning-based autism evaluation assistance system and method improve prediction efficiency and prediction accuracy of autism.