Psychological test of patients with mental disorders based on eye movement data fusion algorithm

Eye movement (EM), as a mature observation technology, has been widely used in the research of psychology, and it is also one of the important methods of multi-quality psychological testing technology. However, there are relatively few researches on psychological testing based on EM technology at present. By introducing convolution neural network (CNN) network into deep long short memory network (DLSTM), this paper develops a new network structure, designs a fusion strategy, and proposes an EM tracking data fusion algorithm based on deep learning (EYE-CNN-DLSTM). By comparing the fusion effect and index values of EYE-CNN-DLSTM algorithm with two deep learning algorithms MLP and DLSTM on 10 sets of real EM data sets and 10 sets of real tracking data sets, the experimental results show that EYE-CNN-DLSTM algorithm performs well in fusion quality. It provides a theoretical basis for the new objective evaluation index of patients with mental disorders.