EEG based Schizophrenia Detection using SPWVD-ViT Model

Authors : Mesut ŞEKER, Mehmet Siraç ÖZERDEM

Pages : 137-144

Doi:10.36222/ejt.1192140

View : 12 | Download : 7

Publication Date : 2022-12-30

Article Type : Research Paper

Abstract :Schizophrenia is a typical neurological disease that affects patients’ mental state, and daily behaviours. Combining image generation techniques with effective machine learning algorithms may accelerate treatment process, and possible early alert systems prevents diseases from reaching out crucial phase. The purpose of current study is to develop an automated EEG based schizophrenia detection with the Vision Transformer insert ignore into journalissuearticles values(ViT); model using Smoothed Pseudo Wigner Ville Distribution insert ignore into journalissuearticles values(SPWVD); time-frequency input images. EEG recordings from 35 schizophrenia insert ignore into journalissuearticles values(sch); and 35 healthy conditions insert ignore into journalissuearticles values(hc); are analyzed. We have used 5-fold cross validation for evaluation and testing of the method. Classification task is carried out as subject-independent and subject-dependent method. We reached out overall accuracy of 87% for subject-independent and 100% for subject-dependent approach for binary classification. While ViT has ben extensively used in Natural Language Processing insert ignore into journalissuearticles values(NLP); field, dividing input images within a sequence of embedded image patches via. transformer encoder is a practical way for medical image learning and developing diagnostic tools. SPWVD-ViT model is recommended as a disease detection tool not only for schizophrenia but other neurological symptoms.
Keywords : EEG, Schizophrenia, Neurological Disease, Vision Transformer, Diagnosis, Detection, Time frequency image