Optimizing Convolutional Neural Networks for EEG Classification in Schizophrenia Diagnosis

To identify schizophrenia patients and healthy individuals, the technique classifies EEG data using convolutional neural networks (CNNs). Schizophrenia poses tremendous difficulties for diagnosis as it is a complicated mental disorder with sensitive brain signals. Aiming at spotting trends between the two groups, the work trained a CNN model using EEG data. The findings underscored the complex nature of the brain activities of the disorder as the model fought to correctly identify schizophrenic patients even if it categorized healthy controls satisfactorily. Showing slight overfitting but generally good performance, the model displayed has a training accuracy of 62.65% and a validation accuracy of 64.55%. Although the model's sensitivity to schizophrenia patients was more restricted. This work highlights CNN's possibilities in mental health diagnosis as well as problems requiring work in model development and dataset extension. Future research will concentrate on improving the detection of schizophrenia in the model so improving early and accurate diagnosis in clinical environments.