Schizophrenia is a persistent and debilitating mind disorder characterised via signs and symptoms such as delusions, hallucinations, disorganized questioning, and lack of motivation.The traditional method to diagnosing schizophrenia is based on scientific tests and EEG assessments, which might be time Consuming and difficult, even for skilled clinicians. With the upward thrust of deep studying strategies, there's developing potential for automating and improving the accuracy of schizophrenia detection. in this examine, we explore using diverse deep learning and machine Learning fashions, along with artificial Neural Networks (ANN), to categorise EEG indicators for schizophrenia detection. We propose a custom method for processing EEG records and evaluate the performance of different models. many of the models examined, the ANN completed the highest accuracy of 84%, demonstrating the feasibility of deep mastering techniques for early and correct detection of schizophrenia. This approach ought to provide a dependable and efficient opportunity to conventional diagnostic strategies, lowering the complexity and subjectivity concerned in the modern- day tactics Keywords: Schizophrenia detection, EEG signals ,EEG learning,Artificial Neural Networks (ANN), Machine earning.
Read full abstract