@article{article_1173093, title={Analysis and Classification of Schizophrenia Using Event Related Potential Signals}, journal={Computer Science}, volume={IDAP-2022 : International Artificial Intelligence and Data Processing Symposium}, pages={32–36}, year={2022}, DOI={10.53070/bbd.1173093}, author={Aksöz, Anıl and Akyüz, Doğukan and Bayır, Furkan and Yıldız, Nevzat Can and Orhanbulucu, Fırat and Latifoğlu, Fatma}, keywords={Schizophrenia, electroencephalography, event-related potential, artificial neural networks}, abstract={Schizophrenia (SZ) is a neuropsychiatric disease that affects many people around the world and causes death if not diagnosed and treated early. One of the commonly used methods for early diagnosis is electroencephalography (EEG). The application of signal processing and machine learning methods to EEG signals can support experts and researchers who want to determine SZ disease. In this study, event-related potential (ERP) signals were obtained from the recorded EEG signals as a result of sending auditory stimuli to the SZ patient and healthy control (HC) group. P300 amplitude-latency, hjorth parameters and entropy values were calculated as features from these signals. The features obtained were evaluated with Support Vector Machines (SVM), K-Nearest Neighbor (KNN) and Artificial Neural Networks (ANN) classifiers to distinguish SZ patients from the HC group. In this study, the most successful result was obtained in the ANN classifier with an accuracy rate of 93.9%.}, publisher={Ali KARCI}