Classification of Schizophrenia Using Multichannel EEG Signals

Abstract

An electroencephalogram (EEG) is a technique that enables non-invasive monitoring of the brain’s electrical activity. EEG signals can be captured by capturing the electrical charge of neurons using electrodes positioned on the scalp. The EEG signal is a complex time-series signal that provides us insights into the ongoing process of the brain. It includes information on cognitive and physiological processes, including attention, perception, memory, emotion, etc. There has been increasing use of EEG signals in neuroscience research to study brain function and dysfunction in healthy individuals and patients with various neurological and psychiatric disorders. Due to the development of this field, EEG signals have been widely used with various signal processing and machine-learning techniques in recent years. This analysis of signals includes efficient methods of extracting features, detecting events, and decoding cognitive states using AI. These technological advancements have opened new possibilities for using EEG signals in different clinical applications, such as diagnosis, mon itoring treatment, and brain-computer interfaces (BCI). Due to the rapid advancements in machine learning and deep learning, we are now able to use EEG signals in both clinical set tings (such as detecting epilepsy, mental disorders, movement disorders, emotion detection, etc.) as well as non-clinical settings (such as gaming, education, marketing research, sports, etc.).