Design and Development of Multi-Model Deep Learning based Approach for Scaling the Severity of Mental Disorders

Electroencephalogram (EEG) is probably the most critical technology for human brain-computer interface applications. People who have mental illnesses frequently go through substantial changes in their routines, emotions, or ideas. The idea that early identification is essential for successful treatment has led to several breakthroughs in the field of mental illness. Using pattern discovery and feature extraction techniques, it is considered that EEG data indicating brain activity are crucial for identifying mental illness. We present a hybrid model based on machine learning and deep learning techniques to categorize and diagnose various brain disorders. The acquired distinctive characteristics from the dataset were utilized in the current study to build a reliable 3D-CNN model. We investigated whether the obtained EEG dataset is adequate to identify healthy individuals and subjects who have been diagnosed with various mental disorders and impairments concerning their prescribed antipsychotic medications. In particular, we are concerned with using specific types of electrodes that can produce such distinctions.