EEG- Driven Emotion Recognition Model Using An Enhanced Convolutional Neural Network Model

Mental health disorders pose a significant global challenge, emphasizing the need for early, accurate, and objective diagnostic tools. The AI-driven EEG analysis for the evaluation and tracking of mental health is examined in this study, concentrating on emotions. Understanding the correct emotional state of the person is primarily important to treat any kind of mental disorder since people with mental disorder may lack correct convey on the feeling they undergo. Understanding the correct emotions in any point of the treatment process would be highly helpful. This study uses Enhanced Convolutional Neural Networks (CNN) layers, a sophisticated deep learning technique, to detect the emotions accurately. EEG is used to record brain activity linked to complex cognitive dysfunctions. Bandpass filtering is used for preprocessing and for feature extraction, the power spectral density is done by fast fourier transform. In this approach the emotions are classified as positive, neutral, and negative, by using an Enhanced CNN. Through rigorous testing, the system's dependability is confirmed. We have achieved the accuracy of 98.5, which is pretty good when compared to the other algorithms which give the medical professionals a precise and early tool for identifying mental emotional state to enhance patient outcomes.