Emotion Recognition using EEG Signal Classification of seed Dataset

Emotions were considered an important component. Everyday lives need emotions on a regular basis. Electroencephalogram (EEG)-based emotion identification was gaining popularity quickly. Signals from electroencephalograms (EEGs) are one of the key resources. The biggest benefit of using EEG signals is that they accurately represent real feelings and it could be prepared by computer systems. EEG is a physiological marker that may be captured from the brain activity within the context of scalp-transmitted brain waves which was used to collect brain signals. With this test, waves representing the brain's activity are recorded. The SEED-IV dataset was utilized to categorize emotions as happy, sad, fear, and neutral. Sampling techniques and classification techniques were used to raise the level of performance of the algorithm. One of the most important advantages of using EEG signals is that is accurately prepared by computer systems and portrayed the real experience. The performance of the emotion recognition systems by brain signals depended on the efficiency of the algorithms used. The instability of the brain's impulses is one of the reasons why this process is seen as challenging. So, pre-process was done to remove noisy data. The proposed method focuses on implementing an algorithm that accurately classified emotions into the said four categories.