A Review on BCI Emotions Classification for EEG Signals Using Deep Learning

Emotion awareness is one of the most important subjects in field affective computing. Using nonverbal behavioral methods such as recognition facial expression, verbal method, speech emotion, or physiological signals-based emotions based on electroencephalogram (EEG) can predict human emotion. However, it notable that data obtained from either behaviors are indirect emotional signals suggesting brain activity. Unlike actions, EEG reported directly cortex and thus may be more effective representing inner states brain. Consequently, when used to measure use accurate than behavior. For this reason, identification emotion has become a very research subject current brain-computer interfaces (BCIs) aimed at inferring recorded. In paper, hybrid deep learning approach proposed using CNN long short-term memory (LSTM) algorithm investigated for purpose automatic classification epileptic disease signals. The have been processed by feature extraction runtime environment while LSTM entire data. Finally, system demonstrates each file normal disease. describes state art detection prediction algorithms. This collaboration numerous existing systems.