Emotion Recognition Through Brainwaves Using Deep Learning and Machine Learning

Emotion is the mental state that represents the body's inherent anxiety and depression. There are many techniques to measure these emotions; the most common ones are PET, ECG, EMG, and MRI, which help in measuring people's emotions. Another very useful and common technique, i.e., EEG, is mostly used to do such analysis. EEG plays a very important role in detecting and correcting brain illness. This activity results in wave lines of EEG signals. Here, we analyze the emotions of the EEG signal based on some main concepts of deep learning and machine learning. The main purpose of the study is to classify EEG brainwaves signal into three categories; positive, negative, and neutral emotions. LSTM, a deep learning model designed for sequential data is used for training and validation of metrics. Various methods have been used to extract the features of the EEG signal, and later with the help of trained classifiers, we find out the signal's accuracy. By comparing different classifiers, we can find out which classifier is more accurate when we need to perform such analysis.