Decoding Emotions from Brain Signals using Recurrent Neural Networks

Despite playing a crucial role in human interactions and decisions, emotions are not well understood. These emotions can appear as electrical signals through electroencephalography (EEG). This paper uses data from the Dataset of Emotional Analysis Using Physiological Signals (DEAP), which recorded the EEG signals of participants as they watched videos that were specifically chosen to elicit strong emotions and rated their emotions on quantitative scales. A Long Short-Term Memory (LSTM) recurrent neural network was trained to find correlations between EEG data and self-reported emotional scores. The purpose of this study was to create an accurate and efficient method of decoding electrical activity into quantitative emotional values. It was found that valence scores, measures of the degree of happiness, predicted by the neural network matched somewhat closely with the actual valence scores given by the participants. The trained LSTM neural network achieved a reasonable accuracy in predicting valence scores given EEG signals.