Ortho-FLD: Analysis of Emotions Based on EEG Signals

One of the well-known technology that is leading to greater attention in affect recognition is brain–computer interfaces (BCI). Understanding and recognizing the human interactions of several emotional states through BCI based on electroencephalogram signals (EEG) in multi-modal interfaces play an essential role in the field of artificial intelligence. This proposed study establishes a new method of effective feature representation along with reducing the dimensions of EEG signals. we employed Fisher linear discriminant (FLD) and orthogonal FLD approaches for identifying four different emotions from a benchmark video game-based GAMEEMO dataset and a generalized regression neural network classifier was used for further performance analysis. In comparison to other state-of-the-art methods, the experimental results of the proposed study are promising and performed well.