providing a four‑layer method based on deep belief network to improveemotion recognition in electroencephalography in brain signals

Background: one of the fields of research in recent years that has been under focused is emotionrecognition in electroencephalography (eeg) signals. this study provides a four‑layer method toimprove people’s emotion recognition through these signals and deep belief neural networks.methods: in this study, using deap dataset, a four-layer method is established, which includes (1)preprocessing, (2) extracting features, (3) dimension reduction, and (4) emotion identification andestimation. to find the optimal choice in some of the steps of these layers, three different tests havebeen conducted. the first is finding the perfect window in feature extraction section that resulted insuperiority of hamming window to the other windows. the second is choosing the most appropriatenumber of filter bank and the best result was 26. the third test was also emotion recognition thatits accuracy was 92.93 for arousal dimension, 92.64 for valence dimension, 93.14 for dominancedimension in two‑class experiment and 76.28 for the arousal, 74.83 for the valence, and 75.64 fordominance in three‑class experiment. results: the results of this method show an improvement of12.34% and 7.74% in two‑ and three‑class levels in the arousal dimension. this improvement in thevalence is 12.77 and 8.52, respectively. conclusion: the results show that the proposed method canbe used to improve the accuracy of emotion recognition.