This work is carried out at Department of Engineering Cybernetics NTNU, Trondheim, Norway.
In this work, we aimed to develop an automated method to accurately detect the human emotions using EEG signals. The available methods in the literature to detect human emotions are having complex network architectures. Hence, we evaluate the SEED and DEAP dataset with less complex classification models such as MLP and CNN. In this way, we can evaluate the effect of the spatial information on the accuracy of the emotion classification models. The CNN model can use spatial information provided by the location of the different EEG channels on the scalp. The MLP architecture is considered since its input is one dimensional and does not take into account the spatial information. Further details are available in the following paper:

M. Kumar, M. Molinas, Human emotion recognition from EEG signals: model evaluation in DEAP and SEED dataset, 21st International Conference of the Italian Association for Artificial Intelligence, December 2022, Udine, Italy