EEG-Based Emotion Recognition Using Deep Learning Network

Year 2025, Volume: 2 Issue: 2, 100 - 113, 27.11.2025

Ahmed Elkassas , Sema Koç Kayhan

Abstract

Emotion recognition has gained significant attention in recent years, due to the ability of electroencephalography (EEG) to capture real-time brain signals activity from a head band. This study presents an analysis and classification of EEG-based emotion recognition using a dataset containing recordings of brain signals during three different emotion classes (positive, negative, and neutral). Three different deep learning models are built, trained with the data set and compared to view the different performances. the three deep learning models used in this study are: a deep learning model with two hidden layers (RNN), a deep learning model using long short-term memory network (LSTM), and a deep learning model using a gated recurrent unit (GRU) model. Moreover, to validate the three different models effectiveness in the proposed method section, the model accuracy, precision, recall, and F1-score results of each model of the three is obtained and compared. furthermore, the classification of the EEG signals are presented in the study and discussed the advantages of the proposed model.

Keywords

Emotion recognition , EEG signals , Deep learning , classification , RNN

Ethical Statement

This paper does not require ethics committee approval

Supporting Institution

Gaziantep University

Thanks

I would like to express my sincere gratitude to my supervisor, Sema Kayhan, for their special guidance throughout the course of this research. I am also thankful to Gaziantep University for providing the necessary resources to complete this study. Special thanks to my family and friends for the support and motivation during this journey

References

• Anonymous (2018). YouTube https://www.youtube.com/watch?v=8HyCNIVRbSU (Accessed date: 20 January 2025).
• Adrian R. A.,. Et al. (2022). EEG-Based Emotion Recognition Using Deep Learning and M3GP. Applied sciences, 12,2527.
• Ayse G. E., Et al. (2022). EEG Signals and spectrogram with deep learning approaches emotion analysis with images. 7th International Conference on Computer Science and Engineering (UBMK).
• Craik, A., He, Y., and Contreras-Vidal, J. (2019). Deep learning for electroencephalogram (EEG) classification tasks: a review. Journal of Neural Engineering, 16(3), 031001.
• Hassaan, I. (2024). Medium https://medium.com/@hassaanidrees7/rnn-vs-lstm-vs-gru-a-comprehensive-guide-to-sequential-data-modeling-03aab16647bb (Accessed date: 22 january 2025).
• Jamal, F. Hwaidi and Thomas, M. Chen. (2022). Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network Approach. IEEE Access. volume 1, 48071-48081.
• Jodie, A. Et al. (2019). Classification of EEG Signals Based on Image Representation of Statistical Features. Part of the book series: Advances in Intelligent Systems and Computing (AISC,volume 1043).
• Jordan, J. B., Et al. (2019). A Deep Evolutionary Approach to Bioinspired Classifier Optimisation for Brain-Machine Interaction. Hindawi Comlexity, Volume 2019, Article ID 4316548, 14 page.
• Jordan, J. Bird. Et al. (2019). Mental Emotional Sentiment Classification with an EEG-based Brain-machine Interface. The international conference on Digital Image & Signal Processing (DISP 19). Oxford University, UK.
• Li, X. (2015). EEG Based Emotion Identification Using Unsupervised Deep Feature Learning. In: SIGIR2015 Workshop on Neuro-Physiological Methods in IR Research, 13 Aug 2015, Santiago, Chile.
• Martin, K. (2021). YouTube https://www.youtube.com/watch?v=b61DPVFX03I (Accessed date: 1 February 2025).
• Rian, D. (2020). Towards data science https://towardsdatascience.com/lstm-networks-a-detailed-explanation-8fae6aefc7f9/ (Accessed date: 1 February 2025).
• Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T. H., and Faubert, J. (2019). Deep learning-based electroencephalography analysis: a systematic review. Journal of Neural Engineering, 16(5), 051001.
• Saul, D. (2022). Towards data science https://towardsdatascience.com/gru-recurrent-neural-networks-a-smart-way-to-predict-sequences-in-python-80864e4fe9f6/ (Accessed date: 2 February 2025).
• Suwicha, J., Et al. (2014). EEG-Based Emotion Recognition Using Deep Learning Network with Principal Component Based Covariate Shift Adaptation. The Scientific World Journal, 2014, Article ID 627892.
• Tashyab, R. (2024). Kaggle https://www.kaggle.com/code/tashyab/emotion-detection-using-eeg-data-with-visuals#3.1-LSTM (Accessed date: 4 December 2024).