Author(s)

YunYi Wang

Affiliation(s)

Zhixin high school, Guangzhou 510060, Guangdong, China.

Corresponding Author

YunYi Wang

ABSTRACT

Throughout history, emotion recognition has played a pivotal role across various fields. Due to technology limitation, emotions were traditionally evaluated through interviews or questionnaires, methods prone to subjectivity even among psychologists. Hence, development of automated emotion recognition system is necessary. In recent years, prodigious process has been made in this area, with EEG-based emotion recognition becoming increasingly popular. However, the models that used to classify the EEG-based emotion data are still not powerful enough. In this paper, we propose an efficient model for emotion classification, utilizing EEG data from DEAP dataset. The neural signals are first decomposed into the Gamma, Alpha, Beta, and Theta bands according to their respective frequencies, and preprocessed using Welch method. A hybrid model, combining Long Short-Term Memory (LSTM), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Linear Discriminant Analysis (LDA), is employed for classification. This hybrid model distinguishes among three emotional states: positive, negative, and neutral. Compared to existing work, our ensemble learning model achieves a higher accuracy, performs with 95.99% and 95.68% for arousal and valence. Furthermore, our method successfully mitigates the weaknesses of these individual base models, bringing in a more robust emotion recognition framework.

KEYWORDS

EEG; Emotion recognition; Ensemble model; Machine learning; Long-Short Term Memory

CITE THIS PAPER

YunYi Wang. EEG-based emotion recognition using ensemble learning model. AI and Data Science Journal. 2025, 2(1): 40-47. DOI: https://doi.org/10.61784/adsj3014.

REFERENCES

[1] L Chen, X Mao, Y Xue, et al. Speech emotion recognition: Features and classification models. Digital Signal Processing, 2012, 22(6): 1154–1160.

[2] A Dzedzickis, A Kaklauskas, V Bucinskas. Human emotion recognition: Review of sensors and methods. Sensors, 2020, 20(3): 592.

[3] X Li, Y Zhang, P Tiwari, et al. EEG based emotion recognition: A tutorial and review. ACM Computing Surveys, 2022, 55(4): 1–57.

[4] S Sahu, R Kumar, H V Long, et al. Early-production stage prediction of movies success using K-fold hybrid deep ensemble learning model. Multimedia Tools and Applications, 2023, 82(3): 4031–4061.

[5] R Jenke, A Peer, M Buss. Feature extraction and selection for emotion recognition from EEG. IEEE Transactions on Affective Computing, 2014, 5(3): 327–339.

[6] N Thammasan, K Moriyama, K Fukui, et al. Continuous music-emotion recognition based on electroencephalogram. IEICE Transactions on Information and Systems, 2016, 99(4): 1234–1241.

[7] R Nawaz, K H Cheah, H Nisar, et al. Comparison of different feature extraction methods for EEG based emotion recognition. Biocybernetics and Biomedical Engineering, 2020, 40(3): 910–926.

[8] X Li, Y Zhang, P Tiwari, et al. EEG based emotion recognition: A tutorial and review. ACM Computing Surveys, 2022, 55(4): 1–57.

[9] R W Picard. Building HAL: Computers that sense, recognize, and respond to human emotion. Proceedings of SPIE – The International Society for Optical Engineering, 2001, 4299: 518–523.

[10] A Lartseva, T Dijkstra, C C Kan, et al. Processing of emotion words by patients with autism spectrum disorders: Evidence from reaction times and EEG. Journal of Autism and Developmental Disorders, 2014, 44: 2882–2894.

[11] A Ko?akowska, A Landowska, M Szwoch, et al. Emotion recognition and its applications. Human-Computer Systems Interaction: Backgrounds and Applications 3, 2014: 51–62.

[12] J á Bitsch, R Ramos, T Ix, et al. Psychologist in a pocket: Towards depression screening on mobile phones. Stud Health Technol Inform, 2015, 211: 153–159.

[13] R Ge, G Feng, X Jing, et al. ENACP: An ensemble learning model for identification of anticancer peptides. Frontiers in Genetics, 2020, 11: 760.

[14] M Mohy-Eddine, A Guezzaz, S Benkirane, et al. An ensemble learning based intrusion detection model for industrial IoT security. Big Data Mining and Analytics, 2023, 6(3): 273–287.

[15] R Dunne, T Morris, S Harper. A survey of ambient intelligence. ACM Computing Surveys (CSUR), 2021, 54(4): 1–27.

[16] U A Khan, Q Xu, Y Liu, et al. Exploring contactless techniques in multimodal emotion recognition: Insights into diverse applications, challenges, solutions, and prospects. Multimedia Systems, 2024, 30(3): 115.

[17] M A Lebedev, M A L Nicolelis. Brain–machine interfaces: Past, present and future. Trends in Neurosciences, 2006, 29(9): 536–546.

[18] K S Rao, S G Koolagudi. Emotion recognition using speech features. Springer Science & Business Media, 2012.

[19] E H Houssein, A Hammad, A A Ali. Human emotion recognition from EEG-based brain–computer interface using machine learning: A comprehensive review. Neural Computing and Applications, 2022, 34(15): 12527–12557.

[20] Y Cai, X Li, J Li. Emotion recognition using different sensors, emotion models, methods and datasets: A comprehensive review. Sensors, 2023, 23(5): 2455.

[21] K Okoye, J T Nganji, J Escamilla, et al. Machine learning model (RG-DMML) and ensemble algorithm for prediction of students’ retention and graduation in education. Computers and Education: Artificial Intelligence, 2024, 6: 100205.

[22] H J Yoon, S Y Chung. EEG-based emotion estimation using Bayesian weighted-log-posterior function and perceptron convergence algorithm. Computers in Biology and Medicine, 2013, 43(12): 2230–2237.

[23] A Bhardwaj, A Gupta, P Jain, et al. Classification of human emotions from EEG signals using SVM and LDA classifiers. International Conference on Signal Processing and Integrated Networks (SPIN). IEEE, 2015: 180–185.

[24] S Alhagry, A A Fahmy, R A El-Khoribi. Emotion recognition based on EEG using LSTM recurrent neural network. International Journal of Advanced Computer Science and Applications, 2017, 8(10).

[25] O Bazgir, Z Mohammadi, S A H Habibi. Emotion recognition with machine learning using EEG signals. National and 3rd International Iranian Conference on Biomedical Engineering (ICBME). IEEE, 2018: 1–5.

[26] J Atkinson, D Campos. Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers. Expert Systems with Applications, 2016, 47: 35–41.

[27] J Liu, H Meng, A Nandi, et al. Emotion detection from EEG recordings. International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). IEEE, 2016: 1722–1727.

[28] D S Naser, G Saha. Recognition of emotions induced by music videos using DT-CWPT. Indian Conference on Medical Informatics and Telemedicine (ICMIT). IEEE, 2013: 53–57.

[29] A R Bhagwat, A N Paithane. Human disposition detection using EEG signals. International Conference on Computing, Analytics and Security Trends (CAST). IEEE, 2016: 366–370.

[30] A Iyer, S S Das, R Teotia, et al. CNN and LSTM based ensemble learning for human emotion recognition using EEG recordings. Multimedia Tools and Applications, 2023, 82(4): 4883–4896.