A System for the Study of Emotions with EEG Signals Using Machine Learning and Deep Learning
Human life deals with a lot of emotions. Analyzing the emotions using EEG signals plays a pivotal role in determining the internal/inner state of a particular human. EEG deals with the spontaneous electrical activity of neurons as recorded from multiple electrodes placed in the interior region of the brain. Initially, EEG signals are captured and preprocessed for the removal of noise signals. Selection of appropriate classification techniques in emotion analysis is an important task. The classifiers like k-nearest neighbor (k-NN), SVM, LDA were evaluated. Performances of the classifiers in analyzing a wide range of emotions (arousal and valence emotions) were examined. The results examined demonstrated that emotion analysis using EEG signals is highly advantageous and efficient than the existing traditional recognition systems.
KeywordsEEG Machine learning Feature extraction Classification
- 2.Becker, H., Fleureau, J., Guillotel, P., Wendling, F., Merlet, I., Albera, L., Member, S.: Emotion recognition based on high-resolution EEG recordings and reconstructed brain sources. IEEE Trans. Affect. Comput. 3045(1949), 1–14 (2017). https://doi.org/10.1109/TAFFC.2017.2768030CrossRefGoogle Scholar
- 3.Ding, Y., Hu, X., Xia, Z., Liu, Y., Member, S., Zhang, D.: Inter-brain EEG feature extraction and analysis for continuous implicit emotion tagging during video watching. IEEE Trans.Affect. Comput. (c), 1 (2018). https://doi.org/10.1109/TAFFC.2018.2849758
- 6.Zheng, W., Zhu, J., Lu, B., Member, S.: Identifying stable patterns over time for emotion recognition from EEG. IEEE Trans.Affect. Comput. 1–15 (2018)Google Scholar