EEG-Based Emotion Recognition Using Logistic Regression with Gaussian Kernel and Laplacian Prior and Investigation of Critical Frequency Bands
Source abstract
Abstract
Emotion plays a nuclear part in human attention, decision-making, and communication. Electroencephalogram (EEG)-based emotion recognition has developed a lot due to the application of Brain-Computer Interface (BCI) and its effectiveness compared to body expressions and other physiological signals. Despite significant progress in affective computing, emotion recognition is still an unexplored problem. This paper introduced Logistic Regression (LR) with Gaussian kernel and Laplacian prior for EEG-based emotion recognition. The Gaussian kernel enhances the EEG data separability in the transformed space. The Laplacian prior promotes the sparsity of learned LR regressors to avoid over-specification. The LR regressors are optimized using the logistic regression via variable splitting and augmented Lagrangian (LORSAL) algorithm. For simplicity, the introduced method is noted as LORSAL. Experiments were conducted on the dataset for emotion analysis using EEG, physiological and video signals (DEAP). Various spectral features and features by combining electrodes (power spectral density (PSD), differential entropy (DE), differential asymmetry (DASM), rational asymmetry (RASM), and differential caudality (DCAU)) were extracted from different frequency bands (Delta, Theta, Alpha, Beta, Gamma, and Total) with EEG signals. The Naive Bayes (NB), support vector machine (SVM), linear LR with L1-regularization (LR_L1), linear LR with L2-regularization (LR_L2) were used for comparison in the binary emotion classification for valence and arousal. LORSAL obtained the best classification accuracies (77.17% and 77.03% for valence and arousal, respectively) on the DE features extracted from total frequency bands. This paper also investigates the critical frequency bands in emotion recognition. The experimental results showed the superiority of Gamma and Beta bands in classifying emotions. It was presented that DE was the most informative and DASM and DCAU had lower computational complexity with relatively ideal accuracies. An analysis of LORSAL and the recently deep learning (DL) methods is included in the discussion. Conclusions and future work are presented in the final section.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: EEG and Brain-Computer Interfaces · Emotion and Mood Recognition · Blind Source Separation Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Technology, Xidian University, Xi’an 710071, China
School of Electronic Engineering, Xidian University, Xi’an 710071, China
College Counselor Reach Perfection with Morality Studio of Shaanxi Province, Xi’an 710071, China
School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China
Undergraduate School, Xidian University, Xi’an 710071, China
State Key Laboratory of Integrated Services Networks, Xi’an 710071, China
Funding
National Natural Science Foundation of China · Fundamental Research Funds for the Central Universities · Construction Project Achievement of College Counselor Studio of Shaanxi Province
References (80)
Show source-provided references
1. Picard, R.W. (1997). Affective Computing, MIT Press.10.1037/e526112012-054 ↗
2. The autonomic nervous system and emotion10.1177/1754073913512003 ↗
3. A review, current challenges, and future possibilities on emotion recognition using machine learning and physiological signals10.1109/ACCESS.2019.2944001 ↗
4. Shu, L., Xie, J., Yang, M., Li, Z., Li, Z., Liao, D., Xu, X., and Yang, X. (2018). A review of emotion recognition using physiological signals. Sensors, 8.10.3390/s18072074 ↗
5. The James-Lange theory of emotions: A critical examination and an alternative theory10.2307/1415404 ↗
6. Ayaz, H., Curtin, A., Mark, J., Kraft, A., and Ziegler, M. (2019, January 6–9). Predicting Future Performance based on Current Brain Activity: An fNIRS and EEG Study. Proceedings of the 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), Bari, Italy.10.1109/SMC.2019.8914412 ↗
7. Saadati, M., Nelson, J., and Ayaz, H. (2019, January 24–28). Convolutional Neural Network for Hybrid fNIRS-EEG Mental Workload Classification. Proceedings of the International Conference on Applied Human Factors and Ergonomics, Washington, DC, USA.10.1007/978-3-030-20473-0_22 ↗
8. Deep Convolutional Neural Networks for mental load classification based on EEG data10.1016/j.patcog.2017.12.002 ↗
9. Sargent, A., Heiman-Patterson, T., Feldman, S., Shewokis, P.A., and Ayaz, H. (2018). Mental Fatigue Assessment in Prolonged BCI Use Through EEG and fNIRS.-Neuroergonomics, Academic Press.10.1016/B978-0-12-811926-6.00092-0 ↗
10. Abdul, A., Chen, J., Liao, H.Y., and Chang, S.H. (2018). An emotion-aware personalized music recommendation system using a convolutional neural networks approach. Appl. Sci., 8.10.3390/app8071103 ↗
11. Jiao, Z., You, H., Yang, F., Li, X., Zhang, H., and Shen, D. (2019, January 10–16). Decoding EEG by visual-guided deep neural networks. Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China.10.24963/ijcai.2019/192 ↗
12. Ren, Z., Li, J., Xue, X., Li, X., Yang, F., Jiao, Z., and Gao, X. (2019). Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning. arXiv.
13. A review of classification algorithms for EEG-based brain–computer interfaces10.1088/1741-2560/4/2/R01 ↗
14. A review of classification algorithms for EEG-based brain–computer interfaces: A 10 year update10.1088/1741-2552/aab2f2 ↗
15. A circumplex model of affect10.1037/h0077714 ↗
16. A review on the computational methods for emotional state estimation from the human EEG
17. Feelings and emotions: Roles for electrophysiological markers10.1016/j.biopsycho.2004.03.009 ↗
18. Sanei, S., and Chambers, J. (2007). EEG Signal Processing, Wiley.10.1002/9780470511923 ↗
19. Al-Nafjan, A., Hosny, M., Al-Ohali, Y., and Al-Wabil, A. (2017). Review and classification of emotion recognition based on EEG brain-computer interface system research: A systematic review. Appl. Sci., 7.10.3390/app7121239 ↗
20. Subject-independent odor pleasantness classification using brain and peripheral signals10.1109/TAFFC.2015.2496310 ↗
21. Zhang, J.H., Chen, M., Zhao, S.K., Hu, S.Q., Shi, Z.G., and Cao, Y. (2016). Relieff-based EEG sensor selection methods for emotion recognition. Sensors, 16.10.3390/s16101558 ↗
22. Aesthetic preference recognition of 3d shapes using EEG10.1007/s11571-015-9363-z ↗
23. Tang, J., Alelyani, S., and Liu, H. (2014). Feature Selection for Classification: A Review. Data Classification: Algorithms and Applications, CRC Press.
24. Chao, G., Luo, Y., and Ding, W. (2019). Recent advances in supervised dimension reduction: A Survey. Mach. Learn. Knowl. Extr., 1.10.3390/make1010020 ↗
25. Lin, Y.-P., Wang, C.-H., Wu, T.-L., Jeng, S.-K., and Chen, J.-H. (2009, January 19–24). EEG-based emotion recognition in music listening: A comparison of schemes for multiclass support vector machine. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Taipei, Taiwan.10.1109/ICASSP.2009.4959627 ↗
26. Horlings, R., Datcu, D., and Rothkrantz, L.J.M. (2008, January 12–13). Emotion recognition using brain activity. Proceedings of the 9th International Conference on Computer Systems and Technologies and Workshop for PhD students in Computing, Gabrovo, Bulgaria.10.1145/1500879.1500888 ↗
27. DEAP: A database for emotion analysis; using physiological signals10.1109/T-AFFC.2011.15 ↗
28. Deep learning for electroencephalogram (EEG) classification tasks: A review10.1088/1741-2552/ab0ab5 ↗
29. Deep learning-based electroencephalography analysis: A systematic review10.1088/1741-2552/ab260c ↗
30. Zheng, W.L., Zhu, J.Y., Peng, Y., and Lu, B.L. (2014, January 14–18). EEG-based emotion classification using deep belief networks. Proceedings of the 2014 IEEE International Conference on Multimedia and Expo (ICME), Chengdu, China.10.1109/ICME.2014.6890166 ↗
31. Zheng, W.L., Guo, H.T., and Lu, B.L. (2015, January 22–24). Revealing critical channels and frequency bands for emotion recognition from EEG with deep belief network. Proceedings of the 2015 7th International IEEE/EMBS Conference on Neural Engineering (NER), Montpellier, France.10.1109/NER.2015.7146583 ↗
32. Yang, Y., Wu, Q., Qiu, M., Wang, Y., and Chen, X. (2018, January 8–13). Emotion recognition from multi-channel EEG through parallel convolutional recurrent neural network. Proceedings of the International Joint Conference on Neural Networks, Rio, Brasil.10.1109/IJCNN.2018.8489331 ↗
33. Accurate EEG-based emotion recognition on combined features using deep convolutional neural networks10.1109/ACCESS.2019.2908285 ↗
34. A hierarchical bidirectional GRU model with attention for EEG-based emotion classification10.1109/ACCESS.2019.2936817 ↗
35. Learning deep physiological models of affect10.1109/MCI.2013.2247823 ↗
36. Chen, J.X., Mao, Z.J., Yao, W.X., and Huang, Y.F. (2019). EEG-based biometric identification with convolutional neural network. Multimed. Tools Appl., 1–21.
37. Lee, J., and Yoo, S.K. (2018). Design of user-customized negative emotion classifier based on feature selection using physiological signal sensors. Sensors, 18.10.3390/s18124253 ↗
38. Hosmer, D.W., Lemeshow, S., and Sturdivant, R.X. (2013). Applied Logistic Regression, John Wiley & Sons.10.1002/9781118548387 ↗
39. Automatic seizure detection in EEG using logistic regression and artificial neural network10.1016/j.jneumeth.2005.04.009 ↗
40. Classification of EEG signals using neural network and logistic regression10.1016/j.cmpb.2004.10.009 ↗
41. Tomioka, R., Aihara, K., and Müller, K.R. (2006). Logistic regression for single trial EEG classification. Advances in Neural Information Processing Systems 19, Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems, Vancouver, BC, Canada, 4–7 December 2006, MIT Press.10.7551/mitpress/7503.003.0177 ↗
42. Direct brain stimulation modulates encoding states and memory performance in humans10.1016/j.cub.2017.03.028 ↗
43. Comparison of logistic regression, support vector machines, and deep learning classifiers for predicting memory encoding success using human intracranial EEG recordings10.1088/1741-2552/aae131 ↗
44. Sparse multinomial logistic regression: Fast algorithms and generalization bounds10.1109/TPAMI.2005.127 ↗
45. Bioucas-Dias, J., and Figueiredo, M. (2009). Logistic Regression via Variable Splitting and Augmented Lagrangian Tools, Instituto Superior Técnico.10.1109/WHISPERS.2009.5289072 ↗
46. Hyperspectral image segmentation using a new Bayesian approach with active learning10.1109/TGRS.2011.2128330 ↗
47. Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks10.1109/TAMD.2015.2431497 ↗
48. Identifying stable patterns over time for emotion recognition from EEG10.1109/TAFFC.2017.2712143 ↗
49. Measuring emotion: The self-assessment manikin and the semantic differential10.1016/0005-7916(94)90063-9 ↗
50. Feature extraction and selection for emotion recognition from EEG10.1109/TAFFC.2014.2339834 ↗
51. Brain oscillations and BIS/BAS (behavioral inhibition/activation system) effects on processing masked emotional cues: ERS/ERD and coherence measures of alpha band10.1016/j.ijpsycho.2009.08.006 ↗
52. EEG-based emotion recognition The Influence of Visual and Auditory Stimuli
53. Chanel, G., Karim, A.-A., and Thierry, P. (2007, January 7–10). Valence-arousal evaluation using physiological signals in an emotion recall paradigm. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Montreal, QC, Canada.10.1109/ICSMC.2007.4413638 ↗
54. EEG-based emotion recognition in music listening10.1109/TBME.2010.2048568 ↗
55. Shi, L., Jiao, Y., and Lu, B. (2013, January 3–7). Differential entropy feature for EEG-based vigilance estimation. Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan.
56. Duan, R., Zhu, J., and Lu, B. (2013, January 6–8). Differential entropy feature for EEG-based emotion classification. Proceedings of the 6th International IEEE/EMBS Conference on Neural Engineering (NER), San Diego, CA, USA.10.1109/NER.2013.6695876 ↗
57. Gibbs, J.W. (1902). Elementary Principles in Statistical Mechanics—Developed with Especial Reference to the Rational Foundation of Thermodynamics, C. Scribner’s Sons.10.5962/bhl.title.32624 ↗
58. Asymmetrical brain activity discriminates between positive and negative stimuli infants10.1126/science.7146906 ↗
59. Fusion of electroencephalographic dynamics and musical contents for estimating emotional responses in music listening10.3389/fnins.2014.00094 ↗
60. Semi-supervised hyperspectral image segmentation using multinomial logistic regression with active learning
61. A tutorial on MM algorithms10.1198/0003130042836 ↗
62. Borges, J.S., Bioucas-Dias, J.M., and Marçal, A.R.S. (2006, January 18–20). Fast Sparse Multinomial Regression Applied to Hyperspectral Data. Proceedings of the Third International Conference on Image Analysis and Recognition—Volume Part II, Póvoa de Varzim, Portugal.10.1007/11867661_63 ↗
63. LIBLINEAR: A library for large linear classification
64. LIBSVM: A library for support vector machines10.1145/1961189.1961199 ↗
65. RBF neural network center selection based on Fisher ratio class separability measure10.1109/TNN.2002.1031953 ↗
66. Feature selection with kernel class separability10.1109/TPAMI.2007.70799 ↗
67. Markov random fields integrating adaptive interclass-pair penalty and spectral similarity for hyperspectral image classification10.1109/TGRS.2018.2874077 ↗
68. EEG alpha activity reflects attentional demands, and beta activity reflects emotional and cognitive processes10.1126/science.3992243 ↗
69. Induced alpha band power changes in the human EEG and attention10.1016/S0304-3940(98)00122-0 ↗
70. High-frequency broadband modulations of electroencephalographic spectra
71. Mu, L., and Lu, B.-L. (2009, January 3–6). Emotion classification based on gamma-band EEG. Proceedings of the Annual International Conference of the IEEE, Minneapolis, MN, USA.10.1109/IEMBS.2009.5334139 ↗
72. EEG-based emotion estimation using Bayesian weighted-log-posterior function and perceptron convergence algorithm10.1016/j.compbiomed.2013.10.017 ↗
73. Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers10.1016/j.eswa.2015.10.049 ↗
74. Rozgic, V., Vitaladevuni, S.N., and Prasad, R. (2013, January 26–31). Robust the EEG emotion classification using segment level decision fusion. Proceedings of the IEEE Conference of Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, BC, Canada.10.1109/ICASSP.2013.6637858 ↗
75. Li, X., Song, D., Zhang, P., Yu, G., and Hu, B. (2016, January 15–18). Emotion recognition from multi-channel the EEG data through convolutional recurrent neural network. Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Shenzhen, China.10.1109/BIBM.2016.7822545 ↗
76. Tripathi, S., Acharya, S., Sharma, R.D., Mittal, S., and Bhattacharya, S. (2015, January 25–30). Using deep and convolutional neural networks for accurate emotion classification on DEAP dataset. Proceedings of the Twenty-Ninth AAAI Conference on Innovative Applications (IAAI-17), Austin, TX, USA.
77. Emotion recognition based on EEG using LSTM recurrent neural network
78. EEG-based emotion recognition using 3D convolutional neural networks
79. Multisubject “learning” for mental workload classification using concurrent EEG, fNIRS, and physiological measures10.3389/fnhum.2017.00389 ↗
80. Saadati, M., Nelson, J., and Ayaz, H. (2019, January 24–28). Multimodal fNIRS-EEG Classification Using Deep Learning Algorithms for Brain-Computer Interfaces Purposes. Proceedings of the International Conference on Applied Human Factors and Ergonomics, Washington, DC, USA.10.1007/978-3-030-20473-0_21 ↗