Volume 15, Issue 2 (Journal of Control, V.15, N.2 Summer 2021)                   JoC 2021, 15(2): 139-157 | Back to browse issues page


XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Kalhor E, Bakhtiari B. Subject-Independent Channel and Feature Selection for Emotion Classification Based on EEG Signal: A Multi-Task Approach. JoC. 2021; 15 (2) :139-157
URL: http://joc.kntu.ac.ir/article-1-695-en.html
1- , Sadjad University of Technology, Mashhad
Abstract:   (9819 Views)
Several researches have shown that emotion is a mental process and relates to the human’s brain. The emotion has impacts on important procedures, such as memory, concentration, thinking and decision-making. As a result, investigating the mechanism and performance of the emotion have attracted the cognitive science researchers’ attentions. In addition to clinical applications on quick detection, diagnosis and treatment of psychological disorders, investigating the emotion through biological signal processing can play an important role in human-computer communication-based sciences. This will result in progressive improvements in this field. Due to the fact that number of channels and features extracted out of the EEG signal are usually high, selecting relevant channels, with the aim of obtaining effective features, can have a prominent role in the efficiency of these methods. On the other hand, these features should result in the appropriate efficiency when encounter new subjects. In this paper, a multi-task approach is represented for emotion-related channel selection and proper subject-independent feature selection purposes. Moreover, to demonstrate the efficiency of the proposed method, DREAMER and DEAP datasets are used. Also, considering two emotional dimensions, including arousal and valance, some experiments are performed to show the desired efficiency of the proposed method for channel selection and subject-independent feature selection. Experimental results show that the proposed method has better efficiency in comparison with used methods.
Full-Text [PDF 1025 kb]   (167 Downloads)    
Type of Article: Research paper | Subject: Special
Received: 2019/07/22 | Accepted: 2020/06/27 | ePublished ahead of print: 2020/07/5

References
1. [ ] Savran A, Çiftçi K, Chanel G, Rombaut M. Emotion Detection in the Loop from Brain Signals and Facial Images. Proceedings of the eNTERFACE; 2066 Jul 11- 17; Dubrovnik, Croatia: 2006.
2. [2] Chen L, Mao X, Xue Y, Cheng LL. Speech emotion recognition: Features and classification models. Digital Signal Processing 2012;22(6):1154-60. [DOI:10.1016/j.dsp.2012.05.007]
3. [3] Zheng WL, Zhu JY, Lu BL. Identifying stable patterns over time for emotion recognition from EEG. IEEE Transactions on Affective Computing; IEEE; 2017.‏
4. [4] N .Sebe , et al. "Multimodal approaches for emotion recognition: a survey." Internet Imaging VI. Vol. 5670. International Society for Optics and Photonics, (2005). [DOI:10.1117/12.600746]
5. [5] D.Oude Bos, "EEG-based emotion recognition-The Influence of Visual and Auditory Stimuli." Capita Selecta (MSc course),(2006)..‏
6. [6] J.Gratch, and S. Marsella. "A domain-independent framework for modeling emotion." Cognitive Systems Research5.4: 269-306, (2004). [DOI:10.1016/j.cogsys.2004.02.002]
7. [7] M.Grimm, and K. Kroschel. "Rule-based emotion classification using acoustic features." in Proc. Int. Conf. on Telemedicine and Multimedia Communication.( 2005).
8. [8] Y.Dai, et al. "Sparsity constrained differential evolution enabled feature-channel-sample hybrid selection for daily-life EEG emotion recognition." Multimedia Tools and Applications: 1-28, (2018). [DOI:10.1007/s11042-018-5618-0]
9. [9] F.Ren ,Y.Dong, and Wei Wang. "Emotion recognition based on physiological signals using brain asymmetry index and echo state network." Neural Computing and Applications,1-11, (2018).‏ [DOI:10.1007/s00521-018-3664-1]
10. [10] H. Jaeger, Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the" echo state network" approach. Vol. 5. Bonn: GMD-Forschungszentrum Informationstechnik, (2002).
11. [11] M. Li, et al. "Emotion recognition from multichannel EEG signals using K-nearest neighbor classification." Technology and Health Care Preprint (2018): 1-11. [DOI:10.3233/THC-174836]
12. [12] Z.‏Mohammadi, J. Frounchi, and M. Amiri. "Wavelet-based emotion recognition system using EEG signal." Neural Computing and Applications 28.8: 1985-1990, (2017). [DOI:10.1007/s00521-015-2149-8]
13. [13] A R.Subhani, et al. "MRMR based feature selection for the classification of stress using EEG." Sensing Technology (ICST), 2017 Eleventh International Conference on. IEEE, (2017). [DOI:10.1109/ICSensT.2017.8304499]
14. [14] Atkinson, John, and Daniel Campos. "Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers." Expert Systems with Applications 47 (2016): 35-41. [DOI:10.1016/j.eswa.2015.10.049]
15. [15] Yan, Yixin, Chenyang Li, and Shaoliang Meng. "Emotion recognition based on sparse learning feature selection method for social communication." Signal, Image and Video Processing (2019): 1-5. [DOI:10.1007/s11760-019-01448-x]
16. [16] M.Siems, et al. "Measuring the cortical correlation structure of spontaneous oscillatory activity with EEG and MEG." NeuroImage 129: 345-355, (2016). [DOI:10.1016/j.neuroimage.2016.01.055]
17. [17] J.Gao, W.Wang, and Ji Zhang. "Explore interregional EEG correlations changed by sport training using feature selection." Computational intelligence and neuroscience 2016: 30, (2016). [DOI:10.1155/2016/6184823]
18. [18] E.Kroupi, A. Yazdani, and T. Ebrahimi. "EEG correlates of different emotional states elicited during watching music videos." Affective Computing and Intelligent Interaction. Springer, Berlin, Heidelberg. 457-466,(2011).‏ [DOI:10.1007/978-3-642-24571-8_58]
19. [19] L.Piho, and T. Tjahjadi. "A mutual information based adaptive windowing of informative EEG for emotion recognition." IEEE Transactions on Affective Computing,(2018).
20. [20] M.Wang, et al. "Anxiety Level Detection Using BCI of Miner's Smart Helmet." Mobile Networks and Applications 23.2: 336-343, (2018). [DOI:10.1007/s11036-017-0935-5]
21. [21] V. ‏Bajaj, S. Taran, and A. Sengur. "Emotion classification using flexible analytic wavelet transform for electroencephalogram signals." Health information science and systems 6.1: 12, (2018).‏ [DOI:10.1007/s13755-018-0048-y]
22. [22] N.Zhuang, et al. "Emotion recognition from EEG signals using multidimensional information in EMD domain." BioMed research international 2017 (2017).‏ [DOI:10.1155/2017/8317357]
23. [23] Rayatdoost, Soheil, and Mohammad Soleymani. "Cross-Corpus EEG-based emotion recognition." 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2018. [DOI:10.1109/MLSP.2018.8517037]
24. [24] B.Zhang , E. M.Provost, & G.Essl, (2016, March). Cross-corpus acoustic emotion recognition from singing and speaking: A multi-task learning approach. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5805-5809). IEEE. [DOI:10.1109/ICASSP.2016.7472790]
25. [25] R.Xia , & Y.Liu, (2015). A multi-task learning framework for emotion recognition using 2D continuous space. IEEE Transactions on affective computing, 8(1), 3-14. [DOI:10.1109/TAFFC.2015.2512598]
26. [26] B.Zhang , E. M.Provost, & G.Essl, (2017). Cross-corpus acoustic emotion recognition with multi-task learning: Seeking common ground while preserving differences. IEEE Transactions on Affective Computing, 10(1), 85-99. [DOI:10.1109/TAFFC.2017.2684799]
27. [27] C.Wang, J.Zeng, S.Shan, & X.Chen, (2019, September). Multi-Task Learning of Emotion Recognition and Facial Action Unit Detection with Adaptively Weights Sharing Network. In 2019 IEEE International Conference on Image Processing (ICIP) (pp. 56-60). IEEE. [DOI:10.1109/ICIP.2019.8802914]
28. [28] D.Le, Z.Aldeneh , & E. M.Provost, (2017, August). Discretized Continuous Speech Emotion Recognition with Multi-Task Deep Recurrent Neural Network. In Interspeech (pp. 1108-1112). [DOI:10.21437/Interspeech.2017-94]
29. [29] M.Correa, J.Abdon, and Ioannis Patras. ( 2018) "A multi-task cascaded network for prediction of affect, personality, mood and social context using eeg signals." 13th IEEE International Conference on Automatic Face & Gesture Recognition.
30. [30] H. Sunhee, et al. 2020,"Subject-Independent EEG-based Emotion Recognition using Adversarial Learning." 2020 8th International Winter Conference on Brain-Computer Interface (BCI). IEEE.
31. [31] Yang, F., Zhao, X., Jiang, W., Gao, P., & Liu, G. (2019). Multi-method fusion of cross-subject emotion recognition based on high-dimensional EEG features. Frontiers in computational neuroscience, 13. [DOI:10.3389/fncom.2019.00053]
32. [32] H .Janati, T. Bazeille , B.Thirion, (2020). Multi-subject MEG/EEG source imaging with sparse multi-task regression. NeuroImage, 116847. [DOI:10.1016/j.neuroimage.2020.116847]
33. [33] Y.Song, D .Wang, K.Yue,. (2019, July). EEG-Based Motor Imagery Classification with Deep Multi-Task Learning. In 2019 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE. [DOI:10.1109/IJCNN.2019.8852362]
34. [34] G.Chanel, et al. "Emotion assessment: Arousal evaluation using EEG's and peripheral physiological signals." International workshop on multimedia content representation, classification and security. Springer, Berlin, Heidelberg, 2006.‏ [DOI:10.1007/11848035_70]
35. [35] G.Obozinski, B. Taskar, and M. Jordan. "Multi-task feature selection." Statistics Department, UC Berkeley, Tech. Rep 2 (2006).
36. [36] A .Beck and M.Teboulle. "A fast iterative shrinkage-thresholding algorithm for linear inverse problems." SIAM journal on imaging sciences 2.1: 183-202, (2009). [DOI:10.1137/080716542]
37. [37] S.Katsigiannis, and N. Ramzan. "DREAMER: a database for emotion recognition through EEG and ECG signals from wireless low-cost off-the-shelf devices." IEEE journal of biomedical and health informatics 22.1: 98-107, (2018).‏ [DOI:10.1109/JBHI.2017.2688239]
38. [38] Koelstra, Sander, et al. "Deap: A database for emotion analysis; using physiological signals." IEEE transactions on affective computing 3.1 (2012): 18-31. [DOI:10.1109/T-AFFC.2011.15]
39. [39] S.Tripathi, S.Acharya , R. D.Sharma, S.Mittal , & S. Bhattacharya (2017, February). Using Deep and Convolutional Neural Networks for Accurate Emotion Classification on DEAP Dataset. In Twenty-Ninth IAAI Conference.
40. [40] S.Alhagry, A. A.Fahmy, & R. A. El-Khoribi (2017). Emotion recognition based on EEG using LSTM recurrent neural network. Emotion, 8(10), 355-358. [DOI:10.14569/IJACSA.2017.081046]
41. [41] M. L. R.Menezes, A.Samara, L.Galway, A.Sant'Anna. (2017). Towards emotion recognition for virtual environments: an evaluation of eeg features on benchmark dataset. Personal and Ubiquitous Computing, 21(6), 1003-1013. [DOI:10.1007/s00779-017-1072-7]
42. [42] J.Atkinson, & D.Campos, (2016). Improving BCI-based emotion recognition by combining EEG feature selection and kernel classifiers. Expert Systems with Applications, 47, 35-41. [DOI:10.1016/j.eswa.2015.10.049]
43. [43] Song, Tengfei, et al. "EEG emotion recognition using dynamical graph convolutional neural networks." IEEE Transactions on Affective Computing (2018).
44. [44] P.Arnau-Gonzalez, S.Katsigiannis, N.Ramzan, D.Tolson, & M. Arevalillo-Herrez, (2017, October). ES1D: A deep network for EEG-based subject identification. In 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering (BIBE) (pp. 81-85). IEEE. [DOI:10.1109/BIBE.2017.00-74]
45. [45] Zhang, Tong, et al. "GCB-Net: Graph convolutional broad network and its application in emotion recognition." IEEE Transactions on Affective Computing (2019). [DOI:10.1109/TAFFC.2019.2937768]
46. [46] R.Jenke, A. Peer, and M. Buss. "Feature extraction and selection for emotion recognition from EEG." IEEE Transactions on Affective Computing 5.3: 327-339, (2014).‏ [DOI:10.1109/TAFFC.2014.2339834]
47. [47] W. Zheng, (2016). Multichannel EEG-based emotion recognition via group sparse canonical correlation analysis. IEEE Transactions on Cognitive and Developmental Systems, 9(3), 281-290. [DOI:10.1109/TCDS.2016.2587290]
48. [48] N. Zheng, Y. Zeng, L. Tong, C. Zhang, H. Zhang, & B. Yan, (2017). Emotion recognition from EEG signals using multidimensional information in EMD domain. BioMed research international, 2017.‏ [DOI:10.1155/2017/8317357]
49. [49] B. Nakisa, M. Rastgoo, N. D.Tjondronegoro, & V. Chandran, (2018). Evolutionary computation algorithms for feature selection of EEG-based emotion recognition using mobile sensors. Expert Systems with Applications, 93, 143-155. [DOI:10.1016/j.eswa.2017.09.062]
50. [50] J. Zhang, M. Chen, S. Zhao, S. Hu, Z. Shi, & Y. Cao, (2016). ReliefF-based EEG sensor selection methods for emotion recognition. Sensors, 16(10), 1558. [DOI:10.3390/s16101558]
51. [51]M.Robnik-Šikonja and I. Kononenko. "Theoretical and empirical analysis of ReliefF and RReliefF." Machine learning53.1-2: 23-69,(2003). [DOI:10.1023/A:1025667309714]
52. [52] Schuller, B., et al., Cross-corpus acoustic emotion recognition: Variances and strategies. IEEE Transactions on Affective Computing, 2010. 1(2): p. 119-131. [DOI:10.1109/T-AFFC.2010.8]

Add your comments about this article : Your username or Email:
CAPTCHA

Send email to the article author


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

© 2022 CC BY-NC 4.0 | Journal of Control

Designed & Developed by : Yektaweb