IJBTT

Novel Model Architecture for EEG Emotion Classification

	International Journal of Biotech Trends and Technology (IJBTT)
	© 2019 by IJBTT Journal
	Volume - 9 Issue - 3
	Year of Publication : 2019
	Authors : Lars Rune Christensen , Mohamed Ahmed Abdullah
	DOI :  10.14445/22490183/IJBTT-V9I3P601

Citation

MLA Style:Lars Rune Christensen , Mohamed Ahmed Abdullah "Novel Model Architecture for EEG Emotion Classification" International Journal of Biotech Trends and Technology 9.2 (2019): 1-5.

APA Style:Lars Rune Christensen , Mohamed Ahmed Abdullah(2019). Novel Model Architecture for EEG Emotion Classification. International Journal of Biotech Trends and Technology, 9(2), 1-5.

Abstract

Enhancing the communication between the human and the machine is the core purpose of the HCI field (Human Machine Interaction), Identifying human emotion is an important aspect of enhancing this communication. This work will identify 10 distinctive emotions, the emotions will be measured by Dominance, Valance, and Arousal. The classification will run five different models with respect to Riemannian Geometry to enhance the filtering. The EEG signal is being collected in a form of two sessions per subject, one session for training purposes the other for testing, then the data is filtered then the model was trained to give an accuracy between 50% to 70%. SAM assessment technique has been conducted to tag the data.

References

[1] M. M. Bradley and P. J. Lang, “Measuring emotion: The selfassessment manikin and the semantic differential,” J. Behav. Ther. Exp. Psychiatry, vol. 25, no. 1, pp. 49–59, 1994.
[2] A. Barachantet al., “Classification of covariance matrices using a Riemannian-based kernel for BCI applications To cite this version : HAL Id : hal-00820475 Classification of covariance matrices using a Riemannian-based kernel for BCI applications,” 2013.
[3] H. Xu and K. N. (Kostas) Plataniotis, “Affect recognition using EEG signal,” IEEE 14th Int. Work. Multimed. Signal Process., pp. 299–304, 2012.
[4] K. J. Miller, G. Schalk, D. Hermes, J. G. Ojemann, and R. P. N. Rao, “Spontaneous Decoding of the Timing and Content of Human Object Perception from Cortical Surface Recordings Reveals Complementary Information in the Event-Related Potential and Broadband Spectral Change,” PLoSComput. Biol., vol. 12, no. 1, pp. 1–20, 2016.
[5] A. Barachant, S. Bonnet, A. Barachant, S. Bonnet, C. Selection, and A. Barachant, “Channel Selection Procedure using Riemannian distance for BCI applications To cite this version : Channel Selection Procedure using Riemannian distance for BCI applications,” 2011.
[6] S. Lemm, B. Blankertz, G. Curio, and K. R. Müller, “Spatiospectral filters for improving the classification of single trial EEG,” IEEE Trans. Biomed. Eng., vol. 52, no. 9, pp. 1541– 1548, 2005.
[7] Z. J. Koles, M. S. Lazar, and S. Z. Zhou, “Spatial patterns underlying population differences in the background EEG,” Brain Topogr., vol. 2, no. 4, pp. 275–284, 1990.
[8] G. Cheng, “A closed-loop Brain-Computer Music Interface for continuous affective interaction,” no. December, pp. 176– 179, 2017.
[9] B. Rivet, A. Souloumiac, V. Attina, and G. Gibert, “xDAWN algorithm to enhance evoked potentials: application to brain computer interface,” Biomed Eng, IEEE Trans, vol. 56, pp. 1–9, 2009.
[10] B. Rivet, H. Cecotti, A. Souloumiac, E. Maby, and J. Mattout, “Theoretical analysis of XDAWN algorithm: Application to an efficient sensor selection in a P300 BCI BT - 19th European Signal Processing Conference, EUSIPCO 2011, August 29, 2011 - September 2, 2011,” Eur. Signal Process. Conf., no. Eusipco, pp. 1382–1386, 2011.
[11] S. Jirayucharoensak, S. Pan-Ngum, and P. Israsena, “EEGBased Emotion Recognition Using Deep Learning Network with Principal Component Based Covariate Shift Adaptation,” Sci. World J., vol. 2014, 2014.
[12] M. Congedo, A. Barachant, and A. Andreev, “A New Generation of Brain-Computer Interface Based on Riemannian Geometry,” arXivPrepr. arXiv1310.8115, vol. 33, no. 0, 2013.
[13] X. Li et al., “Emotion Recognition from Multi-Channel EEG Data through Convolutional Recurrent Neural Network,” 2016 Ieee Int. Conf. Bioinforma. Biomed., pp. 352–359, 2016.
[14] H. Zhang et al., “A feasibility study of detecting brain signal in EEG during emotional self-regulation,” pp. 184–187, 2017.
[15] S. I. Alzahrani, “P300 Wave Detection Using EmotivEpoc+ Headset: Effects of Matrix Size, Flash Duration, and Colors,” p. 76f., 2016.
[16] W. L. Zheng, W. Liu, Y. Lu, B. L. Lu, and A. Cichocki, “EmotionMeter: A Multimodal Framework for Recognizing Human Emotions,” IEEE Trans. Cybern., pp. 1–13, 2018.
[17] L. R. Christensen, M. A. Abdullah “EEG Emotion Detection Review,” 2018 IEEE Conf. Comput. Intell. Bioinforma. Comput. Biol., pp. 1–7, 2018.

Keywords
EEG; Emotion Recognition; Emotion Detection; HMI; BCI, Riemannian Geometry, TangentSpace