Facial Expression Decoding based on fMRI Brain Signal

Abstract

The analysis of facial expressions is a hot topic in brain-computer interface research. To determine the facial expressions of the subjects under the corresponding stimulation, we analyze the fMRI images acquired by the Magnetic Resonance. There are six kinds of facial expressions: "anger", "disgust", "sadness", "happiness", "joy" and "surprise". We demonstrate that brain decoding is achievable through the parsing of two facial expressions ("anger" and "joy"). Support vector machine and extreme learning machine are selected to classify these expressions based on time series features. Experimental results show that the classification performance of the extreme learning machine algorithm is better than support vector machine. Among the eight participants in the trials, the classification accuracy of three subjects reached 70-80%, and the remaining five subjects also achieved accuracy of 50-60%. Therefore, we can conclude that the brain decoding can be used to help analyzing human facial expressions.

References

[1] Arlot, S.; Celisse, A.(2010). A survey of cross-validation procedures for model selection, Statistics Survey, 4, 40-79, 2010.
https://doi.org/10.1214/09-SS054

[2] Blum, A.; Kalai, A.(1999). Beating the hold-out:bounds for K-fold and progressive crossvalidation, Proceedings of the twelfth annual conference on Computational learning theory. ACM, 203-208, 1999.
https://doi.org/10.1145/307400.307439

[3] Davis, M; Whalen, P. J.(2001). The amygdala: vigilance and emotion, Mol Psychiatry, 6(1), 13-34, 2001.
https://doi.org/10.1038/sj.mp.4000812

[4] Desikan, R.S.; Segonne, F; Fischl, B.(2006). An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest, Neuroimage, 31(3), 968-980, 2006.
https://doi.org/10.1016/j.neuroimage.2006.01.021

[5] Ekman, P.(1992). An argument for basic emotions, Cognition & Emotion, 6(3-4), 169-200, 1992.
https://doi.org/10.1080/02699939208411068

[6] Forman, S D; Cohen, J.D.; Fitzgerald, M. et al.(1992). Improved Assessment of Significant Activation in Functional Magnetic Resonance Imaging (fMRI): Use of a Cluster-Size Threshold, Magnetic Resonance in Medicine, 3(5), 636-647, 2010.
https://doi.org/10.1002/mrm.1910330508

[7] Gilead, M.; Liberman, N.; Maril, A.(2013). The language of future-thought: An fMRI study of embodiment and tense processing, Neuroimage, 65(2), 267-279, 2013.
https://doi.org/10.1016/j.neuroimage.2012.09.073

[8] Huang, G.B.; Zhu, Q.Y.; Siew, C.K.(2004). Extreme learning machine: a new learning scheme of feedforward neural networks, IEEE International Joint Conference on Neural Networks, 2, 985-990, 2005.

[9] Huang, G. B.; Zhu, Q. Y.; Siew, C.K.(2006). Extreme learning machine: Theory and applications, Neurocomputing, 70(1), 489-501, 2006.
https://doi.org/10.1016/j.neucom.2005.12.126

[10] Kearns, M; Ron, D.(1997). Algorithmic stability and sanity-check bounds for leave-one-out cross-validation, Neural Computation, 11(6), 1427-1453, 1997.
https://doi.org/10.1162/089976699300016304

[11] Logothetis, N.K.; Pauls, J.; Augath, M.(2001). Neurophysiological investigation of the basis of the fMRI signal, Nature, 412(6843), 150-157, 2001.
https://doi.org/10.1038/35084005

[12] Lehmann, T.M; Gonner, C.; Spitzer, K.(1999). Survey: interpolation methods in medical image processing, IEEE Transactions on Medical Imaging, 18(11), 1049-1075, 1999.
https://doi.org/10.1109/42.816070

[13] Litvak, V.; Mattout, J.; Kiebel, S. et al. (2011). EEG and MEG Data Analysis in SPM8, Computational Intelligence and Neuroscience, 2011(3), 852961, 2011.
https://doi.org/10.1155/2011/852961

[14] Michel, C.M; Murray, M.M.; Lantz, G.(2004). EEG source imaging, Clinical Neurophysiology, 115(10), 2195-2222, 2004.
https://doi.org/10.1016/j.clinph.2004.06.001

[15] Rodriguez, J.D.; Perez, A.; Lozano, J.A.(2010). Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation, IEEE Computer Society, 32(3), 569-575, 2010.
https://doi.org/10.1109/TPAMI.2009.187

[16] Schalk, G.; Mcfarland, D.J.; Hinterberger, T.(2004). BCI2000: a general-purpose braincomputer interface (BCI) system, IEEE Transactions on Bio-medical Engineering, 51(6), 1034-1043, 2004.
https://doi.org/10.1109/TBME.2004.827072

[17] Suykens, J.A.K.(1999). Least squares support vector machine classifiers: a large scale algorithm[ C]. European Conference on Circuit Theory and Design, 1999, 839-842, 1999.

[18] Tugui, A. (2014). GLM Analysis for fMRI using Connex Array International Journal of Computers Communications & Control, 9(6), 768-775, 2014.
https://doi.org/10.15837/ijccc.2014.6.1482

[19] Ziegel, E.R.(2012). An Introduction to Generalized Linear Models[J]. Technometrics, 44(4), 406-407, 2012.
https://doi.org/10.1198/tech.2002.s91

[20] Zilles, K; Amunts, K.(2010). Centenary of Brodmann's map-conception and fate, Nature Reviews Neuroscience, 11(2), 139-145, 2010.
https://doi.org/10.1038/nrn2776
Published
2019-08-05
How to Cite
CAO, Benchun et al. Facial Expression Decoding based on fMRI Brain Signal. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, [S.l.], v. 14, n. 4, p. 475-488, aug. 2019. ISSN 1841-9844. Available at: <http://univagora.ro/jour/index.php/ijccc/article/view/3433>. Date accessed: 02 july 2020. doi: https://doi.org/10.15837/ijccc.2019.4.3433.

Keywords

Brain-computer interface, machine learning, extreme learning machine, fMRI, image processing