This paper proposed a new semi-supervised algorithm combined with Mutual-cross Imperial Competition Algorithm (MCICA) optimizing Support Vector Machine (SVM) for motion imagination EEG classification, which not only reduces the tedious and time-consuming training process and enhances the adaptability of Brain Computer Interface (BCI), but also utilizes the MCICA to optimize the parameters of SVM in the semi-supervised process. This algorithm combines mutual information and cross validation to construct objective function in the semi-supervised training process, and uses the constructed objective function to establish the semi-supervised model of MCICA for optimizing the parameters of SVM, and finally applies the selected optimal parameters to the data set Iva of 2005 BCI competition to verify its effectiveness. The results showed that the proposed algorithm is effective in optimizing parameters and has good robustness and generalization in solving small sample classification problems.
LuhrsM.RiemenschneiderB.EckJ. et al., The potential of MR-Encephalography for BCI/Neurofeedback applications with high temporal resolution, NeuroImage194 (2019), 228–243.
2.
RazaH.RatheeD.ZhouS-M. et al., Covariate shift estimation based adaptive ensemble learning for handling non-stationarity in motor imagery related EEG-based brain-computer interface, Neurocomputing343 (2019), 154–166.
3.
Al-NafjanA.HosnyM.Al-OhaliY. et al., Review and classification of emotion recognition based on EEG brain-computer interface system research: a systematic review, Applied Sciences-Basel7(12) (2017).
4.
WangJ.J.GuZ.H.YuZ.L. et al., An online semi-supervised P300 speller based on extreme learning machine, Neurocomputing269 (2017), 148–151.
5.
ScudderH., Probability of error of some adaptive pattern-recognition machines, IEEE Transactions on Information Theory11(3) (1965), 363–371.
6.
FralickS., Learning to recognize patterns without a teacher, IEEE Transductions on Information Theory13(1) (1967), 57–64.
7.
ChapelleSchölkopfB. and ZienA., A semi-supervised learning, Cambridge, USA: MIT Press, 2006.
8.
MerzC.J., D.CSt. Clair and BondW.E., SeMi-supervised adaptive resonance theory, in: IJCNN International Joint Conference on Neural Networks, 1992, pp. 851–856.
9.
BlumA. and MitchellT., Combining Labeled and Unlabeled Data with Co-Training, in: Proceedings of the 11th Annual Conference on Computational Learning Theory, 1998, pp. 92–100.
10.
VapnikV. and SterinA., On structural risk minimization or overall risk in a problem of pattern recognition, Automation and Remote Control10(3) (1997), 1495–1503.
11.
ZhangL.ChenY.TanX. et al., An improved self-training algorithm for classifying motor imagery electroencephalography in brain-computer interface, Journal of Medical Imaging and Health Informatics7(2) (2017), 330–337.
12.
YoonA.S.LeeT.LimY. et al., Semi-supervised learning with deep generative models for asset failure prediction, in: KDD17 Workshop on Machine Learning for Prognostics and Health Management, 2017.
13.
DuW.PhlypoR. and AdaliT., Adaptive feature selection and feature fusion for semi-supervised classification, Journal of Signal Processing Systems for Signal Image and Video Technology91(5) (2019), 521–537.
14.
CevikalpH. and FrancV., Large-scale robust transductive support vector machines, Neurocomputing235 (2017), 199–209.
15.
XuY.L.HuaJ.ZhangH. et al., Improved transductive support vector machine for a small labelled set in motor imagery-based brain-computer interface, Computational Intelligence and Neuroscience, 2019.
16.
ZhaoX.H.ZhaoJ.Z.CaiW.M. et al., Transferring common spatial filters with semi-supervised learning for zero-training motor imagery brain-computer interface, IEEE Access7(2019) (2019), 58120–58130.
17.
SheQ.S.HuB.LuoZ.Z. et al., A hierarchical semi-supervised extreme learning machine method for EEG recognition, Medical & Biological Engineering & Computing57(1) (2019), 147–157.
18.
LiY.Q.GuanC.T.LiH.Q. et al., A self-training semi-supervised SVM algorithm and its application in an EEG-based brain computer interface speller system, Pattern Recognition Letters29(9) (2008), 1285–1294.
19.
FuC.J. and YangY.P., A batch-mode active learning SVM method based on semi-supervised clustering, Intelligent Data Analysis19(2) (2015), 345–358.
20.
LiaoR.J.ZhengH.B. and GrzyborwskiS., A multiclass SVM-based classifier for transformer fault diagnosis using a particle swarm optimizer with time-varying acceleration coefficients, International Transactions on Electrical Energy Systems23(2) (2013), 181–190.
21.
FeiS.W. and ZhangX.B., Fault diagnosis of power transformer based on support vector machine with genetic algorithm, Expert Systems with Applications36(8) (2009), 11352–11357.
22.
RenH.B.YangL. and ChenS.Z., Sliding mode switch control of adjustable hydro-pneumatic suspension based on parallel adaptive clonal selection algorithm, Journal of Vibroengineering17(6) (2015), 3196–3210.
23.
Atashpaz-GargariE. and LucasC., Imperialist competitive algorithm: an algorithm for optimization inspired by imperialistic competition, in: IEEE Congress on Evolutionary Computation, 2007, pp. 4661–4667.
24.
VapnikV., Estimation of Dependences Based on Empirical Data, 1982, Springer Verlag.
25.
HouH.R.MengQ.H.ZengM. et al., Improving classification of slow cortical potential signals for BCI systems with polynomial fitting and voting support vector machine, IEEE Signal Processing Letters25(2) (2018).
26.
Kefi-FattehT.KsantiniR.KaanicheM.B. et al., A novel incremental one-class support vector machine based on low variance direction, Pattern Recognition91 (2019), 308–321.
27.
ZhanquanS. and FoxG., Large scale classification based on combination of parallel SVM and interpolative MDS.
28.
TrostianchynA.DuriaginaZ.TkachenkoR. et al., The combined use of the wiener polynomial and SVM for material classification task in medical implants production, I.J. Intelligent Systems and Applications (2018), 40–47.
29.
AbeS., Fuzzy support vector machines for multilabel classification, Pattern Recognition48(6) (2015), 2110–2117.
30.
TharwatA., Parameter investigation of support vector machine classifier with kernel functions, Knowledge and Information Systems61(3) (2019), 1269–1302.
31.
SharminS.ShoyaibM. et al., Simultaneous feature selection and discretization based on mutual information, Pattern Recognition91 (2019), 162–174.
32.
MahmoudiM. and ShansiM., Multi-class EEG classification of motor imagery signal by finding optimal time segments and features using SNR-based mutual information, Australasian Physical & Engineering Sciences in Medicine41(4) (2018), 957–972.
33.
AngK.K.ChinZ.Y.ZhangH. et al., Mutual information-based selection of optimal spatial-temporal patterns for single-trial EEG-based BCIs, Pattern Recognition45(6) (2012), 2137–2144.
34.
SimaC. and DoughertyE.R., Optimal convex error estimators for classification, Pattern Recognition39(9) (2006), 1763–1780.
35.
WangJ.FengZ.LuN. et al., An information fusion scheme based common spatial pattern method for classification of motor imagery tasks, Biomedical Signal Processing And Control46 (2018), 10–17.
36.
CalvoH.ParedesJ.L. and Figueroa-NazunoJ., Measuring concept semantic relatedness through common spatial pattern feature extraction on EEG signals, Cognitive Systems Research50 (2018), 36–51.
37.
AlotaibyT.N.AlshebeiliS.A.AljafarL.M. et al., ECG-based subject identification using common spatial pattern and SVM, Journal of Sensors (2019).
