Advertisement

Accurate Classification of EEG Signals Using Neural Networks Trained by Hybrid Population-Physic-Based Algorithm

  • Sajjad Afrakhteh
  • Mohammad-Reza MosaviEmail author
  • Mohammad Khishe
  • Ahmad Ayatollahi
Research Article

Abstract

A brain-computer interface (BCI) system is one of the most effective ways that translates brain signals into output commands. Different imagery activities can be classified based on the changes in μ and β rhythms and their spatial distributions. Multi-layer perceptron neural networks (MLP-NNs) are commonly used for classification. Training such MLP-NNs has great importance in a way that has attracted many researchers to this field recently. Conventional methods for training NNs, such as gradient descent and recursive methods, have some disadvantages including low accuracy, slow convergence speed and trapping in local minimums. In this paper, in order to overcome these issues, the MLP-NN trained by a hybrid population-physics-based algorithm, the combination of particle swarm optimization and gravitational search algorithm (PSOGSA), is proposed for our classification problem. To show the advantages of using PSOGSA that trains NNs, this algorithm is compared with other meta-heuristic algorithms such as particle swarm optimization (PSO), gravitational search algorithm (GSA) and new versions of PSO. The metrics that are discussed in this paper are the speed of convergence and classification accuracy metrics. The results show that the proposed algorithm in most subjects of encephalography (EEG) dataset has very better or acceptable performance compared to others.

Keywords

Brain-computer interface (BCI) classification electroencephalography (EEG) gravitational search algorithm (GSA) multi-layer perceptron neural network (MLP-NN) particle swarm optimization 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    A. S. Aghaei, M. S. Mahanta, K. N. Plataniotis. Separable common spatio-spectral patterns for motor imagery BCI systems. IEEE Transactions on Biomedical Engineering, vol. 63, no. 1, pp. 15–29, 2016. DOI: 10.1109/TBME.2015. 2487738.CrossRefGoogle Scholar
  2. [2]
    D. D. Huang, K. Qian, D. Y. Fei, W. C. Jia, X. D. Chen, O. Bai. Electroencephalography (EEG)-based brain-computer interface (BCI): A 2-D virtual wheelchair control based on event-related desynchronization/synchronization and state control. IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 20, no. 3, pp. 379–388, 2012. DOI: 10.1109/TNSRE.2012.2190299.CrossRefGoogle Scholar
  3. [3]
    K. LaFleur, K. Cassady, A. Doud, K. Shades, E. Rogin, B. He. Quadcopter control in three-dimensional space using a noninvasive motor imagery based brain-computer interface. Journal of Neural Engineering, vol. 10, no. 4, Article number 046003, 2013. DOI: 10.1088/1741-2560/10/4/046 003/meta.Google Scholar
  4. [4]
    J. R. Wolpaw, N. Birbaumer, D. J. McFarland, G. Pfurtscheller, T. M. Vaughan. Brain-computer interfaces for communication and control. Clinical Neurophysiology, vol. 113, no. 6, pp. 767–791, 2002. DOI: 10.1016/S1388-2457(02)00057-3.CrossRefGoogle Scholar
  5. [5]
    T. M. Vaughan. Guest editorial brain-computer interface technology: A review of the second international meeting. IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 11, no. 2, pp. 94–109, 2003. DOI: 10.1109/TNSRE.2003.814799.CrossRefGoogle Scholar
  6. [6]
    C. R. Hema, M. P. Paulraj, S. Yaacob, A. H. Adom, R. Nagarajan. EEG motor imagery classification of hand movements for a brain machine interface. Biomedical Soft Computing and Human Sciences, vol. 14, no. 2, pp. 49–56, 2009. DOI: 10.24466/ijbschs.14.2_49.Google Scholar
  7. [7]
    B. Blankertz, G. Dornhege, M. Krauledat, K. R. Muller, G. Curio. The non-invasive Berlin brain-computer interface: Fast acquisition of effective performance in untrained subjects. NeuroImage, vol. 37, no. 2, pp. 539–550, 2007. DOI: 10.1016/j.neuroimage.2007.01.051.CrossRefGoogle Scholar
  8. [8]
    X. Y. Yu, P. Chum, K. B. Sim. Analysis the effect of PCA for feature reduction in non-stationary EEG based motor imagery of BCI system. Optik-International Journal for Light and Electron Optics, vol. 125, no. 3, pp. 1498–1502, 2014. DOI: 10.1016/j.ijleo.2013.09.013.CrossRefGoogle Scholar
  9. [9]
    R. N. Vigário. Extraction of ocular artefacts from EEG using independent component analysis. Electroencephalography and Clinical Neurophysiology, vol. 103, no. 3, pp. 395–404, 1997. DOI: 10.1016/S0013-4694(97)00042-8.CrossRefGoogle Scholar
  10. [10]
    J. B. Tenenbaum, V. de Silva, J. C. Langford. A global geometric framework for nonlinear dimensionality reduction. Science, vol. 290, no. 5500, pp. 2319–2323, 2000. DOI: 10.1126/science.290.5500.2319.CrossRefGoogle Scholar
  11. [11]
    T. Wu, G. Z. Yan, B. H. Yang, H. Sun. EEG feature extraction based on wavelet packet decomposition for brain computer interface. Measurement, vol. 41, no. 6, pp. 618–625, 2008. DOI: 10.1016/j.measurement.2007.07.007.CrossRefGoogle Scholar
  12. [12]
    H. Ramoser, J. Muller-Gerking, G. Pfurtscheller. Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Transactions on Rehabilitation Engineering, vol. 8, no. 4, pp. 441–446, 2000. DOI: 10.1109/86. 895946.CrossRefGoogle Scholar
  13. [13]
    G. Pfurtscheller, C. Neuper, A. Schlogl, K. Lugger. Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Transactions on Rehabilitation Engineering, vol. 6, no. 3, pp. 316–325, 1998. DOI: 10.1109/86.712230.CrossRefGoogle Scholar
  14. [14]
    S. Lemm, C. Schafer, G. Curio. BCI competition 2003-data set III: Probabilistic modeling of sensorimotor mu rhythms for classification of imaginary hand movements. IEEE Transactions on Biomedical Engineering, vol. 51, no. 6, pp. 1077–1080, 2004. DOI: 10.1109/TBME.2004. 827076.CrossRefGoogle Scholar
  15. [15]
    S. M. Zhou, J. Q. Gan, F. Sepulveda. Classifying mental tasks based on features of higher-order statistics from EEG signals in brain-computer interface. Information Sciences, vol. 178, no. 6, pp. 1629–1640, 2008. DOI: 10.1016/j.ins.2007. 11.012.CrossRefGoogle Scholar
  16. [16]
    Y. L. Ma, X. H. Ding, Q. S. She, Z. Z. Luo, T. Potter, Y. C. Zhang. Classification of motor imagery EEG signals with support vector machines and particle swarm optimization. Computational and Mathematical Methods in Medicine, vol. 2016, Article number 4941235, 2016. DOI: 10.1155/2016/4941235.Google Scholar
  17. [17]
    A. Subasi, E. Erçelebi. Classification of EEG signals using neural network and logistic regression. Computer Methods and Programs in Biomedicine, vol. 78, no. 2, pp. 87–99, 2005. DOI: 10.1016/j.cmpb.2004.10.009.CrossRefzbMATHGoogle Scholar
  18. [18]
    D. Whitley. A genetic algorithm tutorial. Statistics and Computing, vol. 4, no. 2, pp. 65–85, 1994. DOI: 10.1007/BF00175354.CrossRefGoogle Scholar
  19. [19]
    J. Kennedy, R. Eberhart. Particle swarm optimization. In Proceedings of International Conference on Neural Networks, Perth, Australia, pp. 1942–1948, 1995. DOI: 10.1109/ICNN.1995.488968.CrossRefGoogle Scholar
  20. [20]
    M. Dorigo, V. Maniezzo, A. Colorni. Ant system: Optimization by a colony of cooperating agents. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 26, no. 1, pp. 29–41, 1996. DOI: 10.1109/3477.484436.CrossRefGoogle Scholar
  21. [21]
    X. H. Shi, Y. C. Liang, H. P. Lee, C. Lu, L. M. Wang. An improved GA and a novel PSO-GA-based hybrid algorithm. Information Processing Letters, vol. 93, no. 5, pp. 255–261, 2005. DOI: 10.1016/j.ipl.2004.11.003.MathSciNetCrossRefzbMATHGoogle Scholar
  22. [22]
    A. J. Ouyang, Y. Q. Zhou. An improved PSO-ACO algorithm for solving large-scale TSP. Advanced Materials Research, vol. 143–144, pp. 1154–1158, 2011. DOI: 10.4028/www.scientific.net/AMR.143-144.1154.Google Scholar
  23. [23]
    S. T. Li, M. K. Tan, I. W. Tsang, J. T. Y. Kwok. A hybrid PSO-BFGS strategy for global optimization of multimodal functions. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 41, no. 4, pp. 1003–1014, 2011. DOI: 10.1109/TSMCB.2010.2103055.CrossRefGoogle Scholar
  24. [24]
    S. Mirjalili, S. Z. M. Hashim. A new hybrid PSOGSA algorithm for function optimization. In Proceedings of International Conference on Computer and Information Application, Tianjin, China, pp. 374–377, 2010. DOI: 10.1109/ICCIA.2010.6141614.Google Scholar
  25. [25]
    S. Q. Sun, Q. K. Peng. A hybrid PSO-GSA strategy for high-dimensional optimization and microarray data clustering. In Proceedings of IEEE International Conference on Information and Automation, Hailar, China, pp. 41–46, 2014. DOI: 10.1109/ICInfA.2014.6932623.Google Scholar
  26. [26]
    H. Aminzadeh, M. Miri. Optimal placement of phasor measurement units to obtain network observability using a hybrid PSO-GSA algorithm. Australian Journal of Electrical and Electronics Engineering, vol. 12, no. 4, pp. 342–349, 2015. DOI: 10.1080/1448837X.2015.1092929.Google Scholar
  27. [27]
    E. Rashedi, H. Nezamabadi-Pour, S. Saryazdi. GSA: A gravitational search algorithm. Information Sciences, vol. 179, no. 13, pp. 2232–2248, 2009. DOI: 10.1016/j.ins. 2009.03.004.CrossRefzbMATHGoogle Scholar
  28. [28]
    Y. Jiang, T. S. Hu, C. C. Huang, X. N. Wu. An improved particle swarm optimization algorithm. Applied Mathematics and Computation, vol. 193, no. 1, pp. 231–239, 2007. DOI: 10.1016/j.amc.2007.03.047.CrossRefzbMATHGoogle Scholar
  29. [29]
    T. Geetha, M. Sathya. Modified particle swarm optimization (MPSO) algorithm for web service selection (WSS) problem. In Proceedings of International Conference on Data Science & Engineering, Cochin, India, pp. 113–116, 2012. DOI: 10.1109/ICDSE.2012.6281954.Google Scholar
  30. [30]
    G. Q. Bao, K. F. Mao. Particle swarm optimization algorithm with asymmetric time varying acceleration coefficients. In Proceedings of IEEE International Conference on Robotics and Biomimetics, Guilin, China, pp. 2134–2139, 2009. DOI: 10.1109/ROBIO.2009.5420504.Google Scholar
  31. [31]
    C. Cortes, V. Vapnik. Support-vector networks. Machine Learning, vol. 20, no. 3, pp. 273–297, 1995. DOI: 10.1007/BF00994018.zbMATHGoogle Scholar
  32. [32]
    N. S. Altman. An introduction to kernel and nearestneighbor nonparametric regression. The American Statistician, vol. 46, no. 3, pp. 175–185, 1992. DOI: 10.1080/0003 1305.1992.10475879.MathSciNetGoogle Scholar
  33. [33]
    M. Wessel. Pioneering Research into Brain Computer Interfaces, Master dissertation, Delft University of Technology, the Netherlands, 2006.Google Scholar
  34. [34]
    H. Jasper, W. Penfield. Electrocorticograms in man: Effect of voluntary movement upon the electrical activity of the precentral gyrus. Archiv fur Psychiatrie und Nervenkrankheiten, no. 1–2, pp. 163–174, 1949. DOI: 10.1007/BF01062488.CrossRefGoogle Scholar
  35. [35]
    Z. J. Koles. The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG. Electroencephalography and Clinical Neurophysiology, vol. 79, no. 6, pp. 440–447, 1991. DOI: 10.1016/0013-4694 (91)90163-X.CrossRefGoogle Scholar
  36. [36]
    V. Abedifar, M. Eshghi, S. Mirjalili, S. M. Mirjalili. An optimized virtual network mapping using PSO in cloud computing. In Proceedings of the 21st Iranian Conference on Electrical Engineering, Mashhad, Iran, 2013. DOI: 10.1109/IranianCEE.2013.6599723.Google Scholar
  37. [37]
    L. S. Nguyen, D. Frauendorfer, M. S. Mast, D. Gatica-Perez. Hire me: Computational inference of hirability in employment interviews based on nonverbal behavior. IEEE Transactions on Multimedia, vol. 16, no. 4, pp. 1018–1031, 2014. DOI: 10.1109/TMM.2014.2307169.CrossRefGoogle Scholar
  38. [38]
    P. Auer, H. Burgsteiner, W. Maass. A learning rule for very simple universal approximators consisting of a single layer of perceptrons. Neural Networks, vol. 21, no. 5, pp. 786–795, 2008. DOI: 10.1016/j.neunet.2007.12.036.CrossRefzbMATHGoogle Scholar
  39. [39]
    M. R. Mosavi, M. Khishe. Training a feed-forward neural network using particle swarm optimizer with autonomous groups for sonar target classification. Journal of Circuits, Systems and Computers, vol. 26, no. 11, Article number 1750185, 2017. DOI: 10.1142/S0218126617501857.Google Scholar
  40. [40]
    M. Khishe, M. R. Mosavi, M. Kaveh. Improved migration models of biogeography-based optimization for sonar dataset classification by using neural network. Applied Acoustics, vol. 118, pp. 15–29, 2017. DOI: 10.1016/j.apacoust. 2016.11.012.CrossRefGoogle Scholar
  41. [41]
    M. R. Mosavi, M. Khishe, A. Ghamgosar. Classification of sonar data set using neural network trained by gray wolf optimization. Neural Network World, vol. 26, no. 4, pp. 393–415, 2016. DOI: 10.14311/NNW.2016.26.023.CrossRefGoogle Scholar
  42. [42]
    M. R. Mosavi, M. Khishe, M. Akbarisani. Neural network trained by biogeography-based optimizer with chaos for sonar data set classification. Wireless Personal Communications, vol. 95, no. 4, pp. 4623–4642, 2017. DOI: 10.1007/s11277-017-4110-x.CrossRefGoogle Scholar
  43. [43]
    J. Müller-Gerking, G. Pfurtscheller, H. Flyvbjerg. Designing optimal spatial filters for single-trial EEG classification in a movement task. Clinical Neurophysiology, vol. 110, no. 5, pp. 787–798, 1999. DOI: 10.1016/S1388-2457 (98)00038-8.CrossRefGoogle Scholar
  44. [44]
    J. Yan. The Attract Force Equation of Energy. American Journal of Modern Physics, vol. 3, no. 6, pp. 224–226, 2014. DOI: 10.11648/j.ajmp.20140306.13.CrossRefGoogle Scholar
  45. [45]
    A. A. Abarghouei, A. Ghanizadeh, S. M. Shamsuddin. Advances of soft computing methods in edge detection. International Journal of Advances in Soft Computing and Its Applications, vol. 1, no. 2, pp. 162–203, 2009.Google Scholar
  46. [46]
    E. Rashedi, H. Nezamabadi-Pour, S. Saryazdi. BGSA: Binary gravitational search algorithm. Natural Computing, vol. 9, no. 3, pp. 727–745, 2010. DOI: 10.1007/s11047-009-9175-3.MathSciNetCrossRefzbMATHGoogle Scholar
  47. [47]
    S. Mirjalili, S. M. Mirjalili, A. Lewis. Let a biogeographybased optimizer train your multi-layer perceptron. Information Sciences, vol. 269, pp. 188–209, 2014. DOI: 10.1016/j.ins.2014.01.038.MathSciNetCrossRefGoogle Scholar
  48. [48]
    D. H. Wolpert, W. G. Macready. No free lunch theorems for optimization. IEEE Transactions on Evolutionary Computation, vol. 1, no. 1, pp. 67–82, 1997. DOI: 10.1109/4235.585893.CrossRefGoogle Scholar
  49. [49]
    H. Higashi, T. Tanaka. Common spatio-time-frequency patterns for motor imagery-based brain machine interfaces. Computational Intelligence and Neuroscience, vol. 2013, Article number 537218, 2013. DOI: 10.1155/2013/537218.Google Scholar
  50. [50]
    W. He, P. F. Wei, L. P. Wang, Y. X. Zou. A novel emdbased common spatial pattern for motor imagery braincomputer interface. In Proceedings of IEEE-EMBS International Conference on Biomedical and Health Informatics, Hong Kong, China, pp. 216–219, 2012. DOI: 10.1109/BHI.2012.6211549.Google Scholar
  51. [51]
    H. H. Zhang, C. T. Guan, K. K. Ang, C. C. Wang, Z. Y. Chin. BCI competition IV - data set I: Learning discriminative patterns for self-paced EEG-based motor imagery detection. Frontiers in Neuroscience, vol. 6, Article number 7, 2012. DOI: 10.3389/fnins.2012.00007. DOI: 10.3389/fnins.2012.00007.Google Scholar
  52. [52]
    A. M. Alvarez-Meza, L. F. Velasquez-Martinez, G. Castellanos-Dominguez. Time-series discrimination using feature relevance analysis in motor imagery classification. Neurocomputing, vol. 151, pp. 122–129, 2015. DOI: 10.1016/j.neucom.2014.07.077.CrossRefGoogle Scholar

Copyright information

© Institute of Automation, Chinese Academy of Sciences and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Electrical EngineeringIran University of Science and TechnologyTehranIran

Personalised recommendations