Multi-Layer Perceptron Neural Network Classifier with Binary Particle Swarm Optimization Based Feature Selection for Brain-Computer Interfaces

Brain-Computer Interfaces (BCIs) measure brain signals activity, intentionally and unintentionally induced by users, and provides a communication channel without depending on the brain’s normal peripheral nerves and muscles output pathway. Feature Selection (FS) is a global optimization machine learning problem that reduces features, removes irrelevant and noisy data resulting in acceptable recognition accuracy. It is a vital step affecting pattern recognition system performance. This study presents a new Binary Particle Swarm Optimization (BPSO) based feature selection algorithm. Multi-layer Perceptron Neural Network (MLPNN) classifier with backpropagation training algorithm and Levenberg-Marquardt training algorithm classify selected features.

Authors:

• K. Akilandeswari
• G. M. Nasira

Keywords:

• Brain-Computer Interfaces (BCI)
• Feature Selection (FS)
• Walsh–Hadamard Transform (WHT)
• Binary Particle Swarm Optimization (BPSO)
• Multi-Layer Perceptron (MLP)
• Levenberg–Marquardt algorithm.

References:

[1] Wolpaw, J. R., Birbaumer, N., McFarland, D. J., Pfurtscheller, G., &
Vaughan, T. M. (2002). Brain–computer interfaces for communication
and control. Clinical neurophysiology, 113(6), 767-791.
[2] Vallabhaneni, A., Wang, T., & He, B. (2005). Brain—computer
interface. In Neural engineering (pp. 85-121). Springer US.
[3] Millán, J. D. R., Franzé, M., Mouriño, J., Cincotti, F., & Babiloni, F.
(2002). Relevant EEG features for the classification of spontaneous
motor-related tasks. Biological cybernetics, 86(2), 89-95.
[4] Khushaba, R. N., Al-Ani, A., & Al-Jumaily, A. (2008, December).
Differential evolution based feature subset selection. In Pattern
Recognition, 2008. ICPR 2008. 19th International Conference on (pp. 1-
4). IEEE. [5] Zhao, Z., Morstatter, F., Sharma, S., Alelyani, S., Anand, A., & Liu, H.
(2010). Advancing feature selection research. ASU feature selection
repository.
[6] Koprinska, I. (2010). Feature selection for brain-computer interfaces. In
New frontiers in applied data mining (pp. 106-117). Springer Berlin
Heidelberg.
[7] Schalk, G., & Leuthardt, E. C. (2011). Brain-computer interfaces using
electrocorticographic signals. Biomedical Engineering, IEEE Reviews
in, 4, 140-154.
[8] Leuthardt, E. C., Schalk, G., Wolpaw, J. R., Ojemann, J. G., & Moran,
D. W. (2004). A brain–computer interface using electrocorticographic
signals in humans. Journal of neural engineering, 1(2), 63.
[9] Shenoy, P., Miller, K. J., Ojemann, J. G., & Rao, R. P. (2008).
Generalized features for electrocorticographic BCIs. Biomedical
Engineering, IEEE Transactions on, 55(1), 273-280.
[10] Mishra, A. K., Das, M., & Panda, T. C. (2013). Hybrid Swarm
Intelligence Technique for CBIR Systems. International Journal of
Computer Science Issues (IJCSI), 10(2).
[11] Abraham, A., Guo, H., & Liu, H. (2006). Swarm intelligence:
foundations, perspectives and applications (pp. 3-25). Springer Berlin
Heidelberg.
[12] Moubayed, A. (2010). Binary-SDMOPSO and its application in channel
selection for Brain-Computer Interfaces. In 2010 UK Workshop on
Computational Intelligence (UKCI) (pp. 1-6).
[13] Ang, K. K., Yu, J., & Guan, C. (2012, March). Extracting effective
features from high density nirs-based BCI for assessing numerical
cognition. InAcoustics, Speech and Signal Processing (ICASSP), 2012
IEEE International Conference on (pp. 2233-2236). IEEE.
[14] Polat, D., & Cataltepe, Z. (2012, April). Feature selection and
classification on brain computer interface (BCI) data. In Signal
Processing and Communications Applications Conference (SIU), 2012
20th (pp. 1-4). IEEE.
[15] Hatamikia, S., Nasrabadi, A. M., & Shourie, N. (2014, November).
Plausibility assessment of a subject independent mental task-based BCI
using electroencephalogram signals. In Biomedical Engineering
(ICBME), 2014 21th Iranian Conference on (pp. 150-155). IEEE.
[16] Zhiping, H., Guangming, C., Cheng, C., He, X., & Jiacai, Z. (2010,
November). A new EEG feature selection method for self-paced braincomputer
interface. InIntelligent Systems Design and Applications
(ISDA), 2010 10th International Conference on (pp. 845-849). IEEE.
[17] Nasehi, S., & Pourghassem, H. (2011, May). A novel effective feature
selection algorithm based on S-PCA and wavelet transform features in
EEG signal classification. In Communication Software and Networks
(ICCSN), 2011 IEEE 3rd International Conference on (pp. 114-117).
IEEE.
[18] Huang, D., Qian, K., Oxenham, S., Fei, D. Y., & Bai, O. (2011, April).
Event-related desynchronization/synchronization-based brain-computer
interface towards volitional cursor control in a 2D center-out paradigm.
In Computational Intelligence, Cognitive Algorithms, Mind, and Brain
(CCMB), 2011 IEEE Symposium on (pp. 1-8). IEEE.
[19] Samiee, S., Hajipour, S., & Shamsollahi, M. B. (2010, June). Five-class
finger flexion classification using ECoG signals. In Intelligent and
Advanced Systems (ICIAS), 2010 International Conference on (pp. 1-4).
IEEE.
[20] Elsawy, A. S., Eldawlatly, S., Taher, M., & Aly, G. M. (2013,
September). A principal component analysis ensemble classifier for
P300 speller applications. In Image and Signal Processing and Analysis
(ISPA), 2013 8th International Symposium on (pp. 444-449). IEEE.
[21] Yang, Y., Chevallier, S., Wiart, J., & Bloch, I. (2012, August). Timefrequency
selection in two bipolar channels for improving the
classification of motor imagery EEG. In Engineering in Medicine and
Biology Society (EMBC), 2012 Annual International Conference of the
IEEE (pp. 2744-2747). IEEE.
[22] Gottemukkula, V., & Derakhshani, R. (2011, April). Classificationguided
feature selection for NIRS-based BCI. In Neural Engineering
(NER), 2011 5th International IEEE/EMBS Conference on (pp. 72-75).
IEEE.
[23] Gonzalez, A., Nambu, I., Hokari, H., Iwahashi, M., & Wada, Y. (2013,
October). Towards the Classification of Single-Trial Event-Related
Potentials Using Adapted Wavelets and Particle Swarm Optimization. In
Systems, Man, and Cybernetics (SMC), 2013 IEEE International
Conference on (pp. 3089-3094). IEEE.
[24] Bhattacharyya, S., Rakshiti, P., Konar, A., Tibarewala, D. N., Das, S., &
Nagar, A. K. (2013, April). Differential evolution with temporal
difference Q-learning based feature selection for motor imagery EEG
data. In Computational Intelligence, Cognitive Algorithms, Mind, and
Brain (CCMB), 2013 IEEE Symposium on (pp. 138-145). IEEE.
[25] Shahriari, Y., & Erfanian, A. (2011, April). A mutual information based
channel selection scheme for P300-based brain computer interface. In
Neural Engineering (NER), 2011 5th International IEEE/EMBS
Conference on (pp. 434-437). IEEE.
[26] Jayathilake, A. A. C. A., Perera, A. A. I., & Chamikara, M. A. P.
Discrete Walsh-Hadamard Transform in Signal Processing.
[27] Johnson, J., & Puschel, M. (2000). In search of the optimal Walsh-
Hadamard transform. In Acoustics, Speech, and Signal Processing,
2000. ICASSP'00. Proceedings. 2000 IEEE International Conference on
(Vol. 6, pp. 3347-3350). IEEE.
[28] Sasikala, D., & Neelaveni, R. (2010). Correlation coefficient measure of
multimodal brain image registration using fast walsh hadamard
transform. Journal of Theoretical & Applied Information Technology,
22(2).
[29] Abdolreza Asadi Ghanbari, Karim Adinehvand, & Mousa Mohammad
Nia (2014) Overhead Reduction in EEG signals using Particle Swarm
Optimization and Independent Component Analysis
[30] Hasan, B. A. S., & Gan, J. Q. (2009). Multi-objective particle swarm
optimization for channel selection in brain-computer interfaces.
[31] Das, S., Abraham, A., & Konar, A. (2008). Particle swarm optimization
and differential evolution algorithms: technical analysis, applications
and hybridization perspectives. In Advances of Computational
Intelligence in Industrial Systems (pp. 1-38). Springer Berlin
Heidelberg.
[32] Balochian, S., Seidabad, E. A., & Rad, S. Z. (2013). Neural Network
Optimization by Genetic Algorithms for the Audio Classification to
Speech and Music. International Journal of Signal Processing, Image
Processing & Pattern Recognition, 6(3).
[33] Taravat, A., Proud, S., Peronaci, S., Del Frate, F., & Oppelt, N. (2015).
Multilayer Perceptron Neural Networks Model for Meteosat Second
Generation SEVIRI Daytime Cloud Masking. Remote Sensing, 7(2),
1529-1539.
[34] Lotte, F., Congedo, M., Lécuyer, A., & Lamarche, F. (2007). A review
of classification algorithms for EEG-based brain–computer interfaces.
Journal of neural engineering, 4.
[35] Craven, M. P. (1997). A faster learning neural network classifier using
selective backpropagation.
[36] CH Satyananda Reddy (2012) design of multilayer perceptron neural
network for mental task recognition, 1(1), 74-80.
[37] Yu, H., & Wilamowski, B. M. (2011). Levenberg-marquardt training.
Industrial Electronics Handbook, 5, 12-1.
[38] Sapna, S., Tamilarasi, A., & Kumar, M. P. (2012). Backpropagation
learning algorithm based on Levenberg Marquardt Algorithm. DOI=
DOI, 10.
[39] Mojtaba Ahmadieh Khanesar, Hassan Tavakoli, Mohammad Teshnehlab
and Mahdi Aliyari Shoorehdeli (2009). Novel Binary Particle Swarm
Optimization, Particle Swarm Optimization, Aleksandar Lazinica (Ed.),
[40] Khanesar, M. A., Teshnehlab, M., & Shoorehdeli, M. A. (2007, June). A
novel binary particle swarm optimization. In Control & Automation,
2007. MED'07. Mediterranean Conference on (pp. 1-6). IEEE.