Abstract
The brain computer interface (BCI) is a method of measuring brain activity via electrical impulses. However, for measuring brain activity, electrodes are placed on human brain. The purpose of this paper is to investigate a novel electroencephalograph (EEG) motor imagery classification technique with greater accuracy. The EEG output is extremely sensitive to human activity when recorded. As a result, EEG pre-processing is required before meaningful information from an EEG signal can be recovered; however, after pre-processing, key features can be recovered easily. In order to achieve effective classification results, feature selection is crucial. To get the best feature set for motor imagery (MI) classification, the Harmony search algorithm of feature selection is utilised. Finally, long short-term memory (LSTM) deep neural networks are used to classify EEG data. The alpha and beta waves are considered in this paper. For pre-processing and feature extractions of EEG fundamental approaches are considered to prove the utility of LSTM DNN. The results are obtained using computer simulation. The accuracy of the proposed method is found to be greater than 97%.
Similar content being viewed by others
References
Wolpaw JR (2007) Brain–computer interfaces as new brain output pathways. J Physiol 579(3):613–619
Soumya I, Zia Ur Rahman M, Rama Koti Reddy D, Lay Ekuakille A (2015) Efficient block processing of long duration biotelemetric brain data for health care monitoring. Rev Sci Instrum 86(3):035003
Karthik GVS, Fathima SY, Rahman MZU, Ahamed SR, Lay-Ekuakille A (2013) Efficient signal conditioning techniques for brain activity in remote health monitoring network. IEEE Sens J 13(9):3276–3283
Wang J, Feng Z, Lu N, Sun L, Luo J (2018) An information fusion scheme based common spatial pattern method for classification of motor imagery tasks. Biomed Signal Process Control 46:10–17
StefanoFilho CA, Attux R, Castellano G (2018) “Can graph metrics be used for EEG-BCIS based on hand motor imagery? Biomed Signal Process Control 40:359–365
Blankertz B, Tomioka R, Lemm S, Kawanabe M, Muller K-R (2007) Optimizing spatial filters for robust eeg single-trial analysis. IEEE Signal Process Mag 25(1):41–56
Kam T-E, Lee S-W (2011) Time-dependent common spatial patterns optimization for EEG signal classification. In: The first Asian conference on pattern recognition. IEEE, 2011, pp 643–646
Ang KK, Chin ZY, Zhang H, Guan C (2008) Filter bank common spatial pattern (FBCSP) in brain–computer interface. In: 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence). IEEE, pp 2390–2397
Blankertz B, Kawanabe M, Tomioka R, Hohlefeld F, Müller K-R, Nikulin VV (2008) Invariant common spatial patterns: alleviating nonstationarities in brain–computer interfacing. Adv Neural Inf Process Syst 20:113–120
Lotte F, Guan C (2010) Regularizing common spatial patterns to improve bci designs: unified theory and new algorithms. IEEE Trans Biomed Eng 58(2):355–362
Wang H, Li X (2015) Regularized filters for l1-norm-based common spatial patterns. EEE Trans Neural Syst Rehabil Eng 24(2):201–211
Pfurtscheller G, Aranibar A (1977) Event-related cortical desynchronization detected by power measurements of scalp EEG. Electroencephalogr Clin Europhysiol 42(6):817–826
Park C, Looney D, Ur Rehman N, Ahrabian A, Mandic DP (2012) Classification of motor imagery BCI using multivariate empirical mode decomposition. IEEE Trans Neural Syst Rehabil Eng 21(1):10–22
Kevric J, Subasi A (2017) Comparison of signal decomposition methods in classification of EEG signals for motor-imagery bci system. Biomed Signal Process Control 31:398–406
Mirvaziri H, Mobarakeh ZS (2017) Improvement of EEG-based motor imagery classification using ring topology-based particle swarm optimization. Biomed Signal Process Control 32:69–75
Luo J, Feng Z, Lu N (2019) Spatio-temporal discrepancy feature for classification of motor imageries. Biomed Signal Process Control 47:137–144
Samanta K, Chatterjee S, Bose R (2019) Cross-subject motor imagery tasks eeg signal classification employing multiplex weighted visibility graph and deep feature extraction. IEEE Sens Lett 4(1):1–4
Cheng L, Li D, Yu G, Zhang Z, Li X, Yu S (2020) A motor imagery EEG feature extraction method based on energy principal component analysis and deep belief networks. IEEE Access 8:21453–21472
Park Y, Chung W (2020) Optimal channel selection using correlation coefficient for CSP based EEG classification. IEEE Access 8:111514–111521
Ang JC, Mirzal A, Haron H, Hamed HNA (2015) Supervised, unsupervised, and semi-supervised feature selection: a review on gene selection. IEEE/ACM Trans Comput Biol Bioinf 13(5):971–989
Peng H, Long F, Ding C (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and minredundancy. IEEE Trans Pattern Anal Mach Intell 8:1226–1238
Chandrashekar G, Sahin F (2014) A survey on feature selection methods. Comput Electr Eng 40(1):16–28
Kira K, Rendell LA (1992) A practical approach to feature selection. In: Machine learning proceedings 1992. Elsevier, pp 249–256
Jin X, Xu A, Bie R, Guo P (2006) Machine learning techniques and chi-square feature selection for cancer classification using sage gene expression profiles. In: International workshop on data mining for biomedical applications. Springer, pp 106–115
Zhang J, Chen M, Zhao S, Hu S, Shi Z, Cao Y (2016) Relieff-based EEG sensor selection methods for emotion recognition. Sensors 16(10):1558
Subhani AR, Mumtaz W, Kamil N, Saad NM, Nandagopal N, Malik AS (2017) MRMR based feature selection for the classification of stress using EEG. In: 2017 eleventh international conference on sensing technology (ICST). IEEE, pp 1–4
González J, Ortega J, Damas M, Martín-Smith P, Gan JQ (2019) A new multi-objective wrapper method for feature selection–accuracy and stability analysis for bci. Neurocomputing 333:407–418
Ortega J, Asensio-Cubero J, Gan JQ, Ortiz A (2016) Classification of motor imagery tasks for bci with multiresolution analysis and multiobjective feature selection. Biomed Eng Online 15(1):73
Wu S-L, Liu Y-T, Hsieh T-Y, Lin Y-Y, Chen C-Y, Chuang C-H, Lin C-T (2016) Fuzzy integral with particle swarm optimization for a motor-imagery-based brain–computer interface. IEEE Trans Fuzzy Syst 25(1):21–28
Baig MZ, Aslam N, Shum HP, Zhang L (2017) Differential evolution algorithm as a tool for optimal feature subset selection in motor imagery EEG. Expert Syst Appl 90:184–195
Geem ZW, Kim JH, Loganathan GV (2001) A new heuristic optimization algorithm: harmony search. SIMULATION 76(2):60–68
Herman GP, McGinnity TM, Coyle D (2008) Comparative analysis of spectral approaches to feature extraction for EEG-based motor imagery classification. IEEE Trans Neural Syst Rehabil Eng 16(4):317–326
Miao S, Chao W, Xian-Zhe L, Ming-Qiang L, Lu W, Neng-Gang X (2020) EEG signal classification based on SVM with improved squirrel search algorithm. Biomedical Engineering/Biomedizinische Technik
Bhateja V, Gopal S, Atul S, Jay S (2014) Speckle reduction in ultrasound images using an improved conductance function based on anisotropic diffusion. In: 2014 international conference on computing for sustainable global development (INDIACom). IEEE, pp 619–624
Xu B-G, Song A-G (2008) Pattern recognition of motor imagery EEG using wavelet transform. J Biomed Sci Eng 1(1):64
Castillo E, Cobo A, Gutierrez M, Pruneda E (1998) Functional networks with applications. Kluwer Academic Publishers, Dordrecht
Sobol IM (2001) Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates. Math Comput Simul 55(1–3):271–280
Diao R, Shen Q (2012) Feature selection with harmony search. IEEE Trans Syst Man Cybern Part B (Cybernetics) 42(6):1509–1523
(2021) Recent Innovations in Computing. Springer Science and Business Media LLC
Werbos PJ (1988) Generalization of backpropagation with application to a recurrent gas market model. Neural Netw 1:339–356
Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5:157–166
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Olah C (2015) Understanding lstm networks. http://colah.github.io/posts/2015-08-Understanding-LSTMs 19 (2015): 1–19.
Nagabushanam P, Thomas George S, Radha S (2019) EEG signal classification using LSTM and improved neural network algorithms. Soft Comput 2:1–23
Lajnef T, Chaibi S, Ruby P, Aguera P-E, Eichenlaub J-B, Samet M, Kachouri A, Jerbi K (2015) Learning machines and sleeping brains: automatic sleep stage classification using decision-tree multi-class support vector machines. Comput Neurosci J Neurosci Methods 250:94–105
Aboalayon KAI, Faezipour M, Almuhammadi WS, Moslehpour S (2016) Sleep stage classification using EEG signal analysis: a comprehensive survey and new investigation. Entropy 18:272. https://doi.org/10.3390/e18090272
Cui Z, Zheng X, Shao X, Cui L (2018) Automatic sleep stage classification based on convolutional neural network and finegrained segments. Hindawi Complex 2018:9248410. https://doi.org/10.1155/2018/9248410
Tang Z, Li C, Sun S (2017) Single-trial EEG classification of motor imagery using deep convolutional neural networks. Optik 130:11–18
Kumar S, Mamun K, Sharma A (2017) CSP-TSM: optimizing the performance of Riemannian tangent space mapping using common spatial pattern for MI-BCI. Comput Biol Med 91(Supplement C):231–242
Zhang Y, Wang Y, Zhou G et al (2018) Multi-kernel extreme learning machine for EEG classification in brain-computer interfaces. Expert Syst Appl 96:302–310
Bashar SK, Hassan AR, Bhuiyan MIH (2015) Identification of motor imagery movements from EEG signals using dual tree complex wavelet transform. In: 2015 international conference on advances in computing, communications and informatics (ICACCI). IEEE, pp 290–296
Bashar SK, Hassan AR, Bhuiyan MIH (2015) Motor imagery movements classification using multivariate EMD and short time Fourier transform. In: 2015 annual IEEE India conference (INDICON). IEEE, pp 1–6
Tang X, Ting W, Yiming D, Yuyan D (2019) Motor imagery EEG recognition with KNN-based smooth auto-encoder. Artif Intell Med 101:101747
Wang L, Wu XP (2008) Classification of four-class motor imagery EEG data using spatial filtering. In: 2nd international conference on bioinformatics and biomedical engineering. https://doi.org/10.1109/ICBBE.2008.868
Aljalal M, Djemal R (2017) A comparative study of wavelet and CSP features classified using LDA, SVM and ANN in EEG based motor imagery, 9th IEEE-GCC conference and exhibition. https://doi.org/10.1109/IEEEGCC.2017.8448212
Mirnaziri M, Rahimi M, Alavikakhaki S, Ebrahimpour R (2013) Using combination of μ, β and γ bands in classification of EEG signals. Basic Clin Neurosci 4(1):76–87
Silva VF, Barbosa RM, Vieira PM, Lima CS (2017) Ensemble learning based classification for BCI applications. In: IEEE 5th Portuguese meeting on bioengineering. https://doi.org/10.1109/ENBENG.2017.7889483
Wang J, Feng Z, Lu N (2017) Feature extraction by common spatial pattern in frequency domain for motor imagery tasks classification, 29th Chinese control and decision conference (CCDC), pp 5883−5888. https://doi.org/10.1109/CCDC.2017.7978220
Alansari M, Kamel M, Hakim B, Kadah Y (2018) Study of wavelet-based performance enhancement for motor imagery brain–computer interface. In: 6th international conference on brain-computer interface (BCI). https://doi.org/10.1109/IWW-BCI.2018.8311520
Mishuhina V, Jiang X (2018) Feature weighting and regularization of common spatial patterns in EEG-based motor imagery BCI. IEEE Signal Process Lett 25(6):783–787. https://doi.org/10.1109/LSP.2018.2823683
Behri M, Subasi A, Qaisar SM (2018) Comparison of machine learning methods for two class motor imagery tasks using EEG in brain–computer interface. Adv Sci Eng Technol Int Conf. https://doi.org/10.1109/ICASET.2018.8376886
Zhang Y, Liu J, Sheng J, Lv J (2018) EEG recognition of motor imagery based on SVM ensemble. In: 5th international conference on systems and informatics, pp 866−870. https://doi.org/10.1109/ICSAI.2018.8599464
Li B, Yang B, Guan C, Hu C (2019) Three-class motor imagery classification based on FBCSP combined with voting mechanism. IEEE Int Conf Comput Intell Virtual Environ Meas Syst Appl. https://doi.org/10.1109/CIVEMSA45640.2019.9071618
Molla KI, Shiam AA, Islam R, Tanaka T (2020) Discriminative feature selection-based motor imagery classification using EEG signal. IEEE Access. https://doi.org/10.1109/ACCESS.2020.2996685
Venkatachalam K, Devipriya A, Maniraj J, Sivaram M, Ambikapathy A, Amiri Iraj S (2020) A novel method of motor imagery classification using EEG signal. Artif Intell Med 103:101787
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nakra, A., Duhan, M. Deep neural network with harmony search based optimal feature selection of EEG signals for motor imagery classification. Int. j. inf. tecnol. 15, 611–625 (2023). https://doi.org/10.1007/s41870-021-00857-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41870-021-00857-x