Skip to main content

Advertisement

SpringerLink
Log in

Motor imagery classification using sparse nonnegative matrix factorization and convolutional neural networks

  • S.I.: Improving Healthcare outcomes using Multimedia Big Data Analytics
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The motor movement performed by different body parts affects the synaptic potential at different brain cortices, which can be observed by the electroencephalogram (EEG) signal. The recorded EEG signals can be used to decode the imagined motor task. The EEG signals are non-stationary and transient and contain time, frequency, and space information. Extracting this information and processing them with the latest machine learning and deep learning algorithms can be useful for brain–computer interfacing and other human–machine interaction techniques. EEG signal contains negative values. Hence, nonnegative matrix factorization can be used to provide a meaningful explanation of information within EEG signals. Sparseness in feature vectors is another essential factor to consider while identifying the structures in an input signal. In this work, we propose a novel motor imagery classification model that extracts the weights for predefined motor imagery features from EEG signals and classifies them using a convolution neural network (CNN). Sparse nonnegative matrix factorization is used to extract the fundamental feature vectors for different motor imagery events, which are further used to extract the combined weight matrix of unknown motor imagery events. The designed CNN classifies the extracted weight matrix in the corresponding classes. The acquired EEG signals from all the channels are processed simultaneously using the CNN, which helps extract spatial information from the signals. BCI Competition IV dataset IIa and BCI Competition III dataset IVa are used to validate the proposed method. The proposed method has been compared with existing methods and validates their superiority in terms of average accuracy. The classification accuracy for two types and four types of motor imagery signals is 99.53% and 94.58%, respectively. Empirical results show that EEG signals’ sparseness characteristics can be considered an effective feature for motor imagery classification.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data Availability

Data available on request from the authors.

References

  1. Bashashati H, Ward RK, Bashashati A (2016) User-customized brain computer interfaces using Bayesian optimization. J Neural Eng 13(2):026001

    Article  Google Scholar 

  2. Batula AM, Mark JA, Kim YE, Ayaz H (2017) Comparison of brain activation during motor imagery and motor movement using FNIRS. Comput Intell Neurosci 2017

  3. Brunner C, Leeb R, Müller-Putz G, Schlögl A, Pfurtscheller G (2008) Bci competition 2008–graz data set a. Institute for Knowledge Discovery (Laboratory of Brain-Computer Interfaces), Graz University of Technology 16:1–6

  4. Chacon-Murguia MI, Olivas-Padilla BE, Ramirez-Quintana J (2020) A new approach for multiclass motor imagery recognition using pattern image features generated from common spatial patterns. SIViP 14(5):915–923

    Article  Google Scholar 

  5. Chaudhary P, Agrawal R (2020) Non-dyadic wavelet decomposition for sensory-motor imagery EEG classification. Brain–Comput Interfaces 7(1–2):11–21

    Article  Google Scholar 

  6. Chaudhary P, Agrawal R (2021) Sensory motor imagery EEG classification based on non-dyadic wavelets using dynamic weighted majority ensemble classification. Intell Decis Technol 15(1):33–43

    Article  Google Scholar 

  7. Chaudhary S, Taran S, Bajaj V, Sengur A (2019) Convolutional neural network based approach towards motor imagery tasks EEG signals classification. IEEE Sens J 19(12):4494–4500

    Article  Google Scholar 

  8. Dong E, Li C, Li L, Du S, Belkacem AN, Chen C (2017) Classification of multi-class motor imagery with a novel hierarchical SVM algorithm for brain–computer interfaces. Med Biol Eng Comput 55(10):1809–1818

    Article  Google Scholar 

  9. Dornhege G, Blankertz B, Curio G, Muller KR (2004) Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms. IEEE Trans Biomed Eng 51(6):993–1002

    Article  Google Scholar 

  10. Gupta MD, Xiao J (2011) Non-negative matrix factorization as a feature selection tool for maximum margin classifiers. In: CVPR 2011. IEEE, pp 2841–2848

  11. Hoyer PO (2004) Non-negative matrix factorization with sparseness constraints. J Mach Learn Res 5(9):1

    MathSciNet  Google Scholar 

  12. Jung Y, Hu J (2015) Ak-fold averaging cross-validation procedure. J Nonparamet Stat 27(2):167–179

    Article  Google Scholar 

  13. 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

    Article  Google Scholar 

  14. Khan GH, Hashmi MA, Awais MM, Khan NA, Ahmad RB (2020) High performance multi-class motor imagery eeg classification. In: BIOSIGNALS, pp 149–155

  15. Krishna DH, Pasha I, Savithri TS (2016) Classification of EEG motor imagery multi class signals based on cross correlation. Procedia Computer Science 85:490–495

    Article  Google Scholar 

  16. Kwon K, Shin JW, Kim NS (2015) Target source separation based on discriminative nonnegative matrix factorization incorporating cross-reconstruction error. IEICE Trans Inf Syst 98(11):2017–2020

    Article  Google Scholar 

  17. Lee D, Seung HS (2000) Algorithms for non-negative matrix factorization. Adv Neural Inf Process Syst 13:1

    Google Scholar 

  18. Lee H, Choi S (2009) Group nonnegative matrix factorization for EEG classification. In: Artificial intelligence and statistics. PMLR, pp 320–327

  19. Lee H, Cichocki A, Choi S (2006) Nonnegative matrix factorization for motor imagery EEG classification. In: International conference on artificial neural networks. Springer, pp 250–259

  20. Lee H, Cichocki A, Choi S (2009) Kernel nonnegative matrix factorization for spectral EEG feature extraction. Neurocomputing 72(13–15):3182–3190

    Article  Google Scholar 

  21. Liu M, Wang J, Zheng C, Yan N (2006) Using non-negative matrix fact factorization to extract attention-related EEG features. Society of China

  22. Liu S, Bai W, Srivastava G, Machado JA (2020) Property of self-similarity between baseband and modulated signals. Mobile Networks Appl 25(4):1537–1547

    Article  Google Scholar 

  23. Ma X, Wang D, Liu D, Yang J (2020) Dwt and cnn based multi-class motor imagery electroencephalographic signal recognition. J Neural Eng 17(1):016073

    Article  Google Scholar 

  24. Phadikar S, Sinha N, Ghosh R (2022) Neural network-based feature extraction for multi-class motor imagery classification. arXiv preprint arXiv:2201.01468

  25. Rashid M, Bari BS, Hasan MJ, Razman MAM, Musa RM, Ab Nasir AF, Majeed APA (2021) The classification of motor imagery response: an accuracy enhancement through the ensemble of random subspace k-nn. PeerJ Comput Sci 7:e374

  26. Sadiq MT, Yu X, Yuan Z, Aziz MZ (2020) Identification of motor and mental imagery EEG in two and multiclass subject-dependent tasks using successive decomposition index. Sensors 20(18):5283

    Article  Google Scholar 

  27. Sakhavi S, Guan C, Yan S (2018) Learning temporal information for brain–computer interface using convolutional neural networks. IEEE Trans Neural Netw Learn Syst 29(11):5619–5629

    Article  MathSciNet  Google Scholar 

  28. Siuly Li Y, Wen P (2013) Identification of motor imagery tasks through CC–LR algorithm in brain computer interface. Int J Bioinform Res Appl 9(2):156–172

    Article  Google Scholar 

  29. Siuly S, Li Y (2012) Improving the separability of motor imagery EEG signals using a cross correlation-based least square support vector machine for brain-computer interface. IEEE Trans Neural Syst Rehabil Eng 20(4):526–538

    Article  Google Scholar 

  30. Siuly S, Li Y (2015) Discriminating the brain activities for brain-computer interface applications through the optimal allocation-based approach. Neural Comput Appl 26(4):799–811

    Article  Google Scholar 

  31. Stojanović O, Kuhlmann L, Pipa G (2020) Predicting epileptic seizures using nonnegative matrix factorization. PLoS ONE 15(2):e0228025

    Article  Google Scholar 

  32. Sugi T, Kawana F, Nakamura M (2009) Automatic EEG arousal detection for sleep apnea syndrome. Biomed Signal Process Control 4(4):329–337

    Article  Google Scholar 

  33. Suk HI, Lee SW (2011) Subject and class specific frequency bands selection for multiclass motor imagery classification. Int J Imaging Syst Technol 21(2):123–130

    Article  Google Scholar 

  34. Taran S, Bajaj V, Sharma D, Siuly S, Sengur A (2018) Features based on analytic IMF for classifying motor imagery EEG signals in BCI applications. Measurement 116:68–76

    Article  Google Scholar 

  35. Tosun M, Çetin O (2022) A new phase-based feature extraction method for four-class motor imagery classification. SIViP 16(1):283–290

    Article  Google Scholar 

  36. Varshney YV, Abbasi Z, Abidi M, Farooq O, Upadhyaya P (2017) Snmf based speech denoising with wavelet decomposed signal selection. In: 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET). IEEE, pp 2603–2606

  37. Verma NK, Rao LVS, Sharma SK (2014) Motor imagery eeg signal classification on dwt and crosscorrelated signal features. In: 2014 9th International Conference on Industrial and Information Systems (ICIIS). IEEE, pp 1–6

  38. Zhou T, Kang J, Cong F, Li X (2020) Stability-driven non-negative matrix factorization-based approach for extracting dynamic network from resting-state eeg. Neurocomputing 389:123–131

    Article  Google Scholar 

Download references

Funding

 This article did not receive any Funding from any External Sources.

Author information

Authors and Affiliations

  1. Department of CSE, The NorthCap University, Gurugram, India

    Poonam Chaudhary

  2. Speedlabs, Mumbai, India

    Yash Vardhan Varshney

  3. Dept of Math and Computer Science, Brandon University, Brandon, Canada

    Gautam Srivastava

  4. Research Centre for Interneural Computing, China Medical University, Taichung, Taiwan

    Gautam Srivastava

  5. Department of Computer Science and Math, Lebanese American University, 1102, Beirut, Lebanon

    Gautam Srivastava

  6. Department of Information Systems, College of Computer Sciences and Information Technology, King Faisal University, Al-Hasa, Saudi Arabia

    Surbhi Bhatia

Authors
  1. Poonam Chaudhary
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yash Vardhan Varshney
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Gautam Srivastava
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Surbhi Bhatia
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

P.C. contributed to conceptualization, methodology, software, data curation, validation, investigation, visualization, and writing—original draft. Y.V. contributed to supervision, conceptualization, methodology, investigation, and writing—review and editing. G.S. contributed to methodology, validation, and writing—review and editing. S.B. contributed to methodology and writing—review and editing.

Corresponding authors

Correspondence to Poonam Chaudhary or Gautam Srivastava.

Ethics declarations

Conflict of Interest

The authors have no Conflicts of Interest to declare for this manuscript.

Ethical Approval

For this type of study formal consent was not required. This manuscript does not contain any studies with human participants or animals performed by any of the authors.

Code Availability

Code available on request from the authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chaudhary, P., Varshney, Y.V., Srivastava, G. et al. Motor imagery classification using sparse nonnegative matrix factorization and convolutional neural networks. Neural Comput & Applic 36, 213–223 (2024). https://doi.org/10.1007/s00521-022-07861-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07861-7

Keywords

Search

Navigation