Skip to main content
SpringerLink
Log in

A Personalized Feature Extraction and Classification Method for Motor Imagery Recognition

  • Published:
Mobile Networks and Applications Aims and scope Submit manuscript

Abstract

In practical applications of the motor imagery-based brain–computer interface (BCI) system, the differences in electroencephalogram (EEG) signal manifestation and corresponding rhythm ranges in different individuals pose a significant challenge. The corresponding EEG features in different frequency bands differ; therefore, personalized screening must be conducted to obtain information that is conducive to the classification of EEG signals for different motor imageries. Also, in current BCI system, to obtain more information, multi-channel electrodes are often used to collect EEG signals, but also increasing the complexity of calculation. In this paper, a personalized feature extraction method based on filter bank and elastic net and a personalized channel selection based on Deep Belief Network to obtain a classification accuracy similar to or even higher than using all channels is proposed. Compared with the typically used feature extraction and classification algorithms, this method obtains higher calculation rates and recognition accuracy and provides a theoretical reference for the practical application of BCI systems. The shortcomings of the common spatial pattern (CSP) algorithm are addressed. The major contribution of this paper is the flexible screening of feature vectors and channels containing more classification information based on individual differences, thereby preventing the manual adjustment of specific frequency ranges in traditional CSP for performing feature extraction and avoiding inputting all channels. In the case study, the highest test accuracy reaches 86.94%.

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
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Rashid M, Sulaiman N, Majeed APPA, Musa RM (2020) Current Status, Challenges, and Possible Solutions of EEG-Based Brain Computer Interface: A Comprehensive Review. Frontiers in Neurorobotics 14:25

  2. Abiri R, Borhani S, Sellers EW, Jiang Y (2019) A comprehensive review of EEG-based brain computer interface paradigms. Journal of Neural Engineering, 16(1):1–21

  3. Curran EA, Stokes MJ, Cui (2003) Learning to control brain activity: a review of the production and control of EEG components for driving brain-computer interface (BCI) systems. Brain Cognit 51(3):326–336

    Article  Google Scholar 

  4. Huang D, Lin P, Fei D, Chen X, Bai O (2009) EEG-based online two dimensional cursor control. In: Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, pp 4547–4550

  5. Leeb R, Friedman D, Müller-Putz GR, Scherer R, Slater M, Pfurtscheller G (2007) Self-paced (asynchronous) BCI control of a wheelchair in virtual environments: A case study with a tetraplegic. Comput Intell Neurosci 2007:79642

    Article  Google Scholar 

  6. Long J, Li Y, Wang H, Yu T, Pan J, Li F (2012) A hybrid brain computer interface to control the direction and speed of a simulated or real wheelchair. IEEE Trans Neural Syst Rehabil Eng 20(5):720–729

    Article  Google Scholar 

  7. Meng J, Zhang S, Bekyo A, Olsoe J, Baxter B, He B (2016) Noninvasive electroencephalogram-based control of a robotic arm for reach and grasp tasks. Sci Rep 6(Dec):38565

    Article  Google Scholar 

  8. Coogan CG, He B (2018) Brain-computer interface control in a virtual reality environment and applications for the Internet of Things. IEEE Access 6:10840–10849

    Article  Google Scholar 

  9. Zhang R, Li X et al (2019) Using brain network features to increase the classification accuracy of MI-BCI inefficiency subject, IEEE Access 7:74490–74499

  10. Geethanjali P, Mohan YK, Sen J (2012) Time domain Feature extraction and classification of EEG data for Brain Computer Interface, pp 1136–1139

  11. Pei X, Zheng C (2008) Classification of left and right hand motor imagery tasks based on EEG frequency component selection. In: 2nd International Conference on Bioinformatics and Biomedical Engineering, iCBBE, pp 1888–1891

  12. Manshouri N, Maleki M, Kayikcioglu T (2020) An EEG-based stereoscopic research of the PSD differences in pre and post 2D3D movies watching. Biomed Sig Process Control 55:101642

  13. Saxena A, Tripathi K, Khanna A, Gupta D, Sundaram S (eds) (2020) Emotion detection through EEG signals using FFT and machine learning techniques. In: Proceedings of the 2nd International Conference on Innovative Computing and Communication, vol 1087. ICICC 2019, pp 543–550

  14. McFarland DJ, Anderson CW, Muller K-R, Schlogl A, Krusienski DJ (2006) BCI Meeting 2005 - Workshop on BCI signal processing: Feature extraction and translation. IEEE Trans Neural Syst Rehabil Eng 14(2):135–138

  15. Chen H, Hagiwara I (2006) Image reconstruction based on combination of wavelet decomposition, inpainting and texture synthesis. In: 14th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG'2006 - In Co-operation with EUROGRAPHICS, pp 21–22

  16. Zhu X, Wu F (2007) An improved approach to remove cloud and mist from remote sensing images based on mallat algorithm. International Symposium on Photoelectronic Detection and Imaging, ISPDI 2007:  Related Technologies and Applications, vol 6625

  17. Zhao J, Sun F, Wang H (2011) Pipeline leak fault feature extraction based on wavelet packet analysis and application. In: Proceedings of the 2nd Annual Conference on Electrical and Control Engineering, ICECE 2011, pp 1148–1151

  18. Dong Z-G, Liao N-F, Qu L, Lv H (2013) Data reconstructing for windowing broom Fourier transform imaging spectrometers based on multi-core techniques. In: 5th International Symposium on Photoelectronic Detection and Imaging (ISPDI) - Imaging Spectrometer Technologies and Applications, vol 8910

  19. Barry RJ, De Blasio FM (2018) EEG frequency PCA in EEG-ERP dynamics. Psychophysiology 55(5):e13042

  20. Mizuhara H, Yonehara E, Gofuku A (2007) Parallel Factor Analysis can decompose human EEG during a finger movement task. In: Proceedings of the SICE (Society of Instrument and Control Engineers) Annual Conference, SICE 2007,  pp 1945–1950

  21. Zhu Y, Zhang C, Poikonen H, Toiviainen P, Huotilainen M, Mathiak K et al (2020) Exploring Frequency-Dependent Brain Networks from Ongoing EEG Using Spatial ICA During Music Listening. Brain Topogr 33(3):289–302

    Article  Google Scholar 

  22. Ramoser H, Muller-Gerking J, Pfurtscheller G (2000) Optimal spatial filtering of single trial EEG during imagined hand movement. Ieee Trans Rehab Eng 8(4):441–446

    Article  Google Scholar 

  23. Chacon-Murguia MI, Olivas-Padilla BE (2020) A new approach for multiclass motor imagery recognition using pattern image features generated from common spatial patterns. Sig Image Video Process 14(5):915–923

    Article  Google Scholar 

  24. Fu R, Tian Y, Bao T, Meng Z, Shi P (2019) Improvement motor imagery EEG classification based on regularized linear discriminant analysis. J Neuroscience Meth 343:108833

  25. Shaabani MNAH, Fuad N, Jamal N, Ismail MF (2019) kNN and SVM Classification for EEG: A Review. 5th International Conference on Electrical. Control Comput Eng 632:555–556

    Google Scholar 

  26. Sagee GS, Hema S (2017) EEG feature extraction and classification in multiclass multiuser motor imagery brain computer interface u sing Bayesian Network and ANN. In: Proceedings of the 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies, ICICICT 2017, pp 938–943

  27. Luu L, Pham P, Le T (2020) Feature Extraction and Electrophysiological Modeling in Personalized Deep Brain Structure Using Electroencephalography Signal. IFMBE Proceedings 69:551–556

    Article  Google Scholar 

  28. Cheah, K (2019) Short-time-span EEG-based personalized emotion recognition with deep convolutional neural network. In: Proceedings of the 2019 IEEE International Conference on Signal and Image Processing Applications, ICSIPA, pp 78–83

  29. Lin Y (2020) Constructing a Personalized Cross-Day EEG-Based Emotion-Classification Model Using Transfer Learning. IEEE J Biomed Health Inf 24(5):1255–1264

    Article  Google Scholar 

  30. Rodrigues P G, Filho C A S, Attux R (2019)  Space-time recurrences for functional connectivity evaluation and feature extraction in motor imagery brain-computer interfaces. Med Bio Eng Comput 57(8):1709–1725

  31. Koizumi Y, Shibanoki T, Tsuji T (2020) A training system for brain-computer interfaces based on motor imagery selection. In: 2nd IEEE Global Conference on Life Sciences and Technologies, LifeTech 2020,  pp 217–218

  32. Wang J-G, Chen Z, Yao Y (2019) Personalized EEG Feature Extraction Method Based on Filter Bank and Elastic Network. Lect Notes Inst Comput Sci Soc Inf Telecommun Eng 329:116–129

    Google Scholar 

  33. Shi T, Ren L, Cui W (2019) Feature recognition of motor imaging EEG signals based on deep learning. Personal Ubiquitous Comput 23(3-4): 499–510

  34. Popescu F, Fazli S, Badower Y (2007) Single Trial Classification of Motor Imagination Using 6 Dry EEG Electrodes. PLOS ONE 2(7):637–637

    Article  Google Scholar 

  35. Biag M, Aslam (2020) Filtering techniques for channel selection in motor imagery. EEG Appl A Survey Artif Intell Rev 53(2):1207–1232

    Article  Google Scholar 

  36. Al M N, Hasan BAS,Gan JQ (2012) Continuous presentation for multi-objective channel selection in Brain-Computer Interfaces. Evolutionary Computation. IEEE, pp 1–7

  37. Blankertz B, Dornhege G, Krauledat M, Mueller K-R, Curio G (2007) The non-invasive Berlin Brain-Computer Interface: Fast acquisition of effective performance in untrained subjects. Neuroimage 37(2):539–550

    Article  Google Scholar 

  38. Mingai L, Jingyu L, Dongmei H (2001) A method of motion imaging EEG signal recognition based on improved CSP algorithm. Chin J Biomed Eng 28(2):161–165

    Google Scholar 

  39. Mcfarland DJ, Anderson CW, Muller KR (2006) BCI meeting 2005-workshop on BCI signal processing: feature extraction and translation. IEEE Trans Neural Syst Rehab Eng 14(2):135–138

    Article  Google Scholar 

  40. Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. J R Stat Soc 67(5):768–768

    Article  MathSciNet  Google Scholar 

  41. Mcdonald GC (2010) Ridge regression. Wiley Interdisciplinary Reviews Computational Statistics 1(1):93–100

  42. Hoerl AE, Kennard RW (2000) Ridge Regression: Biased Estimation for Nonorthogonal Problems. Technometrics 12(1):55–67

    Article  Google Scholar 

  43. Friedman J, Hastie T, Höfling H (2007) Pathwise coordinate optimization. Ann Appl Stat 1(2):302–303

    Article  MathSciNet  Google Scholar 

  44. Zhao B, Wu CJ (2020) Sound quality evaluation of electronic expansion valve using Gaussianrestricted Boltzmann machines based DBN. Appl Acoust 170:15

    Google Scholar 

  45. Lu N, Li TF (2017) A Deep Learning Scheme for Motor Imagery Classification based onRestricted Boltzmann Machines. IEEE Trans Neural Syst Rehab Eng 25(6):566–576

    Article  Google Scholar 

  46. Hai W, Cai Y, Long CA (2014) A Vehicle Detection Algorithm Based on Deep Belief Network. Sci World J 2014(2):647380

    Google Scholar 

  47. Prasath TA (2015) Neural network segmented CD algorithm-based PET liver image reconstruction. Inderscience Publishers 17(3):276–289

    Google Scholar 

  48. Kim S, Park B (2016) Deep belief network based statistical feature learning for fingerprint liveness detection. Pattern Recognition Lett 77:58–65

    Article  Google Scholar 

Download references

Acknowledgments

Wang was supported in part by Shanghai Science and Technology Commission Project, under project number 19511105202. Yao was supported in part by Minister of Science and Technology, ROC, under project number MOST 108-2221-E-007-068-MY3.

Author information

Authors and Affiliations

  1. School of Mechatronic Engineering and Automation, Shanghai University, Shanghai Key Lab of Power Station Automation Technology, Shanghai, 200072, China

    Jian-Guo Wang, Hui-Min Shao & Shi-Wei Ma

  2. Department of Chemical Engineering, National Tsing Hua University, Hsinchu, 30013, Taiwan

    Yuan Yao

  3. Shanghai Minghua Electric Power Science &Technology Co., Ltd., Shanghai, 200092, China

    Jian-Long Liu

Authors
  1. Jian-Guo Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hui-Min Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuan Yao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jian-Long Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shi-Wei Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yuan Yao.

Additional information

Publisher’s note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, JG., Shao, HM., Yao, Y. et al. A Personalized Feature Extraction and Classification Method for Motor Imagery Recognition. Mobile Netw Appl 26, 1359–1371 (2021). https://doi.org/10.1007/s11036-021-01754-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11036-021-01754-0

Keywords

Search

Navigation