Skip to main content
SpringerLink
Log in

KDLPCCA-Based Projection for Feature Extraction in SSVEP-Based Brain-Computer Interfaces

  • Article
  • Published:
Journal of Shanghai Jiaotong University (Science) Aims and scope Submit manuscript

Abstract

An electroencephalogram (EEG) signal projection using kernel discriminative locality preserving canonical correlation analysis (KDLPCCA)-based correlation with steady-state visual evoked potential (SSVEP) templates for frequency recognition is presented in this paper. With KDLPCCA, not only a non-linear correlation but also local properties and discriminative information of each class sample are considered to extract temporal and frequency features of SSVEP signals. The new projected EEG features are classified with classical machine learning algorithms, namely, K-nearest neighbors (KNNs), naive Bayes, and random forest classifiers. To demonstrate the effectiveness of the proposed method, 16-channel SSVEP data corresponding to 4 frequencies collected from 5 subjects were used to evaluate the performance. Compared with the state of the art canonical correlation analysis (CCA), experimental results show significant improvements in classification accuracy and information transfer rate (ITR), achieving 100% and 240 bits/min with 0.5 s sample block. The superior performance demonstrates that this method holds the promising potential to achieve satisfactory performance for high-accuracy SSVEP-based brain-computer interfaces.

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

Similar content being viewed by others

Abbreviations

a e :

Projection vector of EEG signals

a r :

Projection vector of the reference signals

A e :

Eigenvector of EEG signals

A r :

Eigenvector of reference signals

B :

One matrix

c :

Number of channels

C i :

A term in objective function (i = 1,2,3,4)

d :

Number of eigenvalues

D e :

Diagonal matrix of EEG signals from same stimulus frequency

\(\tilde{D}_{\rm{e}}\) :

Diagonal matrix of EEG signals from different stimulus frequencies

D r :

Diagonal matrix of reference signals from same stimulus frequency

\(\tilde{D}_{\rm{r}}\) :

Diagonal matrix of reference signals from different stimulus frequencies

e i :

Concatenated EEG signals matrix of one block

e te :

a new EEG feature vector for test

e tr k :

Concatenated EEG signals matrix from training set

E :

Segmented EEG signals matrix

f :

Base frequency

f k :

Label set

h :

Number of harmonics

i :

Index of features

I :

Identity matrix

i,j :

Indices of features

k :

Index of frequencies

K :

Number of stimulus frequencies

K e :

Gram matrix of EEG signals

L c :

Laplacian matrix of EEG signals from same stimulus frequency

\(\tilde{L}_{\rm{e}}\) :

Laplacian matrix of EEG signals from different stimulus frequencies

L r :

Laplacian matrix of reference signals from same stimulus frequency

\(\tilde{L}_{\rm{r}}\) :

Laplacian matrix of reference signals from different stimulus frequencies

m :

Dimension of Xe

M :

A centering matrix

n :

Dimension of Xr

n ITR :

Information transfer rate (ITR)

N :

Total number of sample blocks of all stimulus frequencies collected from one subject

p :

Dimension of Ψe

P :

Classification accuracy

q :

Dimension of Ψr

r i :

Concatenated reference signals matrix of one block

R :

Segmented reference signals matrix

s te :

Projected EEG feature vector of a new EEG feature vector

s i>tr k :

Projected EEG feature vector of an EEG feature vector from training set

S :

Sampling rate

S tr :

Training set

T :

Number of sampling points of a sample block

w :

Index of eigenvalues

X e :

Concatenated EEG signals matrix

X r :

Concatenated reference signals matrix

γ :

Correlation coefficient of ae and ar

σ e :

Mean of all mapped EEG signals

ζ :

Balancing parameter

θ i>e ij :

L2-norm distance of two mapped EEG signals

Θ e :

Similarity matrix of EEG signals from same stimulus frequency

Θ e :

Similarity matrix of EEG signals from different stimulus frequencies

Θ r :

Similarity matrix of reference signals from same stimulus frequency

\(\tilde{\Theta}_{\rm{e}}\) :

Similarity matrix of reference signals from different stimulus frequencies

λ w :

Generalized eigenvalues

μ e :

Width of the EEG Gaussian kernel

μ r :

Width of the reference Gaussian kernel

\(\tilde{\Theta}_{\rm{r}}\) :

Mean vector of ψe(ei), i = 1, 2, ⋯, N

Ψ e :

Mapped EEG signals matrix

Ψ r :

Mapped reference signals matrix

ω c :

Projection vector of EEG signals

ω r :

Projection vector of reference signals

e:

EEG signals

r:

Reference signals

te:

Test set

tr:

Training set

References

  1. WOLPAW J R, BIRBAUMER N, MCFARLAND D J, et al. Brain-computer interfaces for communication and control [J]. Clinical Neurophysiology, 2002, 113(6): 767–791.

    Article  Google Scholar 

  2. LOTTE F, BOUGRAIN L, CICHOCKI A, et al. A review of classification algorithms for EEG-based brain-computer interfaces: A 10 year update [J]. Journal of Neural Engineering, 2018, 15(3): 031005.

    Article  Google Scholar 

  3. WANG M, LI R, ZHANG R, et al. A wearable SSVEP-based BCI system for quadcopter control using head-mounted device [J]. IEEE Access, 2018, 6(99): 26789–26798.

    Article  Google Scholar 

  4. NEUMANN N, KÜBLER A, KAISER J, et al. Conscious perception of brain states: Mental strategies for brain-computer communication [J]. Neuropsychologia, 2003, 41(8): 1028–1036.

    Article  Google Scholar 

  5. CHAURASIYA R, LONDHE N, GHOSH S. A novel weighted edit distance-based spelling correction approach for improving the reliability of Devanagari script-based P300 speller system [J]. IEEE Access, 2016, 4: 8184–8198.

    Article  Google Scholar 

  6. SANTAMARIA L, JAMES C. Using brain connectivity metrics from synchrostates to perform motor imagery classification in EEG-based BCI systems [J]. Healthcare Technology Letters, 2018, 5(3): 88–93.

    Article  Google Scholar 

  7. CURRAN E, SYKACEK P, STOKES M, et al. Cognitive tasks for driving a brain-computer interfacing system: A pilot study [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2004, 12(1): 48–54.

    Article  Google Scholar 

  8. NAKANISHI M, WANG Y, WANG Y T, et al. Generating visual flickers for eliciting robust steady-state visual evoked potentials at flexible frequencies using monitor refresh rate [J]. PLoS One, 2014, 9(6): e99235.

    Article  Google Scholar 

  9. CHEN X, CHEN Z, GAO S, et al. A high-ITR SSVEP-based BCI speller [J]. Brain-Computer Interfaces, 2014, 1(3/4): 181–191.

    Article  Google Scholar 

  10. DREYER A M, HERRMANN C S. Frequency-modulated steady-state visual evoked potentials: A new stimulation method for brain-computer interfaces [J]. Journal of Neuroscience Methods, 2015, 241: 1–9.

    Article  Google Scholar 

  11. ORTIZ-ROSARIO A, ADELI H. Brain-computer interface technologies: From signal to action [J]. Reviews in the Neurosciences, 2013, 24(5): 537–552.

    Article  Google Scholar 

  12. TREJO L J, ROSIPAL R, MATTHEWS B. Brain-computer interfaces for 1-D and 2-D cursor control: Designs using volitional control of the EEG spectrum or steady-state visual evoked potentials [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2006, 14(2): 225–229.

    Article  Google Scholar 

  13. JIA D, DAI H, TAKASHIMA Y, et al. EEG processing in Internet of medical things using non-harmonic analysis: Application and evolution for SSVEP responses [J]. IEEE Access, 2019, 7: 11318–11327.

    Article  Google Scholar 

  14. TRIGUI O, ZOUCH W, BEN M. Anti-noise capability improvement of minimum energy combination method for SSVEP detection [J]. International Journal of Advanced Computer Science and Applications, 2016, 7(9): 393–401.

    Article  Google Scholar 

  15. ABU-ALQUMSAN M, PEER A. Advancing the detection of steady-state visual evoked potentials in brain-computer interfaces [J]. Journal of Neural Engineering, 2016, 13(3): 036005.

    Article  Google Scholar 

  16. LIN Z, ZHANG C, WU W, et al. Frequency recognition based on canonical correlation analysis for SSVEP-based BCIs [J]. IEEE Transactions on Biomedical Engineering, 2007, 54(6): 1172–1176.

    Article  Google Scholar 

  17. PORYZALA P, MATERKA A. Cluster analysis of CCA coefficients for robust detection of the asynchronous SSVEPs in brain-computer interfaces [J]. Biomedical Signal Processing and Control, 2014, 10: 201–208.

    Article  Google Scholar 

  18. BIN G, GAO X, WANG Y, et al. A high-speed BCI based on code modulation VEP [J]. Journal of Neural Engineering, 2011, 8(2): 025015.

    Article  Google Scholar 

  19. ZHANG Y, ZHOU G, JIN J, et al. Frequency recognition in SSVEP-based BCI using multiset canonical correlation analysis [J]. International Journal of Neural Systems, 2014, 24(4): 1450013.

    Article  Google Scholar 

  20. BAILLET S, MOSHER J C, LEAHY R M. Electromagnetic brain mapping [J]. IEEE Signal Processing Magazine, 2001, 18(6): 14–30.

    Article  Google Scholar 

  21. SAWATA R, OGAWA T, HASEYAMA M. Novel audio feature projection using KDLPCCA-based correlation with EEG features for favorite music classification [J]. IEEE Transactions on Affective Computing, 2019, 10(3): 430–444.

    Article  Google Scholar 

  22. AKAHO S. A kernel method for canonical correlation analysis [EB/OL]. (2007-02-14). https://arxiv.org/abs/cs/0609071.

  23. ZHANG X, GUAN N, LUO Z, et al. Discriminative locality preserving canonical correlation analysis [M]//Pattern recognition. Berlin, Heidelberg: Springer, 2012: 341–349.

    Chapter  Google Scholar 

  24. HE X, NIYOGI P. Locality preserving projections [M]//Advances in neural information processing systems. Cambridge, USA: MIT Press, 2004.

    Google Scholar 

  25. ARIS S A M, JALIL S Z A, BANI N A, et al. EEG features extraction and k-NN classification during eyes closed [C]// 2016 IEEE EMBS Conference on Biomedical Engineering and Sciences. Kuala Lumpur, Malaysia: IEEE, 2016: 679–684.

    Chapter  Google Scholar 

  26. RAKSHIT A, KHASNOBISH A, TIBAREWALA D N. A Naive Bayesian approach to lower limb classification from EEG signals [C]//2016 2nd International Conference on Control, Instrumentation, Energy & Communication (CIEC). Kolkata, India: IEEE, 2016: 140–144.

    Chapter  Google Scholar 

  27. BOSE S, RAMA V, WARANGAL N, et al. EEG signal analysis for Seizure detection using Discrete Wavelet Transform and Random Forest [C]//2017 International Conference on Computer and Applications (ICCA). Doha, Qatar: IEEE, 2017: 369–378.

    Chapter  Google Scholar 

  28. HERRMANN C S. Human EEG responses to 1–100 Hz flicker: Resonance phenomena in visual cortex and their potential correlation to cognitive phenomena [J]. Experimental Brain Research, 2001, 137(3/4): 346–353.

    Article  Google Scholar 

Download references

Acknowledgment

The authors would thank Mr. Bang Xiong and Mr. Cheng Fang for the assistance of the data acquisition in this study.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Xidian University, Xi’an, 710071, China

    Jiayang Huang  (黄嘉阳), Pengfei Yang  (杨鹏飞) & Bo Wan  (万 波)

  2. School of Electronic and Electrical Engineering, University of Leeds, Leeds, LS2 9JT, UK

    Zhiqiang Zhang  (张志强)

Authors
  1. Jiayang Huang  (黄嘉阳)
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pengfei Yang  (杨鹏飞)
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bo Wan  (万 波)
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhiqiang Zhang  (张志强)
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pengfei Yang  (杨鹏飞).

Additional information

Foundation item: the National Natural Science Foundation of China (Nos. 61702395 and 61972302), and the Science and Technology Projects of Xi’an, China (No. 201809170CX11JC12)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Huang, J., Yang, P., Wan, B. et al. KDLPCCA-Based Projection for Feature Extraction in SSVEP-Based Brain-Computer Interfaces. J. Shanghai Jiaotong Univ. (Sci.) 27, 168–175 (2022). https://doi.org/10.1007/s12204-021-2387-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12204-021-2387-0

Key words

CLC number

Document code

Search

Navigation