Closed Loop Subject-Independent SSVEP Frequency Detection System Using CCA Features and Ensemble Learning Methods

M. Moein Esfahani; Hosein Najafi; Hossein Sadati

doi:10.18502/fbt.v11i3.15878

Closed Loop Subject-Independent SSVEP Frequency Detection System Using CCA Features and Ensemble Learning Methods

M. Moein Esfahani

Hosein Najafi

Hossein Sadati

Abstract

Purpose: In recent years, the use of Steady-State Visual Evoked Potentials (SSVEPs) in Brain-Computer Interface (BCI) systems has dramatically increased across several fields, such as rehabilitation, cognitive impairment, and brain disease or disorder detection, as well as artificial limbs, wheelchairs, and biomechanical systems. In this study, a novel method is proposed to help scientists develop more efficient BCI systems for Machine Learning Operations (MLOps). This study proposed a state-of-the-art method for detecting SSVEP-based stimulation frequencies with statistical models to design an optimal BCI system.
Materials and Methods: In this study, the Canonical Correlation Analysis (CCA) method has been implemented to extract features from the accessible-to-the-public Tsinghua University Benchmark dataset. A limited number of subjects are being studied. After completing feature selection methods and selecting the best subset of features using a specified feature selection method, the classification of the best features using machine learning-based classification methods has been completed. Furthermore, it is assumed that scientists will design and implement a system specifically for subjects. Models work for subjects independently. However, because model training is subject-specific, we must execute the proposed methods on each subject separately.
Results: The findings indicate that the novel suggested BCI system achieves an average accuracy of 83±9% in stimulation detection, which is higher than that of the traditional CCA approach with an accuracy of 80±11% (p<0.05).
Conclusion: Based on the findings, we demonstrated an increase in accuracy with the novel method. It was also discovered that by using the proposed techniques, it is possible to keep MLOps systems as an advantage.

1- M. Moein Esfahani and H. Sadati, “Cross-Subject fNIRS Signals Channel-Selection based on Multi-Objective NSGA-II Algorithm,” in 2021 28th National and 6th International Iranian Conference on Biomedical Engineering (ICBME), Nov. (2021), pp. 242–247, doi: 10.1109/ICBME54433.2021.9750364.
2- M. M. Esfahani and H. Sadati, “fNIRS Signals Classification with Ensemble Learning and Adaptive Neuro-Fuzzy Inference System,” in 2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS), Dec. (2021), pp. 1–5, doi: 10.1109/ICSPIS54653.2021.9729388.
3- A. T. Dehkordi, H. Ghasemi, and M. J. V. Zoej, “Machine Learning-Based Estimation of Suspended Sediment Concentration along Missouri River using Remote Sensing Imageries in Google Earth Engine,” in 2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS), Dec. (2021), pp. 1–5, doi: 10.1109/ICSPIS54653.2021.9729382.
4- M. Moein Esfahani and H. Sadati, “Application of NSGA-II in Channel Selection of Motor Imagery EEG Signals with Common Spatio-Spectral Patterns in BCI Systems,” in 2022 8th International Conference on Control, Instrumentation and Automation (ICCIA), Mar. (2022), pp. 1–6, doi: 10.1109/ICCIA54998.2022.9737199.
5- A. Yousefiankalareh, M. A. Manoochehri, S. A. Khoshnevis, and S. R. Surakanti, “Improve the Frequency Identification in SSVEP based BCI Systems with Moving Windows Algorithm,” Proc. - 2019 6th Int. Conf. Control. Instrum. Autom. ICCIA 2019, pp. 1–5, 2019, doi: 10.1109/ICCIA49288.2019.9030862.
6- S. Aggarwal and N. Chugh, “Signal processing techniques for motor imagery brain computer interface: A review,” Array, vol. 1–2, no. August, p. 100003, (2019), doi: 10.1016/j.array.2019.100003.
7- M. Norizadeh Cherloo, H. Kashefi Amiri, and M. R. Daliri, “Spatio-Spectral CCA (SS-CCA): A novel approach for frequency recognition in SSVEP-based BCI,” J. Neurosci. Methods, vol. 371, no. January, p. 109499, (2022), doi: 10.1016/j.jneumeth.2022.109499.
8- W. Yan, Y. Wu, C. Du, and G. Xu, “Cross-subject spatial filter transfer method for SSVEP-EEG feature recognition,” J. Neural Eng., vol. 19, no. 3, (2022), doi: 10.1088/1741-2552/ac6b57.
9- P. Ma et al., “A classification algorithm of an SSVEP brain-Computer interface based on CCA fusion wavelet coefficients,” J. Neurosci. Methods, vol. 371, p. 109502, (2022), doi: 10.1016/j.jneumeth.2022.109502.
10- M. Testi et al., “MLOps: A Taxonomy and a Methodology,” IEEE Access, vol. 10, pp. 63606–63618, (2022), doi: 10.1109/access.2022.3181730.
11- M. M. Esfahani and H. Sadati, “Application of Transfer Learning in Optimized Filter-Bank Regularized CSP to Classification of EEG Signals with Small Dataset,” in 2022 30th International Conference on Electrical Engineering (ICEE), May (2022), pp. 963–967, doi: 10.1109/ICEE55646.2022.9827057.
12- W. Liu, L. Zhang, and C. Li, “A method for recognizing high-frequency steady-state visual evoked potential based on empirical modal decomposition and canonical correlation analysis,” Proc. 2019 IEEE 3rd Inf. Technol. Networking, Electron. Autom. Control Conf. ITNEC 2019, no. Itnec, pp. 774–778, (2019), doi: 10.1109/ITNEC.2019.8729005.
13- Y. Wang, X. Chen, X. Gao, and S. Gao, “A Benchmark Dataset for SSVEP-Based Brain-Computer Interfaces,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 25, no. 10, pp. 1746–1752, (2017), doi: 10.1109/TNSRE.2016.2627556.
14- Z. Lin, C. Zhang, W. Wu, and X. Gao, “Frequency recognition based on canonical correlation analysis for SSVEP-Based BCIs,” IEEE Trans. Biomed. Eng., vol. 54, no. 6, pp. 1172–1176, (2007), doi: 10.1109/TBME.2006.889197.
15- R. Wang, W. Wu, K. Iramina, and S. Ge, “The combination of CCA and PSDA detection methods in a SSVEP-BCI system,” Proc. World Congr. Intell. Control Autom., vol. 2015-March, no. March, pp. 2424–2427, (2015), doi: 10.1109/WCICA.2014.7053101.
16- A. M. Ray et al., “A subject-independent pattern-based brain-computer interface,” Front. Behav. Neurosci., vol. 9, no. OCTOBER, pp. 1–15, (2015), doi: 10.3389/fnbeh.2015.00269.
17- Q. Liu et al., “Efficient representations of EEG signals for SSVEP frequency recognition based on deep multiset CCA,” Neurocomputing, vol. 378, pp. 36–44, (2020), doi: 10.1016/j.neucom.2019.10.049.
18- P. Ma et al., “A classification algorithm of an SSVEP brain-Computer interface based on CCA fusion wavelet coefficients,” J. Neurosci. Methods, vol. 371, p. 109502, (2022), doi: 10.1016/j.jneumeth.2022.109502.
19- D. J. McFarland, L. M. McCane, S. V. David, and J. R. Wolpaw, “Spatial filter selection for EEG-based communication,” Electroencephalogr. Clin. Neurophysiol., vol. 103, no. 3, pp. 386–394, (1997), doi: 10.1016/S0013-4694(97)00022-2.
20- D. J. McFarland and J. R. Wolpaw, “Brain-computer interfaces for communication and control,” Commun. ACM, vol. 54, no. 5, pp. 60–66, (2011), doi: 10.1145/1941487.1941506.
21- J. Lu, D. J. McFarland, and J. R. Wolpaw, “Adaptive Laplacian filtering for sensorimotor rhythm-based brain-computer interfaces,” J. Neural Eng., vol. 10, no. 1, (2013), doi: 10.1088/1741-2560/10/1/016002.
22- X. Chen, Y. Wang, S. Gao, T. P. Jung, and X. Gao, “Filter bank canonical correlation analysis for implementing a high-speed SSVEP-based brain-computer interface,” J. Neural Eng., vol. 12, no. 4, (2015), doi: 10.1088/1741-2560/12/4/046008.
23- X. Chen, B. Zhao, Y. Wang, S. Xu, and X. Gao, “Control of a 7-DOF Robotic Arm System with an SSVEP-Based BCI,” Int. J. Neural Syst., vol. 28, no. 8, (2018), doi: 10.1142/S0129065718500181.
24- A. Taheri Dehkordi, M. J. Valadan Zoej, H. Ghasemi, E. Ghaderpour, and Q. K. Hassan, “A New Clustering Method to Generate Training Samples for Supervised Monitoring of Long-Term Water Surface Dynamics Using Landsat Data through Google Earth Engine,” Sustainability, vol. 14, no. 13, p. 8046, Jun. (2022), doi: 10.3390/su14138046.
25- A. C. Ramos, R. G. Hernández, and M. Vellasco, “Feature Selection methods applied to Motor Imagery task classification,” 2016 IEEE Lat. Am. Conf. Comput. Intell. LA-CCI 2016 - Proc., no. Mi, (2017), doi: 10.1109/LA-CCI.2016.7885731.
26- O. Sagi and L. Rokach, “Ensemble learning: A survey,” no. December 2017, pp. 1–18, (2018), doi: 10.1002/widm.1249.

Files	XML PDF (856KB)
Issue	Vol 11 No 3 (2024)
Section	Original Article(s)
DOI	https://doi.org/10.18502/fbt.v11i3.15878
Keywords
Steady-State Visual Evoked Potentials Canonical Correlation Analysis Ensemble Learning Machine Learning Operations Brain-Computer Interface Electroencephalogram

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

How to Cite

Esfahani MM, Najafi H, Sadati H. Closed Loop Subject-Independent SSVEP Frequency Detection System Using CCA Features and Ensemble Learning Methods. Frontiers Biomed Technol. 2024;11(3):315-325.

Vancouver

Download Citation