Review and Evaluation of Trending Canonical Correlation Analyses-Based Brain-Computer Interface Methods

The fast development of technology that has advanced neuroscience and human interaction with computers has enabled solutions to various problems and issues of this new era. The Brain-Computer Interface (BCI) has opened the door to several new research areas and have been able to provide solutions to critical and vital issues such as supporting a paralyzed patient to interact with the outside world, controlling a robot arm, playing games in VR with the brain, driving a wheelchair. This review presents the state-of-the-art methods and improvements of canonical correlation analyses (CCA), an SSVEP-based BCI method. These are the methods used to extract EEG signal features or, to be said differently, the features of interest that we are looking for in the EEG analyses. Each of the methods from oldest to newest has been discussed while comparing their advantages and disadvantages. This would create a great context and help researchers understand the most state-of-the-art methods available in this field, their pros and cons, and their mathematical representations and usage. This work makes a vital contribution to the existing field of study. It differs from other similar recently published works by providing the following: (1) stating most of the main methods used in this field in a hierarchical way, (2) explaining the pros and cons of each method and their performance, (3) presenting the gaps that exist at the end of each method that can improve the understanding and open doors to new researches or improvements. 

• Bayar Shahab

• BCI
• CCA
• SSVEP
• EEG

[1] Zerafa, R., Camilleri, T., Falzon, O., & Camilleri, K. (2018 ). To train or not to train?A survey on training of feature extraction method for SSVEP-based BCIs. Journal of Neural Engineering, 29.
[2] Hotelling, H., (1936). relations between two sets of variates, biometrika, volume 28, issue 3-4, december 1936, Pages 321–377, https://doi.org/10.1093/biomet/28.3-4.321
[3] Lin, Z., Zhang, C., Wu, W., & Gao, X. (2007). Frequency Recognition Based on Canonical. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1172 - 1176.
[4] Bin, G., Gao, X., Wang, Y., Li, Y., Hong, B., & Gao, S. (2011). A high-speed BCI based on code modulation VEP. Journal Of Neural Engineering, 8(2), 025015. doi: 10.1088/1741-2560/8/2/025015
[5] Pan, J., Gao, X., Duan, F., Yan, Z., & Gao, S. (2011). Enhancing the classification accuracy of steady-state visual evoked potential-based brain–computer interfaces using phase constrained canonical correlation analysis. Journal Of Neural Engineering, 8(3), 036027. doi: 10.1088/1741-2560/8/3/036027
[6] Yu, Z., Guoxu, Z., Qibin, Z., Akinari, O., Jing, J., Xingyu, W., & Andrzej, C. (2021). Multiway Canonical Correlation Analysis for Frequency Components Recognition in SSVEP-Based BCIs. In Neural Information Processing - 18th International Conference, ICONIP 2011. Shanghai. Retrieved from http://10.1007/978-3-642-24955-6_35
[7] Zhang, Y., Zhou, G., Jin, J., Wang, M., Wang, X., & Cichocki, A. (2013). L1-Regularized Multiway Canonical Correlation Analysis for SSVEP-Based BCI. IEEE Transactions On Neural Systems And Rehabilitation Engineering, 21(6), 887-896. doi: 10.1109/tnsre.2013.2279680
[8] Zhang, Y., Zhou, G., Jin, J., Wang, X., & Cichocki, A. (2014). frequency recognition in ssvep-based bci using multiset canonical correlation analysis. international journal of neural systems, 24(04), 1450013. doi: 10.1142/s0129065714500130
[9] Poryzala, P., & Materka, A. (2014). Cluster analysis of CCA coefficients for robust detection of the asynchronous SSVEPs in brain–computer interfaces. Biomedical Signal Processing and Control, 201-208.
[10] Chen, X., Wang, Y., Gao, S., Jung, T., & Gao, X. (2015). Filter bank canonical correlation analysis for implementing a high-speed SSVEP-based brain–computer interface. Journal Of Neural Engineering, 12(4), 046008. doi: 10.1088/1741-2560/12/4/0460