Comparison of Spectral and Template Matching Features for SSVEP BCI Target Frequency Classification

Keywords: Classification, BCI, SSVEP, Feature Extraction, Visual Evoked Potential, Target Frequency Signal Ratio, PSDA


Brain-computer interfaces (BCI) provide new communication and control channels to restore and support these functions of the restricted users. Among these Visual Evoked Potential (VEP) based BCIs are the most promising in terms of ease of use and performance. The frequency following phenomenon of VEPs produce Steady State Visual Evoked Potentials (SSVEP) at the frequency of stimulation of the human visual system. In such interface systems, each target is encoded with a particular stimulation frequency and phase. In communication purpose speller interfaces each target flickers a letter or character with the stimulation frequency and phase. The detection of the focused target correctly by the computer is required. In this process classification methods and feature extraction method play critical roles. This study used a publicly available benchmark dataset of a 40 target SSVEP BCI. In the analysis, two feature vectors are obtained from power spectrum parameters and one from stimulus template matching correlation coefficients. The performance of the three classification methods, namely Fine Tree, Linear Discriminant Analysis (LDA) and K-Nearest Neighbors (KNN), are compared using these feature vectors. Spectral features performed better than the template matching features. Especially target frequency signal ratio (TFSR) to the total stimulation band energy features provided better accuracy values. LDA and KNN performed better than decision tree in classification.


Download data is not yet available.


J. V. Odom et al., “ISCEV standard for clinical visual evoked potentials:(2016 update),” Doc. Ophthalmol., vol. 133, no. 1, pp. 1-9, Aug. 2016.

F. B. Vialatte et al., “Steady-state visually evoked potentials: focus on essential paradigms and future perspectives,” Prog. in Neurobiol., vol. 90, no. 4, pp. 418-38, Apr. 1, 2010.

Ö. Özdamar, J. Bohórquez, “Signal-to-noise ratio and frequency analysis of continuous loop averaging deconvolution (CLAD) of overlapping evoked potentials,” JASA, vol. 119, no. 1, pp. 429-38, Jan. 2006.

A. Capilla et al., “Steady-state visual evoked potentials can be explained by temporal superposition of transient event-related responses,” PloS one, vol. 6, no. 1, e14543, Jan. 18 2011.

P. L. Nunez, “Electric and magnetic fields produced by the brain,” in Brain-Computer Interfaces: Principles and Practice, pp. 171-212,

Jan 24 2012.

G. G. Celesia, “Steady‐state and transient visual evoked potentials in clinical practice,” Ann. N. Y. Acad. Sci., vol. 388, no. 1, pp 290-305, Jun. 1982.

D. Regan, “Human brain electrophysiology. Evoked potentials and evoked magnetic fields in science and medicine.” New York, Elsevier, 1989.

D. Regan, “Comparison of transient and steady‐state methods,” Ann. N. Y. Acad. Sci.. vol. 388, no. 1, pp. 45-71, Jun. 1982.

J. R. Wolpaw, E. W. Wolpaw. “Brain-computer interfaces: something new under the sun,” in Brain-computer interfaces: principles and practice, 14, Jan. 24 2012.

G. Bin et al., “An online multi-channel SSVEP-based brain–computer interface using a canonical correlation analysis method,” J. Neural Eng., vol. 6, no. 4, 046002, Jun. 3 2009.

Y. Wang et al., “Brain-computer interfaces based on visual evoked potentials,” IEEE Eng. Med. Biol. Mag., vol. 27, no. 5, pp. 64-71, Sep. 16 2008.

Y. Wang et al., “A benchmark dataset for SSVEP-based brain–computer interfaces,” IEEE Trans. Neural Syst., vol. 10, no. 25, pp. 1746-52, Nov. 10 2016.

Y. Zhang et al.. “Multivariate synchronization index for frequency recognition of SSVEP-based brain–computer interface,” J. Neurosci. Methods. Issue: 221, pp. 32-40, Jan. 15 2014.

X. Chen et al., “A high-itr ssvep-based bci speller,” Brain-Computer Interfaces. vol. 1, issue 3-4, pp. 181-191, Oct. 2 2014.

N. V. Manyakov et al.. “Sampled sinusoidal stimulation profile and multichannel fuzzy logic classification for monitor-based phase-coded SSVEP brain–computer interfacing,” J. Neural Eng., vol. 10, no. 3, 036011, Apr 18 2013.

J. Castillo-Garcia et al., “Comparison among feature extraction techniques based on power spectrum for a SSVEP-BCI,” In 2014 12th IEEE International Conference on Industrial Informatics (INDIN) , pp. 284-288. IEEE. July 2014.

Q. Wei, M. Xiao, Z. Lu, “A comparative study of canonical correlation analysis and power spectral density analysis for SSVEP detection,” In 2011 Third International Conference on Intelligent Human-Machine Systems and Cybernetics, vol. 2, pp. 7-10. IEEE. August 2011.

Richard M. G. Tello et al., "A comparison of techniques and technologies for SSVEP classification," 5th ISSNIP-IEEE Biosignals and Biorobotics Conference (2014): Biosignals and Robotics for Better and Safer Living (BRC). IEEE, 2014.

M. T. Puth, M. Neuhäuser, G.D. Ruxton, “Effective use of Pearson's product–moment correlation coefficient,” Animal behaviour. vol. 93, pp. 183-189, Jul. 1 2014.

S. R. Safavian, D. Landgrebe, “A survey of decision tree classifier methodology,” IEEE Trans. Syst., Man, Cybern., vol. 21, no. 3, pp. 660-674, May 1991.

R. O. Duda, P. E. Hart, D. G. Stork, Pattern Classification. John Willey and Sons, New York. 2001.

K. Fukunaga. Statistical Pattern Recognition 2nd edn (New York: Academic), 1990.

F. Lotte, “A tutorial on EEG signal-processing techniques for mental-state recognition in brain–computer interfaces,” In: Miranda E., Castet J. (eds) Guide to Brain-Computer Music Interfacing. Springer, London. pp. 133-161, 2014.

L. F. Nicolas-Alonso, J. Gomez-Gil. “Brain computer interfaces, a review,” sensors, vol. 12, no. 2, pp. 1211-1279, Feb. 2012.

F. Lotte , “A review of classification algorithms for EEG-based brain–computer interfaces,” J. Neural Eng. vol. 4, no. 2, R1. Jan. 31 2007.

How to Cite
I. Kaya, “Comparison of Spectral and Template Matching Features for SSVEP BCI Target Frequency Classification”, IJISAE, vol. 9, no. 2, pp. 64-68, Jun. 2021.
Research Article