CoChat

A Comparison Study of Canonical Correlation Analysis Based Methods for Detecting Steady-State Visual Evoked Potentials

Open access
Nakanishi, Masaki, Wang, Yijun, Wang, Yu-Te, Jung, Tzyy-Ping · 2015 · PLoS ONE

The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.

Abstract

Canonical correlation analysis (CCA) has been widely used in the detection of the steady-state visual evoked potentials (SSVEPs) in brain-computer interfaces (BCIs). The standard CCA method, which uses sinusoidal signals as reference signals, was first proposed for SSVEP detection without calibration. However, the detection performance can be deteriorated by the interference from the spontaneous EEG activities. Recently, various extended methods have been developed to incorporate individual EEG calibration data in CCA to improve the detection performance. Although advantages of the extended CCA methods have been demonstrated in separate studies, a comprehensive comparison between these methods is still missing. This study performed a comparison of the existing CCA-based SSVEP detection methods using a 12-class SSVEP dataset recorded from 10 subjects in a simulated online BCI experiment. Classification accuracy and information transfer rate (ITR) were used for performance evaluation. The results suggest that individual calibration data can significantly improve the detection performance. Furthermore, the results showed that the combination method based on the standard CCA and the individual template based CCA (IT-CCA) achieved the highest performance.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pone.0140703

Cites

36 of 36 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig 1 Stimulus design of the 12-target BCI system. (A) The user interface of a virtual keypad for a phone-dialing program. (B) Frequency and phase values specified for each target. The red square in (A) is the visual cue indicating a target symbol ‘5’ in the experiment.
Fig 1 Stimulus design of the 12-target BCI system. (A) The user interface of a virtual keypad for a phone-dialing program. (B) Frequency and phase values specified for each target. The red square in (A) is the visual cue indicating a target symbol ‘5’ in the experiment.CC BY · PubMed Central
Fig 2 Performance comparison of seven CCA-based SSVEP detection methods. (A) Averaged classification accuracy and (B) simulated ITRs across subject using different data lengths. Error bars indicate standard errors. The asterisks indicate significant difference between different methods (*p<0.05).
Fig 2 Performance comparison of seven CCA-based SSVEP detection methods. (A) Averaged classification accuracy and (B) simulated ITRs across subject using different data lengths. Error bars indicate standard errors. The asterisks indicate significant difference between different methods (*p<0.05).CC BY · PubMed Central
Fig 3 Comparison of accuracy with different parameters. Averaged classification accuracy for each method using (A) different numbers of harmonics (N h in Eq (5)) and (B) different number of channels (N c) across subjects. Error bars indicate standard errors.
Fig 3 Comparison of accuracy with different parameters. Averaged classification accuracy for each method using (A) different numbers of harmonics (N h in Eq (5)) and (B) different number of channels (N c) across subjects. Error bars indicate standard errors.CC BY · PubMed Central
Fig 4 The waveforms of the training data of SSVEPs and sinusoidal reference signals at 12.25Hz after spatial filtering based on CCA for each subject.
Fig 4 The waveforms of the training data of SSVEPs and sinusoidal reference signals at 12.25Hz after spatial filtering based on CCA for each subject.CC BY · PubMed Central
Fig 5 Examples of feature values and r-square values for each method. (A) Averaged feature values and (B) r-square values for SSVEPs at 12.25Hz. The dotted line in (A) indicates the stimulus frequency. Error bars in each subfigure indicate standard errors. The asterisks indicate significant difference between two different methods.
Fig 5 Examples of feature values and r-square values for each method. (A) Averaged feature values and (B) r-square values for SSVEPs at 12.25Hz. The dotted line in (A) indicates the stimulus frequency. Error bars in each subfigure indicate standard errors. The asterisks indicate significant difference between two different methods.CC BY · PubMed Central
Fig 6 Averaged classification accuracy across subjects with different numbers of training trials for each method. Error bars indicate standard errors.
Fig 6 Averaged classification accuracy across subjects with different numbers of training trials for each method. Error bars indicate standard errors.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 36 references

Research works printed but not linked: 3

  1. W Nan, 2011, Proc 5th Int IEEE EMBS Neural Eng Conf, 469
  2. RMG Tello, 2014, Proc 5th ISSNIP-IEEE Biosig Biorobot Conf Biosig and Robot Better Safer Living, 1
  3. Y Wang, 2014, Proc 36th Ann Int Conf IEEE Eng Med Biol Soc, 3037

Cited by

See all 389

Metadata

Authors
Nakanishi, M., Wang, Y., Wang, Y.-T., & Jung, T.-P.
Affiliations
  • University of California San Diego (US)
  • Chinese Academy of Sciences (CN)
Corresponding author
Wang, Yijun
Venue
PLoS ONE
Published
2015-10-19
Volume
10
Issue
10
Pages
e0140703
ISSN
1932-6203 (ISSN-L)
OpenAlex
W2338492816
Cited by
376
References
36
Citations by year
2026: 16 · 2025: 50 · 2024: 51 · 2023: 46 · 2022: 43 · 2021: 37 · 2020: 41 · 2019: 38 · 2018: 23 · 2017: 21 · 2016: 9
FWCI
10.63
Type
journal article
Language
en
Open access
Locations
  • PLoS ONE (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • eScholarship (California Digital Library) (submittedVersion)
  • eScholarship (California Digital Library) (submittedVersion, cc-by)
  • SEMI-IR (submittedVersion)
Funders
  • Recruitment Program for Young Professionals
  • National Institutes of Health (W911NF-10-2-0022)
  • Defense Advanced Research Projects Agency (W911NF-10-2-0022, USDI D11PC20183)
  • Office of Naval Research (W911NF-10-2-0022, N00014-08-1215, N00014)
  • National Eye Institute (R21EY025056)
  • Army Research Office (W911NF-10-2-0022, W911NF-09-1-0510, W911NF)
  • Army Research Laboratory (W911-NF-10-2-0022, W911NF, W911NF-10)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
  • Physical Sciences › Computer Science › Human-Computer Interaction › Gaze Tracking and Assistive Technology
  • Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
Keywords
steady-state visual evoked potentials, canonical correlation analysis, SSVEP detection, brain-computer interface, information transfer rate, classification accuracy
MeSH terms
Adult, Electroencephalography, Evoked Potentials, Visual, Female, Humans, Male, Statistics as Topic, Brain-Computer Interfaces

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A Comparison Study of Canonical Correlation Analysis Based Methods for Detecting Steady-State Visual Evoked Potentials. https://app.cochat.ai/papers/10.1371/journal.pone.0140703
The paper
Nakanishi, M., Wang, Y., Wang, Y.-T., & Jung, T.-P. (2015). A Comparison Study of Canonical Correlation Analysis Based Methods for Detecting Steady-State Visual Evoked Potentials. PLoS ONE. https://doi.org/10.1371/journal.pone.0140703

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.