Enhancing Detection of Multi-Frequency-Modulated SSVEP Using Phase Difference Constrained Canonical Correlation Analysis

Wong, Chi Man; Wang, Ze; Wang, Boyu; Rosa, Agostinho; Jung, Tzyy-Ping; Wan, Feng

doi:10.1109/tnsre.2023.3243290

Cited by 4 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, score 1 is not adjusted, while score 2 is slightly reduced. Although T best is a crucial indicator that reflects the performance of the BCI system, the evaluation of the BCI system currently focuses on the accuracy and the information transfer rate [ 7 , 18 , 35 ]. Therefore, score 4 was appropriately reduced, while score 3 and score 5 were appropriately increased.…”

Section: Methodsmentioning

confidence: 99%

Dataset Evaluation Method and Application for Performance Testing of SSVEP-BCI Decoding Algorithm

Liang

Zhang

Zhou

et al. 2023

Sensors

View full text Add to dashboard Cite

Steady-state visual evoked potential (SSVEP)-based brain–computer interface (BCI) systems have been extensively researched over the past two decades, and multiple sets of standard datasets have been published and widely used. However, there are differences in sample distribution and collection equipment across different datasets, and there is a lack of a unified evaluation method. Most new SSVEP decoding algorithms are tested based on self-collected data or offline performance verification using one or two previous datasets, which can lead to performance differences when used in actual application scenarios. To address these issues, this paper proposed a SSVEP dataset evaluation method and analyzed six datasets with frequency and phase modulation paradigms to form an SSVEP algorithm evaluation dataset system. Finally, based on the above datasets, performance tests were carried out on the four existing SSVEP decoding algorithms. The findings reveal that the performance of the same algorithm varies significantly when tested on diverse datasets. Substantial performance variations were observed among subjects, ranging from the best-performing to the worst-performing. The above results demonstrate that the SSVEP dataset evaluation method can integrate six datasets to form a SSVEP algorithm performance testing dataset system. This system can test and verify the SSVEP decoding algorithm from different perspectives such as different subjects, different environments, and different equipment, which is helpful for the research of new SSVEP decoding algorithms and has significant reference value for other BCI application fields.

show abstract

Section: Methodsmentioning

confidence: 99%

Dataset Evaluation Method and Application for Performance Testing of SSVEP-BCI Decoding Algorithm

Liang

Zhang

Zhou

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Chen et al [7] first proposed to apply the FB technique to the CCA algorithm and optimized the sub-band design and the weighting scheme of the sub-band features. The FB technique integrates band-specific classification features to effectively utilize SSVEP EEG information, and many studies have demonstrated its effectiveness in improving various algorithms [32], [33], [34], [35], [36], [37], [38].…”

Section: E Classification Algorithmmentioning

confidence: 99%

A SSVEP-Based Brain–Computer Interface With Low-Pixel Density of Stimuli

Meng,

Liu,

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

The brain-computer interface (BCI) based on the steady-state visual evoked potential (SSVEP) has drawn widespread attention due to its high communication speed and low individual variability. However, there is still a need to enhance the comfort of SSVEP-BCI, especially considering the assurance of its effectiveness. This study aims to achieve a perfect balance between comfort and effectiveness by reducing the pixel density of SSVEP stimuli. Three experiments were conducted to determine the most suitable presentation form (flickering square vs. flickering checkerboard), pixel distribution pattern (random vs. uniform), and pixel density value (100%, 90%, 80%, 70%, 60%, 40%, 20%). Subjects' electroencephalogram (EEG) and fatigue scores were recorded, while comfort and effectiveness were measured by fatigue score and classification accuracy, respectively. The results showed that the flickering square with random pixel distribution achieved a lower fatigue score and higher accuracy. EEG responses induced by stimuli with a square-random presentation mode were then compared across various pixel densities. In both offline and online tests, the fatigue score decreased as the pixel density decreased. Strikingly, when the pixel density was above 60%, the accuracies of low-pixel-density SSVEP were all satisfactory (>90%) and showed no significant difference with that of the conventional 100%-pixel density. These results support the feasibility of using 60%-pixel density with a square-random presentation mode to improve the comfort of SSVEP-BCI, thereby promoting its practical applications in communication and control.

show abstract

Enhancing multi-class SSVEP classification performance using regularized covariance estimators, spatiotemporal beamforming, and short-time EEG trials

Zarei,

Asl

2024

Measurement

View full text Add to dashboard Cite

Enhancing Detection of Multi-Frequency-Modulated SSVEP Using Phase Difference Constrained Canonical Correlation Analysis

Cited by 4 publications

References 49 publications

Dataset Evaluation Method and Application for Performance Testing of SSVEP-BCI Decoding Algorithm

Dataset Evaluation Method and Application for Performance Testing of SSVEP-BCI Decoding Algorithm

A SSVEP-Based Brain–Computer Interface With Low-Pixel Density of Stimuli

Enhancing multi-class SSVEP classification performance using regularized covariance estimators, spatiotemporal beamforming, and short-time EEG trials

Contact Info

Product

Resources

About