Small Data Least-Squares Transformation (sd-LST) for Fast Calibration of SSVEP-Based BCIs

Bian, Rui; Wu, Huanyu; Liu, Bin; Wu, Dongrui

doi:10.1109/tnsre.2022.3225878

Cited by 12 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where ∥∥ F is the Frobenius norm. The solution of (4) can solved as [22,27]. And the reconstructed source signal is estimated as:…”

Section: Samementioning

confidence: 99%

“…However, these cross-stimulus transfer methods focus only on reducing calibration trials or calibration commands. As a result, they have not yet completely realized fast calibration scenarios, where the subject is required to gaze at some of the targets only once [26,27]. This scenario not only reduces the number of calibration commands, but also reduces the number of calibration trials per command to only one.…”

Section: Introductionmentioning

confidence: 99%

“…Unlike unsupervised methods, it captures individual variability in EEG while minimizing the calibration effort required by supervised methods. Previous studies have achieved this scenario by transferring whole calibration data across multiple subjects, such as subject transfer-based CCA (stCCA) [26], and small data least-squares transformation (sd-LST) [27]. However, it is worth noting that collecting EEG data from additional subjects still entails a lengthy calibration process [18].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Almost free of calibration for SSVEP-based brain-computer interfaces

Luo,

Xiao,

Chen

et al. 2023

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) is a promising technology that can achieve high information transfer rate (ITR) with supervised algorithms such as ensemble task-related component analysis (eTRCA) and task-discriminant component analysis (TDCA). However, training individual models requires a tedious and time-consuming calibration process, which hinders the real-life use of SSVEP-BCIs. A recent data augmentation method, called source aliasing matrix estimation (SAME), can generate new EEG samples from a few calibration trials. But SAME does not exploit the information across stimuli as well as only reduces the number of calibration trials per command, so it still has some limitations. Approach. This study proposes an extended version of SAME, called multi-stimulus SAME (msSAME), which exploits the similarity of the aliasing matrix across frequencies to enhance the performance of SSVEP-BCI with insufficient calibration trials. We also propose a semi-supervised approach based on msSAME that can further reduce the number of SSVEP frequencies needed for calibration. We evaluate our method on two public datasets, Benchmark and BETA, and an online experiment. Main results. The results show that msSAME outperforms SAME for both eTRCA and TDCA on the public datasets. Moreover, the semi-supervised msSAME-based method achieves comparable performance to the fully calibrated methods and outperforms the conventional free-calibrated methods. Remarkably, our method only needs 24 seconds to calibrate 40 targets in the online experiment and achieves an average ITR of 213.8 bits/min with a peak of 242.6 bits/min. Significance. This study significantly reduces the calibration effort for individual SSVEP-BCIs, which is beneficial for developing practical plug-and-play SSVEP-BCIs.

show abstract

“…where ∥∥ F is the Frobenius norm. The solution of (4) can solved as [22,27]. And the reconstructed source signal is estimated as:…”

Section: Samementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Almost free of calibration for SSVEP-based brain-computer interfaces

Luo,

Xiao,

Chen

et al. 2023

J. Neural Eng.

View full text Add to dashboard Cite

show abstract

“…In recent years, transfer learning-based methods have demonstrated the ability to reduce the calibration effort for SSVEP-BCIs by transferring information across subjects [10], [11], [12], [13], [14], across sessions [15], across stimulus frequencies [16], [17], [18], and across devices [19], [20], [21]. However, to achieve good enough recognition performance, these transfer learning-based methods need not only source domain training data but also enough target domain data, i.e., calibration data acquisition is still required for a new user or device.…”

Section: Introductionmentioning

confidence: 99%

Enhancing SSVEP Identification With Less Individual Calibration Data Using Periodically Repeated Component Analysis

Ke,

Liu,

Ming

2024

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Objective: Spatial filtering and template matching-based methods are commonly used to identify the stimulus frequency from multichannel EEG signals in steady-state visually evoked potentials (SSVEP)-based brain-computer interfaces (BCIs). However, these methods require sufficient calibration data to obtain reliable spatial filters and SSVEP templates, and they underperform in SSVEP identification with small-sample-size calibration data, especially when a single trial of data is available for each stimulus frequency. Methods: In contrast to the state-of-theart task-related component analysis (TRCA)-based methods, which construct spatial filters and SSVEP templates based on the inter-trial task-related components in SSVEP, this study proposes a method called periodically repeated component analysis (PRCA), which constructs spatial filters to maximize the reproducibility across periods and constructs synthetic SSVEP templates by replicating the periodically repeated components (PRCs). We also introduced PRCs into two improved variants of TRCA. Performance evaluation was conducted using a selfcollected 16-target dataset and a public 40-target dataset. Results: The proposed methods show significant improvements with less training data and can achieve comparable performance to the baseline methods with 5 trials by using 2 or 3 training trials. Using a single trial of calibration data for each frequency, the PRCA-based methods achieved the highest average accuracies of over 95% and 90% with a 1-s data length and maximum average information transfer rates of 198.8±57.3 bits/min and 191.2±48.1 bits/min for the two datasets, respectively. Significance: Our results demonstrate the effectiveness and robustness of PRCA-based methods for SSVEP identification with reduced calibration effort and suggest its potential for practical applications of SSVEP-BCIs.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhancing SSVEP Identification with Less Individual Calibration Data Using Periodically Repeated Component Analysis

Ke¹,

Liu²,

Ming³

2023

Preprint

View full text Add to dashboard Cite

<p> Spatial filtering and template matching-based methods are commonly used to identify the stimulus frequency from multichannel EEG signals in steady-state visually evoked potentials (SSVEP)-based brain-computer interfaces (BCIs). However, these methods require sufficient calibration data to obtain reliable spatial filters and SSVEP templates, and they underperform in SSVEP identification with small-sample-size calibration data, especially when a single trial of data is available for each stimulus frequency. In contrast to the state-of-the-art task-related component analysis (TRCA)-based methods, which construct spatial filters and SSVEP templates based on the inter-trial task-related components in SSVEP, this study proposes a method called periodically repeated component analysis (PRCA), which constructs spatial filters to maximize the reproducibility across periods and constructs synthetic SSVEP templates by replicating the periodically repeated components (PRCs). We also introduced PRCs into two improved variants of TRCA. Performance evaluation was conducted using a self-collected 16-target dataset and a public 40-target dataset. The proposed methods show significant improvements with less training data and can achieve comparable performance to the baseline methods with 5 trials by using 2 or 3 training trials. Using a single trial of calibration data for each frequency, the PRCA-based methods achieved the highest average accuracies of over 95% and 90% with a 1-s data length and maximum average information transfer rates of 198.8±57.3 bits/min and 191.2±48.1 bits/min for the two data sets, respectively. Our results demonstrate the effectiveness and robustness of PRCA-based methods for SSVEP identification with reduced calibration effort and suggest its potential for practical applications of SSVEP-BCIs. </p>

show abstract

Small Data Least-Squares Transformation (sd-LST) for Fast Calibration of SSVEP-Based BCIs

Cited by 12 publications

References 34 publications

Almost free of calibration for SSVEP-based brain-computer interfaces

Almost free of calibration for SSVEP-based brain-computer interfaces

Enhancing SSVEP Identification With Less Individual Calibration Data Using Periodically Repeated Component Analysis

Enhancing SSVEP Identification with Less Individual Calibration Data Using Periodically Repeated Component Analysis

Contact Info

Product

Resources

About