A brain-computer interface (BCI) provides a direct communication channel between a brain and an external device. Steady-state visual evoked potential based BCI (SSVEP-BCI) has received increasing attention due to its high information transfer rate, which is accomplished by individual calibration for frequency recognition. Task-related component analysis (TRCA) is a recent and state-of-the-art method for individually calibrated SSVEP-BCIs. However, in TRCA, the spatial filter learned from each stimulus may be redundant and temporal information is not fully utilized. To address this issue, this paper proposes a novel method, i.e., task-discriminant component analysis (TDCA), to further improve the performance of individually calibrated SSVEP-BCI. The performance of TDCA was evaluated by two publicly available benchmark datasets, and the results demonstrated that TDCA outperformed ensemble TRCA and other competing methods by a significant margin. An offline and online experiment testing 12 subjects further validated the effectiveness of TDCA. The present study provides a new perspective for designing decoding methods in individually calibrated SSVEP-BCI and presents insight for its implementation in high-speed brain speller applications.

/pdf/improving-the-performance-of-individually-calibrated-ssvep-5g84du4ssk.pdf

Improving the Performance of Individually Calibrated SSVEP-BCI by Task- Discriminant Component Analysis

• SSVEP-StarGAN, a novel signal-to-signal translation method for SSVEP-based BCIs, was proposed. • Artificial SSVEP signals were successfully generated using resting EEG data. • The classification accuracies and ITR were significantly improved using the artificial SSVEP signals. • The artificial SSVEP signals can be used to effectively reduce the time-consuming calibration time. Generative adversarial networks (GANs) have shown promising performance in image-to-image translation. Inspired by StarGAN v2, which was introduced to address the multidomain image-to-image translation, the authors propose a novel multidomain signal-to-signal translation method to generate artificial steady-state visual evoked potential (SSVEP) signals from resting electroencephalograms (EEGs). The proposed StarGAN-based signal-to-signal translation model was trained using EEG data acquired from three subjects and could successfully generate sufficient numbers of artificial SSVEP signals of 15 test participants using resting EEG data acquired over an extremely short time period (∼16 s) from each test participant. The possibility of improving the performance of SSVEP-based brain–computer interfaces (BCIs) was investigated by incorporating the artificially generated SSVEP signals and Combined-ECCA, which is proposed in this study as an extended version of combined canonical correlation analysis (Combined-CCA). Fifteen healthy individuals participated in the SSVEP-based BCI study to distinguish four visual stimuli with different flickering frequencies. To evaluate the degree of performance improvement, the average classification accuracy and information transfer rate (ITR) obtained using the proposed methods were compared with those obtained using filter bank CCA (FBCCA), a state-of-the-art training-free method for SSVEP-based BCIs. The performances in terms of the classification accuracy and ITR of SSVEP-based BCIs were significantly improved by using the proposed methods (95.47% and 40.09 bit/min) compared with those using FBCCA (92.03% and 31.80 bit/min, p < 0.05). In addition, more than four individual training trials per class were necessary to achieve better classification accuracy than that of the proposed approach if the conventional individual training approach was employed. 

Novel Signal-to-Signal translation method based on StarGAN to generate artificial EEG for SSVEP-based brain-computer interfaces

Estimating brain periodic sources activities in steady-state visual evoked potential using local fourier independent component analysis

This study details the development of a novel, approx. £20 electroencephalogram (EEG)-based brain-computer interface (BCI) intended to offer a financially and operationally accessible device that can be deployed on a mass scale to facilitate education and public engagement in the domain of EEG sensing and neurotechnologies. Real-time decoding of steady-state visual evoked potentials (SSVEPs) is achieved using variations of the widely-used canonical correlation analysis (CCA) algorithm: multi-set CCA and generalised CCA. All BCI functionality is executed on board an inexpensive ESP32 microcontroller. SSVEP decoding accuracy of 95.56 ± 3.74% with an ITR of 102 bits/min was achieved with modest calibration.

https://www.biorxiv.org/content/biorxiv/early/2022/01/29/2022.01.29.478203.full.pdf

Development of an Ultra Low-Cost SSVEP-based BCI Device for Real-Time On-Device Decoding

Objective. Task-related component analysis (TRCA) is a representative subject-specific training algorithm in steady-state visual evoked potential (SSVEP)-based brain-computer interfaces. Task-related components (TRCs), extracted by the TRCA-based spatial filtering from electroencephalogram (EEG) signals through maximizing the reproducibility across trials, may contain some task-related inherent noise that is still trial-reproducible.Approach. To address this problem, this study proposed a similarity-constrained TRCA (scTRCA) algorithm to remove the task-related noise and extract TRCs maximally correlated with SSVEPs for enhancing SSVEP detection. Similarity constraints, which were created by introducing covariance matrices between EEG training data and an artificial SSVEP template, were added to the objective function of TRCA. Therefore, a better spatial filter was obtained by maximizing not only the reproducibility across trials but also the similarity between TRCs and SSVEPs. The proposed scTRCA was compared with TRCA, multi-stimulus TRCA, and sine-cosine reference signal based on two public datasets.Main results. The performance of TRCA in target identification of SSVEPs is improved by introducing similarity constraints. The proposed scTRCA significantly outperformed the other three methods, and the improvement was more significant especially with insufficient training data.Significance. The proposed scTRCA algorithm is promising for enhancing SSVEP detection considering its better performance and robustness against insufficient calibration.

Similarity-constrained task-related component analysis for enhancing SSVEP detection.

Canonical correlation analysis (CCA) is a widely used method for the identification of steady-state visual evoked potential (SSVEP). Many studies dedicated to improving the performance of CCA via incorporating individual training data, whereas its variants are still not comparable to other state-of-the-art subject-specific training methods such as task-related component analysis (TRCA). This study employs a generalized canonical correlation analysis (GCCA) method that simultaneously maximizes the correlation among three sets of data, i.e. the individual training data, the individual template, and the predefined sine-cosine signal for improving SSVEP detection. The proposed GCCA-based method and its ensemble version (eGCCA) were validated on a 40-class SSVEP benchmark dataset. The study results showed that GCCA significantly outperformed TRCA and the improvement was more significant as training data decreased. Similarly, eGCCA achieved a higher performance than eTRCA and the improvement was significant with insufficient training data. Therefore, the proposed GCCA-based method is promising in the SSVEP-based brain-computer interfaces, owing to its advantages of high performance in target identification and robustness against less calibration.

Minyou Chen

Papers

Similarity-constrained task-related component analysis for enhancing SSVEP detection.

Improving SSVEP Identification Accuracy via Generalized Canonical Correlation Analysis