Enhancing SSVEP Identification with Less Individual Calibration Data Using Periodically Repeated Component Analysis DOI Creative Commons
Yufeng Ke, Shuang Liu, Dong Ming

et al.

Published: July 20, 2023

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

Language: Английский

A memristor-based adaptive neuromorphic decoder for brain–computer interfaces DOI
Zhengwu Liu, Jie Mei, Jianshi Tang

et al.

Nature Electronics, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 17, 2025

Language: Английский

Citations

3
Cross-Stimulus Transfer Method Using Common Impulse Response for Fast Calibration of SSVEP-Based BCIs DOI
Bang Xiong, Bo Wan, Jiayang Huang

et al.

IEEE Transactions on Instrumentation and Measurement, Journal Year: 2024, Volume and Issue: 73, P. 1 - 14

Published: Jan. 1, 2024

To achieve a high information transfer rate (ITR) in steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs), current decoding methods require extensive calibration efforts to train the model parameters for each stimulus. facilitate process, this study proposed cross-stimulus method, which learns common spatial filter and impulse response from few source stimuli then transfers them new target stimulus SSVEP feature extraction. First, are obtained by minimizing deviation between spatially filtered SSVEPs constructed templates. Then, vector comprised of two correlation coefficients is utilized recognition, one coefficient templates, other canonical reference signals. For performance evaluation, recognition method was compared with state-of-art on public datasets self-collected dataset. Results showed that can obtain higher fewer training blocks, demonstrating has capability fast SSVEP-based BCIs.

Language: Английский

Citations

5
Short-length SSVEP data extension by a novel generative adversarial networks based framework DOI
Yudong Pan, Ning Li, Yangsong Zhang

et al.

Cognitive Neurodynamics, Journal Year: 2024, Volume and Issue: 18(5), P. 2925 - 2945

Published: May 31, 2024

Language: Английский

Citations

4
Enhancing detection of SSVEPs using discriminant compacted network DOI

Dian Li,

Yongzhi Huang, Ruixin Luo

et al.

Journal of Neural Engineering, Journal Year: 2025, Volume and Issue: 22(1), P. 016043 - 016043

Published: Jan. 31, 2025

Objective. Steady-state visual evoked potential-based brain-computer interfaces (SSVEP-BCIs) have gained significant attention due to their simplicity, high signal noise ratio and information transfer rates (ITRs). Currently, accurate detection is a critical issue for enhancing the performance of SSVEP-BCI systems.Approach.This study proposed novel decoding method called Discriminant Compacted Network (Dis-ComNet), which exploited advantages both spatial filtering deep learning (DL). Specifically, this enhanced SSVEP features using global template alignment discriminant pattern, then designed compacted temporal-spatio module (CTSM) extract finer features. The was evaluated on self-collected high-frequency dataset, public Benchmark dataset wearable dataset.Main Results.The results showed that Dis-ComNet significantly outperformed state-of-the-art methods, DL other fusion methods. Remarkably, improved classification accuracy by 3.9%, 3.5%, 3.2%, 13.3%, 17.4%, 37.5%, 2.5% when comparing with eTRCA, eTRCA-R, TDCA, DNN, EEGnet, Ensemble-DNN, TRCA-Net respectively in dataset. achieved were 4.7%, 4.6%, 23.6%, 52.5%, 31.7%, 7.0% higher than those TRCA-Net, respectively, comparable TDCA 9.5%, 7.1%, 36.1%, 26.3%, 15.7% 4.7% TDCA. Besides, our model ITRs up 126.0 bits/min, 236.4 bits/min 103.6 high-frequency, datasets respectively.Significance.This develops an effective SSVEPs, facilitating development systems.

Language: Английский

Citations

0
Inter- and Intra-Subject transfer learning for High-Performance SSVEP-BCI with extremely little calibration effort DOI
Hui Li, Guanghua Xu, Zejin Li

et al.

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127208 - 127208

Published: March 1, 2025

Language: Английский

Citations

0
Enhancing SSVEP Identification With Less Individual Calibration Data Using Periodically Repeated Component Analysis DOI
Yufeng Ke, Shuang Liu, Dong Ming

et al.

IEEE Transactions on Biomedical Engineering, Journal Year: 2023, Volume and Issue: 71(4), P. 1319 - 1331

Published: Nov. 16, 2023

Spatial filtering and template matching-based steady-state visually evoked potentials (SSVEP) identification methods usually underperform in SSVEP with small-sample-size calibration data, especially when a single trial of data is available for each stimulation frequency.

Language: Английский

Citations

8
A Novel Data Augmentation Approach Using Mask Encoding for Deep Learning-Based Asynchronous SSVEP-BCI DOI Creative Commons
Wenlong Ding, Aiping Liu, Ling Guan

et al.

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Journal Year: 2024, Volume and Issue: 32, P. 875 - 886

Published: Jan. 1, 2024

Deep learning (DL)-based methods have been successfully employed as asynchronous classification algorithms in the steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) system. However, these often suffer from limited amount of electroencephalography (EEG) data, leading to overfitting. This study proposes an effective data augmentation approach called EEG mask encoding (EEG-ME) mitigate EEG-ME forces models learn more robust features by masking partial enhanced generalization capabilities models. Three different network architectures, including architecture integrating convolutional neural networks (CNN) with Transformer (CNN-Former), time domain-based CNN (tCNN), and a lightweight (EEGNet) are utilized validate effectiveness on publicly available benchmark BETA datasets. The results demonstrate that significantly enhances average accuracy various DL-based lengths windows two public Specifically, CNN-Former, tCNN, EEGNet achieve respective improvements 3.18%, 1.42%, 3.06% dataset well 11.09%, 3.12%, 2.81% dataset, 1-second window example. performance SSVEP promotes implementation SSVEP-BCI system, improved robustness flexibility human-machine interaction.

Language: Английский

Citations

2
OS-SSVEP: One-shot SSVEP classification DOI
Yang Deng, Zhiwei Ji, Yijun Wang

et al.

Neural Networks, Journal Year: 2024, Volume and Issue: 180, P. 106734 - 106734

Published: Sept. 25, 2024

Language: Английский

Citations

2
Dataset Evaluation Method and Application for Performance Testing of SSVEP-BCI Decoding Algorithm DOI Creative Commons
Liyan Liang, Qian Zhang, Jie Zhou

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(14), P. 6310 - 6310

Published: July 11, 2023

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

Language: Английский

Citations

5
MetaBCI: An open-source platform for brain–computer interfaces DOI Creative Commons
Jie Mei, Ruixin Luo, Lichao Xu

et al.

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 168, P. 107806 - 107806

Published: Dec. 4, 2023

Recently, brain-computer interfaces (BCIs) have attracted worldwide attention for their great potential in clinical and real-life applications. To implement a complete BCI system, one must set up several links to translate the brain intent into computer commands. However, there is not an open-source software platform that can cover all of chain.

Language: Английский

Citations

4