Objective: This study presents a novel brain-computer interface paradigm of dual-frequency modulated steady-state visual evoked potential (SSVEP), aiming to suppress the unpredictable intermodulation components in current applications. This paradigm is especially suitable for training-free scenarios.
Approach: This study built a dual-frequency binocular vision SSVEP brain-computer interface system using circularly polarized light technology. Two experiments, including a 6-target offline experiment and a 40-target online experiment, were taken with this system. Meanwhile, an improved algorithm filter bank dual-frequency canonical correlation analysis (FBDCCA) was presented for the dual-frequency SSVEP paradigm.
Main Results: Energy analysis was conducted for 9 subjects in the 6-target dual-frequency offline experiment, among which the signal-to-noise ratio of target frequency components have increased by 2 dB compared to the one of unpredictable intermodulation components. Subsequently, the online experiment with 40 targets was conducted with 12 subjects. With this new dual-frequency paradigm, the online training-free experiment's average information transmission rate (ITR) reached 104.56 ± 15.74 bits/min, which was almost twice as fast as the current best dual-frequency paradigm. And the average information transfer rate for offline training analysis of this new paradigm was 180.87 ± 17.88 bits/min.
Significance: These results demonstrate that this new dual-frequency SSVEP brain-computer interface paradigm can suppress the unpredictable intermodulation harmonics and generate higher quality responses while completing dual-frequency encoding. Moreover, its performance shows high ITR in applications both with and without training. It is thus believed that this paradigm is competent for achieving large target numbers in brain-computer interface systems and has more possible practices.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TBME.2022.3212192 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A multi-branch, multi-scale, and multi-view CNN with lightweight temporal attention mechanism for EEG-based motor imagery decoding.
Comput Methods Biomech Biomed Engin
January 2025
The School of Computer Science, Hangzhou Dianzi University, Hangzhou, China.
Convolutional neural networks (CNNs) have been widely utilized for decoding motor imagery (MI) from electroencephalogram (EEG) signals. However, extracting discriminative spatial-temporal-spectral features from low signal-to-noise ratio EEG signals remains challenging. This paper proposes MBMSNet , a multi-branch, multi-scale, and multi-view CNN with a lightweight temporal attention mechanism for EEG-Based MI decoding.
View Article and Find Full Text PDFhvEEGNet: a novel deep learning model for high-fidelity EEG reconstruction.
Front Neuroinform
December 2024
Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy.
Introduction: Modeling multi-channel electroencephalographic (EEG) time-series is a challenging tasks, even for the most recent deep learning approaches. Particularly, in this work, we targeted our efforts to the high-fidelity reconstruction of this type of data, as this is of key relevance for several applications such as classification, anomaly detection, automatic labeling, and brain-computer interfaces.
Methods: We analyzed the most recent works finding that high-fidelity reconstruction is seriously challenged by the complex dynamics of the EEG signals and the large inter-subject variability.
Biologically inspired heterogeneous learning for accurate, efficient and low-latency neural network.
Natl Sci Rev
January 2025
School of Astronautics, Beihang University, Beijing 100191, China.
The pursuit of artificial neural networks that mirror the accuracy, efficiency and low latency of biological neural networks remains a cornerstone of artificial intelligence (AI) research. Here, we incorporated recent neuroscientific findings of self-inhibiting autapse and neuron heterogeneity for innovating a spiking neural network (SNN) with enhanced learning and memorizing capacities. A bi-level programming paradigm was formulated to respectively learn neuron-level biophysical variables and network-level synapse weights for nested heterogeneous learning.
View Article and Find Full Text PDFEfficacy of brain-computer interface training with motor imagery-contingent feedback in improving upper limb function and neuroplasticity among persons with chronic stroke: a double-blinded, parallel-group, randomized controlled trial.
J Neuroeng Rehabil
January 2025
Translational Research Center for Rehabilitation Robots, National Rehabilitation Center, Ministry of Health and Welfare, Seoul, Korea.
Background: Brain-computer interface (BCI) technology can enhance neural plasticity and motor recovery in persons with stroke. However, the effects of BCI training with motor imagery (MI)-contingent feedback versus MI-independent feedback remain unclear. This study aimed to investigate whether the contingent connection between MI-induced brain activity and feedback influences functional and neural plasticity outcomes.
View Article and Find Full Text PDFA BEM-FMM TMS Coil Designer Using MATLAB Platform.
Brain Stimul
January 2025
Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA, 01609; Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA 02129; Department of Mathematics, Worcester Polytechnic Institute, Worcester, MA, USA, 01609.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!