Dual regularized spatial-temporal features adaptation for multi-source selected cross-subject motor imagery EEG classification

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 255, P. 124673 - 124673

Published: July 4, 2024

Language: Английский

---

A multi-branch, multi-scale, and multi-view CNN with lightweight temporal attention mechanism for EEG-based motor imagery decoding

Computer Methods in Biomechanics & Biomedical Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 15

Published: Jan. 6, 2025

Convolutional neural networks (CNNs) have been widely utilized for decoding motor imagery (MI) from electroencephalogram (EEG) signals. However, extracting discriminative spatial-temporal-spectral features low signal-to-noise ratio EEG signals remains challenging. This paper proposes MBMSNet , a multi-branch, multi-scale, and multi-view CNN with lightweight temporal attention mechanism EEG-Based MI decoding. Specifically, first extracts representations raw signals, followed by independent branches to capture spatial, spectral, temporal-spatial, temporal-spectral features. Each branch includes domain-specific convolutional layer, variance layer. Finally, the derived each are concatenated weights classified through fully connected Experiments demonstrate outperforms state-of-the-art models, achieving accuracies of 84.60% on BCI Competition IV 2a, 87.80% 2b, 74.58% OpenBMI, showcasing its potential robust applications.

Language: Английский

---

Motor Imagery EEG Classification Based on Multi-Domain Feature Rotation and Stacking Ensemble

Brain Sciences, Journal Year: 2025, Volume and Issue: 15(1), P. 50 - 50

Published: Jan. 7, 2025

Decoding motor intentions from electroencephalogram (EEG) signals is a critical component of imagery-based brain-computer interface (MI-BCIs). In traditional EEG signal classification, effectively utilizing the valuable information contained within crucial. To further optimize use various domains, we propose novel framework based on multi-domain feature rotation transformation and stacking ensemble for classifying MI tasks. Initially, extract features Time Domain, Frequency domain, Time-Frequency Spatial Domain signals, perform selection each domain to identify significant that possess strong discriminative capacity. Subsequently, local transformations are applied set generate rotated set, enhancing representational capacity features. Next, were fused with original obtain composite domain. Finally, employ approach, where prediction results base classifiers corresponding different undergo linear discriminant analysis dimensionality reduction, yielding integration as input meta-classifier classification. The proposed method achieves average classification accuracies 92.92%, 89.13%, 86.26% BCI Competition III Dataset IVa, IV I, 2a, respectively. Experimental show in this paper outperforms several existing methods, such Common Time-Frequency-Spatial Patterns Selective Extract Multi-View Decomposed Spatial, terms accuracy robustness.

Language: Английский

---

Multi-domain feature analysis of MI-EEG signals using tensor train decomposition and projected gradient Non-negative Matrix Factorization

Neurocomputing, Journal Year: 2025, Volume and Issue: unknown, P. 129410 - 129410

Published: Jan. 1, 2025

Language: Английский

---

Motor Imagery EEG Signals Decoding with Multi-view Weighted Features

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 338 - 349

Published: Jan. 1, 2025

Language: Английский

---

Joint spatial feature adaption and confident pseudo-label selection for cross-subject motor imagery EEG signals classification

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127312 - 127312

Published: March 1, 2025

Language: Английский

---

A session-incremental broad learning system for motor imagery EEG classification

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 97, P. 106717 - 106717

Published: Aug. 14, 2024

Language: Английский

---

Diffusion models-based motor imagery EEG sample augmentation via mixup strategy

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 262, P. 125585 - 125585

Published: Oct. 24, 2024

Language: Английский

---

Enhancing motor imagery classification: a novel CNN with self-attention using local and global features of filtered EEG data

Connection Science, Journal Year: 2024, Volume and Issue: 36(1)

Published: Nov. 16, 2024

Language: Английский

---

fNIRSNET: A multi-view spatio-temporal convolutional neural network fusion for functional near-infrared spectroscopy-based auditory event classification

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 137, P. 109256 - 109256

Published: Sept. 6, 2024

Language: Английский

---