Pullback Euclidean sliced-Wasserstein on correlation manifolds (CorSW under OLM/LSM) improves EEG domain generalization under session shifts with closed-form slices and no inference overhead.
Fbcnet: An efficient multi-view convolutional neural network for brain-computer interface.arXiv preprint arXiv:2104.01233
7 Pith papers cite this work, alongside 126 external citations. Polarity classification is still indexing.
7
Pith papers citing it
126
external citations · Pith
abstract
Lack of adequate training samples and noisy high-dimensional features are key challenges faced by Motor Imagery (MI) decoding algorithms for electroencephalogram (EEG) based Brain-Computer Interface (BCI). To address these challenges, inspired from neuro-physiological signatures of MI, this paper proposes a novel Filter-Bank Convolutional Network (FBCNet) for MI classification. FBCNet employs a multi-view data representation followed by spatial filtering to extract spectro-spatially discriminative features. This multistage approach enables efficient training of the network even when limited training data is available. More significantly, in FBCNet, we propose a novel Variance layer that effectively aggregates the EEG time-domain information. With this design, we compare FBCNet with state-of-the-art (SOTA) BCI algorithm on four MI datasets: The BCI competition IV dataset 2a (BCIC-IV-2a), the OpenBMI dataset, and two large datasets from chronic stroke patients. The results show that, by achieving 76.20% 4-class classification accuracy, FBCNet sets a new SOTA for BCIC-IV-2a dataset. On the other three datasets, FBCNet yields up to 8% higher binary classification accuracies. Additionally, using explainable AI techniques we present one of the first reports about the differences in discriminative EEG features between healthy subjects and stroke patients. Also, the FBCNet source code is available at https://github.com/ravikiran-mane/FBCNet.
years
2026 7representative citing papers
A Riemannian self-attention model based on the Bures-Wasserstein metric and its learnable generalized version is claimed to improve robustness of EEG decoding on three benchmark datasets.
MST combines Morlet wavelet tokenization, long-context baseline removal, and frequency-specific spatial projections with a Transformer backbone to outperform pretrained EEG models on SEED datasets for cross-subject emotion decoding.
NAKUL achieves 91.7% accuracy on motor imagery EEG with 28% fewer parameters than EEG-Conformer by using dynamic kernel generation, spectral context modeling, and graph-guided spatial attention.
MPNet aggregates multi-view Riemannian nodes from EEG rhythms via a new manifold node pooling layer to achieve state-of-the-art accuracy with up to 10x faster runtime than comparable models on public datasets.
StaFlowNet improves MI-EEG decoding by separating and coordinating global state vectors with temporal flow features via a dual-branch design and state-modulated flow module, outperforming prior methods on three public datasets.
DS-MTNet uses frequency-constrained source decomposition and reusable information slots to jointly decode three EEG-based cognitive readouts in a driving task, outperforming single-task and multi-task baselines.
citing papers explorer
-
A Sliced-Wasserstein Framework on Correlation Matrices for EEG Decoding
Pullback Euclidean sliced-Wasserstein on correlation manifolds (CorSW under OLM/LSM) improves EEG domain generalization under session shifts with closed-form slices and no inference overhead.
-
Towards Robust EEG Decoding Based on Riemannian Self-Attention
A Riemannian self-attention model based on the Bures-Wasserstein metric and its learnable generalized version is claimed to improve robustness of EEG decoding on three benchmark datasets.
-
Dive into Waves: Morlet Spectral Transformer for Cross-Subject Emotion Decoding from EEG
MST combines Morlet wavelet tokenization, long-context baseline removal, and frequency-specific spatial projections with a Transformer backbone to outperform pretrained EEG models on SEED datasets for cross-subject emotion decoding.
-
NAKUL-Med: Spectral-Graph State Space Models with Dynamics Kernels for Medical Signals
NAKUL achieves 91.7% accuracy on motor imagery EEG with 28% fewer parameters than EEG-Conformer by using dynamic kernel generation, spectral context modeling, and graph-guided spatial attention.
-
MPNet: A Robust and Efficient Manifold Pooling Network for Multi-Rhythm EEG Signal Decoding
MPNet aggregates multi-view Riemannian nodes from EEG rhythms via a new manifold node pooling layer to achieve state-of-the-art accuracy with up to 10x faster runtime than comparable models on public datasets.
-
State-Flow Coordinated Representation for MI-EEG Decoding
StaFlowNet improves MI-EEG decoding by separating and coordinating global state vectors with temporal flow features via a dual-branch design and state-modulated flow module, outperforming prior methods on three public datasets.
-
DS-MTNet:Structured Multi-Task EEG Decoding for Human-Machine Collaboration
DS-MTNet uses frequency-constrained source decomposition and reusable information slots to jointly decode three EEG-based cognitive readouts in a driving task, outperforming single-task and multi-task baselines.