AFPM: Alignment-based Frame Patch Modeling for Cross-Dataset EEG Decoding

2025/07/16 by Chen, Xiaoqing, Li, Siyang, Wu, Dongrui
#FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Information Retrieval (cs.IR) #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2507.11911

Abstract

Electroencephalogram (EEG) decoding models for brain-computer interfaces (BCIs) struggle with cross-dataset learning and generalization due to channel layout inconsistencies, non-stationary signal distributions, and limited neurophysiological prior integration. To address these issues, we propose a plug-and-play Alignment-Based Frame-Patch Modeling (AFPM) framework, which has two main components: 1) Spatial Alignment, which selects task-relevant channels based on brain-region priors, aligns EEG distributions across domains, and remaps the selected channels to a unified layout; and, 2) Frame-Patch Encoding, which models multi-dataset signals into unified spatiotemporal patches for EEG decoding. Compared to 17 state-of-the-art approaches that need dataset-specific tuning, the proposed calibration-free AFPM achieves performance gains of up to 4.40% on motor imagery and 3.58% on event-related potential tasks. To our knowledge, this is the first calibration-free cross-dataset EEG decoding framework, substantially enhancing the practicalness of BCIs in real-world applications.

Citations

• CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding
• EEG-Deformer: A Dense Convolutional Transformer for Brain-computer Interfaces
• EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization
• Transformer Convolutional Neural Networks for Automated Artifact Detection in Scalp EEG
• Transformer-based Spatial-Temporal Feature Learning for EEG Decoding
• FBCNet: A Multi-view Convolutional Neural Network for Brain-Computer Interface
• BENDR: using transformers and a contrastive self-supervised learning\n task to learn from massive amounts of EEG data
• Language Models are Few-Shot Learners
• A Comprehensive Survey on Transfer Learning
• A Comprehensive Survey on Transfer Learning
• Brain Invaders Adaptive versus Non-Adaptive P300 Brain-Computer Interface dataset
• Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach
• Deep learning with convolutional neural networks for EEG decoding and visualization
• EEG-based discrimination between imagination of right and left hand movement
• Optimizing Spatial filters for Robust EEG Single-Trial Analysis

Related

• CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding
• Optimising EEG decoding with refined sampling and multimodal feature integration
• Latent Alignment with Deep Set EEG Decoders
• Combining Euclidean Alignment and Data Augmentation for BCI decoding
• CLEAN-MI: A Scalable and Efficient Pipeline for Constructing High-Quality Neurodata in Motor Imagery Paradigm