HCFT: Hierarchical Convolutional Fusion Transformer for EEG Decoding

TL;DR

The paper introduces HCFT, a novel EEG decoding framework combining convolutional encoders and hierarchical Transformers, achieving superior accuracy and stability in classifying complex EEG signals for BCI applications.

Contribution

It proposes a lightweight, generalizable EEG decoding model with a hierarchical Transformer structure and a Dynamic Tanh normalization, improving stability and performance over existing methods.

Findings

HCFT outperforms ten baseline methods on benchmark datasets.

Achieves 80.83% accuracy and 0.6165 Cohen's kappa on BCI IV-2b.

Attains 99.10% sensitivity and 98.82% specificity on CHB-MIT.

Abstract

Electroencephalography (EEG) decoding requires models that can effectively extract and integrate complex temporal, spectral, and spatial features from multichannel signals. To address this challenge, we propose a lightweight and generalizable decoding framework named Hierarchical Convolutional Fusion Transformer (HCFT), which combines dual-branch convolutional encoders and hierarchical Transformer blocks for multi-scale EEG representation learning. Specifically, the model first captures local temporal and spatiotemporal dynamics through time-domain and time-space convolutional branches, and then aligns these features via a cross-attention mechanism that enables interaction between branches at each stage. Subsequently, a hierarchical Transformer fusion structure is employed to encode global dependencies across all feature stages, while a customized Dynamic Tanh normalization module is introduced to replace traditional Layer Normalization in order to enhance training stability and reduce redundancy. Extensive experiments are conducted on two representative benchmark datasets, BCI Competition IV-2b and CHB-MIT, covering both event-related cross-subject classification and continuous seizure prediction tasks. Results show that HCFT achieves 80.83% average accuracy and a Cohen's kappa of 0.6165 on BCI IV-2b, as well as 99.10% sensitivity, 0.0236 false positives per hour, and 98.82% specificity on CHB-MIT, consistently outperforming over ten state-of-the-art baseline methods. Ablation studies confirm that each core component of the proposed framework contributes significantly to the overall decoding performance, demonstrating HCFT's effectiveness in capturing EEG dynamics and its potential for real-world BCI applications.