IncepFormerNet: A multi-scale multi-head attention network for SSVEP classification

TL;DR

IncepFormerNet is a novel hybrid deep learning model combining Inception and Transformer architectures, designed to improve SSVEP classification accuracy by capturing multi-scale temporal features and global dependencies in EEG signals.

Contribution

The paper introduces IncepFormerNet, a new hybrid model that integrates multi-scale convolution and multi-head attention for enhanced SSVEP classification.

Findings

Achieves 87.41% accuracy on Dataset 1

Achieves 71.97% accuracy on Dataset 2

Outperforms existing deep learning models in SSVEP classification

Abstract

In recent years, deep learning (DL) models have shown outstanding performance in EEG classification tasks, particularly in Steady-State Visually Evoked Potential(SSVEP)-based Brain-Computer-Interfaces(BCI)systems. DL methods have been successfully applied to SSVEP-BCI. This study proposes a new model called IncepFormerNet, which is a hybrid of the Inception and Transformer architectures. IncepFormerNet adeptly extracts multi-scale temporal information from time series data using parallel convolution kernels of varying sizes, accurately capturing the subtle variations and critical features within SSVEP signals.Furthermore, the model integrates the multi-head attention mechanism from the Transformer architecture, which not only provides insights into global dependencies but also significantly enhances the understanding and representation of complex patterns.Additionally, it takes advantage of filter bank techniques to extract features based on the spectral characteristics of SSVEP data. To validate the effectiveness of the proposed model, we conducted experiments on two public datasets, . The experimental results show that IncepFormerNet achieves an accuracy of 87.41 on Dataset 1 and 71.97 on Dataset 2 using a 1.0-second time window. To further verify the superiority of the proposed model, we compared it with other deep learning models, and the results indicate that our method achieves significantly higher accuracy than the others.The source codes in this work are available at: https://github.com/CECNL/SSVEP-DAN.