Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 1, 2025International Journal of Imaging Systems and TechnologyOpen Access

Shallow Convolution and Parallel Coarse‐To‐Fine Attention for Brain Signal Classification

View Full Paper
Ask AI
Bookmark
Share

Authors

XQXiwen QinJWJiayao WangDXDingxin Xu

Discussion

Loading...

Member takes

Overview

This model demonstrates improved accuracy in brain signal classification for BCI applications, suggesting advances in emotion recognition.

Key Points

  • This research aims to enhance the accuracy and robustness of EEG classification in complex environments.
  • Proposes a novel Parallel Hybrid CNN-Transformer (PHCT) model for EEG classification.
  • Utilizes a shallow feature extraction module and parallel feature extractors.
  • Implements multi-head self-attention mechanisms.
  • Applies data augmentation and Gaussian noise injection to improve generalization.
  • Achieves at least a 4.2% increase in average classification accuracy compared to existing models.
  • Demonstrates effectiveness on the BCI Competition IV-2b dataset across nine subjects.

Cite This Study

Qin et al. (2025) studied this question.

synapsesocial.com/papers/6925435ec0ce034ddc357f61https://doi.org/10.1002/ima.70249
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Automatic Classification of EEG Signals, Based on Image Interpretation of Spatio-Temporal Information2025 · 2 citations
  2. 2A Hybrid Deep Learning Framework Using Scaling‐Basis Chirplet Transform for Motor Imagery <scp>EEG</scp> Recognition in Brain–Computer Interface Applications2024 · 3 citations
  3. 3Optimizing EEG Signal Classification in BCI Systems: A Comparative Study of Hybrid Transfer Learning and Advanced Machine Learning Approaches2024 · 3 citations
  4. 4Predicting Human Intention-Behavior Through EEG Signal Analysis Using Multi-Scale CNN2020 · 54 citations
  5. 5EEG classification for visual brain decoding with spatio-temporal and transformer based paradigms2024