Research map / Probabilistic and scientific modeling / Dynamical systems
Cascade and Parallel Convolutional Recurrent Neural Networks on EEG-based Intention Recognition for Brain Computer Interface
Dalin Zhang, Lina Yao, Xiang Zhang, Sen Wang, Weitong Chen, Robert Boots, Boualem Benatallah
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| cascade CNN+RNN on 2D EEG meshes vs image-based recurrent-convolutional baseline | EEG intention recognition · PhysioNet cross-subject 5-class | accuracy: 0.6731 -> 0.9831 | Improved |
| add spatial mesh structure (2D-CNN vs 1D-CNN) (ablation) | CNN baseline · PhysioNet cross-subject 5-class | accuracy: 0.8622 -> 0.8841 | Improved |
| add local temporal info (3D-CNN vs 2D-CNN) (ablation) | CNN baseline · PhysioNet cross-subject 5-class | accuracy: 0.8841 -> 0.9238 | Improved |
| add global temporal RNN on CNN features (cascade vs 3D-CNN) (ablation) | EEG model · PhysioNet cross-subject 5-class | accuracy: 0.9238 -> 0.9831 | Improved |
| increase CNN layers from 1 to 3 (ablation) | Cascade model · PhysioNet | accuracy: 0.9310 -> 0.9831 | Improved |
| add FC layer between CNN and RNN (ablation) | Cascade model · PhysioNet | accuracy: 0.9217 -> 0.9831 | Improved |
| add second RNN layer (ablation) | Cascade model · PhysioNet | accuracy: 0.9813 -> 0.9831 | No clear effect |
| use FC/conv fusion instead of plain concatenation (ablation) | Parallel model · PhysioNet | accuracy: 0.9828 -> 0.9696 | Hurt |
| summation instead of concatenation fusion (ablation) | Parallel model · PhysioNet | accuracy: 0.9828 -> 0.9813 | No clear effect |
| apply parallel model on 14-channel real-world BCI | Parallel model · Emotiv 5-instruction dataset | accuracy: 93.1% | Improved |
Closest papers by meaning
- BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals (NeurIPS 2025 · similarity 0.86)
- CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding (ICLR 2025 · similarity 0.86)
- Decoding Natural Images from EEG for Object Recognition (ICLR 2024 · similarity 0.85)
- NeurIPT: Foundation Model for Neural Interfaces (NeurIPS 2025 · similarity 0.85)
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · similarity 0.85)
- B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
