AI Paper Atlas

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

AAAI 2018 · Probabilistic and scientific modeling › Dynamical systems · approach: Synaptic plasticity learning rules · 238 citations (OpenAlex)

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 changedWhereMeasuredEffect
cascade CNN+RNN on 2D EEG meshes vs image-based recurrent-convolutional baselineEEG intention recognition · PhysioNet cross-subject 5-classaccuracy: 0.6731 -> 0.9831Improved
add spatial mesh structure (2D-CNN vs 1D-CNN) (ablation)CNN baseline · PhysioNet cross-subject 5-classaccuracy: 0.8622 -> 0.8841Improved
add local temporal info (3D-CNN vs 2D-CNN) (ablation)CNN baseline · PhysioNet cross-subject 5-classaccuracy: 0.8841 -> 0.9238Improved
add global temporal RNN on CNN features (cascade vs 3D-CNN) (ablation)EEG model · PhysioNet cross-subject 5-classaccuracy: 0.9238 -> 0.9831Improved
increase CNN layers from 1 to 3 (ablation)Cascade model · PhysioNetaccuracy: 0.9310 -> 0.9831Improved
add FC layer between CNN and RNN (ablation)Cascade model · PhysioNetaccuracy: 0.9217 -> 0.9831Improved
add second RNN layer (ablation)Cascade model · PhysioNetaccuracy: 0.9813 -> 0.9831No clear effect
use FC/conv fusion instead of plain concatenation (ablation)Parallel model · PhysioNetaccuracy: 0.9828 -> 0.9696Hurt
summation instead of concatenation fusion (ablation)Parallel model · PhysioNetaccuracy: 0.9828 -> 0.9813No clear effect
apply parallel model on 14-channel real-world BCIParallel model · Emotiv 5-instruction datasetaccuracy: 93.1%Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy