BCI42b_0">BCI4-2b研究进展
论文 | 年份 | 方法 | 数据选取 | 精度(%) | kappa | 备注 |
---|---|---|---|---|---|---|
Feature Extraction of EEG Signal by Power Spectral Density for Motor Imagery Based BCI | 2021 | PSD;LDA | 按每个sub来,各做各的。。 | 74 | 0.52 | |
RFNet: Riemannian Fusion Network for EEG-based Brain-Computer Interfaces | 2020 | SCM;PSD;DE;黎曼融合 | 按每个sub来。前3个block训练,后两个block测试 | 83.60 ±13.90 | 0.6720 ±0.2800 | |
Few-Shot Relation Learning with Attention for EEG-based Motor Imagery Classification | 2020 | 深度学习 | 8个训练,一个测试 | 74.6 ± 10.2 | ||
Classify Motor Imagery by a Novel CNN with Data Augmentation | 2020 | 深度学习 | 每个sub,5折 | 81.52 | ||
EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classification | 2021 | 深度学习 | 按每个sub来,好像还是5个 block打乱 | 85.77 | ||
Discriminative Feature Selection-Based Motor Imagery Classification Using EEG Signal | 2020 | FBCSP里面换了个特征选择算法 | 按每个sub来 | 81.57±13.72 | ||
Review on Motor Imagery Based EEG Signal Classification for BCI Using Deep Learning Techniques | 2021 | - | - | 结果80~83 | ||
Motor imagery EEG recognition based on conditional optimization empirical mode decomposition and multi-scale convolutional neural network | 2020 | 深度学习 | 应该是按 每个 来。 | 82.61 | ||
Motor imagery based brain-computer interface: improving the EEG classification using Delta rhythm and LightGBM algorithm | 2022 | Delta rhythm and LightGBM algorithm | 94左右 | |||
Classification of motor imagery electroencephalography signals using continuous small convolutional neural network | 2020 | 深度学习 | 按每个sub来,9/1分 | 82.8 | 0.663 | |
Discriminative and Robust Feature Learning for MIBCI-based Disability Rehabilitation | 2021 | 深度学习 | 按每个sub来 | 86.10 (9.01) | ||
A classification method for EEG motor imagery signals based on parallel convolutional neural network | 2022 | 深度学习 | 按每个sub来,9/1分 | 83.0 ±3.4 | 0.659 ±0.067 | |