This repo contains a list of papers for motor imagery using machine learning/deep learning.
If you have any suggested papers, please contact me ziyujia{at}bjtu.edu.cn
| Title | Author | Date | Publication | Paper Link | Dataset | Model |
|---|---|---|---|---|---|---|
| MMCNN: A Multi-branch Multi-scale Convolutional Neural Network for Motor Imagery Classification | Ziyu Jia, et al. | Feb-2021 | ECML PKDD | URL | BCIC IV 2a BCIC IV 2b | CNN |
| Motor imagery EEG recognition based on conditional optimization empirical mode decomposition and multi-scale convolutional neural network | Tang, X., Li, W., Li, X., Ma, W., & Dang, X. | Jul-2020 | Expert Systems with Applications | URL | BCIC IV 2b Private | CNN |
| Making sense of spatio-temporal preserving representations for EEG-based human intention recognition | Zhang D, Yao L, Chen K, et al. | Jul-2020 | IEEE transactions on cybernetics | URL | PhysioNet EEG Dataset | CNN, LSTM |
| A deep CNN approach to decode motor preparation of upper limbs from time–frequency maps of EEG signals at source level | Mammone, N., Ieracitano, C., & Morabito, F. C. | Apr-2020 | Neural Networks | URL | ULM | CNN (CWT, TF) |
| Convolutional neural network based features for motor imagery EEG signals classification in brain–computer interface system | Taheri, S., Ezoji, M., & Sakhaei, S. M. | Mar-2020 | SN Applied Sciences | URL | BCIC III 4a | SVM |
| A novel simplified convolutional neural network classification algorithm of motor imagery EEG signals based on deep learning | Li, F., He, F., Wang, F., Zhang, D., Xia, Y., & Li, X. | Feb-2020 | Applied Sciences | URL | BCIC IV 2b | SCNN (CWT) |
| HS-CNN: a CNN with hybrid convolution scale for EEG motor imagery classification | Dai, G., Zhou, J., Huang, J., & Wang, N. | Jan-2020 | Journal of neural engineering | URL | BCIC IV 2a BCIC IV 2b | CNN |
| Application of continuous wavelet transform and convolutional neural network in decoding motor imagery brain-computer interface | Lee H K, Choi Y S. | Dec-2019 | Entropy | URL | BCIC IV 2b BCIC II 3 | CNN (CWT) |
| Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion | Amin S U, Alsulaiman M, Muhammad G, et al. | Dec-2019 | Future Generation computer systems | URL | BCIC IV 2a HGD | CNN |
| A novel end‐to‐end deep learning scheme for classifying multi‐class motor imagery electroencephalography signals. | Hassanpour A, Moradikia M, Adeli H, et al. | Dec-2019 | Expert Systems | URL | BCIC IV 2a | GDL |
| Deep Channel-Correlation Network for Motor Imagery Decoding From the Same Limb | Ma, X., Qiu, S., Wei, W., Wang, S., & He, H. | Nov-2019 | IEEE Transactions on Neural Systems and Rehabilitation Engineering | URL | Private | CNN |
| A parallel multiscale filter bank convolutional neural networks for motor imagery EEG classification. | Wu H, Niu Y, Li F, et al. | Nov-2019 | Frontiers in neuroscience | URL | BCIC IV 2a BCIC IV 2b HGD | CNN |
| Subject-independent brain–computer interfaces based on deep convolutional neural networks. | Kwon O Y, Lee M H, Guan C, et al. | Nov-2019 | IEEE transactions on neural networks and learning systems | URL | Private | CNN (SSFR) |
| A new approach for motor imagery classification based on sorted blind source separation, continuous wavelet transform, and convolutional neural network | Ortiz-Echeverri C J, Salazar-Colores S, Rodríguez-Reséndiz J, et al. | Oct-2019 | Sensors | URL | BCIC III 4a | CNN (CWT) |
| A multi-branch 3D convolutional neural network for EEG-based motor imagery classification. | Zhao X, Zhang H, Zhu G, et al. | Oct-2019 | IEEE Transactions on Neural Systems and Rehabilitation Engineering | URL | BCIC IV 2a | CNN |
| A novel hybrid deep learning scheme for four-class motor imagery classification. | Zhang R, Zong Q, Dou L, et al. | Oct-2019 | Journal of neural engineering | URL | BCIC IV 2a | CNN, LSTM (FBCSP) |
| An advanced bispectrum features for EEG-based motor imagery classification. | Sun L, Feng Z, Lu N, et al. | Oct-2019 | Expert Systems with Applications | URL | Private BCIC IV 2b | SVM (VSBS) |
| Densely feature fusion based on convolutional neural networks for motor imagery EEG classification | Li D, Wang J, Xu J, et al. | Sep-2019 | IEEE Access | URL | BCIC IV 2a | CNN (DFFN) |
| A deep learning framework for decoding motor imagery tasks of the same hand using eeg signals | Alazrai R, Abuhijleh M, Alwanni H, et al. | Aug-2019 | IEEE Access | URL | Private | CNN (QTFD) |
| A deep transfer convolutional neural network framework for EEG signal classification. | Xu G, Shen X, Chen S, et al. | Jul-2019 | IEEE Access | URL | BCIC IV 2b | CNN |
| A channel-projection mixed-scale convolutional neural network for motor imagery EEG decoding | Li Y, Zhang X R, Zhang B, et al. | Jun-2019 | IEEE Transactions on Neural Systems and Rehabilitation Engineering | URL | BCIC IV 2a HGD | CNN |
| Learning joint space–time–frequency features for EEG decoding on small labeled data. | Zhao D, Tang F, Si B, et al. | Jun-2019 | Neural Networks | URL | BCIC IV 2a BCIC IV 2b ULM | CNN |
| Motor imagery EEG classification using capsule networks | Ha K W, Jeong J W. | Jun-2019 | Sensors | URL | BCIC IV 2b | CNN (STFT) |
| Semisupervised deep stacking network with adaptive learning rate strategy for motor imagery EEG recognition. | Tang X L, Ma W C, Kong D S, et al. | May-2019 | Neural computation | URL | Private BCIC IV 2b | SADSN |
| Efficient classification of motor imagery electroencephalography signals using deep learning methods. | Majidov I, Whangbo T. | Apr-2019 | Sensors | URL | BCIC IV 2a BCIC IV 2b | CNN |
| Separated channel convolutional neural network to realize the training free motor imagery BCI systems | Zhu X, Li P, Li C, et al. | Mar-2019 | Biomedical Signal Processing and Control | URL | BCIC IV 2b Private | SCNN (CSP) |
| A convolutional recurrent attention model for subject-independent eeg signal analysis. | Zhang D, Yao L, Chen K, et al. | Mar-2019 | IEEE Signal Processing Letters | URL | BCIC IV 2a | CNN, RNN (CRAM) |
| Classification of multiple motor imagery using deep convolutional neural networks and spatial filters | Olivas-Padilla B E, Chacon-Murguia M I. | Feb-2019 | Applied Soft Computing | URL | BCIC IV 2a Private | CNN (DFBCSP) |
| Convolutional neural network based approach towards motor imagery tasks EEG signals classification | Chaudhary S, Taran S, Bajaj V, et al. | Feb-2019 | IEEE Sensors Journal | URL | BCIC III 4a | CNN (STFT, CWT) |
| Domain adaptation with source selection for motor-imagery based BCI | Jeon E, Ko W, Suk H I. | Feb-2019 | 2019 7th International Winter Conference on Brain-Computer Interface (BCI) | URL | BCIC IV 2a | CNN (PSD) |
| Validating deep neural networks for online decoding of motor imagery movements from EEG signals. | Tayeb Z, Fedjaev J, Ghaboosi N, et al. | Jan-2019 | Sensors | URL | BCIC IV 2b Private | LSTM, CNN |
| Multilevel weighted feature fusion using convolutional neural networks for EEG motor imagery classification | Amin S U, Alsulaiman M, Muhammad G, et al. | Jan-2019 | IEEE Access | URL | BCIC IV 2a | CNN |
| A novel deep learning approach with data augmentation to classify motor imagery signals. | Zhang Z, Duan F, Sole-Casals J, et al. | Jan-2019 | IEEE Access | URL | BCIC II 3 Private | CNN, WNN |
| EEG classification of motor imagery using a novel deep learning framework | Dai M, Zheng D, Na R, et al. | Jan-2019 | Sensors | URL | BCIC IV 2b Private | CNN (STFT) |
| Walking imagery evaluation in brain computer interfaces via a multi-view multi-level deep polynomial network. | Lei B, Liu X, Liang S, et al. | Jan-2019 | IEEE transactions on neural systems and rehabilitation engineering | URL | Private | MMDPN (CSP, PSD, WPT) |
| Multimodal fuzzy fusion for enhancing the motor-imagery-based brain computer interface. | Ko, Li-Wei, et al. | Jan-2019 | IEEE Computational Intelligence Magazine | URL | Private | MFF |
| Wavelet transform time-frequency image and convolutional network-based motor imagery EEG classification. | Xu B, Zhang L, Song A, et al. | Dec-2018 | IEEE Access | URL | BCIC II 3 BCIC IV 2a | CNN |
| An end-to-end deep learning approach to MI-EEG signal classification for BCIs. | Dose H, Møller J S, Iversen H K, et al. | Dec-2018 | Expert Systems with Applications | URL | PhysioNet EEG Dataset | CNN |
| Deep fusion feature learning network for MI-EEG classification. | Yang J, Yao S, Wang J. | Nov-2018 | IEEE Access | URL | Private BCIC III BCIC IV | CNN, LSTM (DWT) |
| LSTM-based EEG classification in motor imagery tasks. | Wang P, Jiang A, Liu X, et al. | Oct-2018 | IEEE transactions on neural systems and rehabilitation engineering | URL | BCIC IV 2a | LSTM |
| EEG classification using sparse Bayesian extreme learning machine for brain–computer interface. | Jin Z, Zhou G, Gao D, et al. | Oct-2018 | Neural Computing and Applications | URL | BCIC IV 2b | SBELM |
| Exploring spatial-frequency-sequential relationships for motor imagery classification with recurrent neural network. | Luo T, Chao F. | Sep-2018 | BMC bioinformatics | URL | BCIC IV 2a BCIC IV 2b | LSTM, GRU (FBCSP) |
| A hierarchical semi-supervised extreme learning machine method for EEG recognition. | She Q, Hu B, Luo Z, et al. | Jul-2018 | Medical & biological engineering & computing | URL | BCIC IV 2a | HSS-ELM |
| EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces. | Lawhern V J, Solon A J, Waytowich N R, et al. | Jul-2018 | Journal of neural engineering | URL | BCIC IV 2a | CNN |
| The motor imagination EEG recognition combined with convolution neural network and gated recurrent unit. | Cai J, Wei C, Tang X L, et al. | Jul-2018 | Chinese Control Conference (CCC) | URL | Private BCIC IV 2b | CNN, GRU |
| A Deep Convolutional Neural Network Based Classification Of Multi-Class Motor Imagery With Improved Generalization. | Kar A, Bera S, Karri S P K, et al. | Jul-2018 | 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) | URL | BCIC IV 2a | CNN |
| Temporally constrained sparse group spatial patterns for motor imagery BCI. | Zhang Y, Nam C S, Zhou G, et al. | Jun-2018 | IEEE transactions on cybernetics | URL | BCIC III 3a, BCIC IV 2a, BCIC IV 2b | SVM (TSGSP) |
| Classification of multi-class BCI data by common spatial pattern and fuzzy system | Nguyen T, Hettiarachchi I, Khatami A, et al. | May-2018 | IEEE Access | URL | BCIC III 3a, BCIC IV 2a | FLS |
| Multi-kernel extreme learning machine for EEG classification in brain-computer interfaces. | Zhang Y, Wang Y, Zhou G, et al. | Apr-2018 | Expert Systems with Applications | URL | BCIC III 4a BCIC IV 2b | MKELM |
| Learning temporal information for brain-computer interface using convolutional neural networks. | Sakhavi S, Guan C, Yan S. | Mar-2018 | IEEE transactions on neural networks and learning systems | URL | BCIC IV 2a | CNN (FBCSP) |
| Deep recurrent spatio-temporal neural network for motor imagery based BCI. | Ko W, Yoon J, Kang E, et al. | Jan-2018 | 2018 6th International Conference on Brain-Computer Interface (BCI) | URL | BCIC IV 2a | CNN, RNN |
| Classification of motor imagery for Ear-EEG based brain-computer interface. | Kim Y J, Kwak N S, Lee S W. | Jan-2018 | 2018 6th International Conference on Brain-Computer Interface (BCI) | URL | Private BCIC III 4a | CSP |
| A convolution neural networks scheme for classification of motor imagery EEG based on wavelet time-frequecy image. | Lee, Hyeon Kyu, and Young-Seok Choi. | Jan-2018 | 2018 International Conference on Information Networking (ICOIN) | URL | BCIC IV 2b | CNN (CWT) |
| Deep convolutional neural network for decoding motor imagery based brain computer interface. | Zhang J, Yan C, Gong X. | Oct-2017 | 2017 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) | URL | Private | CNN (STFT) |
| Deep learning with convolutional neural networks for EEG decoding and visualization. | Schirrmeister R T, Springenberg J T, Fiederer L D J, et al. | Aug-2017 | Human brain mapping | URL | BCIC IV 2a HGD | CNN |
| EEG feature extraction and classification in multiclass multiuser motor imagery brain computer interface u sing Bayesian Network and ANN. | Sagee G S, Hema S. | Jul-2017 | 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT) | URL | PhysioNet EEG Dataset | BN |
| A deep learning approach for motor imagery EEG signal classification. | Kumar S, Sharma A, Mamun K, et al. | Dec-2016 | 2016 3rd Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE) | URL | BCIC III 4a | CSP |
| A novel deep learning approach for classification of EEG motor imagery signals. | Tabar Y R, Halici U. | Nov-2016 | Journal of neural engineering | URL | BCIC II 3 BCIC IV 2b | CNN (SAE) |
| A deep learning scheme for motor imagery classification based on restricted Boltzmann machines. | Lu N, Li T, Ren X, et al. | Aug-2016 | IEEE transactions on neural systems and rehabilitation engineering | URL | BCIC IV 2b | RBM (FFT, WPD) |
| A multi-label classification method for detection of combined motor imageries. | Lindig-Leon C, Bougrain L. | Oct-2015 | 2015 IEEE International Conference on Systems, Man, and Cybernetics | URL | Private | CSP |
| On the use of convolutional neural networks and augmented CSP features for multi-class motor imagery of EEG signals classification. | Yang H, Sakhavi S, Ang K K, et al. | Aug-2015 | 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) | URL | BCIC IV 2a | CNN (FCMS) |
| Parallel convolutional-linear neural network for motor imagery classification. | Sakhavi S, Guan C, Yan S. | Aug-2015 | 2015 23rd European Signal Processing Conference (EUSIPCO) | URL | BCIC IV 2a | CNN |
| Increase performance of four-class classification for motor-imagery based brain-computer interface. | Temiyasathit C. | Jul-2014 | 2014 International Conference on Computer, Information and Telecommunication Systems (CITS) | URL | BCIC IV 2a | CSP |
| A novel classification method for motor imagery based on Brain-Computer Interface. | Chen C Y, Wu C W, Lin C T, et al. | Jul-2014 | 2014 International Joint Conference on Neural Networks (IJCNN). | URL | Private | LDA (CSP) |
| Neural network-based three-class motor imagery classification using time-domain features for BCI applications. | Hamedi M, Salleh S H, Noor A M, et al. | Apr-2014 | 2014 IEEE Region 10 Symposium | URL | Private | MLP, RBF |
| EEG feature comparison and classification of simple and compound limb motor imagery. | Yi W, Qiu S, Qi H, et al. | Oct-2013 | Journal of neuroengineering and rehabilitation | URL | Private | CSP (SVM) |
| Evolving spatial and frequency selection filters for brain-computer interfaces. | Aler R, Galván I M, Valls J M. | Jul-2010 | IEEE congress on evolutionary computation | URL | BCIC III | CSP |
| Dataset | Paper | Link | Download |
|---|---|---|---|
| Upper limb movements（ULM） | Upper limb movements can be decoded from the time-domain of low-frequency EEG | Link | URL |
| High gamma dataset(HGD) | Deep learning with convolutional neural networks for EEG decoding and visualization | Link | URL |
| PhysioNet EEG Dataset | PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals | Link | URL |
| BCI Competition | Link |
Tianhang Liu, Kaixin Yang, Ziyu Jia, and Xiyang Cai collaborated to organize and summarize the above papers.