Datasets
Models
Downloads: 1
| # | Title | Citation | Task | Metric | Model | Description | Architecture | Result | Comment | |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | EEG-signals based cognitive workload detection of vehicle driver using deep learning | Almogbel2018 | mental workload classification | accuracy | arch1 | CNN 30 s | CNN | 0.8725 | ||
| 2 | Almogbel2018 | mental workload classification | accuracy | arch2 | CNN 60 s | CNN | 0.9202 | |||
| 3 | Almogbel2018 | mental workload classification | accuracy | arch3 | CNN 90 s | CNN | 0.8838 | |||
| 4 | Almogbel2018 | mental workload classification | accuracy | arch4 | CNN 120 | CNN | 0.8224 | |||
| 5 | Almogbel2018 | mental workload classification | accuracy | arch5 | CNN 150 | CNN | 0.9531 | |||
| 6 | Almogbel2018 | mental workload classification | accuracy | arch6 | CNN 180 | CNN | 0.8469 | |||
| 7 | Automatic ocular artifacts removal in EEG using deep learning | Yang2018 | artifact correction | rmse | arch1 | MLP | FC | 1.2838 | Also report accuracy, but on surrogate task | |
| 8 | Yang2018 | artifact correction | rmse | dl1 | SAE | 1.2602 | ||||
| 9 | Yang2018 | artifact correction | rmse | trad1 | ICA | 1.4934 | ||||
| 10 | Yang2018 | artifact correction | rmse | trad2 | K-ICA | 1.426 | ||||
| 11 | Yang2018 | artifact correction | rmse | trad3 | SOBI | 1.371 | ||||
| 12 | An end-to-end framework for real-time automatic sleep stage classification | Patanaik2018 | sleep staging | accuracy | arch1 | CNN + MLP | CNN | 0.898 | ||
| 13 | Patanaik2018 | sleep staging | cohen's kappa | arch1 | CNN + MLP | CNN | 0.862 | |||
| 14 | Patanaik2018 | sleep staging (DS3 subset) | cohen's kappa | arch1 | CNN + MLP | CNN | 0.711 | |||
| 15 | Patanaik2018 | sleep staging (DS3 subset) | cohen's kappa | trad1 | Expert rescoring | 0.673 | ||||
| 16 | Patanaik2018 | sleep staging (DS4 subset) | cohen's kappa | arch1 | CNN + MLP | CNN | 0.588 | |||
| 17 | Patanaik2018 | sleep staging (DS4 subset) | cohen's kappa | trad1 | Expert rescoring | 0.576 | ||||
| 18 | Epileptic Seizure Detection: A Deep Learning Approach | Hussein2018 | seizure detection (2-class, hold-out) | accuracy | arch1 | LSTM | RNN | 1 | ||
| 19 | Hussein2018 | seizure detection (2-class, hold-out) | sensitivity | arch1 | LSTM | RNN | 1 | |||
| 20 | Hussein2018 | seizure detection (2-class, hold-out) | accuracy | trad1 | SVM | 0.9725 | ||||
| 21 | Hussein2018 | seizure detection (2-class, hold-out) | sensitivity | trad1 | SVM | 0.945 | ||||
| 22 | Hussein2018 | seizure detection (2-class, hold-out) | accuracy | trad2 | SVM | 0.975 | ||||
| 23 | Hussein2018 | seizure detection (2-class, hold-out) | sensitivity | trad2 | SVM | 0.98 | ||||
| 24 | Hussein2018 | seizure detection (2-class, hold-out) | accuracy | trad3 | BLDA | 0.9667 | ||||
| 25 | Hussein2018 | seizure detection (2-class, hold-out) | sensitivity | trad3 | BLDA | 0.9625 | ||||
| 26 | Hussein2018 | seizure detection (2-class, LOSO) | accuracy | arch1 | LSTM | RNN | 1 | |||
| 27 | Hussein2018 | seizure detection (2-class, LOSO) | sensitivity | arch1 | LSTM | RNN | 1 | |||
| 28 | Hussein2018 | seizure detection (2-class, LOSO) | accuracy | trad4 | ELM | N/M | ||||
| 29 | Hussein2018 | seizure detection (2-class, LOSO) | sensitivity | trad4 | ELM | 0.9948 | ||||
| 30 | Hussein2018 | seizure detection (2-class, 10-CV) | accuracy | arch1 | LSTM | RNN | 1 | |||
| 31 | Hussein2018 | seizure detection (2-class, 10-CV) | sensitivity | arch1 | LSTM | RNN | 1 | |||
| 32 | Hussein2018 | seizure detection (2-class, 10-CV) | accuracy | trad5 | DT | 0.9869 | ||||
| 33 | Hussein2018 | seizure detection (2-class, 10-CV) | sensitivity | trad5 | DT | 0.9887 | ||||
| 34 | Hussein2018 | seizure detection (2-class B, hold-out) | accuracy | arch1 | LSTM | RNN | 1 | |||
| 35 | Hussein2018 | seizure detection (2-class B, hold-out) | sensitivity | arch1 | LSTM | RNN | 1 | |||
| 36 | Hussein2018 | seizure detection (2-class B, hold-out) | accuracy | trad6 | CVANN | 0.9933 | ||||
| 37 | Hussein2018 | seizure detection (2-class B, hold-out) | sensitivity | trad6 | CVANN | 1 | ||||
| 38 | Hussein2018 | seizure detection (2-class B, hold-out) | accuracy | trad7 | KNN | 0.984 | ||||
| 39 | Hussein2018 | seizure detection (2-class B, hold-out) | sensitivity | trad7 | KNN | N/M | ||||
| 40 | Hussein2018 | seizure detection (2-class B, hold-out) | accuracy | trad8 | ANN | 0.9827 | ||||
| 41 | Hussein2018 | seizure detection (2-class B, hold-out) | sensitivity | trad8 | ANN | 0.955 | ||||
| 42 | Hussein2018 | seizure detection (2-class B, 10-CV) | accuracy | arch1 | LSTM | RNN | 1 | |||
| 43 | Hussein2018 | seizure detection (2-class B, 10-CV) | sensitivity | arch1 | LSTM | RNN | 1 | |||
| 44 | Hussein2018 | seizure detection (2-class B, 10-CV) | accuracy | trad9 | SVM | 0.9925 | ||||
| 45 | Hussein2018 | seizure detection (2-class B, 10-CV) | sensitivity | trad9 | SVM | 0.9798 | ||||
| 46 | Hussein2018 | seizure detection (2-class B, 10-CV) | accuracy | trad10 | ANN | 0.9872 | ||||
| 47 | Hussein2018 | seizure detection (2-class B, 10-CV) | sensitivity | trad10 | ANN | 0.983 | ||||
| 48 | Hussein2018 | seizure detection (3-class, hold-out) | accuracy | arch1 | LSTM | RNN | 1 | |||
| 49 | Hussein2018 | seizure detection (3-class, hold-out) | sensitivity | arch1 | LSTM | RNN | 1 | |||
| 50 | Hussein2018 | seizure detection (3-class, hold-out) | accuracy | trad11 | MLPNN | 0.991 | ||||
| 51 | Hussein2018 | seizure detection (3-class, hold-out) | sensitivity | trad11 | MLPNN | 0.992 | ||||
| 52 | Hussein2018 | seizure detection (3-class, hold-out) | accuracy | trad12 | ECOC | 0.9867 | ||||
| 53 | Hussein2018 | seizure detection (3-class, hold-out) | sensitivity | trad12 | ECOC | 0.9855 | ||||
| 54 | Hussein2018 | seizure detection (3-class, LOSO) | accuracy | arch1 | LSTM | RNN | 1 | |||
| 55 | Hussein2018 | seizure detection (3-class, LOSO) | sensitivity | arch1 | LSTM | RNN | 1 | |||
| 56 | Hussein2018 | seizure detection (3-class, LOSO) | accuracy | trad13 | SVM | 0.95 | ||||
| 57 | Hussein2018 | seizure detection (3-class, LOSO) | sensitivity | trad13 | SVM | 0.96 | ||||
| 58 | Hussein2018 | seizure detection (3-class, 10-CV) | accuracy | arch1 | LSTM | RNN | 1 | |||
| 59 | Hussein2018 | seizure detection (3-class, 10-CV) | sensitivity | arch1 | LSTM | RNN | 1 | |||
| 60 | Hussein2018 | seizure detection (3-class, 10-CV) | accuracy | trad14 | LSSVM | 0.9719 | ||||
| 61 | Hussein2018 | seizure detection (3-class, 10-CV) | sensitivity | trad14 | LSSVM | 0.9696 | ||||
| 62 | Hussein2018 | seizure detection (3-class, 10-CV) | accuracy | trad15 | GMM | 0.99 | ||||
| 63 | Hussein2018 | seizure detection (3-class, 10-CV) | sensitivity | trad15 | GMM | 0.99 | ||||
| 64 | Hussein2018 | seizure detection (5-class, hold-out) | accuracy | arch1 | LSTM | RNN | 1 | |||
| 65 | Hussein2018 | seizure detection (5-class, hold-out) | sensitivity | arch1 | LSTM | RNN | 1 | |||
| 66 | Hussein2018 | seizure detection (5-class, hold-out) | accuracy | trad16 | MSVM | 0.9999 | ||||
| 67 | Hussein2018 | seizure detection (5-class, hold-out) | sensitivity | trad16 | MSVM | 0.9999 | ||||
| 68 | Hussein2018 | seizure detection (5-class, hold-out) | accuracy | trad17 | SVM | 0.9997 | ||||
| 69 | Hussein2018 | seizure detection (5-class, hold-out) | sensitivity | trad17 | SVM | 0.9837 | ||||
| 70 | Hussein2018 | seizure detection (5-class, 10-CV) | accuracy | arch1 | LSTM | RNN | 1 | |||
| 71 | Hussein2018 | seizure detection (5-class, 10-CV) | sensitivity | arch1 | LSTM | RNN | 1 | |||
| 72 | Hussein2018 | seizure detection (5-class, 10-CV) | accuracy | trad18 | MSVM | 0.96 | ||||
| 73 | Hussein2018 | seizure detection (5-class, 10-CV) | sensitivity | trad18 | MSVM | N/M | ||||
| 74 | Development of a brain computer interface interface using multi-frequency visual stimulation and deep neural networks | Perez-Benitez2018 | SSVEP (normalized spectrum) | accuracy | arch1 | MLP | FC | 0.9533 | ||
| 75 | Perez-Benitez2018 | SSVEP (normalized spectrum) | accuracy | trad1 | MC-SVM | 0.9621 | ||||
| 76 | Perez-Benitez2018 | SSVEP (normalized spectrum) | accuracy | trad2 | Rule induction | 0.7117 | ||||
| 77 | Perez-Benitez2018 | SSVEP (normalized spectrum) | accuracy | trad3 | kNN | 0.9912 | ||||
| 78 | Perez-Benitez2018 | SSVEP (normalized spectrum) | accuracy | trad4 | GBT | 0.9387 | ||||
| 79 | Deep Semantic Architecture with discriminative feature visualization for neuroimage analysis | Ghosh2018 | exercise vs. control group classification | accuracy | arch1 | CNN | CNN | 0.987 | ||
| 80 | Cascade and Parallel Convolutional Recurrent Neural Networks on EEG-based Intention Recognition for Brain Computer Interface | Zhang2018c | motor imagery | accuracy | arch1 | CNN-cascade | CNN | 0.9831 | ||
| 81 | Zhang2018c | motor imagery | accuracy | arch2 | CNN-parallel | CNN | 0.9828 | |||
| 82 | Zhang2018c | motor imagery | accuracy | dl1 | RNN | 0.7468 | ||||
| 83 | Zhang2018c | motor imagery | accuracy | dl2 | RNN | 0.8493 | ||||
| 84 | Zhang2018c | motor imagery | accuracy | dl3 | 3D-CNN | 0.9238 | ||||
| 85 | Zhang2018c | motor imagery | accuracy | dl4 | 2D-CNN | 0.8841 | ||||
| 86 | Zhang2018c | motor imagery | accuracy | dl5 | 1D-CNN | 0.8622 | ||||
| 87 | Zhang2018c | motor imagery | accuracy | trad1 | SVM | 0.8505 | ||||
| 88 | Zhang2018c | motor imagery | accuracy | trad2 | SR-FBCSP | 0.8206 | ||||
| 89 | Zhang2018c | motor imagery | accuracy | trad3 | CSP + RF | 0.805 | ||||
| 90 | A hierarchical LSTM model with attention for modeling EEG non-stationarity for human decision prediction | Hasib2018 | guard decision classification | auc | trad1 | SVM | 0.652 | |||
| 91 | Hasib2018 | guard decision classification | auc | dl1 | CNN | 0.694 | ||||
| 92 | Hasib2018 | guard decision classification | auc | dl2 | LSTM | 0.553 | ||||
| 93 | Hasib2018 | guard decision classification | auc | dl3 | LSTM (0.5-s) | 0.702 | ||||
| 94 | Hasib2018 | guard decision classification | auc | dl4 | LSTM (2.5-s) | 0.613 | ||||
| 95 | Hasib2018 | guard decision classification | auc | dl5 | LSTM (5-s) | 0.606 | ||||
| 96 | Hasib2018 | guard decision classification | auc | arch1 | H-LSTM (0.5-s) | RNN | 0.826 | |||
| 97 | Hasib2018 | guard decision classification | auc | arch2 | H-LSTM (2.5-s) | RNN | 0.81 | |||
| 98 | Hasib2018 | guard decision classification | auc | arch3 | H-LSTM (5-s) | RNN | 0.816 | |||
| 99 | Deep EEG super-resolution: Upsampling EEG spatial resolution with Generative Adversarial Networks | Corley2018 | EEG upsampling (2x) | mse | arch1 | WGAN | GAN | 2060 | Use a surrogate classification task to see how useful the superresolution was | |
| 100 | Corley2018 | EEG upsampling (4x) | mse | arch1 | WGAN | GAN | 8680 |