behnamnia.a
/
DG_DA_fMedical_Survey
Watch 1
Star 0
Fork 0
Code Issues 0 Pull Requests 0 Releases 0 Wiki Activity
Browse Source

Update.

master
Armin Behnamnia 1 year ago
parent
f5bf14d66c
commit
17193fe8f2
14 changed files with 165 additions and 6 deletions
Split View Show Diff Stats
  1. 17
    6
      README.md
  2. BIN
      figures/DA_scenarios_labels.pdf
  3. BIN
      figures/EEG_domains_distributions.pdf
  4. BIN
      figures/EEG_tasks_distributions.pdf
  5. BIN
      figures/Hierarchy_Architecture.pdf
  6. BIN
      figures/Hierarchy_DA.pdf
  7. BIN
      figures/Hierarchy_DG.pdf
  8. BIN
      figures/fMRI_domains_distributions.pdf
  9. BIN
      figures/fMRI_tasks_distributions.pdf
  10. BIN
      figures/transfer_learning_categories.pdf
  11. 18
    0
      tables/EEG datasets.md
  12. 91
    0
      tables/EEG papers.md
  13. 11
    0
      tables/fMRI datasets.md
  14. 28
    0
      tables/fMRI papers.md

+ 17
- 6
README.md View File

@@ -1,14 +1,25 @@
# DA_fMedical_Survey

DML Git page for the paper "Domain Adaptation and Generalization on Functional Medical Images: A
Systematic Survey"
# Domain Adaptation and Generalization on Functional Medical Images: A Systematic Survey

This GitHub repository provides a systematic overview of novel domain adaptation and domain generalization methods on functional brain images. It contains a variety of resources and papers to help researchers and practitioners understand and apply these methods in their own projects. The repository also contains tables and references related to novel domain adaptation and generalization techniques, as well as a collection of related datasets. This repository is a valuable resource for anyone interested in exploring and exploiting the field of domain adaptation and domain generalization on functional brain images.

# Contents
* Table of papers
* [EEG papers](tables/EEG%20papers.md)
* [fMRI papers](tables/fMRI%20papers.md)
* Table of Datasets
* New papers
* [EEG datasets](tables/EEG%20datasets.md)
* [fMRI datasets](tables/fMRI%20datasets.md)
* Figures
* [Fig 1. Transfer Learning Categories](figures/transfer_learning_categories.pdf)
* [Fig 2. Different Domain Adaptation (DA) scenarios based on label distribution](figures/DA_scenarios_labels.pdf)
* [Fig 3. Distribution of related works on EEG data in recent years based on different domains](figures/EEG_domains_distributions.pdf)
* [Fig 4. Distribution of related works on EEG data in recent years based on different tasks](figures/EEG_tasks_distributions.pdf)
* [Fig 5. Distribution of related works on fMRI data in recent years based on different domains](figures/fMRI_domains_distributions.pdf)
* [Fig 6. Distribution of related works on fMRI data in recent years based on different tasks](figures/fMRI_tasks_distributions.pdf)
* [Fig 7. Hierarchy of different types of architecture used in recent works](figures/Hierarchy_Architecture.pdf)
* [Fig 8. Hierarchy of different Domain Adaptation approaches used in recent works](figures/Hierarchy_DA.pdf)
* [Fig 9. Hierarchy of different Domain Generalization approaches used in recent works](figures/Hierarchy_DG.pdf)


# Cite
[Arxiv version of paper](https://arxiv.org/abs/2212.03176):
@@ -23,4 +34,4 @@ This GitHub repository provides a systematic overview of novel domain adaptation
year = {2022},
copyright = {arXiv.org perpetual, non-exclusive license}
}
```
```

BIN
figures/DA_scenarios_labels.pdf View File


BIN
figures/EEG_domains_distributions.pdf View File


BIN
figures/EEG_tasks_distributions.pdf View File


BIN
figures/Hierarchy_Architecture.pdf View File


BIN
figures/Hierarchy_DA.pdf View File


BIN
figures/Hierarchy_DG.pdf View File


BIN
figures/fMRI_domains_distributions.pdf View File


BIN
figures/fMRI_tasks_distributions.pdf View File


BIN
figures/transfer_learning_categories.pdf View File


+ 18
- 0
tables/EEG datasets.md View File

@@ -0,0 +1,18 @@
| **Dataset Name** | **Subject #** | **Total Sample Count** | **Channel #** | **Task** | **Class #** | **Link + Availability** |
| :---------------------------: | :-----------: | :--------------------: | :----------------: | :------: | :---------: | :------------------------------------------------------------------------------------------------------------------: |
| SEED | 15 | 675 | 62 | ER | 3 | [Access Request](https://bcmi.sjtu.edu.cn/home/seed/downloads.html#seed-access-anchor) |
| DEAP | 32 | 1280 | 32 | ER | 5 | [Access Request](https://www.eecs.qmul.ac.uk/mmv/datasets/deap/index.html) |
| DREAMER | 32 | 414 | 14 | ER | 3 | [Access Request](https://zenodo.org/record/546113#.Ynq8P5NBxQI) |
| SEED-IV | 15 | 1080 | 62 | ER | 4 | [Access Request](https://bcmi.sjtu.edu.cn/home/seed/seed-iv.html) |
| CHB-MIT | 22 | 664 | Mostly 23 or 24-26 | SA | 4 | [Available](https://physionet.org/content/chbmit/1.0.0/) |
| ISRUC-Sleep | 100, 8, 10 | 126 | 6 | SD | 3 | [Available](https://sleeptight.isr.uc.pt/?page_id=48) |
| MASS | 200 | 200 | 4, 17, 19, 20 | SD | 5 | [Access Request](http://ceams-carsm.ca/en/mass/) |
| Taiwan Driving Dataset | 27 | 81576 | 32 | AM | 3 | [Raw](https://doi.org/10.6084/m9.figshare.6427334.v5) [Preprocessed](https://doi.org/10.6084/m9.figshare.7666055.v3) |
| BCI Competition IV: dataset 1 | 7 | 1960 | 59 | MI | 2 | [Available](https://bbci.de/competition/iv/desc_1.html) |
| BCI Competition IV: 2a | 9 | 5184 | 22 | MI | 4 | [Available](http://www.bbci.de/competition/iv/#dataset2a) |
| BCI Competition IV: 2b | 9 | 6480 | 3 bipolar | MI | 2 | [Available](http://www.bbci.de/competition/iv/#dataset2b) |
| THU-EP | 80 | 2240 | 32 | ER | 9 | [Available](https://cloud.tsinghua.edu.cn/d/3d176032a5a545c1b927/) |
| MAHNOB-HCI | 27 | 540 | 32 | ER | 2 | [Access Request](https://mahnob-db.eu/hci-tagging/) |
| SEED-VIG | 23 | 885 | 6, 12 | AM | 2 | [Access Request](https://bcmi.sjtu.edu.cn/~seed/seed-vig.html) |
| KU | 54 | 5400 | 62 | MI | 2 | [Access Request](http://deepbci.korea.ac.kr/opensource/opendb/) |
| GIST | 52 | 5200 << 6240 | 62 | MI | 2 | [Available](http://gigadb.org/dataset/100295) |

+ 91
- 0
tables/EEG papers.md View File

@@ -0,0 +1,91 @@
| **Article** | **Year** | **Github Link/ Repo** | **DA/DG** | **Method** | **Dataset** | **Architecture** | **Multi-source or Single-source** | **Task** | **Domain** |
| :-----------------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :--------------------------------------------------------------------------------------------------------------------: | :-------: | :-----------------------------------------------------------------------------------------: | :-----------------------------: | :---------------------: | :-------------------------------: | :----------------------------------: | :---------------------------: |
| EEG-Based Cross-Subject Driver Drowsiness Recognition With an Interpretable Convolutional Neural Network | 2022 | [link](https://github.com/cuijiancorbin/EEG-based-CrossSubject-Driver-Drowsiness-Recognition-with-anInterpretable-CNN) | DG | Architecture Embedded | Others | CNN | SS | Drowsiness Recognition | Cross-Subject |
| Domain-Invariant Representation Learning from EEG with Private Encoders | 2022 | - | DG | Multi-source Domain Alignment | SEED - DEAP - SEED-IV - DREAMER | ANN | MS | Emotion Recognition | Cross-Subject |
| Capsule neural networks on spatio-temporal EEG frames for cross-subject emotion recognition | 2022 | - | DG | Architecture Embedded | DEAP | CNN | SS | Drowsiness Recognition | Cross-Subject |
| Privacy-Preserving Domain Adaptation for Motor Imagery-based Brain-Computer Interfaces | 2022 | [link](https://github.com/xkazm/ASFA) | DA | Classifier Alignment - Data Augmentation - Self-supervised Learning | - | ANN | SS | Motor Imagery Classification | Cross-Subject |
| Deep BiLSTM neural network model for emotion detection using cross-dataset approach | 2022 | - | DG | Architecture Embedded | SEED - DEAP - Others | RNN | SS | Emotion Recognition | Cross-Dataset |
| Inter-subject Contrastive Learning for Subject Adaptive EEG-based Visual Recognition | 2022 | [link](https://github.com/DeepBCI/Deep-BCI/tree/master/1_Intelligent_BCI/Inter_Subject_Contrastive_Learning_for_EEG) | DA | Instance Alignment | Others | ANN | MS | Visual Recognition | Cross-Subject |
| Motor Imagery Classification via Kernel-Based Domain Adaptation on an SPD Manifold | 2022 | - | DA | Domain Alignment - Pseudo-label Training | BCI Competition | Non-Deep | SS | Motor Imagery Classification | Cross-Subject |
| EEG-based emotion charting for Parkinson's disease patients using Convolutional Recurrent Neural Networks and cross dataset learning | 2022 | - | DG | Architecture Embedded | SEED-IV - Others | CNN - RNN - Non-Deep | MS | Emotion Recognition | Cross-Dataset |
| Domain adaptation for epileptic EEG classification using adversarial learning and Riemannian manifold | 2022 | - | DA-DG | Adversarial Feature Alignment - Multi Source Domain Alignment | Others | ANN - Autoencoder | MS | Seizure Detection/Prediction | Cross-Subject |
| Disentangled and Side-aware Unsupervised Domain Adaptation for Cross-dataset Subjective Tinnitus Diagnosis | 2022 | - | DA-DG | Adversarial Feature Alignment - Feature Disentanglement - Data Manipulation | Others | Autoencoder | MS | Tinnitus Diagnosis | Cross-Dataset |
| Exploiting Multiple EEG Data Domains with Adversarial Learning. | 2022 | [link](https://github.com/philipph77/acse-framework) | DG | Adversarial Training | SEED - DEAP - SEED-IV - DREAMER | ANN-CNN | MS | evaluating subjects’ mental states | Cross-Dataset |
| Generator-based Domain Adaptation Method with Knowledge Free for Cross-subject EEG Emotion Recognition | 2022 | - | DA | Adversarial Feature Alignment | DEAP | GAN | SS | Emotion Recognition | Cross-Subject |
| A Decomposition-Based Hybrid Ensemble CNN Framework for Improving Cross-Subject EEG Decoding Performance | 2022 | - | DG | Ensemble Learning - Architecture Embedded | Others | CNN | SS | Situation Awareness Recognition | Cross-Subject |
| A deep subdomain associate adaptation network for cross-session and cross-subject EEG emotion recognition | 2022 | - | DA | Domain Alignment - Pseudo-label Training | SEED | CNN | SS | Emotion Recognition | Cross-Subject/Session |
| Mental Workload Classification Method Based on EEG Cross-Session Subspace Alignment | 2022 | - | DA | Domain Alignment | Others | Non-Deep | MS | Mental Workload Classification | Cross-Session |
| Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning | 2022 | - | DG | Meta-Learning - Self-supervised Learning | Others | CNN | SS | Sleep Scoring | Cross-Subject/Dataset |
| From unsupervised to semi-supervised adversarial domain adaptation in EEG-based sleep staging | 2022 | - | DA | Adversarial Training - Pseudo-label Training | Others | RNN | SS | Sleep Stage Classification | Cross-Dataset |
| Prototype-based Domain Generalization Framework for Subject-Independent Brain-Computer Interfaces | 2022 | - | DG | Multi Source Domain Alignment | Others | CNN | SS | Motor Imagery Classification | Cross-Subject |
| Enhancing Affective Representations of Music-Induced EEG through Multimodal Supervision and latent Domain Adaptation | 2022 | [link](https://github.com/klean2050/EEG_CrossModal) | DA | Adversarial Training | DEAP | RNN | SS | Emotion Recognition | Cross-Subject |
| Cross-Task Cognitive Workload Recognition Based on EEG and Domain Adaptation. | 2022 | - | DA | Domain Alignment - Pseudo-label Training | Others | Non-Deep | SS | Mental Workload Classification | Cross-Task/Subject |
| Cross-Session EEG-Based Emotion Recognition Via Maximizing Domain Discrepancy | 2022 | - | DA | Adversarial Feature Alignment | SEED | CNN | SS | Emotion Recognition | Cross-Session |
| Cross-Day EEG-Based Emotion Recognition Using Transfer Component Analysis | 2022 | - | DA | Domain Alignment | SEED - DEAP - Others | Non-Deep | SS | Emotion Recognition | Cross-Day |
| Multi-view cross-subject seizure detection with information bottleneck attribution | 2022 | - | DG | Adversarial Training | Others | ANN - GAN | SS | Seizure Detection | Cross-Subject |
| Cross-subject EEG-based emotion recognition through neural networks with stratified normalization | 2021 | - | DG | Data Manipulation | SEED | ANN | MS | Emotion Recognition | Cross-Subject |
| Multi-view spatial-temporal graph convolutional networks with domain generalization for sleep stage classification. | 2021 | [link](https://github.com/ziyujia/mstgcn) | DG | Adversarial Training | Others | Attention - Graph | SS | Sleep Stage Classification | Cross-Subject |
| A prototype-based SPD matrix network for domain adaptation EEG emotion recognition | 2021 | - | DA | Adversarial Feature Alignment | DEAP - DREAMER | CNN - GAN | MS | Emotion Recognition | Cross-Subject |
| Deep Learning for Patient-Independent Epileptic Seizure Prediction Using Scalp EEG Signals | 2021 | - | DG | Architecture Embedded | Others | CNN | SS | Epileptic Seizure Prediction | Cross-Subject |
| Plug-and-play domain adaptation for cross-subject eeg-based emotion recognition | 2021 | - | DA-DG | Instance Alignment - Feature Disentanglement - Ensemble Learning | SEED | RNN - Attention | MS | Emotion Recognition | Cross-Subject |
| Two-Level Domain Adaptation Neural Network for EEG-Based Emotion Recognition | 2021 | - | DA | Adversarial Feature Alignment - Domain Alignment | SEED | CNN | MS | Emotion Recognition | Cross-Day/Subject |
| Cross-subject EEG emotion recognition with self-organized graph neural network | 2021 | [link](https://github.com/tailofcat/SOGNN) | DG | Architecture Embedded | SEED - SEED-IV | Graph | SS | Emotion Recognition | Cross-Subject |
| Standardization-refinement domain adaptation method for cross-subject EEG-based classification in imagined speech recognition. | 2021 | - | DA - DG | Domain Alignment - Pseudo-label Training - Architecture embedded | Others | RNN | SS | Imagined Speech Recognition | Cross-Subject |
| An EEG-based transfer learning method for cross-subject fatigue mental state prediction | 2021 | - | DA | Adversarial Feature Alignment | Others | ANN | SS | Fatigue Mental State Prediction | Cross-Subject |
| EEGNet with ensemble learning to improve the cross-session classification of SSVEP based BCI from Ear-EEG | 2021 | - | DG | Ensemble Learning | Others | CNN | SS | SSVEP-based BCI Classification | Cross-Session |
| Dynamic Joint Domain Adaptation Network for Motor Imagery Classification | 2021 | - | DA | Adversarial Feature Alignment - Pseudo-label Training | BCI Competition | CNN | SS | Motor Imagery Classification | Cross-Session |
| Subject-Invariant EEG Representation Learning For Emotion Recognition | 2021 | [link](https://github.com/philipph77/acse-framework) | DA | Adversarial Feature Alignment | Others | CNN | SS | Emotion Recognition | Cross-Subject/Dataset |
| MS-MDA: Multisource Marginal Distribution Adaptation for Cross-subject and Cross-session EEG Emotion Recognition | 2021 | [link](https://github.com/VoiceBeer/MS-MDA) | DA | Domain Alignment - Classifier Alignment | SEED - SEED-IV | ANN | MS | Emotion Recognition | Cross-Subject/Session |
| Subject matching for cross-subject eeg-based recognition of driver states related to situation awareness | 2021 | - | DA | Instance Alignment | Others | CNN | SS | Situation Awareness Recognition | Cross-Subject |
| A deep multi-source adaptation transfer network for cross-subject electroencephalogram emotion recognition | 2021 | - | DA | Adversarial Feature Alignment - Instance Alignment | SEED | CNN | SS | Emotion Recognition | Cross-Subject |
| Multi-Source Co-adaptation for EEG-based emotion recognition by mining correlation information | 2021 | - | DA | Instance Alignment - Pseudo-label Training | SEED - DEAP | ANN | MS | Emotion Recognition | Cross-Subject/Dataset |
| Label-Based Alignment Multi-Source Domain Adaptation for Cross-Subject EEG Fatigue Mental State Evaluation | 2021 | - | DA | Domain Alignment - Classifier Alignment | Others | ANN - Non-Depp | MS | Mental State Prediction | Cross-Subject |
| Multi-source signal alignment and efficient multi-dimensional feature classification in the application of EEG-based subject-independent drowsiness detection | 2021 | [link](https://github.com/shenmusmart/MSSA-TN) | DA | Instance Alignment | Others | Non-Deep | MS | Drowsiness Recognition | Cross-Subject |
| An adversarial discriminative temporal convolutional network for EEG-based cross-domain emotion recognition. | 2021 | - | DA | Adversarial Feature Alignment | DEAP - DREAMER | CNN | SS | Emotion Recognition | Cross-Subject/Dataset |
| Domain Adaptation for Cross-Subject Emotion Recognition by Subject Clustering | 2021 | - | DA | Preprocessing | DEAP | ANN | MS | Emotion Recognition | Cross-Subject |
| Semi-Supervised Contrastive Learning for Generalizable Motor Imagery EEG Classification | 2021 | - | DA - DG | Pseudo-label Training - Adversarial Training - Data Augmentation - Self-supervised Learning | BCI Competition | CNN | SS | Motor Imagery Classification | Cross-Subject/Session |
| Learning Subject-Generalized Topographical EEG Embeddings Using Deep Variational Autoencoders and Domain-Adversarial Regularization | 2021 | - | DG | Adversarial Training | SEED - DEAP | Autoencoder | SS | Emotion Recognition | Cross-Subject |
| Contrastive learning of subject-invariant EEG representations for cross-subject emotion recognition. | 2021 | - | DG | Self-supervised Learning | SEED - Others | CNN | MS | Emotion Recognition | Cross-Subject |
| EEG-Based Emotion Recognition via Joint Domain Adaptation and Semi-supervised RVFL Network | 2021 | - | DA | Domain Alignment - Pseudo-label Training - Data Augmentation | SEED-IV | - | SS | Emotion Recognition | Cross-Session |
| Subject Adaptive EEG-Based Visual Recognition | 2021 | [link](https://github.com/DeepBCI/Deep-BCI) | DA | Domain Alignment | Others | RNN | MS | Visual Recognition | Cross-Subject |
| Cross-subject And Cross-device Wearable EEG Emotion Recognition Using Frontal EEG Under Virtual Reality Scenes | 2021 | - | DA | Domain Alignment | Others | Graph | SS | Emotion Recognition | Cross-Subject/Device |
| Seizure prediction in EEG signals using STFT and domain adaptation. | 2021 | - | DA | Adversarial Feature Alignment - Domain Alignment | Others | Non-Deep | SS | Seizure Prediction | Cross-Subject |
| Cross-Subject EEG Emotion Recognition Using Domain Adaptive Few-Shot Learning Networks | 2021 | - | DA | Domain Alignment | SEED - DEAP | CNN - Attention-based | SS | Emotion Recognition | Cross-Subject |
| Cross-subject EEG-based Emotion Recognition Using Adversarial Domain Adaptation with Attention Mechanism | 2021 | - | DA | Adversarial Feature Alignment | SEED | Attention-based - Graph | MS | Emotion Recognition | Cross-Subject |
| Cross-subject electroencephalogram emotion recognition based on maximum classifier discrepancy | 2021 | - | DA | Adversarial Feature Alignment | SEED | GAN | SS | Emotion Recognition | Cross-Subject/Session |
| Subject-Independent Brain-Computer Interface for Decoding High-Level Visual Imagery Tasks. | 2021 | - | DG | Architecture Embedded | Others | CNN | SS | Decoding Visual Imagery | Cross-Subject |
| Domain-guided Self-supervision of EEG Data Improves Downstream Classification Performance and Generalizability | 2021 | - | DG | Self-supervised Learning | Others | CNN | SS | Behavioral State Estimation | Cross-Subject/Session/Dataset |
| Common Spatial Generative Adversarial Networks based EEG Data Augmentation for Cross-Subject Brain-Computer Interface | 2021 | - | DG | Data Augmentation | BCI Competition | GAN | MS | Motor Imagery Classification | Cross-Subject |
| EEG emotion Enhancement using Task-specific Domain Adversarial Neural Network | 2021 | - | DA | Adversarial Feature Alignment | SEED | ANN | SS | Emotion Recognition | Cross-Subject/Phase |
| Single-channel EEG based insomnia detection with domain adaptation. | 2021 | - | DA | Adversarial Feature Alignment | Others | RNN | MS | Sleep Stage Classification | Cross-Dataset |
| ADAST: Attentive Cross-domain EEG-based Sleep Staging Framework with Iterative Self-Training | 2021 | [link](https://github.com/emadeldeen24/ADAST) | DA | Adversarial Feature Alignment - Pseudo-label Training | Others | CNN - Attention-based | SS | Sleep Stage Classification | Cross-Dataset |
| Multi-Branch Network for Cross-Subject EEG-based Emotion Recognition | 2021 | - | DA | Instance Alignment | SEED | CNN | SS | Emotion Recognition | Cross-Subject |
| Coupled Projection Transfer Metric Learning for Cross-Session Emotion Recognition from EEG | 2021 | - | DA | Domain Alignment - Pseudo-label Training | SEED-IV | Non-Deep | SS | Emotion Recognition | Cross-Session/Trial |
| A Pseudo Domain Adaptation Paradigm for Subject-independent EEG-based Emotion Recognition | 2021 | - | DG | Meta Learning | SEED | RNN | SS | Emotion Recognition | Cross-Subject |
| Wasserstein-Distance-Based Multi-Source Adversarial Domain Adaptation for Emotion Recognition and Vigilance Estimation | 2021 | - | DA | Adversarial Feature Alignment | SEED - SEED-VIG | - | SS | Vigilance Estimation | Cross-Subject |
| Cross-Subject Domain Adaptation for Classifying Working Memory Load with Multi-Frame EEG Images | 2021 | - | DA - DG | Domain Alignment - Data Manipulation | Others | CNN - Attention-based | SS | Workload Classification | Cross-Subject |
| Learning invariant representations from EEG via adversarial inference | 2020 | - | DG | Adversarial Training | Others | CNN | SS | Motor Imagery Classification | Cross-Subject |
| Subject-Aware Contrastive Learning for Biosignals | 2020 | - | DG | Data Augmentation - Self-supervised Learning | Others | Autoencoder - Non-deep | SS | EEG Decoding | Cross-Subject |
| Fusion convolutional neural network for cross-subject EEG motor imagery classification | 2020 | - | DG | Ensemble Learning | Others | CNN | SS | Motor Imagery Classification | Cross-Subject |
| Deep representation-based domain adaptation for nonstationary EEG classification. | 2020 | - | DA | Adversarial Feature Alignment - Pseudo-label Training | BCI Competition - Others | CNN | SS | Motor Imagery Classification | Cross-Subject |
| Conditional Adversarial Domain Adaptation Neural Network for Motor Imagery EEG Decoding | 2020 | - | DA | Adversarial Feature Alignment | Others | CNN | SS | Motor Imagery Classification | Cross-Subject |
| Meta learn on constrained transfer learning for low resource cross subject EEG classification | 2020 | - | DG | Meta Learning | SEED - DEAP - BCI Competition | - | MS | Motor Imagery Classification | Cross-Subject |
| Supervised domain generalization for integration of disparate scalp EEG datasets for automatic epileptic seizure detection | 2020 | - | DG | Multi Source Domain Alignment | Others | CNN - RNN | MS | Epileptic Seizure Prediction | Cross-Dataset |
| Tensor-based EEG network formation and feature extraction for cross-session driving drowsiness detection | 2020 | - | DA | Domain Alignment | Others | Non-Deep | SS | Driving Drowsiness Detection | Cross-Session |
| Data Augmentation for Domain-Adversarial Training in EEG-based Emotion Recognition | 2020 | - | DA | Adversarial Feature Alignment | DEAP | Non-Deep | SS | Emotion Recognition | Cross-Subject/Session/Dataset |
| Domain Adaptation for EEG Emotion Recognition Based on Latent Representation Similarity | 2019 | - | DA | Adversarial Feature Alignment | SEED - DEAP | ANN | SS | Emotion Recognition | Cross-Subject/Session |
| A Convolutional Recurrent Attention Model for Subject-Independent EEG Signal Analysis | 2019 | [link](https://github.com/dalinzhang/CRAM) | DG | Multi Source Domain Alignment | BCI Competition | CNN - Attention-based | SS | Motor Imagery Classification | Cross-Subject |
| Generalizing to unseen domains via distribution matching | 2019 | [link](https://github.com/belaalb/G2DM) | DG | Adversarial Training | SEED | - | MS | Emotion Recognition | Cross-Subject |
| A Novel Bi-hemispheric Discrepancy Model for EEG Emotion Recognition | 2019 | - | DA | Adversarial Feature Alignment | SEED - SEED-IV - Others | RNN | SS | Emotion Recognition | Cross-Subject |
| Multi-method fusion of cross-subject emotion recognition based on high-dimensional EEG features | 2019 | - | DG | Feature selection | SEED - DEAP | Non-Deep | SS | Emotion Recognition | Cross-Subject |
| Manifold Embedded Knowledge Transfer for Brain-Computer Interfaces | 2019 | [link](https://github.com/chamwen/MEKT) | DA | Domain Alignment - Pseudo-label Training | Others | - | SS | Motor Imagery Classification | Cross-Subject |
| EEG-based driver drowsiness estimation using feature weighted episodic training | 2019 | - | DG | Feature Weighting | Others | ANN | MS | Drowsiness Recognition | Cross-Subject |
| Cross-subject EEG signal recognition using deep domain adaptation network | 2019 | - | DA | Domain Alignment | BCI Competition | CNN | SS | Motor Imagery Classification | Cross-Subject |
| Reducing the Subject Variability of EEG Signals with Adversarial Domain Generalization | 2019 | - | DG | Adversarial Training | SEED - SEED-VIG | ANN | MS | Emotion Recognition | Cross-Subject |
| EEG-based cross-subject mental fatigue recognition | 2019 | - | DA | Domain Alignment | Others | CNN | SS | Mental Fatigue Recognition | Cross-Subject |
| Subject adaptation network for EEG data analysis | 2019 | - | DG | Adversarial Training | Others | GAN | SS | VIgilance Estimation | Cross-Subject/Session |
| Mutual Information-driven Subject-invariant and Class-relevant Deep Representation Learning in BCI | 2019 | [link](https://github.com/eunjin93/SICR_BCI) | DA | Feature Disentanglement | Others | ANN | SS | Motor Imagery Classification | Cross-Subject |
| Cross-subject statistical shift estimation for generalized electroencephalography-based mental workload assessment | 2019 | - | DA | Data Manipulation | Others | - | MS | Mental Workload Assessment | Cross-Subject |
| Domain adaptation with optimal transport improves EEG sleep stage classifiers. | 2018 | - | DA | Instance Alignment | Others | CNN | SS | Sleep Stage Classification | Cross-Dataset |
| Automatic epileptic seizure detection in EEG signals using multi-domain feature extraction and nonlinear analysis. | 2017 | - | DG | Multi Source Domain Alignment | Others | Non-Deep | SS | Epileptic Seizure Prediction | Cross-Subject |
| Unsupervised domain adaptation techniques based on auto-encoder for non-stationary EEG-based emotion recognition. | 2016 | - | DA | Domain Alignment | SEED | Autoencoder | SS | Emotion Recognition | Cross-Subject/Session |

+ 11
- 0
tables/fMRI datasets.md View File

@@ -0,0 +1,11 @@
| **Dataset Name** | **Subject #** | **Task** | **Class #** | **Link + Availablity** | **Extra Information** |
| :----------------------------------------: | :-----------: | :------: | :---------: | :----------------------------------------------------------------------------: | :-------------------: |
| ABIDE I | 1112 | ASD-D | 2 | [Access Request](http://fcon_1000.projects.nitrc.org/indi/req_access.html) | Site #: 17 |
| ABIDE II | 1114 | ASD-D | 2 | [Access Request](http://fcon_1000.projects.nitrc.org/indi/req_access.html) | Site #: 19 |
| HCP | 1206 | HTA | 2 | [Available](https://humanconnectome.org/study/hcp-young-adult) | -- |
| OpenfMRI: A Multi-Modal Human Neuroimaging | 19 | HTA | 3 | [Available](https://openfmri.org/dataset/ds000117/) | Total Samples #: 1200 |
| OpenfMRI: Balloon Analog Risk-Taking Task | 16 | HTA | 2 | [Available](https://legacy.openfmri.org/dataset/ds000001/) | -- |
| ADHD-200 | 973 | ADHD-D | 3 | [Access Request](http://fcon_1000.projects.nitrc.org/indi/req_access.html) | Site #: 8 |
| ADNI I | 819 | AD-D | 3 | [Access Request](https://ida.loni.usc.edu/collaboration/access/appLicense.jsp) | -- |
| ADNI II | 1601 | AD-D | 4 | [Access Request](https://ida.loni.usc.edu/collaboration/access/appLicense.jsp) | -- |
| ABCD | 4521 | NCP | 3 | [Access Request](https://nda.nih.gov/abcd/request-access.html) | Site #: 21 |

+ 28
- 0
tables/fMRI papers.md View File

@@ -0,0 +1,28 @@
| **Article** | **Year** | **Github Link/ Repo** | **DA/DG** | **Method** | **Dataset** | **Architecture** | **Task** | **Domain** |
| :------------------------------------------------------------------------------------------------------------------------: | :------: | :-----------------------------------------------------------------------: | :-------: | :---------------------------------------------------: | :------------: | :---------------------: | :-------------------------------------: | :------------------: |
| Multi-site clustering and nested feature extraction for identifying autism spectrum disorder with resting-state fMRI | 2022 | - | DA | Domain Alignment | ABIDE | ANN | Identify Autism Spectrum Disorders | Site |
| Domain adaptation based on rough adjoint inconsistency and optimal transport for identifying autistic patients | 2022 | - | DA | Domain Alignment | ABIDE | Non-Deep | Identify Autism Spectrum Disorders | Site |
| Privacy preserving multi-source domain adaptation for medical data | 2022 | - | DA | Domain Alignment - Pseudo-label Training | ABIDE - Others | ANN | Identify Autism Spectrum Disorders | Site |
| Using DeepGCN to identify the autism spectrum disorder from multi-site resting-state data | 2021 | - | DG | Architecture Embedded | ABIDE | Graph-based | Identify Autism Spectrum Disorders | Site |
| A Deep Learning Approach to Predict Autism Spectrum Disorder Using Multisite Resting-State fMRI | 2021 | - | DG | Feature Selection | ABIDE | ANN | Identify Autism Spectrum Disorders | Site |
| Fader Networks for domain adaptation on fMRI: ABIDE-II study | 2021 | [link](https://github.com/kondratevakate/fmri-fader-net) | DA | Adversarial Feature Alignment | ABIDE | CNN - GAN - Autoencoder | Identify Autism Spectrum Disorders | Site |
| Identifying Autism Spectrum Disorder Based on Individual-Aware Down-Sampling and Multi-Modal Learning | 2021 | [link](http://github.com/jhonP-Li/ASD_GP_GCN) | DG | Feature Selection | ABIDE | Graph-based | Identify Autism Spectrum Disorders | Site |
| Domain Adaptation Using a Three-Way Decision Improves the Identification of Autism Patients from Multisite fMRI Data | 2021 | - | DA | Pseudo-label Training | ABIDE | Non-Deep | Identify Autism Spectrum Disorders | Site |
| Learning shared neural manifolds from multi-subject FMRI data | 2021 | - | DG | Multi-source Domain Alignment - Architecture Embedded | Others | ANN | Visual Perception Analysis | Subject |
| Few-shot domain-adaptive anomaly detection for cross-site brain images | 2021 | - | DA | Adversarial Feature Alignment | HCP - Others | ANN | Anomaly Detection of Brain Images | Site |
| Attention module improves both performance and interpretability of 4D fMRI decoding neural network | 2021 | - | DG | Architecture Embedded | HCP | CNN - Attention | Decoding Cognitive States | Subject-Task-Dataset |
| Graph Convolutional Networks via Low-Rank Subspace for Multi-Site rs-fMRI ASD Diagnosis | 2021 | - | DG | Multi-source Domain Alignment | ABIDE | Graph-based | Identify Autism Spectrum Disorders | Site |
| Extracting Sequential Features from Dynamic Connectivity Network with rs-fMRI Data for AD Classification | 2021 | - | DG | Architecture Embedded | ADNI | CNN - RNN | Alzheimer’s disease (AD) classification | Subject |
| Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation: ABIDE results | 2020 | [link](https://github.com/xxlya/Fed_ABIDE) | DA | Adversarial Feature Alignment | ABIDE | ANN | Identify Autism Spectrum Disorders | Site |
| Identifying Autism Spectrum Disorder With Multi-Site fMRI via Low-Rank Domain Adaptation | 2020 | - | DA | Instance Alignment | ABIDE | - | Identify Autism Spectrum Disorders | Site |
| Modelling subject variability in the spatial and temporal characteristics of functional modes | 2020 | - | DG | Architecture Embedded | HCP | - | Modelling subject variability | Subject |
| Separated Channel Attention Convolutional Neural Network (SC-CNN-Attention) to Identify ADHD in Multi-Site Rs-fMRI Dataset | 2020 | - | DG | Architecture Embedded | ADHD-200 | CNN - Attention | ADHD classification | Site |
| Transport-Based Joint Distribution Alignment for Multi-site Autism Spectrum Disorder Diagnosis Using Resting-State fMRI | 2020 | - | DA | Domain Alignment - Classifier Alignment | ABIDE | ANN | Identify Autism Spectrum Disorders | Site |
| Shared Space Transfer Learning for analyzing multi-site fMRI data | 2020 | - | DG | Multi-source Domain Alignment | Others | Non-Deep | Decoding Cognitive States | Site |
| Decoding Brain States From fMRI Signals by Using Unsupervised Domain Adaptation | 2020 | - | DA | Domain Alignment | HCP | CNN | Decoding Cognitive States | Subject |
| Conditional Domain Adversarial Transfer for Robust Cross-Site ADHD Classification Using Functional MRI | 2020 | - | DA | Adversarial Feature Alignment | ADHD-200 | ANN | ADHD classification | Site |
| Graph-based decoding model for functional alignment of unaligned fMRI data | 2020 | - | DG | Multi-source Domain Alignment - Architecture Embedded | OpenfMRI | - | Decoding Cognitive States | Subject |
| Improving whole-brain neural decoding of fmri with domain adaptation | 2019 | [link](https://github.com/sz144/DawfMRI) | DA | Domain Alignment | OpenfMRI | ANN | Decoding Cognitive States | Dataset |
| Meta-modulation Network for Domain Generalization in Multi-site fMRI Classification | 2021 | - | DG | Meta Learning | ABIDE | - | Resting-state fMRI classification | Site |
| Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI | 2018 | - | DG | Multi-source Domain Alignment - Architecture Embedded | Others | Non-Deep | Schizophrenia Classification | Site |
| Predicting Autism Spectrum Disorder Using Domain-Adaptive Cross-Site Evaluation | 2018 | [link](https://github.com/ashishpradhan1008/PredictingASDbyCrossSiteEval) | DA | Feature Selection | ABIDE | Non-Deep | Identify Autism Spectrum Disorders | Site |

Write Preview
Loading…
Cancel
Save