Transfer Learning: A Riemannian Geometry framework with applications to Brain-Computer Interfaces
Open accessThe DOI matches its Crossref record; 37 of the 38 references it cites were found in a registry or an index.
Abstract
Objective This paper tackles the problem of transfer learning in the context of electroencephalogram (EEG)-based brain-computer interface (BCI) classification. In particular, the problems of cross-session and cross-subject classification are considered. These problems concern the ability to use data from previous sessions or from a database of past users to calibrate and initialize the classifier, allowing a calibration-less BCI mode of operation. Methods Data are represented using spatial covariance matrices of the EEG signals, exploiting the recent successful techniques based on the Riemannian geometry of the manifold of symmetric positive definite (SPD) matrices. Cross-session and cross-subject classification can be difficult, due to the many changes intervening between sessions and between subjects, including physiological, environmental, as well as instrumental changes. Here, we propose to affine transform the covariance matrices of every session/subject in order to center them with respect to a reference covariance matrix, making data from different sessions/subjects comparable. Then, classification is performed both using a standard minimum distance to mean classifier, and through a probabilistic classifier recently developed in the literature, based on a density function (mixture of Riemannian Gaussian distributions) defined on the SPD manifold. Results The improvements in terms of classification performances achieved by introducing the affine transformation are docum…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Experiments have shown that RA-MDRM outperformed MDRM in MI and ERP tasks [42], when compared in a TL setting.”
From Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach (2020) · cites this paper as [42]
In the citing paper
“But as mentioned above, it still needs a small amount of labeled subject-specific calibration trials for ERP classification.”
From Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach (2020) · cites this paper as [42]
In the citing paper
“Zanini et al. [42] proposed a novel TL approach in the Riemannian space, referred to in this paper as RA-MDRM, to improve the performance of the MDRM classifier by utilizing auxiliary data from other sessions and/or subjects when there are only a few labeled trials from a new subject.”
From Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach (2020) · cites this paper as [42]
In the citing paper
“Although RA-MDRM has demonstrated promising performance in several BCI applications [42], it still has some limitations:”
From Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach (2020) · cites this paper as [42]
In the citing paper
“[42] used the nontarget stimuli as the resting state in ERP, which requires that some labeled trials from the new subject must be known.”
From Transfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach (2020) · cites this paper as [42]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 1×
“The second improvement relates to the problem of transfer learning [30].”
BackgroundOptimizing Spatial filters for Robust EEG Single-Trial Analysis
Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M., & Muller, K.-R. (2008) · IEEE Signal Processing Magazine · doi:10.1109/msp.2008.4408441 · Cited by 2,080 · cited 2×
“First, EEG signals of a training set are transformed through frequency and/or spatial filters in order to extract discriminant features [8], [16].”
BackgroundMethodA Riemannian Framework for Tensor Computing
Pennec, X., Fillard, P., & Ayache, N. (2006) · International Journal of Computer Vision · doi:10.1007/s11263-005-3222-z · Cited by 1,550 · cited 1×
“Some of them try to find the right value through numerical procedure like deterministic line search [17], [26], simple or stochastic gradient descent [10], [31].”
BackgroundSingle-trial analysis and classification of ERP components — A tutorial
Blankertz, B., Lemm, S., Treder, M., Haufe, S., & Müller, K.-R. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2010.06.048 · Cited by 1,138 · cited 4×
“This is done by supervised techniques like, for instance, Linear Discriminant Analysis (LDA) [9].”
MethodInfluentialRegularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms
Lotte, F., & Guan, C. (2011) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2010.2082539 · Cited by 1,045 · cited 1×
“Some examples of transfer learning applied to BCI problem can be found in [15], [21], [27] and [36].”
BackgroundBhatia, R. (2009) · Princeton University Press eBooks · doi:10.1515/9781400827787 · Cited by 1,027
Multiclass Brain–Computer Interface Classification by Riemannian Geometry
Barachant, A., Bonnet, S., Congedo, M., & Jutten, C. (2012) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2011.2172210 · Cited by 878 · cited 7×
“In [2] the authors used a basic classifier, named Minimum Distance to Mean (MDM), which takes into account distances on the manifold between the observations and some reference points of the classes, known as centers of mass, means, or barycenters.”
MethodInfluentialSelf-citationA Differential Geometric Approach to the Geometric Mean of Symmetric Positive-Definite Matrices
Moakher, M. (2005) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/s0895479803436937 · Cited by 702 · cited 1×
“Since P (n) is a Riemannian manifold of non-positive curvature, existence and unicity of the Riemannian mean can be proved [1], [28].”
BackgroundBCI Competition 2008 { Graz data set B
Leeb, R., & Brunner, C. (2008) · Cited by 615
Research works printed but not linked: 1
- said, 2015, Riemannian Gaussian distributions on the space of covariance matrices, arXiv 1507 01760v1
Cited by
A review of classification algorithms for EEG-based brain–computer interfaces: A 10 year update
Lotte, F., Bougrain, L., Cichocki, A., Clerc, M., Congedo, M., Rakotomamonjy, A., & Yger, F. (2018) · Journal of Neural Engineering · doi:10.1088/1741-2552/aab2f2 · Cited by 2,239
“These properties in part explain why Riemannian classification methods provide a good generalization capability [224, 238], which enabled researchers to set up calibration-free adaptive ERP-BCIs using simple subject-tosubject and session-to-session transfer learning strategies [6].”
BackgroundMethodSelf-citationTransfer Learning for Brain–Computer Interfaces: A Euclidean Space Data Alignment Approach
He, H., & Wu, D. (2020) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2913914 · Cited by 569
“Experiments have shown that RA-MDRM outperformed MDRM in MI and ERP tasks [43], when compared in a TL setting.”
BackgroundMethodResultInfluentialEEG Based Emotion Recognition: A Tutorial and Review
Li, X., Zhang, Y., Tiwari, P., Song, D., Hu, B., Yang, M., Zhao, Z., Kumar, N., & Marttinen, P. (2023) · ACM Computing Surveys · doi:10.1145/3524499 · Cited by 508
“One novel knowledge distillation DL framework for Affective BCI based on LSTM-Capsule structure that compresses the large model without performance degradation [198]. while significantly reducing the number of parameters to transfer.”
BackgroundMethodInfluentialA review on transfer learning in EEG signal analysis
Wan, Z., Yang, R., Huang, M., Zeng, N., & Liu, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.09.017 · Cited by 468
Transfer Learning for EEG-Based Brain–Computer Interfaces: A Review of Progress Made Since 2016
Wu, D., Xu, Y., & Lu, B.-L. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2020.3007453 · Cited by 434
“[57] proposed a Riemannian alignment (RA) approach to centre the EEG covariance matrices {C k } Nk n=1 in the k-th domain with respect to a reference covariance matrix Rk specific to that domain.”
Kostas, D., Aroca-Ouellette, S., & Rudzicz, F. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.653659 · Cited by 272
“While this is typical, some procedures, like covariance-based Riemannian classification schemes, do not necessarily need different features for different tasks [2, 5].”
MethodRiemannian Procrustes Analysis: Transfer Learning for Brain–Computer Interfaces
Rodrigues, P. L. C., Jutten, C., & Congedo, M. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2018.2889705 · Cited by 219
“We compared the performance of the RPA procedure for Transfer Learning to that of other distribution-matching methods proposed in [9], [10] and [7].”
BackgroundMethodResultInfluentialSelf-citationDeep Multi-Scale Fusion Neural Network for Multi-Class Arrhythmia Detection
Wang, R., Fan, J., & Li, Y. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.2981526 · Cited by 201
“In recent years, deep learning have achieved remarkable performance in various fields of medicine, such as medical image processing [24], genomic analysis [25], electronic health records analysis [26] and physiological signal analysis [27].”
BackgroundManifold Embedded Knowledge Transfer for Brain-Computer Interfaces
Zhang, W., & Wu, D. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.2985996 · Cited by 183
“[23] proposed a Riemannian alignment (RA) framework to align the EEG covariance matrices from different subjects.”
BackgroundMethodInfluentialWeighted Transfer Learning for Improving Motor Imagery-Based Brain–Computer Interface
Azab, A. M., Mihaylova, L., Ang, K. K., & Arvaneh, M. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2923315 · Cited by 176
“The proposed transfer learning algorithms on raw EEG have been mostly based on either importance sampling cross validation [13], [14] or instance selection [15], [16].”
MethodTransfer learning for motor imagery based brain–computer interfaces: A tutorial
Wu, D., Jiang, X., & Peng, R. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.06.008 · Cited by 174
“Different EEG trial alignment approaches have been proposed recently [22], [23], [25], [28], [29].”
BackgroundAffective Brain–Computer Interfaces (aBCIs): A Tutorial
Wu, D., Lu, B., Hu, B., & Zeng, Z. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3277471 · Cited by 151
“For example, Wang et al. [127] demonstrated the effectiveness of the Riemannian Alignment-Minimum Distance to Riemannian Mean (RA-MDRM) [125] on DEAP, and Jiang et al. [128] demonstrated the effectiveness of Euclidean alignment on both DEAP and SEED.”
MethodShe, Q., Chen, T., Fang, F. Z., Zhang, J., Gao, Y., & Zhang, Y. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3241846 · Cited by 145
“Zanini et al. [19] utilized a Riemannian alignment method to minimize the distance between different domains in Riemannian space, and achieved good MI-EEG classification performance in cross-subject transfer situation.”
MethodCross-Dataset Variability Problem in EEG Decoding With Deep Learning
Xu, L., Xu, M., Ke, Y., An, X., Liu, S., & Ming, D. (2020) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2020.00103 · Cited by 173
“Recently, many Transfer Learning approaches have been introduced into BCIs to reduce cross-subject variability (Zanini et al., 2018; Rodrigues et al., 2019; Yair et al., 2019).”
BackgroundA prototype-based SPD matrix network for domain adaptation EEG emotion recognition
Wang, Z., Qiu, S., Ma, X., & He, H. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107626 · Cited by 131
Parallel Transport on the Cone Manifold of SPD Matrices for Domain Adaptation
Yair, O., Ben‐Chen, M., & Talmon, R. (2019) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2019.2894801 · Cited by 125
“We remark that, in the case of two subsets with means P A ∈ M and P B ∈ M, the affine transformation presented in [12] can be interpreted as two consecutive applications of PT: from”
BackgroundMethodInfluentialTransfer Learning: Survey and Classification
Agarwal, N., Sondhi, A., Chopra, K., & Singh, G. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-5345-5_13 · Cited by 106
Challenges and Future Perspectives on Electroencephalogram-Based Biometrics in Person Recognition
Chan, H.-L., Kuo, P., Cheng, C., & Chen, Y. (2018) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2018.00066 · Cited by 123
“In BCI systems, the purpose of TL is to find common structures across subjects for use in refining the model for each subject (Zanini et al., 2018).”
BackgroundReview of brain encoding and decoding mechanisms for EEG-based brain–computer interface
Xu, L., Xu, M., Jung, T., & Ming, D. (2021) · Cognitive Neurodynamics · doi:10.1007/s11571-021-09676-z · Cited by 110
“Instead of a pre-trial baseline covariance matrix, Zanini et al. (2017) used the Riemannian mean covariance matrix as the reference matrix and transformed the center of all covariance matrices to the identity matrix.”
BackgroundMethodThinker invariance: enabling deep neural networks for BCI across more people
Kostas, D., & Rudzicz, F. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/abb7a7 · Cited by 113
Chu, Y., Zhao, X., Zou, Y., Xu, W., Song, G., Han, J., & Zhao, Y. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/aba7cd · Cited by 97
“Furthermore, as experimentally studied in [54], the proposed approach will be separately tested on the dataset of cross-session within the same subject and the dataset of cross-subject to validate the subject-to-subject transfer learning.”
MethodDifferent Set Domain Adaptation for Brain-Computer Interfaces: A Label Alignment Approach
He, H., & Wu, D. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.2980299 · Cited by 98
“If we view each EEG covariance matrix as a point on a Riemannian manifold, then individual differences cause shifts of these points, although they may entail more than just a simple displacement [26].”
BackgroundEEG-Based Driver Drowsiness Estimation Using Feature Weighted Episodic Training
Cui, Y., Xu, Y., & Wu, D. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2945794 · Cited by 86
“Zanini et al. [31] proposed a Riemannian space transfer learning framework, which uses a reference covariance matrix at the resting state to align data from different domains, before applying a Riemannian space classifier.”
MethodEEG-based emotion recognition systems; comprehensive study
Hamzah, H. A., & Abdalla, K. K. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e31485 · Cited by 102
Common Spatial Pattern Reformulated for Regularizations in Brain–Computer Interfaces
Wang, B., Wong, C. M., Kang, Z., Liu, F., Shui, C., Wan, F., & Chen, C. L. P. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2982901 · Cited by 77
Application of Transfer Learning in EEG Decoding Based on Brain-Computer Interfaces: A Review
Zhang, K., Xu, G., Zheng, X., Li, H., Zhang, S., Yu, Y., & Liang, R. (2020) · Sensors · doi:10.3390/s20216321 · Cited by 76
“14% MI/ ERP [92] FTL Affine transform Minimum distance mean and Bayesian classifier BCIC-IV-2a and Brain Invaders experiment \”
MethodPrivacy-Preserving Domain Adaptation for Motor Imagery-Based Brain-Computer Interfaces
Xia, K., Deng, L., Duch, W., & Wu, D. (2022) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2022.3168570 · Cited by 79
“[38] proposed a Riemannian alignment (RA) approach, which calculates the Riemannian mean of the covariance matrices of the reference state trials (e.”
BackgroundMethodJin, W., Zhu, X., Qian, L., Wu, C., Yang, F., Zhan, D., Kang, Z., Luo, K., Meng, D., & Xu, G. (2024) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2024.1431815 · Cited by 84
Global Adaptive Transformer for Cross-Subject Enhanced EEG Classification
Song, Y., Zheng, Q., Wang, Q., Gao, X., & Heng, P. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3285309 · Cited by 68
“[24] presented a Riemannian geometry framework to center the covariance matrices of every domain with respect to a reference covari-”
Roy, S., Chowdhury, A., McCreadie, K. A., & Prasad, G. (2020) · Frontiers in Neuroscience · doi:10.3389/fnins.2020.00918 · Cited by 71
“In a recent study, a Riemannian geometry-based approach is successfully applied for cross-subject and cross-session transfer learning which significantly improved BCI performance (Zanini et al., 2018; Gaur et al., 2019a).”
MethodLi, F., Xia, Y., Wang, F., Zhang, D., Li, X., & He, F. (2020) · Applied Sciences · doi:10.3390/app10051804 · Cited by 64
“However, one of the methods with the most potential is Riemannian Geometry method [19–21].”
MethodMotor imagery EEG decoding using manifold embedded transfer learning
Cai, Y., She, Q., Ji, J., Ma, Y., Zhang, J., & Zhang, Y. (2022) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2022.109489 · Cited by 53
Long-Term BCI Training of a Tetraplegic User: Adaptive Riemannian Classifiers and User Training
Benaroch, C., Sadatnejad, K., Roc, A., Appriou, A., Monseigne, T., Pramij, S., Mladenović, J., Pillette, L., Jeunet, C., & Lotte, F. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.635653 · Cited by 65
“To do so, we used an adaptive rebias FgMDM classifier (Zanini et al., 2017; Kumar et al., 2019).”
MethodTowards Adaptive Classification using Riemannian Geometry approaches in Brain-Computer Interfaces
Kumar, S., Yger, F., & Lotte, F. (2019) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/iww-bci.2019.8737349 · Cited by 64
“[6] proposed a transfer learning based framework to align the covariance matrices,”
BackgroundInfluentialMDTL: A Novel and Model-Agnostic Transfer Learning Strategy for Cross-Subject Motor Imagery BCI
Li, A., Wang, Z., Zhao, X., Xu, T., Zhou, T., & Hu, H. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3259730 · Cited by 58
“Since the early proposal, MFAR and RA-MDRM were not applied on dataset Lee2019.”
MethodInfluentialKaya, M., & Hajimirza, S. (2019) · Scientific Reports · doi:10.1038/s41598-019-41316-9 · Cited by 50
Cross-subject EEG emotion classification based on few-label adversarial domain adaption
Wang, Y., Liu, J., Ruan, Q., Wang, S., & Wang, C. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115581 · Cited by 53
Multi-Source Transfer Learning for EEG Classification Based on Domain Adversarial Neural Network
Liu, D., Zhang, J., Wu, H., Liu, S., & Long, J. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3219418 · Cited by 53
“[30] transformed the covariance matrices of every session/subject, and applied standard minimum distance to the classifier for cross-subject motor imagery tasks.”
MethodDomain Adaptation with Source Selection for Motor-Imagery based BCI
Jeon, E., Ko, W., & Suk, H. (2019) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/iww-bci.2019.8737340 · Cited by 52
“In recent years, domain adaptation, a case of transfer learning, has drawn increasing attention in various fields, where machine learning plays a core role, to overcome the difference in distributions between training and test samples [5], [6].”
BackgroundSub-band target alignment common spatial pattern in brain-computer interface
Zhang, X., She, Q., Chen, Y., Kong, W., & Mei, C. (2021) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2021.106150 · Cited by 50
Meta Learn on Constrained Transfer Learning for Low Resource Cross Subject EEG Classification
Duan, T., Shaikh, M. A., Chauhan, M., Chu, J., Srihari, R. K., Pathak, A., & Srihari, S. N. (2020) · IEEE Access · doi:10.1109/access.2020.3045225 · Cited by 51
“(RA)-MDRM is proposed in [24], where covariance matrix of each session/subject is centered with respect to a reference matrix, making data from different session/subjects comparable, and forms a calibration-less BCI classifier.”
MethodHuang, X., Xu, Y., Hua, J., Yi, W., Yin, H., Hu, R., & Wang, S. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.733546 · Cited by 56
“In the translation phase, as in Zanini et al. (2018), the source labeled data C sl and the target data C T = C Tl ∪ C Tu are separately re-centered around the identity matrix using the resting activity of each session to compute the Riemannian means of different domains.”
BackgroundMethodMultisource Wasserstein Adaptation Coding Network for EEG emotion recognition
Zhu, L., Ding, W., Zhu, J., Xu, P., Liu, Y., Yan, M. G., & Zhang, J. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103687 · Cited by 49
Transfer learning promotes acquisition of individual BCI skills
Kumar, S., Alawieh, H., Rácz, F. S., Fakhreddine, R., & Millán, J. D. R. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae076 · Cited by 62
“Having demonstrated transfer learning with Riemannian MDM decoders, we also investigated the adaptability of the GR framework to common spatial pattern-based (CSP) classifiers, which is widely used in MI – BCIs (35, 36).”
BackgroundMethodInfluentialMulti-source manifold feature transfer learning with domain selection for brain-computer interfaces
She, Q., Cai, Y., Du, S., & Chen, Y. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.124 · Cited by 44
Beyond Supervised Learning for Pervasive Healthcare
Gu, X., Deligianni, F., Han, J., Liu, X., Chen, W., Yang, G., & Lo, B. P. L. (2023) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2023.3296938 · Cited by 52
“In fact, the poor generalization performance in cross-subject settings has been noted in many healthcare studies [21], [54], [55], [56], [57].”
BackgroundComparison of multi-class motor imagery classification methods for EEG signals
Nikita, M., Kumar, S., Agarwal, P., & Bharti, M. (2022) · International Research Journal on Advanced Science Hub · doi:10.47392/irjash.2022.073 · Cited by 40
Liu, W., Guo, C., & Gao, C. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121612 · Cited by 55
CNN With Large Data Achieves True Zero-Training in Online P300 Brain-Computer Interface
Lee, J., Won, K., Kwon, M., Jun, S. C., & Ahn, M. (2020) · IEEE Access · doi:10.1109/access.2020.2988057 · Cited by 44
“In order to capture such stationary features, information geometry, such as Riemannian geometry, has also been tried to help increase performance and to reduce calibration time [17], [18].”
BackgroundFang, W., Wu, D., Love, P. E. D., Ding, L., & Luo, H. (2022) · Advanced Engineering Informatics · doi:10.1016/j.aei.2022.101729 · Cited by 42
The Riemannian Potato Field: A Tool for Online Signal Quality Index of EEG
Barthélemy, Q., Mayaud, L., Ojeda, D., & Congedo, M. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2893113 · Cited by 42
“posed to cope with this problem [14], [15].”
BackgroundMethodSelf-citationKhalil, K., Asgher, U., & Ayaz, Y. (2022) · Scientific Reports · doi:10.1038/s41598-022-06805-4 · Cited by 44
“In last few years, various researchers have tested different transfer learning approaches on EEG-based BCI 20,32–34 .”
BackgroundMethodLiang, Y., & Ma, Y. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.102101 · Cited by 43
Transfer Learning Based on Optimal Transport for Motor Imagery Brain-Computer Interfaces
Peterson, V., Nieto, N., Wyser, D., Lambercy, O., Gassert, R., Milone, D. H., & Spies, R. D. (2021) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2021.3105912 · Cited by 43
Low dimensional subject representation based transfer learning in eeg decoding
Jeng, P.-Y., Wei, C.-S., Jung, T.-P., & Wang, L.-C. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3025865 · Cited by 35
“First, the baseline-aligning-based transformation method aligns the features of data by removing subjectspecific baselines so that the model can be trained from all the aligned data [24], [25], [28].”
MethodResultLightweight Source-Free Transfer for Privacy-Preserving Motor Imagery Classification
Zhang, W., & Wu, D. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2022.3193731 · Cited by 40
“Data alignment aligns the covariance matrices of different subjects in the Euclidean space [16], [17], Riemannian space [15], [41], or tangent space [19].”
BackgroundImproving NeuCube spiking neural network for EEG-based pattern recognition using transfer learning
Wu, X., Feng, Y., Lou, S., Zheng, H. R., Hu, B., Hong, Z., & Tan, J. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.01.087 · Cited by 34
Gao, W., Yu, T., Yu, J.-G., Gu, Z., Li, K., Huang, Y., Yu, Z. L., & Li, Y. (2021) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2021.3083548 · Cited by 42
T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs
Li, S., Wang, Z., Luo, H., Ding, L., & Wu, D. (2023) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2023.3303289 · Cited by 37
“For multi-channel EEG signals, Riemannian geometry-based approach [11] and Euclidean alignment (EA) [12] have demonstrated outstanding performance.”
BackgroundMulti-Source Decentralized Transfer for Privacy-Preserving BCIs
Zhang, W., Wang, Z., & Wu, D. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3207494 · Cited by 42
Liang, Z., Zheng, Z., Chen, W., Pei, Z., Wang, J., & Chen, J. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106311 · Cited by 37
Reducing Calibration Efforts in RSVP Tasks With Multi-Source Adversarial Domain Adaptation
Wei, W., Qiu, S., Ma, X., Li, D., Wang, B., & He, H. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.3023761 · Cited by 34
“In [24], [28], and [29], the authors also used a similar Riemannian manifold alignment method for EEG”
MethodZhu, L., Yang, J., Ding, W., Zhu, J., Xu, P., Ying, N., & Zhang, J. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3101684 · Cited by 33
Röhr, V., Blankertz, B., Radtke, F. M., Spies, C., & Koch, S. (2022) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2022.911088 · Cited by 31
“Therefore, we find a reference point suitable for our training data and project the training and test set to the corresponding tangent space (Figure 3A; Congedo et al., 2017; Zanini et al., 2018).”
BackgroundA Multi-Source Transfer Joint Matching Method for Inter-Subject Motor Imagery Decoding
Wei, F., Xu, X., Jia, T., Zhang, D., & Wu, X. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3243257 · Cited by 33
“the information on different levels of instances, features, and models [5], [6], [12].”
BackgroundMethodResultInfluentialAhuja, C. K., & Sethia, D. (2024) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2024.1421922 · Cited by 41
Kalaganis, F. P., Laskaris, N., Chatzilari, E., Nikolopoulos, S., & Kompatsiaris, I. Y. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2912066 · Cited by 32
RNeuMark: A Riemannian EEG Analysis Framework for Neuromarketing
Georgiadis, K., Kalaganis, F. P., Oikonomou, V. P., Nikolopoulos, S., Laskaris, N., & Kompatsiaris, I. Y. (2022) · Brain Informatics · doi:10.1186/s40708-022-00171-7 · Cited by 33
“[37] proposed an alignment process operating in the Riemannian framework with the scope of eliminating the phenomenon of “mis-placed” SCMs that will in turn allow the development of competent classifiers.”
BackgroundPan, L., Wang, K., Xu, L., Sun, X., Yi, W., Xu, M., & Ming, D. (2023) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad0a01 · Cited by 36
“…such as minimum distance to Riemannian mean (MDRM) and Riemannian-space alignment (RA), proposed by Barachant et al [31] and Zanini et al [32], has provided a new approach to address the variability in EEG. Unlike traditional CSP algorithms that use Euclidean distance for mean covariance…”
Individual Similarity Guided Transfer Modeling for EEG-based Emotion Recognition
Zhang, X., Liang, W., Ding, T., Pan, J., Shen, J. G., Huang, X., & Gao, J. (2019) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm47256.2019.8982972 · Cited by 37
“to help the model calibration for a new individual, is a promising solution for this challenge [15]–[17].”
BackgroundZhao, X., Zhao, J., Liu, C., & Cai, W. (2020) · BioMed Research International · doi:10.1155/2020/7285057 · Cited by 40
“It is not a deep learning method, so as AT-GM-b in [10].”
BackgroundInfluentialHehenberger, L., Kobler, R. J., Lopes-Dias, C., Srisrisawang, N., Tumfart, P., Uroko, J. B., Torke, P. R., & Müller-Putz, G. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.635777 · Cited by 38
“, 2018), or sometimes other users (Kobler and Scherer, 2016; Zanini et al., 2018).”
MethodXu, Y., Huang, X., & Lan, Q. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.779231 · Cited by 36
“After RA, the aligned covariance matrices are usually input to an MDM classifier (Zanini et al., 2018; Rodrigues et al., 2019).”
BackgroundMethodInfluentialGao, Y., Liu, Y., She, Q., & Zhang, J. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3218453 · Cited by 35
“first proposed to utilize a Riemann alignment (RA) framework for EEG signals [5], which was used to align EEG covariance matrices from different topics.”
MethodLiao, J. J., Luo, J. J., Yang, T., So, R. Q., & Chua, M. C. H. (2020) · Brain-Computer Interfaces · doi:10.1080/2326263x.2020.1801112 · Cited by 33
Xu, L., Xu, M., Ma, Z., Wang, K., Jung, T., & Ming, D. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac1ed2 · Cited by 34
Colorectal cancer diagnosis from histology images: A comparative studyPreprint
Malik, J., Serkan Kiranyaz, B., Kunhoth, S., İnce, T., Al-Maadeed, S. A., Hamila, R., & Gabbouj, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.11210 · Cited by 34
“Transfer learning refers to extracting knowledge learnt from solving a source problem and applying it to an unrelated target task [41], [42].”
BackgroundChannel reflection: Knowledge-driven data augmentation for EEG-based brain–computer interfaces
Wang, Z., Li, S., Luo, J., Liu, J., & Wu, D. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106351 · Cited by 35
Double Stage Transfer Learning for Brain–Computer Interfaces
Gao, Y., Li, M., Peng, Y. F., Fang, F. Z., & Zhang, Y. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3241301 · Cited by 30
“[16] proposed a Riemannian alignment (RA) approach, which centers the EEG covariance matrices of each subject with respect to the reference matrix.”
BackgroundHuang, J., Li, Z., Xia, H., Chen, G., & Meng, Q. (2022) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2022.3198172 · Cited by 28
“The design idea of the target network is to make part or all of the structure of the network refer to the source network, freeze the important feature layer parameters of the source network, use the target gesture set for training, and fine-tune the parameters of the following layers, so as to reduce the learning time…”
MethodGao, W., Huang, W., Li, M., Gu, Z., Pan, J., Yu, T., Yu, Z. L., & Li, Y. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3259991 · Cited by 29
Wang, Y., Wang, J., Wang, W., Su, J., Bunterngchit, C., & Hou, Z. (2024) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2024.3474049 · Cited by 34
“Zanini et al. [22] proposed a Riemannian alignment (RA) approach, which adopted the covariance matrix of EEG signals to represent data based on the Riemannian manifold.”
An Online Data Visualization Feedback Protocol for Motor Imagery-Based BCI Training
Duan, X., Xie, S., Xie, X., Obermayer, K., Cui, Y., & Wang, Z. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.625983 · Cited by 24
“Congedo et al. (2017) introduced Riemannian geometry to EEG classifications such as Fisher Geodesic Discriminant Analysis, Riemannian kernel-SVM, and transfer learning (Barachant et al., 2012, 2013b; Zanini et al., 2018).”
MethodWei, F., Xu, X., Li, X., & Wu, X. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3450010 · Cited by 24
Neural correlates of user learning during long-term BCI training for the Cybathlon competition
Tortora, S., Beraldo, G., Bettella, F., Formaggio, E., Rubega, M., Felice, A. D., Masiero, S., Carli, R., Petrone, N., Menegatti, E., et al. (2022) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-022-01047-x · Cited by 26
“This finding was not completely unexpected since the use of the signal covariance matrices as features of interest for classification of mental tasks is becoming increasingly popular in BCI applications [56–59] and they have been also exploited by a team during the Cybathlon competitions [35].”
ResultTransformed common spatial pattern for motor imagery-based brain-computer interfaces
Ma, Z., Wang, K., Xu, M., Yi, W., Xu, F., & Ming, D. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1116721 · Cited by 28
Dual selections based knowledge transfer learning for cross-subject motor imagery EEG classification
Luo, T.-J. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1274320 · Cited by 25
Chen, X., Wang, Z., & Wu, D. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3391936 · Cited by 31
Spatial filtering based on Riemannian distance to improve the generalization of ErrP classification
Cruz, A., Pires, G., & Nunes, U. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.10.078 · Cited by 22
Motor Imagery EEG Classification Based on Transfer Learning and Multi-Scale Convolution Network
Chang, Z., Zhang, C., & Li, C. (2022) · Micromachines · doi:10.3390/mi13060927 · Cited by 24
“To solve the cross-subject problem of transfer learning, in [24,25], the data in Riemannian space and European space, respectively, were aligned and transformed, which resulted in similar data distribution of different subjects, significantly improving the problem of transfer learning.”
Reichert, C., Dürschmid, S., Bartsch, M. V., Hopf, J., Heinze, H., & Hinrichs, H. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/abb692 · Cited by 23
“across subjects commonly results in a substantially reduced accuracy of the decoder [33, 43, 44].”
BackgroundLi, Y., Wei, Q., Chen, Y., & Zhou, X. (2021) · IEEE Access · doi:10.1109/access.2020.3048683 · Cited by 24
“The reference matrices of different subjects can be approximated as an identity matrix [23].”
BackgroundTang, X., Li, X., Li, W., Hao, B., Xie, Y., & Dang, X. (2021) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2021.3082648 · Cited by 26
“6) TL: A Riemannian geometry framework (RGF) [14].”
BackgroundResultLiang, Z., Zheng, Z., Chen, W., Pei, Z., Wang, J., & Chen, J. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105556 · Cited by 21
Qu, T., Jin, J., Xu, R., Wang, X., & Cichocki, A. S. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac9338 · Cited by 23
“The SCM is a kind of symmetry positive definite matrix, which lies in the differentiable Riemannian manifold [49].”
Tangent space alignment: Transfer learning for Brain-Computer Interface
Bleuzé, A., Mattout, J., & Congedo, M. (2022) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2022.1049985 · Cited by 35
“It is important to do so, however, since, as it has been found in previous studies, there is a large gap between “good” and “bad” subjects in transfer learning accuracy (Zanini et al., 2018; Rodrigues et al., 2019).”
ResultSelf-citationIntra- and Inter-Subject Common Spatial Pattern for Reducing Calibration Effort in MI-Based BCI
Wei, Q., & Ding, X. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3236372 · Cited by 23
“With respect to the latter, Zanini et al. [22] proposed a Riemannian alignment (RA) method to align the SCMs of different subjects, and the aligned SCMs can be used as features to be directly classified by the minimum distance to Riemannian mean (MDRM) classifier.”
BackgroundMethodMetaBCI: An open-source platform for brain–computer interfaces
Mei, J., Luo, R., Xu, L., Zhao, W., Wen, S., Wang, K., Xiao, X., Meng, J., Huang, Y., Tang, J., et al. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107806 · Cited by 29
Time–space–frequency feature Fusion for 3-channel motor imagery classification
Miao, Z., & Zhao, M. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105867 · Cited by 23
Class-specific regularized joint distribution alignment for unsupervised domain adaptation
Luo, T.-J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.107877 · Cited by 22
Metadata
- Authors
- Zanini, P., Congedo, M., Jutten, C., Said, S., & Berthoumieu, Y.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- Venue
- IEEE Transactions on Biomedical Engineering
- Published
- 2018-05
- Volume
- 65
- Issue
- 5
- Pages
- 1107-1116
- ISSN
- 0018-9294 (ISSN-L)
- 1558-2531
- OpenAlex
- W2746829572
- Cited by
- 412
- References
- 38
- Citations by year
- 2026: 48 · 2025: 53 · 2024: 78 · 2023: 53 · 2022: 62 · 2021: 37 · 2020: 49 · 2019: 25 · 2018: 7
- FWCI
- 12.72
- Type
- journal article
- Language
- en
- Open access
- green
- hal.science
- Locations
- IEEE Transactions on Biomedical Engineering (publishedVersion)
- PubMed (publishedVersion)
- HAL (submittedVersion)
- HAL (submittedVersion, other-oa)
- Funders
- ERC (2012-ERC-AdG-320684)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Human-Computer Interaction › Gaze Tracking and Assistive Technology
- Keywords
- transfer learning, brain-computer interface, EEG classification, cross-subject classification, Riemannian geometry, symmetric positive definite matrices, covariance matrix, affine transformation, minimum distance classifier
- MeSH terms
- Machine Learning, Electroencephalography, Humans, Models, Theoretical, Databases, Factual, Brain-Computer Interfaces
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.