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
Items 201–300 of 411
Cernera, S., Gemicioglu, T., Berezutskaya, J., Csáky, R., Verwoert, M., Polyakov, D., Papadopoulos, S., Spagnolo, V., Gonzalez-Astudillo, J., Kumar, S., et al. (2025) · Journal of Neural Engineering · doi:10.1088/1741-2552/adb335 · Cited by 8
“These frameworks are founded on Riemannian Geometry Classifiers, leveraging affine invariant transforms to match covariate shifts on the Riemannian manifold [32, 33], thereby reducing non-stationarities in real-time and providing contingent closed-loop feedback.”
Yang, S., Huang, Z., & Luo, T.-J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127312 · Cited by 8
Sadatnejad, K., Roc, A., Pillette, L., Appriou, A., Monseigne, T., & Lotte, F. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053101 · Cited by 7
“At the machine learning level, one approach consists in matching the statistical distributions of different datasets - corresponding to different sessions or subjects - using geometrical transformations such as translation, scaling and rotation [8, 9, 10].”
BackgroundManifold Trial Selection to Reduce Negative Transfer in Motor Imagery-based Brain–Computer Interface
Liang, Z., Zheng, Z., Chen, W., Wang, J., Zhang, J., Chen, J., & Chen, Z. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9636137 · Cited by 8
“Zanini et al. [20] proposed a center alignment method based on Riemannian space, called Riemann alignment (RA).”
MethodEnd-to-end P300 BCI using Bayesian accumulation of Riemannian probabilities
Barthélemy, Q., Chevallier, S., Bertrand-Lalo, R., & Clisson, P. (2022) · Brain-Computer Interfaces · doi:10.1080/2326263x.2022.2140467 · Cited by 16
A transfer learning-based feedback training motivates the performance of SMR-BCI
Duan, X., Xie, S., Lv, Y., Xie, X., Obermayer, K., & Yan, H. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/acaee7 · Cited by 11
“In fact, the physiological and psychological states, environment, instrument (channel locations) and subjects’ mental strategies may change quickly, leading to the non-stationarity of EEG data [31].”
BackgroundMethodZois, E. N., Said, S., Tsourounis, D., & Alexandridis, A. (2023) · Pattern Recognition Letters · doi:10.1016/j.patrec.2023.02.002 · Cited by 11
Self-citationGeometric means of quasi-Toeplitz matrices
Bini, D. A., Iannazzo, B., & Meng, J. (2023) · BIT Numerical Mathematics · doi:10.1007/s10543-023-00962-2 · Cited by 8
“More recent applications includemachine learning [20, 42], brain-computer interface [45, 47], and network analysis [15].”
MethodOptimal Transport on the Manifold of SPD Matrices for Domain AdaptationPreprint
Yair, O., Dietrich, F., Talmon, R., & Kevrekidis, I. G. (2019) · arXiv (Cornell University) · Cited by 7
Dimitriadis, S. I. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108862 · Cited by 8
Transfer Learning of Surrogate Models via Domain Affine Transformation
Pan, S., Vermetten, D., López‐Ibáñez, M., Bäck, T., & Wang, H. (2024) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3638529.3654032 · Cited by 6
“Several works have explored using an a � ne model for transfer learning outside the context of GPR. Zanini et al. [50] leveraged the a � ne invariance of Riemannian geometry to enhance transfer learning in brain-computer interfaces (BCI) by aligning the spatial covariance matrices of EEG signals…”
Kilani, S., Aghili, S. N., Fathi, Y., & Sburlea, A. I. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1360709 · Cited by 6
Calibration-Free Transfer Learning for EEG-Based Cross-Subject Motor Imagery Classification
Wang, Y., Wang, J., Wang, W., Su, J., & Hou, Z. (2023) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case56687.2023.10260440 · Cited by 7
“[12] proposed a Riemannian alignment approach, which adopted the covariance matrix of EEG signals to represent data based on the Riemannian manifold.”
MethodZhu, F., Cai, J., Zheng, H., Liang, Z., & Zhang, Y. (2024) · Review of Scientific Instruments · doi:10.1063/5.0208524 · Cited by 7
Channel and Trials Selection for Reducing Covariate Shift in EEG-based Brain-Computer Interfaces
He, H., & Wu, D. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8914414 · Cited by 7
“[23] first proposed RA to align covariance matrices of trials from different sessions/subjects in the Riemannian space.”
BackgroundMethodInfluentialSingle Electrode Energy on Clinical Brain–Computer Interface Challenge
de Souza, G. H., Bernardino, H. S., & Vieira, A. B. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102993 · Cited by 7
Human-to-Robot Manipulability Domain Adaptation with Parallel Transport and Manifold-Aware ICP
Reithmeir, A., Figueredo, L., & Haddadin, S. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981796 · Cited by 6
“In [23], a probabilistic GMM on the manifold is proposed for classification where improvements are obtained by the introduction of an additional affine transformation.”
MethodInfluentialTransfer Learning for P300 Brain-Computer Interfaces by Joint Alignment of Feature Vectors
Altindış, F., Banerjee, A., Phlypo, R., Yılmaz, B., & Congedo, M. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3299837 · Cited by 9
“The first attempt has recentered the covariance matrices estimated on the EEG trials of each subject using parallel-transport on the Riemannian manifold of symmetric positive-definite (SPD) matrices [23].”
BackgroundMethodResultInfluentialSelf-citationCross-subject decoding of eye movement goals from local field potentials
Angjelichinoski, M., Choi, J. S., Banerjee, T., Pesaran, B., & Tarokh, V. (2020) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab6df3 · Cited by 7
“Similar to spatial filtering, transfer learning in the Riemannian manifold of the spatial covariance matrices has been also considered in [11] where the authors assume that different subjects/sessions/tasks induce shifts in the trial covariance matrix with respect to a resting state covariance matrix which is further…”
BackgroundWu, X., Ouyang, R., & Zhang, C. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.107345 · Cited by 7
Liu, D. H., Kumar, S., Alawieh, H., Rácz, F. S., & Millán, J. D. R. (2025) · Journal of Neural Engineering · doi:10.1088/1741-2552/ada980 · Cited by 7
“We used AIRM metric to embed the manifold of covariance matrices, which ensured that the distribution of offline covariances remained undistorted in the re-centered space [63].”
Liang, Y., Meng, M., Gao, Y., & Xi, X. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130875 · Cited by 5
EDANet: Efficient domain-adaptive attention neural network for EEG classification of motor imagery
Yang, J., Wang, L., Cai, W., Zhang, L., Xie, C., & Wang, Z. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128783 · Cited by 5
Jagadish, B., Mishra, P., Kiran, M. P. R. S., & Rajalakshmi, P. (2019) · Neural Computation · doi:10.1162/neco_a_01223 · Cited by 5
Gupta, E., & Sivakumar, R. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892115 · Cited by 6
“…have been proposed throughout the literature, spanning different techniques for artifact removal [13] [14], using improved spatial filters [15], combining EEG with fNIRS to compensate for low spatial resolution [16], using domain adaptation techniques for better signal generalization [17], etc.”
MethodCai, Z., Gao, Y., Fang, F. Z., Zhang, Y., & Du, S. (2024) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2024.110332 · Cited by 5
Kulwa, F., Tai, P., Sarwatt, D. S., Asogbon, M. G., Khushaba, R. N., Oyemakinde, T. T., Aboyeji, S. T., Li, G., Samuel, O. W., & Li, Y. (2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2025.3592183 · Cited by 5
“It describes how one can traverse (project) from S 1 towards S r and vice versa [23].”
Mostajeran, C., Grußler, C., & Sepulchre, R. J. (2020) · SIAM Journal on Matrix Analysis and Applications · doi:10.1137/19m1273475 · Cited by 6
“Specific applications include brain-computer interface (BCI) systems [45, 55], radar data processing [3], and diffusion tensor imaging (DTI) [19].”
BackgroundLei, W., Ma, Z., Liu, S., & Lin, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3124028 · Cited by 7
“[30] proposed a Riemannian geometry framework and a classifier for BCI.”
MethodDivergence Framework for EEG based Multiclass Motor Imagery Brain Computer InterfacePreprint
Kumar, S., Reddy, T. K., & Behera, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.07457 · Cited by 5
“Zanini et al. [22] proposed a framework to optimize the classification performance based on an Affine transformation strategy on riemannian manifolds.”
MethodTransfer Learning for Brain-Computer Interfaces: A Complete PipelinePreprint
Wu, D., Peng, R., Huang, J., & Zeng, Z. (2020) · arXiv (Cornell University) · Cited by 6
Editorial: Datasets for Brain-Computer Interface Applications
Daly, I. P., Matran‐Fernandez, A., Valeriani, D., Lebedev, M., & Kübler, A. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.732165 · Cited by 5
“…an excellent set of resources for BCI researchers and have been widely used by numerous researchers to develop and evaluate new signal processing and classification methods (Arvaneh et al., 2013; Ghaemi et al., 2017; Lotte et al., 2018; Sakhavi et al., 2018; Zanini et al., 2018; Zhang et al., 2018).”
BackgroundMotor imagery decoding network with multisubject dynamic transfer
Li, Z., Li, M., & Yang, Y. (2025) · Brain Informatics · doi:10.1186/s40708-025-00267-w · Cited by 5
“Nine representative methods were compared, including traditional methods such as FBCSP [32], traditional transfer learning methods RA-MDRM [33] and EA-CSP-LDA [34], deep learning (DL) methods EEGNet [14] and ConvNet [13], the supervised domain adaptation method MI-DABAN [25], and unsupervised…”
Cross-Subject Mindfulness Meditation EEG Decoding
Karaiskou, A.-Ι., Varon, C., Alaerts, K., & Vos, M. D. (2023) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine58569.2023.10405733 · Cited by 4
“If Σ i and Σ j are two covariance matrices with i ̸ = j from the same subject, then the Riemannian distance metric, called geodesic [16], between those two matrices is defined as: with λ k ( k = 1 , 2 , ..., C ) the real eigenvalues of Σ − 1 i Σ j .”
BackgroundMethodInfluentialTang, C. L., Gao, T., Wang, G., & Chen, B. (2024) · Cognitive Neurodynamics · doi:10.1007/s11571-024-10085-1 · Cited by 6
“Recently, the use of Riemannian geometry in EEG and MEG decoding is attracting increasing attention due to the accumulation of studies on its accuracy, robustness and generalization capabilities (Congedo et al. 2017; Chu et al. 2020; Qu et al. 2022).”
Bai, G., Jin, J., Xu, R., Wang, X., & Cichocki, A. S. (2024) · Cognitive Neurodynamics · doi:10.1007/s11571-023-10053-1 · Cited by 4
“Zanini et al. (Zanini et al. 2017) proposed a Riemannian alignment (RA) framework to align the EEG covariance matrices from different subjects.”
Improved motor imagery training for subject’s self-modulation in EEG-based brain-computer interface
Xu, Y., Jie, L., Jian, W., Yi, W., Yin, H., & Peng, Y. (2024) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2024.1447662 · Cited by 4
Cross-subject domain adaptation for classifying working memory load with multi-frame EEG images
Chen, J., Li, S., & Pi, D. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07748-z · Cited by 5
“Then, the participates can only see a cross in the middle of the screen for a longer period.”
Vadivu, P. B., & Sundararajan, J. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7718-x · Cited by 4
“Also, BCI is characterized as a framework that influences conceivable to use to neuroprosthesis, electromechanical gadgets, and PCs with the idea, without utilizing physical power, without using engine frameworks [25].”
MethodRetractedZhan, Q., Wang, L., Ren, L., & Huang, X. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106220 · Cited by 4
Dual Head and Dual Attention in Deep Learning for End-to-End EEG Motor Imagery Classification
Xu, M., Yao, J., & Ni, H. (2021) · Applied Sciences · doi:10.3390/app112210906 · Cited by 4
“Researchers in [12] utilized a scheme for transfer learning to use the Riemannian geometry of symmetric and positive definite(SPD) matrices, tightly connected to the BMI transfer learning work.”
MethodGaussian distributions on Riemannian symmetric spaces, random matrices, and planar Feynman diagramsPreprint
Heuveline, S., Said, S., & Mostajeran, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.08953 · Cited by 4
Self-citationZhao, Z., Cao, Y., Yu, H., & Huang, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129248 · Cited by 3
Mishra, R., Agrawal, R. K., & Kirar, J. S. (2025) · Cognitive Neurodynamics · doi:10.1007/s11571-025-10337-8 · Cited by 3
“(Zanini et al. 2017 ) introduced a Riemannian alignment (RA) approach that uses the covariance matrix of EEG signals to represent data on the Riemannian manifold.”
A survey of neural signal decoding based on domain adaptation
Li, S., Tang, Z., Li, M., Yang, L., & Shang, Z. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131653 · Cited by 6
Yun, G. A. O., & Deng, H. (2026) · Alexandria Engineering Journal · doi:10.1016/j.aej.2026.03.045 · Cited by 4
Jiang, X., Yang, L., Xu, Y., Song, Z., Wang, Y., & He, Y. (2026) · Alexandria Engineering Journal · doi:10.1016/j.aej.2026.04.006 · Cited by 3
Inter-session Transfer Learning in MI Based BCI for Controlling a Lower-Limb Exoskeleton
Ferrero, L., Quiles, V., Ortíz, M., Juan, J. V., Iáñez, E., & Azorín, J. M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-06527-9_24 · Cited by 3
Parameter transfer and Riemannian space coordinate alignment for EEG intention recognition
Li, X., Tang, X., Liu, J., Liu, Q., Wang, H., & Liu, K. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106044 · Cited by 3
Weighted common spatial pattern based adaptation regularization for multi-source EEG time series
Han, R., Li, Z., Zhang, Y., Meng, X., Wang, Z., & Dong, H. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109680 · Cited by 3
Prototypical Contrastive Domain Adaptation Network for Nonstationary EEG Classification
Li, D., Xu, J., Zhang, Y., Ma, D., & Wang, J.-H. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3476618 · Cited by 5
Enhancing EEG-Based Neuromarketing with Attention mechanism and Riemannian Features
Kalaganis, F. P., Georgiadis, K., Nousias, G., Oikonomou, V. P., Laskaris, N. A., Nikolopoulos, S., & Kompatsiaris, I. Y. (2025) · IEEE International Conference on Digital Signal Processing (DSP) · doi:10.1109/dsp65409.2025.11075055 · Cited by 3
“Then, in an attempt to alleviate the well-known issue of inter-subject variability that obscures EEG recordings, the Riemannian Alignment approach is followed [18].”
Unsupervised MEG classification by Riemannian Geometry and class centroid matching
Ye, H., Yu, T., Liu, S., & Huang, Z. (2020) · International Conference on Artificial Intelligence and Computer Engineering (ICAICE) · doi:10.1109/icaice51518.2020.00090 · Cited by 4
Riemannian geometry-based detection of slow cortical potentials during movement preparation
Rácz, F. S., Fakhreddine, R., Kumar, S., & Millán, J. D. R. (2023) · International IEEE/EMBS Conference on Neural Engineering · doi:10.1109/ner52421.2023.10123857 · Cited by 3
“Furthermore, in order to align the distributions of the covariance matrices from training and validation sets, all matrices were re-centered around the identity matrix [11], [15].”
MethodAn adaptive cross-class transfer learning framework with two-level alignment
Xu, D., Sun, Y.-J., & Li, M. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105155 · Cited by 3
Yang, H., Wu, F., Zhang, N., Chen, C., Wei, A., Peng, F., & Li, Z. (2023) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar58764.2023.10249485 · Cited by 3
Brain computer interfaces in computer science and engineering areas: a systematic study
Katona, J., Kővári, A., Guzsvinecz, T., Szűcs, J., Demeter, R., & Szücs, V. (2023) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v32.i3.pp1755-1765 · Cited by 4
“[49] investigated the problem of transfer learning in BCIs.”
BackgroundWang, X., Li, B., Lin, Y., & Gao, X. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad2710 · Cited by 3
“Zanini et al [19] exploited Riemannian alignment to deal with the inter-subject variability, but non-target trials were needed to construct a reference matrix, which increased system complexity.”
Luo, T.-J. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18648-4 · Cited by 4
“To evaluate the feasibility and effectiveness of the proposed CA-CSP-SSMM method, this paper selected five methods for comparison: (1) CA-MDM [15]: This method employs the CA strategy to align the covariance matrix of each MI-EEG trial.”
InfluentialMeta-Learning for EEG Motor Imagery Classification
Yu, J. Y., Duan, L., Ji, H., Li, J., & Pang, Z. (2024) · Computing and Informatics · doi:10.31577/cai_2024_3_735 · Cited by 3
Predicting cognitive load with EEG using Riemannian geometry-based features
Kremer, I., Halimi, W., Walshe, A., Cerf, M., & Mainar, P. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ad680b · Cited by 4
“Spatial covariance matrices were computed in line with existing protocols [10, 46, 60, 62].”
GRAFT: Unsupervised Adaptation to Resizing for Detection of Image Manipulation
Darmet, L., Wang, K., & Cayre, F. (2020) · IEEE Access · doi:10.1109/access.2020.2980992 · Cited by 3
“In [24], [25], the authors use covariance”
BackgroundVishnupriya, R., Robinson, N., & Reddy, M. R. (2024) · Brain-Computer Interfaces · doi:10.1080/2326263x.2024.2347790 · Cited by 3
Kostas, D., & Rudzicz, F. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.12.17.423197 · Cited by 5
Ahmed, S. G., Ambali Parambil, M. M., Damseh, R., Bouktif, S., Alnajjar, F., & Belkacem, A. N. (2026) · Frontiers in Systems Neuroscience · doi:10.3389/fnsys.2026.1840121 · Cited by 2
“For instance, methods like Riemannian Alignment (RA) operate on covariance matrices within the Riemannian manifold (Zanini et al., 2017).”
Liu, Y., Qin, L., Chen, X., Jeannès, R. L. B., Coatrieux, J.-L., & Shu, H. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3566804 · Cited by 6
The importance of training brain–machine interface skills
Alawieh, H., Kumar, S., & Millán, J. D. R. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-24824-5.00005-3 · Cited by 3
Cross-subject motor imagery classification via transfer Riemannian space-based sparse coding
Yang, Y., & Luo, T.-J. (2025) · International Journal of Intelligent Computing and Cybernetics · doi:10.1108/ijicc-05-2025-0275 · Cited by 2
Characterizing Expectation Mismatch in a Brain-Controlled Upper-Body Rehabilitation Exoskeleton
Kumar, S., Mitra, K., Liu, D. H., Alawieh, H., Rácz, F. S., Gasperina, S. D., Deshpande, A. D., & Millán, J. D. R. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3634889 · Cited by 2
Xiong, W., Ma, L., & Li, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-24466-x · Cited by 2
“…Approaches based on the geometric properties of EEG data distributions, aligning EEG signals to a common feature space using second-order statistics 7 or covariance 6,8,9 , or by balancing distribution discrepancies between source and target domains through trainable hyperparameters 10–12 .”
Cross-domain correlation analysis to improve SSVEP signals recognition in brain-computer interfaces
Hu, K., Wang, Y., Tu, K., Guo, H., & Yan, J. (2025) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ae2772 · Cited by 2
SSAS: Cross-subject EEG-based emotion recognition through source selection with adversarial strategy
Liu, Y., Oung, Q. W., & Lee, H. L. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130843 · Cited by 8
“Therefore, several studies [27, 28, 29, 30, 31] focused on selecting source domain with significant differences from the target domain to reduce their impact on the model.”
Robust Covert Spatial Attention Decoding from Low-Channel Dry EEG by Hybrid AI Model
Kim, D., & Lee, J. (2025) · AI · doi:10.3390/ai7010009 · Cited by 2
“In parallel, we will investigate label-free “baseline” adaptation using eyes-closed resting segments to update normalization statistics (e.g., running mean/variance in normalization layers), thereby mitigating impedance-driven amplitude shifts without requiring task-specific labels [175,178].”
Cyclic deep representation-based domain adaptation for cross-subject motor imagery classification
He, M., Cao, X., & Luo, T.-J. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109762 · Cited by 3
Gao, Y., Ma, Y., Liu, Y., Yin, G., & Qin, Y. (2026) · Cognitive Neurodynamics · doi:10.1007/s11571-026-10427-1 · Cited by 2
“Zanini et al. ( 2017) introduced Riemannian Alignment (RA), aligning covari - ance matrices from different subjects to reduce domain differences.”
Xu, H., Sun, Y., Zhou, Z., Han, C., Huang, J., & Wang, J. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3715901 · Cited by 2
“This creates a gap between static covariance alignment and the dynamic covariance drift observed during test-session evaluation [38], [39].”
Zeng, H., Shen, J., Zheng, W., Song, A., & Liu, J. (2020) · Journal of Healthcare Engineering · doi:10.1155/2020/8829451 · Cited by 2
“For the second-order models above, the ERP template concatenation strategy [26] has also been adopted to build the augmented covariance matrix using the raw EEG trial.”
MethodSemi-supervised Multi-Source Transfer Learning for Motor Imagery Recognition
Gao, C., & Sun, J. (2022) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001422500410 · Cited by 2
Supervised and Semisupervised Manifold Embedded Knowledge Transfer in Motor Imagery-Based BCI
Xu, Y., Yin, H., Yi, W., Huang, X., Jian, W., Wang, C., & Hu, R. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/1603104 · Cited by 4
“Since the covariance matrices belong to a smooth Riemannian manifold of symmetric positive definite (SPD) matrices, they can be viewed as points on the manifold [44].”
BackgroundMethodInfluentialSpatial Feature Regularization and Label Decoupling Based Cross-Subject Motor Imagery EEG Decoding
Zhou, Y., Luo, T.-J., Zhang, X., & Han, T. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8558-6_34 · Cited by 2
Do Weak Brain Signals Get Amplified When Strong Brain Signals are Evoked?
Gupta, E., Chen, C.-Y., & Sivakumar, R. (2024) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops59983.2024.10502941 · Cited by 2
“Xdawn + tangent space and Xdawn + MDM follow a similar signal decoding pipeline which can be summarized as follows (more details can be found in [2] and [30]): • Estimating two sets of xDAWN spatial filters, one for each class (ErrP and non-ErrP), and using these filters to transform the signal…”
BackgroundMethodInfluentialTransfer Learning for P300 Speller: An Alignment Approach for Cross-Subject P300 Data
Liu, M., Ahmad, F., & Beyette, F. R. (2024) · IEEE SoutheastCon · doi:10.1109/southeastcon52093.2024.10500162 · Cited by 3
A Relation Feature Comparison Network for Cross-Domain Recognition of Motion Intention
Xu, J., Li, D., Zhou, P., Zhang, Y., Wang, Z., & Ma, D. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3420350 · Cited by 5
FasterEA-FML for EEG: Federated Meta-learning with Faster Euclidean Space Data Alignment
Yao, M., Chen, W., Xu, T., Zhang, C., Liu, J., Chen, D., & Wang, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5591-2_41 · Cited by 2
Multimodal manifold learning using kernel interpolation along geodesic paths
Katz, O., Lederman, R. R., & Talmon, R. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102637 · Cited by 2
Riemannian Geometry-Based Spatial Filtering (RSF) Method for Motor Imagery EEG Classification
Pan, L., Wang, K., Sun, X., Xu, M., & Ming, D. (2024) · International Conference on Biomedical Signal and Image Processing (ICBIP) · doi:10.1145/3691521.3691529 · Cited by 2
Luo, T.-J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109502 · Cited by 4
Yılmaz, Ç. M. (2025) · Karadeniz Fen Bilimleri Dergisi · doi:10.31466/kfbd.1509850 · Cited by 2
A Fusion Transfer Learning Method of Motor Imagery EEG Signals Based on Riemannian Space
Gao, N., & Yunhui, W. (2022) · 2022 7th International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip55141.2022.9886924 · Cited by 2
Analyzing Data Augmentation Methods for Convolutional Neural Network-based Brain-Computer Interfaces
Faria, G. O. M., de Souza, G. H., Bernardino, H. S., Motta, L. P., & Vieira, A. B. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9891891 · Cited by 3
“To that end, we visualize the covariance matrices of the preprocessed EEG signals with t-SNE [20] using the Riemannian distance, similarly to [21].”
MethodFormative semi-supervised learning based on adaptive combined model for brain–computer interface
Gao, Y., Li, M., Cao, Z., & Meng, M. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01914-6 · Cited by 2
“[34, 38] also shows Riemann’s good generalization ability.”
Task-relevant stimulus design improves P300-based brain–computer interfaces
Kim, J., Cho, Y. S., & Kim, S.-P. (2024) · Journal of Neural Engineering · doi:10.1088/1741-2552/ada0e3 · Cited by 2
“These SPD matrices were represented on the Riemannian manifold and projected onto the tangent space to transform ERP features onto manifolds [37].”
Khabti, J., Al-Ahmadi, S. A., & Soudani, A. (2024) · Sensors · doi:10.3390/s24248127 · Cited by 2
“…approach, with the results demonstrated on the same dataset, as shown in [8]. on this dataset using two approaches: RA-MDRM, detailed in [40], and EA-CSP-LDA The study in [8] also explains and presents the results of the multi-direction transfer-learning (MDTL) strategy applied to the…”
EEG-Based Driver Drowsiness Estimation Using Self-Paced Learning with Label Diversity
Xu, Y., & Wu, D. (2019) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci44817.2019.9002753 · Cited by 2
“[17] proposed a covariance matrices alignment approach that centers the data of every session/subject with respect to the reference covariance matrix at the resting state in the Riemannian space.”
BackgroundCross-subject MEG Transfer Learning by Riemannian Manifold and Feature Subspace Alignment
Liu, S., Yu, T., Huang, Z., & Ye, H. (2020) · International Symposium on Autonomous Systems (ISAS) · doi:10.1109/isas49493.2020.9378879 · Cited by 2
“Zanini proposed a framework called Riemannian Alignment to standardize the covariance matrix by using the resting state trials [8].”
MethodLibert, A., Kerchove, A. V. D., Wittevrongel, B., & Hulle, M. M. V. (2022) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac636a · Cited by 4
“…results in BCI transfer learning have been achieved using Riemannian Geometry and reference EEG signals to transform data from two separate sessions into a common space [51, 57–59], Riemannian geometry has also been used to improve the covariance matrix estimation for beamforming applications [60].”
MethodHyper-Accelerated Learning for Brain-Computer Interfaces via Partial Target-Aware Optimal Transport
Gupta, E., Chen, C.-Y., & Sivakumar, R. (2023) · doi:10.1145/3615592.3616853 · Cited by 3
“[13] improved upon this method by introducing affine transforms which make the data reference across different users identical which improves the accuracy of cross-user generalization.”
MethodA novel transfer algorithm based on time convolution and EEGNet for motor imagery classification
Li, H., Du, C., Liu, J., Yin, F., & Ma, X. (2024) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc62350.2024.10588021 · Cited by 2
Jagadish, B., & Rajalakshmi, P. (2019) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2019.8857393 · Cited by 2
“In [9], the authors proposed affine transformation procedures on the MDRM classification framework and evaluated the performance for cross-subject and cross-session scenarios.”
MethodInfluentialAligning Sets of Temporal Signals with Riemannian Geometry and Koopman Operator
Rahamim, O., & Talmon, R. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413729 · Cited by 2
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.