Spectral representation of EEG data using learned graphs with application to motor imagery decoding

被引:7
作者
Miri, Maliheh [1 ]
Abootalebi, Vahid [1 ]
Saeedi-Sourck, Hamid [1 ]
Ville, Dimitri Van De [2 ,3 ]
Behjat, Hamid [2 ,4 ]
机构
[1] Yazd Univ, Dept Elect Engn, Yazd, Iran
[2] Ecole Polytech Fed Lausanne, Neuro X Inst, Geneva, Switzerland
[3] Univ Geneva, Dept Radiol & Med Informat, Geneva, Switzerland
[4] Lund Univ, Dept Biomed Engn, Lund, Sweden
基金
瑞典研究理事会;
关键词
EEG; Fukunaga-Koontz transform; Graph learning; Graph signal processing; Motor imagery decoding; FEATURE-EXTRACTION; SIGNAL; CLASSIFICATION; PERFORMANCE; PATTERNS; FRAMES;
D O I
10.1016/j.bspc.2023.105537
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Electroencephalography (EEG) data entail a complex spatiotemporal structure that reflects ongoing organi-zation of brain activity. Characterization of the spatial patterns is an indispensable step in numerous EEG processing pipelines. We present a novel method for transforming EEG data into a spectral representation. First, we learn subject-specific graphs from each subject's EEG data. Second, by eigendecomposition of the normalized Laplacian matrix of each subject's graph, an orthonormal basis is obtained using which any given EEG map of the subject can be decomposed, providing a spectral representation of the data. We show that energy of EEG maps is strongly associated with low frequency components of the learned basis, reflecting the smooth topography of EEG maps. As a proof-of-concept for this alternative view of EEG data, we consider the task of decoding two-class motor imagery (MI) data. To this aim, the spectral representations are first mapped into a discriminative subspace for differentiating two-class data using a projection matrix obtained by the Fukunaga-Koontz transform (FKT). An SVM classifier is then trained and tested on the resulting features to differentiate MI classes. The method is benchmarked against features extracted from a subject-specific functional connectivity matrix as well as four alternative MI-decoding methods on Dataset IVa of BCI Competition III. Experimental results show the superiority of the proposed method over alternative approaches in differentiating MI classes, reflecting the added benefit of (i) decomposing EEG data using data-driven, subject-specific harmonic bases, and (ii) accounting for class-specific temporal variations in spectral profiles.
引用
收藏
页数:16
相关论文
共 105 条
[11]  
Bolton TAW, 2020, I S BIOMED IMAGING, P549, DOI [10.1109/ISBI45749.2020.9098644, 10.1109/isbi45749.2020.9098644]
[12]   Capturing the spatiotemporal dynamics of self-generated, task-initiated thoughts with EEG and fMRI [J].
Brechet, Lucie ;
Brunet, Denis ;
Birot, Gwenael ;
Gruetter, Rolf ;
Michel, Christoph M. ;
Jorge, Joao .
NEUROIMAGE, 2019, 194 :82-92
[13]  
Cattai T, 2022, EUR SIGNAL PR CONF, P932
[14]   Improving J-Divergence of Brain Connectivity States by Graph Laplacian Denoising [J].
Cattai, Tiziana ;
Scarano, Gaetano ;
Corsi, Marie-Constance ;
Bassett, Danielle ;
De Vico Fallani, Fabrizio ;
Colonnese, Stefania .
IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS, 2021, 7 :493-508
[15]   Ensemble Regularized Common Spatio-Spectral Pattern (ensemble RCSSP) model for motor imagery-based EEG signal classification [J].
Cherloo, Mohammad Norizadeh ;
Amiri, Homa Kashefi ;
Daliri, Mohammad Reza .
COMPUTERS IN BIOLOGY AND MEDICINE, 2021, 135
[16]  
Chung F.R., 1997, AMS, V92
[17]   A tutorial on generalized eigendecomposition for denoising, contrast enhancement, and dimension reduction in multichannel electrophysiology [J].
Cohen, Michael X. .
NEUROIMAGE, 2022, 247
[18]   The sensitivity of network statistics to incomplete electrode sampling on intracranial EEG [J].
Conrad, Erin C. ;
Bernabei, John M. ;
Kini, Lohith G. ;
Shah, Preya ;
Mikhail, Fadi ;
Kheder, Ammar ;
Shinohara, Russell T. ;
Davis, Kathryn A. ;
Bassett, Danielle S. ;
Litt, Brian .
NETWORK NEUROSCIENCE, 2020, 4 (02) :484-506
[19]   Functional disconnection of associative cortical areas predicts performance during BCI training [J].
Corsi, Marie-Constance ;
Chavez, Mario ;
Schwartz, Denis ;
George, Nathalie ;
Hugueville, Laurent ;
Kahn, Ari E. ;
Dupont, Sophie ;
Bassett, Danielle S. ;
Fallani, Fabrizio De Vico .
NEUROIMAGE, 2020, 209
[20]   The Laplacian spectrum of neural networks [J].
de Lange, Siemon C. ;
de Reus, Marcel A. ;
van den Heuvel, Martijn P. .
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2014, 7