Einzeltreffer — DigiBib

Motor imagery (MI) paradigms have been widely used in neural rehabilitation and drowsiness state assessment. The progress in brain-computer interface (BCI) technology has emphasized the importance of accurately and efficiently detecting motor imagery intentions from electroencephalogram (EEG). Despite the recent breakthroughs made in developing EEG-based algorithms for decoding MI, the accuracy and efficiency of these models remain limited by technical challenges posed by cross-subject heterogeneity in EEG data processing and the scarcity of EEG data for training. Inspired by the optimal transport theory, this study aims to develop a novel three-stage transfer learning (TSTL) method, which uses the existing labeled data from a source domain to improve classification performance on an unlabeled target domain. Notably, the proposed method comprises three components, namely, the Riemannian tangent space mapping (RTSM), source domain transformer (SDT), and optimal subspace mapping (OSM). The RTSM maps a symmetric positive definite matrix from the Riemannian space to the tangent space to minimize the marginal probability distribution drift. The SDT transforms the source domain to a target domain by finding the optimal transport mapping matrix to reduce the joint probability distribution differences. The OSM finally maps the transformed source domain and original target domain to the same subspace to further mitigate the distribution discrepancy. The performance of the proposed method was validated on two public BCI datasets, and the average accuracy of the algorithm on two datasets was 72.24% and 69.29%. Our results demonstrated the improved performance of EEG-based MI detection in comparison with state-of-the-art algorithms.

Titel:	Three-stage transfer learning for motor imagery EEG recognition.
Autor/in / Beteiligte Person:	Li, J ; She, Q ; Meng, M ; Du, S ; Zhang, Y
Link:	Full Text Finder (Volltext)
Zeitschrift:	Medical & biological engineering & computing, Jg. 62 (2024-06-01), Heft 6, S. 1689-1701
Veröffentlichung:	New York, NY : Springer ; <i>Original Publication</i>: Stevenage, Eng., Peregrinus., 2024
Medientyp:	academicJournal
ISSN:	1741-0444 (electronic)
DOI:	10.1007/s11517-024-03036-9
Schlagwort:	Humans Machine Learning Signal Processing, Computer-Assisted Imagination physiology Electroencephalography methods Brain-Computer Interfaces Algorithms
Sonstiges:	Nachgewiesen in: MEDLINE Sprachen: English Publication Type: Journal Article Language: English [Med Biol Eng Comput] 2024 Jun; Vol. 62 (6), pp. 1689-1701. <i>Date of Electronic Publication: </i>2024 Feb 12. MeSH Terms: Electroencephalography* / methods ; Brain-Computer Interfaces* ; Algorithms* ; Humans ; Machine Learning ; Signal Processing, Computer-Assisted ; Imagination / physiology References: He B, Baxter B, Edelman BJ (2015) Noninvasive brain-computer interfaces based on sensorimotor rhythms. Proc IEEE Inst Electr Electron Eng 103(6):907–925. https://doi.org/10.1109/JPROC.2015.2407272. (PMID: 10.1109/JPROC.2015.2407272343348048323842) ; Mane R, Chouhan T, Guan C (2020) BCI for stroke rehabilitation: motor and beyond. J Neural Eng 17(4):041001. https://doi.org/10.1109/JPROC.2015.2407272. (PMID: 10.1109/JPROC.2015.240727232613947) ; Foong R, Ang KK, Quek C, Guan C, Phua KS, Kuah CWK, Deshmukh VA, Yam LHL, Rajeswaran DK, Tang N, Chew E, Chua KSG (2020) Assessment of the efficacy of EEG-based MI-BCI with visual feedback and EEG correlates of mental fatigue for upper-limb stroke rehabilitation. IEEE Trans Biomed Eng 67(3):786–795. https://doi.org/10.1109/TBME.2019.2921198. (PMID: 10.1109/TBME.2019.292119831180829) ; Khan MA, Saibene M, Das R, Brunner I, Puthusserypady S (2012) Emergence of flexible technology in developing advanced systems for post-stroke rehabilitation: a comprehensive review. J Neural Eng 18(6):061003. https://doi.org/10.1088/1741-2552/ac36aa. (PMID: 10.1088/1741-2552/ac36aa) ; Lee J, Lee D, Jeong I, Cho. J (2021) A Study on the content of mental and physical stability game in virtual reality through EEG detection. In: 2021 International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Korea, pp 693–696. https://doi.org/10.1109/ICTC52510.2021.9620932. ; Yang S, Li R, Li H, Xu K, Shi Y, Wang Q, Yang T, Sun X (2021) Exploring the use of brain-computer interfaces in stroke neurorehabilitation. BioMed Res Int 2021:9967348. https://doi.org/10.1155/2021/9967348. (PMID: 10.1155/2021/9967348342399368235968) ; Wei CS, Wang YT, Lin CT, Jung TP (2018) Toward drowsiness detection using non-hair-bearing EEG-based brain-computer interfaces. IEEE Trans Neural Syst Rehabil Eng 26(2):400–406. https://doi.org/10.1109/TNSRE.2018.2790359. (PMID: 10.1109/TNSRE.2018.279035929432111) ; Simeral JD, Hosman T, Saab J et al (2021) Home use of a percutaneous wireless intracortical brain-computer interface by individuals with tetraplegia. IEEE Trans Biomed Eng 68(7):2313–2325. https://doi.org/10.1109/TBME.2021.3069119. (PMID: 10.1109/TBME.2021.3069119337846128218873) ; Gao Y, Liu H, Fang F, Zhang Y (2022) Classification of working memory loads via assessing broken detailed balance of EEG-fNIRS neurovascular coupling measures. IEEE Trans Biomed Eng 70(3):877–887. https://doi.org/10.1109/TBME.2022.3204718. (PMID: 10.1109/TBME.2022.3204718) ; Benzy VK, Vinod AP, Subasree R, Alladi S, Raghavendra K (2020) Motor imagery hand Movement direction decoding using brain computer interface to aid stroke recovery and Rehabilitation. IEEE Trans Neural Syst Rehabil Eng 28(12):3051–3062. https://doi.org/10.1109/TNSRE.2020.3039331. (PMID: 10.1109/TNSRE.2020.303933133211662) ; Wang Z, Yang R, Huang M, Zeng N, Liu X (2021) A review on transfer learning in EEG signal analysis. Neurocomputing 421:1–14. https://doi.org/10.1016/j.neucom.2020.09.017. (PMID: 10.1016/j.neucom.2020.09.017) ; Rodrigues PLC, Jutten C, Congedo M (2019) Riemannian procrustes analysis: transfer learning for brain-computer interfaces. IEEE Trans Biomed Eng 66(8):2390–2401. https://doi.org/10.1109/TBME.2018.2889705. (PMID: 10.1109/TBME.2018.288970530596565) ; Samek W, Meinecke FC, Müller KR (2013) Transferring subspaces between subjects in brain–computer interfacing. IEEE Trans Biomed Eng 60(8):2289–2298. https://doi.org/10.1109/TBME.2013.2253608. (PMID: 10.1109/TBME.2013.225360823529075) ; Lotte F, Bougrain L, Cichocki A, Clerc M, Congedo M, Rakotomamonjy A, Yger F (2018) A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update. J Neural Eng 15(3):031005. https://doi.org/10.1088/1741-2552/aab2f2. (PMID: 10.1088/1741-2552/aab2f229488902) ; Falzon O, Camilleri KP, Muscat J (2012) The analytic common spatial patterns method for EEG-based BCI data. J Neural Eng 9(4):045009. https://doi.org/10.1088/1741-2560/9/4/045009. (PMID: 10.1088/1741-2560/9/4/04500922832090) ; Arpaia P, Esposito A, Natalizio A, Marco P (2022) How to successfully classify EEG in motor imagery BCI: a metrological analysis of the state of the art. J Neural Eng 19(3):031002. https://doi.org/10.1088/1741-2552/ac74e0. (PMID: 10.1088/1741-2552/ac74e0) ; Atyabi A, Shic F, Naples A (2016) Mixture of autoregressive modeling orders and its implication on single trial EEG classification. Expert Syst Appl 65:164–180. https://doi.org/10.1016/j.eswa.2016.08.044. (PMID: 10.1016/j.eswa.2016.08.044287403315521280) ; Craik A, He Y, Contreras-Vidal JL (2019) Deep learning for electroencephalogram (EEG) classification tasks: a review. J Neural Eng 16(3):031001. https://doi.org/10.1088/1741-2552/ab0ab5. (PMID: 10.1088/1741-2552/ab0ab530808014) ; Khademi Z, Ebrahimi F, Kordy HM (2023) A review of critical challenges in MI-BCI: From conventional to deep learning methods. J Neurosci Methods 383:109736. https://doi.org/10.1016/j.jneumeth.2022.109736. (PMID: 10.1016/j.jneumeth.2022.10973636349568) ; Chen P, Wang H, Sun X, Li H, Grebogi C, Gao Z (2022) Transfer learning with optimal transportation and frequency mixup for EEG-based motor imagery recognition. IEEE Trans Neural Syst Rehabil Eng 30:2866–2875. https://doi.org/10.1109/TNSRE.2022.3211881. (PMID: 10.1109/TNSRE.2022.321188136194720) ; Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359. https://doi.org/10.1109/TKDE.2009.191. (PMID: 10.1109/TKDE.2009.191) ; Dagois E, Khalaf A, Sejdic E, Akcakaya M (2019) Transfer learning for a multimodal hybrid EEG-fTCD brain–computer interface. IEEE Sens Lett 3(1):7100704. https://doi.org/10.1109/LSENS.2018.2879466. (PMID: 10.1109/LSENS.2018.2879466) ; Gaur P, McCreadie K, Pachori RB (2019) Tangent space features-based transfer learning classification model for two-class motor imagery brain–computer interface. Int J Neural Syst 29(10):1950025. https://doi.org/10.1142/S0129065719500254. (PMID: 10.1142/S012906571950025431711330) ; Zhuang F, Qi Z, Duan K, Xi D, Zhu Y, Zhu H, Xiong H, He Q (2021) A comprehensive survey on transfer learning. Proc IEEE Inst Electr Electron Eng 109(1):43–76. https://doi.org/10.1109/JPROC.2020.3004555. (PMID: 10.1109/JPROC.2020.3004555) ; He H, Wu D (2020) Transfer learning for brain–computer interfaces: a Euclidean space data alignment approach. IEEE Trans Biomed Eng 67(2):399–410. https://doi.org/10.1109/TBME.2019.2913914. (PMID: 10.1109/TBME.2019.291391431034407) ; Zanini P, Congedo M, Jutten C, Said S, Berthoumieu Y (2017) Transfer learning: a Riemannian geometry framework with applications to brain-computer interfaces. IEEE Trans Biomed Eng 65(5):1107–1116. https://doi.org/10.1109/TBME.2017.2742541. (PMID: 10.1109/TBME.2017.274254128841546) ; Wang J, Chen Y, Hao S, Feng W, Shen Z (2017) Balanced distribution adaptation for transfer learning. In: 2017 IEEE Int Conf Data Mining (ICDM), New Orleans, LA, USA, pp 1129–1134. https://doi.org/10.1109/ICDM.2017.150. ; Zhang W, Wu D (2020) Manifold embedded knowledge transfer for brain-computer interfaces. IEEE Trans Neural Syst Rehabil Eng 28(5):1117–1127. https://doi.org/10.1109/TNSRE.2020.2985996. (PMID: 10.1109/TNSRE.2020.298599632286993) ; Pan SJ, Tsang IW, Kwok JT, Yang Q (2011) Domain adaptation via transfer component analysis. I IEEE Trans Neural Netw 22(2):199–210. https://doi.org/10.1109/TNN.2010.2091281. (PMID: 10.1109/TNN.2010.209128121095864) ; Cai Y, She Q, Ji J, Ma Y, Zhang J, Zhang Y (2022) Motor imagery EEG decoding using manifold embedded transfer learning. J Neurosci Methods 370:109489. https://doi.org/10.1016/j.jneumeth.2022.109489. (PMID: 10.1016/j.jneumeth.2022.10948935090904) ; Gao Y, Liu Y, She Q, Zhang J (2022) Domain adaptive algorithm based on multi-manifold embedded distributed alignment for brain-computer interfaces. IEEE J Biomed Health Informat 27(1):296–307. https://doi.org/10.1109/JBHI.2022.3218453. (PMID: 10.1109/JBHI.2022.3218453) ; Nguyen T, Le T, Zhao H, Tran QH, Nguyen T, Phung D (2021) Most: multi-source domain adaptation via optimal transport for student-teacher learning. In: Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (UAI). 161:225–235. https://www.auai.org/uai2021/pdf/uai2021.106.preliminary.pdf . Accessed 9 Feb 2024. ; She Q, Cai Y, Du S, Chen Y (2022) Multi-source manifold feature transfer learning with domain selection for brain-computer interfaces. Neurocomputing 514:313–327. https://doi.org/10.1016/j.neucom.2022.09.124. (PMID: 10.1016/j.neucom.2022.09.124) ; Courty N, Flamary R, Tuia D, Rakotomamonjy A (2017) Optimal transport for domain adaptation. IEEE Trans Pattern Anal Mach Intell 39(9):1853–1865. https://doi.org/10.1109/TPAMI.2016.2615921. (PMID: 10.1109/TPAMI.2016.261592127723579) ; Peterson V, Nieto N, Wyser D, Lambercy O, Gassert R, H. Milone D, D. Spies R, (2021) Transfer learning based on optimal transport for motor imagery brain-computer interfaces. IEEE Trans Biomed Eng 69(2):807–817. https://doi.org/10.1109/TBME.2021.3105912. (PMID: 10.1109/TBME.2021.3105912) ; Blankertz B, Dornhege G, Krauledat M, Müller KR, Curio G (2007) The non-invasive Berlin brain-computer interface: fast acquisition of effective performance in untrained subjects. Neuroimage 37(2):539–550. https://doi.org/10.1016/j.neuroimage.2007.01.051. (PMID: 10.1016/j.neuroimage.2007.01.05117475513) ; Naeem M, Brunner C, Leeb R, Graimann B, Pfurtscheller G (2006) Seperability of four-class motor imagery data using independent components analysis. J Neural Eng 3(3):208–216. https://doi.org/10.1088/1741-2560/3/3/003. (PMID: 10.1088/1741-2560/3/3/00316921204) ; Kantorovich LV (2006) On the translocation of masses. J Math Sci 133(4):1381–1382. https://doi.org/10.1287/mnsc.5.1.1. (PMID: 10.1287/mnsc.5.1.1) ; Redko I, Courty N, Flamary R, Tuia D (2019) Optimal transport for multi-source domain adaptation under target shift. In: Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, Naha, Okinawa, Japan, pp 849–858. https://doi.org/10.48550/arXiv.1803.04899. ; Pan S J, Kwok J T, Yang Q (2008) Transfer learning via dimensionality reduction. In: Proc 8th AAAI Conf Artif Intell. 8:677–682. https://cdn.aaai.org/AAAI/2008/AAAI08-108.pdf . Accessed 9 Feb 2024. ; Peck R, Van Ness J (1982) The use of shrinkage estimators in linear discriminant analysis. IEEE Trans Pattern Anal Mach Intell 4(5):530–537. https://doi.org/10.1109/TPAMI.1982.4767298. (PMID: 10.1109/TPAMI.1982.476729821869073) ; Yger F, Berar M, Lotte F (2017) Riemannian approaches in brain-computer interfaces: a review. IEEE Trans Neural Syst Rehabil Eng 25(10):1753–1762. https://doi.org/10.1109/TNSRE.2016.2627016. (PMID: 10.1109/TNSRE.2016.262701627845666) ; Gao Y, Li M, Peng Y, Fang F, Zhang Y (2023) Double Stage Transfer Learning for Brain-Computer Interfaces. IEEE Trans Neural Syst Rehabil Eng 31:1128–1136. https://doi.org/10.1109/TNSRE.2023.3241301. (PMID: 10.1109/TNSRE.2023.3241301) ; Wang S, Wang B, Zhang Z, Heidair AA, Chen H (2023) Class-aware sample reweighting optimal transport for multi-source domain adaptation. Neurocomputing 523:213–223. https://doi.org/10.1016/j.neucom.2022.12.048. (PMID: 10.1016/j.neucom.2022.12.048) Grant Information: LZ22F010003 Natural Science Foundation of Zhejiang Province; 62371172 National Natural Science Foundation of China; 62271181 National Natural Science Foundation of China Contributed Indexing: Keywords: Brain-computer interface (BCI); Motor imagery (MI); Optimal transport (OT); Transfer learning (TL) Entry Date(s): Date Created: 20240211 Date Completed: 20240507 Latest Revision: 20240507 Update Code: 20240508

Klicken Sie ein Format an und speichern Sie dann die Daten oder geben Sie eine Empfänger-Adresse ein und lassen Sie sich per Email zusenden.

BibTeX Citavi, JabRef, u.a.
(Literaturverwaltung)

PDF kein Volltext!
(Merkzettel, Notizen)

RIS Endnote, Citavi u.a.
(Literaturverwaltung)

MODS
(XML zur Weiterverarbeitung)

oder

Wählen Sie das für Sie passende Zitationsformat und kopieren Sie es dann in die Zwischenablage, lassen es sich per Mail zusenden oder speichern es als PDF-Datei.

Gewünschter Zitations-Stil:

oder

Bitte prüfen Sie, ob die Zitation formal korrekt ist, bevor Sie sie in einer Arbeit verwenden. Benutzen Sie gegebenenfalls den "Exportieren"-Dialog, wenn Sie ein Literaturverwaltungsprogramm verwenden und die Zitat-Angaben selbst formatieren wollen.

Three-stage transfer learning for motor imagery EEG recognition.