EEG generalizable representations learning via masked fractional fourier domain modeling
Deep learning methods currently represent the state-of-the-art (SOTA) in electroencephalography (EEG) decoding, primarily focusing on the development of supervised models. However, most supervised methods are task-specific and lack the ability to generate generalizable latent features for use across...
Uloženo v:
| Vydáno v: | Applied soft computing Ročník 170; s. 112731 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.02.2025
|
| Témata: | |
| ISSN: | 1568-4946 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Deep learning methods currently represent the state-of-the-art (SOTA) in electroencephalography (EEG) decoding, primarily focusing on the development of supervised models. However, most supervised methods are task-specific and lack the ability to generate generalizable latent features for use across different BCI paradigms. Additionally, as subjects engage in diverse brain–computer interaction tasks, the distribution of recorded EEG data varies according to the specific cognitive paradigms involved. The process of data collection and model training for each task is time-consuming. One potential solution is to construct a pre-trained model capable of transferring knowledge across various tasks. To improve the generalization ability of pre-trained models, we propose a novel masked autoencoder based on fractional Fourier domain reconstruction, denoted as Masked Fractional Fourier Domain Modeling (MFrFM), for learning generalizable time–frequency features. We systematically explore the effects of different degradation methods used within the denoising autoencoder to enhance the robustness of the pre-training model. Moreover, we examine the impact of various masking strategies on model performance. Our experiments demonstrate that the pre-trained MFrFM can effectively capture generalizable representations. Additionally, we conduct a comprehensive evaluation of fine-tuning performance through both cross-task and intra-task experiments. The experimental results show that MFrFM achieves a maximum accuracy of 98.09% in transferring from MI to SSVEP, and 79.76% in transferring from SSVEP to MI. The code is available at https://github.com/zshubin/MFrFM-for-cross-task-EEG-pre-training.
•A EEG generalizable representations learning model for cross-task transfer.•A pre-training model based on Masked fractional fourier domain modeling.•A specific masking strategy for EEG reconstruction-based pre-training.•Denoising mechanism based on various degradation methods. |
|---|---|
| AbstractList | Deep learning methods currently represent the state-of-the-art (SOTA) in electroencephalography (EEG) decoding, primarily focusing on the development of supervised models. However, most supervised methods are task-specific and lack the ability to generate generalizable latent features for use across different BCI paradigms. Additionally, as subjects engage in diverse brain–computer interaction tasks, the distribution of recorded EEG data varies according to the specific cognitive paradigms involved. The process of data collection and model training for each task is time-consuming. One potential solution is to construct a pre-trained model capable of transferring knowledge across various tasks. To improve the generalization ability of pre-trained models, we propose a novel masked autoencoder based on fractional Fourier domain reconstruction, denoted as Masked Fractional Fourier Domain Modeling (MFrFM), for learning generalizable time–frequency features. We systematically explore the effects of different degradation methods used within the denoising autoencoder to enhance the robustness of the pre-training model. Moreover, we examine the impact of various masking strategies on model performance. Our experiments demonstrate that the pre-trained MFrFM can effectively capture generalizable representations. Additionally, we conduct a comprehensive evaluation of fine-tuning performance through both cross-task and intra-task experiments. The experimental results show that MFrFM achieves a maximum accuracy of 98.09% in transferring from MI to SSVEP, and 79.76% in transferring from SSVEP to MI. The code is available at https://github.com/zshubin/MFrFM-for-cross-task-EEG-pre-training.
•A EEG generalizable representations learning model for cross-task transfer.•A pre-training model based on Masked fractional fourier domain modeling.•A specific masking strategy for EEG reconstruction-based pre-training.•Denoising mechanism based on various degradation methods. |
| ArticleNumber | 112731 |
| Author | Liu, Jincun Wei, Yaoguang An, Dong Zhang, Shubin |
| Author_xml | – sequence: 1 givenname: Shubin surname: Zhang fullname: Zhang, Shubin email: zhangshubin@ouc.edu.cn organization: Fisheries college, Ocean University of China, Qingdao, Shandong, 266003, China – sequence: 2 givenname: Dong surname: An fullname: An, Dong email: andong@cau.edu.cn organization: National Innovation Center for Digital Fishery, Beijing, 100083, China – sequence: 3 givenname: Jincun surname: Liu fullname: Liu, Jincun email: liujincun@cau.edu.cn organization: National Innovation Center for Digital Fishery, Beijing, 100083, China – sequence: 4 givenname: Yaoguang surname: Wei fullname: Wei, Yaoguang email: wyg@cau.edu.cn organization: National Innovation Center for Digital Fishery, Beijing, 100083, China |
| BookMark | eNp9kMtOwzAQRb0oEm3hB1j5BxL8yFNig6pSkCqxAYmdNbHHlUviVHaoBF9PorBi0dUs5p7R3LMiC997JOSOs5QzXtwfU4i9TgUTecq5KCVfkCXPiyrJ6qy4JqsYj2wM1qJako_tdkcP6DFA636gaZEGPAWM6AcYXO8jbRGCd_5Azw5oB_ETDbUB9LSFltr-KzgM1PQdOE-73mA7pm_IlYU24u3fXJP3p-3b5jnZv-5eNo_7REvGhsRiycX4o6hzFA2zoHUj88JUouKYWWkQoDC5zCWrTVaWVdMYmfOiaKSuLW_kmoj5rg59jAGtOgXXQfhWnKnJhzqqyYeafKjZxwhV_yDt5rpDANdeRh9mFMdS57G4itqh12hcQD0o07tL-C9bgYGK |
| CitedBy_id | crossref_primary_10_1016_j_eswa_2025_129603 |
| Cites_doi | 10.1109/ICMLA55696.2022.00208 10.1109/JBHI.2022.3213171 10.1016/j.asoc.2023.110079 10.1109/JBHI.2023.3304646 10.1088/1741-2552/ab260c 10.1109/MLSP.2019.8918693 10.1088/1741-2552/abca18 10.1109/TNSRE.2020.3006180 10.1038/nature17435 10.1145/3534678.3539178 10.1109/TLA.2020.9099676 10.1109/CVPR52688.2022.01553 10.1145/3503161.3548243 10.1109/TAFFC.2022.3170428 10.1109/TNSRE.2018.2803066 10.1109/ICASSP49357.2023.10097183 10.1109/TCYB.2019.2905157 10.1109/ACCESS.2020.2994593 10.1109/ACCESS.2021.3078534 10.1088/1741-2560/12/4/046006 10.1007/978-3-031-16437-8_38 10.1109/JBHI.2024.3373019 |
| ContentType | Journal Article |
| Copyright | 2025 |
| Copyright_xml | – notice: 2025 |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.asoc.2025.112731 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_asoc_2025_112731 S1568494625000420 |
| GrantInformation_xml | – fundername: National Key Research and Development Program of China grantid: 2022YFD2001704 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 23M 4.4 457 4G. 53G 5GY 5VS 6J9 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXKI AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABWVN ABXDB ACDAQ ACGFO ACGFS ACNNM ACRLP ACRPL ACZNC ADBBV ADEZE ADJOM ADMUD ADNMO ADTZH AEBSH AECPX AEFWE AEIPS AEKER AENEX AFJKZ AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ANKPU AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HVGLF HZ~ IHE J1W JJJVA KOM M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SDF SDG SES SEW SPC SPCBC SST SSV SSZ T5K UHS UNMZH ~G- 9DU AATTM AAYWO AAYXX ACLOT ACVFH ADCNI AEUPX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP APXCP CITATION EFKBS EFLBG ~HD |
| ID | FETCH-LOGICAL-c300t-fe712273295e2b0faccb356d8281e4f3deaa6d535309d4778bbd35166b3c9f1b3 |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001417868600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1568-4946 |
| IngestDate | Sat Nov 29 08:09:04 EST 2025 Tue Nov 18 22:18:59 EST 2025 Sat Feb 15 15:52:05 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Self-supervised learning (SSL) Motor imagery (MI) Masked autoencoder (MAE) Steady-state visual evoked potential (SSVEP) Fractional fourier transform (frFT) |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c300t-fe712273295e2b0faccb356d8281e4f3deaa6d535309d4778bbd35166b3c9f1b3 |
| ParticipantIDs | crossref_primary_10_1016_j_asoc_2025_112731 crossref_citationtrail_10_1016_j_asoc_2025_112731 elsevier_sciencedirect_doi_10_1016_j_asoc_2025_112731 |
| PublicationCentury | 2000 |
| PublicationDate | February 2025 2025-02-00 |
| PublicationDateYYYYMMDD | 2025-02-01 |
| PublicationDate_xml | – month: 02 year: 2025 text: February 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Applied soft computing |
| PublicationYear | 2025 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Cheng, Fu, Li, Zhang, Huang, Peng, Chen, Fan (b2) 2023; 136 J. Chen, Y. Yang, T. Yu, Y. Fan, X. Mo, C. Yang, Brainnet: Epileptic wave detection from seeg with hierarchical graph diffusion learning, in: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, pp. 2741–2751. Li, Chen, Li, Fu, Wu, Ji, Zhou, Niu, Shi, Zheng (b25) 2023; 14 Cheng, Zhang, Qin, Wang, Wu, Song (b32) 2024; 28 Banville, Chehab, Hyvärinen, Engemann, Gramfort (b22) 2021; 18 Brown, Mann, Ryder, Subbiah (b21) 2020 R. Li, Y. Wang, W. Zheng, B. Lu, A Multi-View Spectral-Spatial-Temporal Masked Autoencoder for Decoding Emotions with Self-Supervised Learning, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 6–14. K. He, X. Chen, S. Xie, Y. Li, P. Dollár, R. Girshick, Masked Autoencoders Are Scalable Vision Learners, in: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, New Orleans, LA, USA, 2022, pp. 15979–15988. Devlin, Chang, Lee, Toutanova (b15) 2019 Li, Yu, Gu, Wu, Li, Jin (b5) 2018; 26 Li, Luo, Zhang, Zhang, Zhang, Lo (b26) 2023; 27 Emadeldeen (b33) 2021 Bouton, Shaikhouni, Annetta, Bockbrader, Friedenberg, Nielson, Sharma, Sederberg, Glenn, Mysiw, Morgan, Deogaonkar, Rezai (b1) 2016; 533 Yuan, Chen, Wang, Gao, Gao (b7) 2015; 12 Zhang, Yao, Chen, Wang, Chang, Liu (b27) 2020; 50 H. Banville, I. Albuquerque, A. Hyvärinen, G. Moffat, D.-A. Engemann, A. Gramfort, Self-Supervised Representation Learning from Electroencephalography Signals, in: 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP, Pittsburgh, PA, USA, 2019, pp. 1–6. Liu (b8) 2023; 35 V. Kumar, L. Reddy, S.K. Sharma, K. Dadi, C. Yarra, R.S. Bapi, S. Rajendran, mulEEG: a multi-view representation learning on EEG signals, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, 2022, pp. 398–407. Wu, Ye, Gu, Zhang, Wang, He (b17) 2023 Deny, Cheon, Son, Choi (b3) 2023; 27 Y. Nie, H. Nguyen Nam, S. Phanwadee, K. Jayant, A Time Series is Worth 64 Words: Long-term Forecasting with Transformers, in: International Conference on Learning Representations, 2023. Panwar, Rad, Jung, Huang (b29) 2020; 28 R. Peng, et al., WAVELET2VEC: A Filter Bank Masked Autoencoder for EEG-Based Seizure Subtype Classification, in: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Rhodes Island, Greece, 2023, pp. 1–5. Mh (b34) 2019; 8 Kostas, Aroca-Ouellette, Rudzicz (b10) 2021; 15 Tian (b19) 2022 Jiahao, Wei, Xiaohang Zhan (b20) 2023 Weng, Gu, Guo, Ma, Yang, Liu, Chen (b14) 2024 Zhao, Dong, Zhou (b28) 2020; 8 Shin, Sun, Lee, Kim (b30) 2021; 9 Roy, Banville, Albuquerque, Gramfort, Falk, Faubert (b6) 2019; 16 İ.Y. Potter, G. Zerveas, C. Eickhoff, D. Duncan, Unsupervised Multivariate Time-Series Transformers for Seizure Identification on EEG, in: 2022 21st IEEE International Conference on Machine Learning and Applications, ICMLA, Nassau, Bahamas, 2022, pp. 1304–1311. Siyuan, Di, Fang, Zelin (b18) 2023 Damian da Silva, da Cruz Júnior, Galvão Pinheiro Júnior (b4) 2020; 18 10.1016/j.asoc.2025.112731_b12 10.1016/j.asoc.2025.112731_b13 10.1016/j.asoc.2025.112731_b11 Bouton (10.1016/j.asoc.2025.112731_b1) 2016; 533 Damian da Silva (10.1016/j.asoc.2025.112731_b4) 2020; 18 Li (10.1016/j.asoc.2025.112731_b26) 2023; 27 10.1016/j.asoc.2025.112731_b31 Yuan (10.1016/j.asoc.2025.112731_b7) 2015; 12 Zhang (10.1016/j.asoc.2025.112731_b27) 2020; 50 Mh (10.1016/j.asoc.2025.112731_b34) 2019; 8 Devlin (10.1016/j.asoc.2025.112731_b15) 2019 Brown (10.1016/j.asoc.2025.112731_b21) 2020 Zhao (10.1016/j.asoc.2025.112731_b28) 2020; 8 Banville (10.1016/j.asoc.2025.112731_b22) 2021; 18 Weng (10.1016/j.asoc.2025.112731_b14) 2024 Cheng (10.1016/j.asoc.2025.112731_b32) 2024; 28 Liu (10.1016/j.asoc.2025.112731_b8) 2023; 35 Cheng (10.1016/j.asoc.2025.112731_b2) 2023; 136 10.1016/j.asoc.2025.112731_b16 Li (10.1016/j.asoc.2025.112731_b25) 2023; 14 10.1016/j.asoc.2025.112731_b9 10.1016/j.asoc.2025.112731_b23 Li (10.1016/j.asoc.2025.112731_b5) 2018; 26 10.1016/j.asoc.2025.112731_b24 Jiahao (10.1016/j.asoc.2025.112731_b20) 2023 Tian (10.1016/j.asoc.2025.112731_b19) 2022 Wu (10.1016/j.asoc.2025.112731_b17) 2023 Roy (10.1016/j.asoc.2025.112731_b6) 2019; 16 Shin (10.1016/j.asoc.2025.112731_b30) 2021; 9 Kostas (10.1016/j.asoc.2025.112731_b10) 2021; 15 Emadeldeen (10.1016/j.asoc.2025.112731_b33) 2021 Siyuan (10.1016/j.asoc.2025.112731_b18) 2023 Deny (10.1016/j.asoc.2025.112731_b3) 2023; 27 Panwar (10.1016/j.asoc.2025.112731_b29) 2020; 28 |
| References_xml | – volume: 27 start-page: 5459 year: 2023 end-page: 5470 ident: b3 article-title: Hierarchical transformer for motor imagery-based brain computer interface publication-title: IEEE J. Biomed. Health Inf. – volume: 15 year: 2021 ident: b10 article-title: BENDR: Using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data publication-title: Front. Hum. Neurosci. – year: 2021 ident: b33 article-title: Time-series representation learning via temporal and contextual contrasting – reference: K. He, X. Chen, S. Xie, Y. Li, P. Dollár, R. Girshick, Masked Autoencoders Are Scalable Vision Learners, in: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, New Orleans, LA, USA, 2022, pp. 15979–15988. – volume: 533 start-page: 247 year: 2016 end-page: 250 ident: b1 article-title: Restoring cortical control of functional movement in a human with quadriplegia publication-title: Nature – volume: 16 year: 2019 ident: b6 article-title: Deep learning-based electroencephalography analysis: a systematic review publication-title: J. Neural Eng. – volume: 14 start-page: 2512 year: 2023 end-page: 2525 ident: b25 article-title: GMSS: Graph-based multi-task self-supervised learning for EEG emotion recognition publication-title: IEEE Trans. Affect. Comput. – reference: H. Banville, I. Albuquerque, A. Hyvärinen, G. Moffat, D.-A. Engemann, A. Gramfort, Self-Supervised Representation Learning from Electroencephalography Signals, in: 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing, MLSP, Pittsburgh, PA, USA, 2019, pp. 1–6. – volume: 9 start-page: 70639 year: 2021 end-page: 70649 ident: b30 article-title: Complementary photoplethysmogram synthesis from electrocardiogram using generative adversarial network publication-title: IEEE Access – reference: İ.Y. Potter, G. Zerveas, C. Eickhoff, D. Duncan, Unsupervised Multivariate Time-Series Transformers for Seizure Identification on EEG, in: 2022 21st IEEE International Conference on Machine Learning and Applications, ICMLA, Nassau, Bahamas, 2022, pp. 1304–1311. – year: 2024 ident: b14 article-title: Self-supervised learning for electroencephalogram: A systematic survey – year: 2023 ident: b17 article-title: Denoising masked AutoEncoders helps robust classification publication-title: 2023 ICLR – volume: 28 start-page: 2687 year: 2024 end-page: 2698 ident: b32 article-title: MaskCAE: Masked convolutional AutoEncoder via sensor data reconstruction for self-supervised human activity recognition publication-title: IEEE J. Biomed. Health Inf. – year: 2022 ident: b19 article-title: Beyond masking: Demystifying token-based pre-training for vision transformers – volume: 18 start-page: 1000 year: 2020 end-page: 1007 ident: b4 article-title: A fast and accurate SSVEP brain machine interface using dry electrodes and high frequency stimuli by employing ensemble learning publication-title: IEEE Latin Am. Trans. – year: 2020 ident: b21 article-title: Language models are few-shot learners publication-title: NeurIPS – volume: 28 start-page: 1720 year: 2020 end-page: 1730 ident: b29 article-title: Modeling EEG data distribution with a Wasserstein generative adversarial network to predict RSVP events publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – volume: 12 year: 2015 ident: b7 article-title: Enhancing performances of SSVEP-based brain-computer interfaces via exploiting inter-subject information publication-title: J. Neural Eng. – reference: J. Chen, Y. Yang, T. Yu, Y. Fan, X. Mo, C. Yang, Brainnet: Epileptic wave detection from seeg with hierarchical graph diffusion learning, in: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, pp. 2741–2751. – volume: 136 year: 2023 ident: b2 article-title: Evolutionary computation-based multitask learning network for railway passenger comfort evaluation from EEG signals publication-title: Appl. Soft Comput. – volume: 8 year: 2019 ident: b34 article-title: EEG dataset and OpenBMI toolbox for three BCI paradigms: an investigation into BCI illiteracy publication-title: Gigascience – reference: V. Kumar, L. Reddy, S.K. Sharma, K. Dadi, C. Yarra, R.S. Bapi, S. Rajendran, mulEEG: a multi-view representation learning on EEG signals, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, 2022, pp. 398–407. – reference: R. Li, Y. Wang, W. Zheng, B. Lu, A Multi-View Spectral-Spatial-Temporal Masked Autoencoder for Decoding Emotions with Self-Supervised Learning, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 6–14. – volume: 50 start-page: 3033 year: 2020 end-page: 3044 ident: b27 article-title: Making sense of spatio-temporal preserving representations for EEG-based human intention recognition publication-title: IEEE Trans. Cybern. – volume: 26 start-page: 563 year: 2018 end-page: 572 ident: b5 article-title: A hybrid network for ERP detection and analysis based on restricted Boltzmann machine publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – volume: 35 start-page: 857 year: 2023 end-page: 876 ident: b8 article-title: Self-supervised learning: Generative or contrastive publication-title: IEEE Trans. Knowl. Data Eng. – volume: 18 year: 2021 ident: b22 article-title: Uncovering the structure of clinical EEG signals with self-supervised learning publication-title: J. Neural Eng. – year: 2019 ident: b15 article-title: Toutanova BERT: Pre-training of deep bidirectional transformers for language understanding publication-title: NAACL – volume: 8 start-page: 93907 year: 2020 end-page: 93921 ident: b28 article-title: Self-supervised learning from multi-sensor data for sleep recognition publication-title: IEEE Access – reference: Y. Nie, H. Nguyen Nam, S. Phanwadee, K. Jayant, A Time Series is Worth 64 Words: Long-term Forecasting with Transformers, in: International Conference on Learning Representations, 2023. – reference: R. Peng, et al., WAVELET2VEC: A Filter Bank Masked Autoencoder for EEG-Based Seizure Subtype Classification, in: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Rhodes Island, Greece, 2023, pp. 1–5. – year: 2023 ident: b20 article-title: Masked frequency modeling for self-supervised visual pre-training publication-title: 2023 ICLR – year: 2023 ident: b18 article-title: Architecture-agnostic masked image modeling - From ViT back to CNN publication-title: 2023 ICLR – volume: 27 start-page: 2647 year: 2023 end-page: 2655 ident: b26 article-title: MtCLSS: Multi-task contrastive learning for semi-supervised pediatric sleep staging publication-title: IEEE J. Biomed. Health Inf. – ident: 10.1016/j.asoc.2025.112731_b12 doi: 10.1109/ICMLA55696.2022.00208 – year: 2019 ident: 10.1016/j.asoc.2025.112731_b15 article-title: Toutanova BERT: Pre-training of deep bidirectional transformers for language understanding – volume: 27 start-page: 2647 issue: 6 year: 2023 ident: 10.1016/j.asoc.2025.112731_b26 article-title: MtCLSS: Multi-task contrastive learning for semi-supervised pediatric sleep staging publication-title: IEEE J. Biomed. Health Inf. doi: 10.1109/JBHI.2022.3213171 – volume: 136 year: 2023 ident: 10.1016/j.asoc.2025.112731_b2 article-title: Evolutionary computation-based multitask learning network for railway passenger comfort evaluation from EEG signals publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2023.110079 – volume: 27 start-page: 5459 issue: 11 year: 2023 ident: 10.1016/j.asoc.2025.112731_b3 article-title: Hierarchical transformer for motor imagery-based brain computer interface publication-title: IEEE J. Biomed. Health Inf. doi: 10.1109/JBHI.2023.3304646 – ident: 10.1016/j.asoc.2025.112731_b31 – volume: 16 issue: 5 year: 2019 ident: 10.1016/j.asoc.2025.112731_b6 article-title: Deep learning-based electroencephalography analysis: a systematic review publication-title: J. Neural Eng. doi: 10.1088/1741-2552/ab260c – ident: 10.1016/j.asoc.2025.112731_b11 doi: 10.1109/MLSP.2019.8918693 – volume: 18 year: 2021 ident: 10.1016/j.asoc.2025.112731_b22 article-title: Uncovering the structure of clinical EEG signals with self-supervised learning publication-title: J. Neural Eng. doi: 10.1088/1741-2552/abca18 – volume: 15 issue: 653659 year: 2021 ident: 10.1016/j.asoc.2025.112731_b10 article-title: BENDR: Using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG data publication-title: Front. Hum. Neurosci. – year: 2023 ident: 10.1016/j.asoc.2025.112731_b18 article-title: Architecture-agnostic masked image modeling - From ViT back to CNN – volume: 28 start-page: 1720 issue: 8 year: 2020 ident: 10.1016/j.asoc.2025.112731_b29 article-title: Modeling EEG data distribution with a Wasserstein generative adversarial network to predict RSVP events publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2020.3006180 – volume: 533 start-page: 247 year: 2016 ident: 10.1016/j.asoc.2025.112731_b1 article-title: Restoring cortical control of functional movement in a human with quadriplegia publication-title: Nature doi: 10.1038/nature17435 – year: 2023 ident: 10.1016/j.asoc.2025.112731_b17 article-title: Denoising masked AutoEncoders helps robust classification – ident: 10.1016/j.asoc.2025.112731_b23 doi: 10.1145/3534678.3539178 – volume: 18 start-page: 1000 issue: 06 year: 2020 ident: 10.1016/j.asoc.2025.112731_b4 article-title: A fast and accurate SSVEP brain machine interface using dry electrodes and high frequency stimuli by employing ensemble learning publication-title: IEEE Latin Am. Trans. doi: 10.1109/TLA.2020.9099676 – year: 2022 ident: 10.1016/j.asoc.2025.112731_b19 – year: 2023 ident: 10.1016/j.asoc.2025.112731_b20 article-title: Masked frequency modeling for self-supervised visual pre-training – ident: 10.1016/j.asoc.2025.112731_b16 doi: 10.1109/CVPR52688.2022.01553 – ident: 10.1016/j.asoc.2025.112731_b9 doi: 10.1145/3503161.3548243 – volume: 14 start-page: 2512 issue: 3 year: 2023 ident: 10.1016/j.asoc.2025.112731_b25 article-title: GMSS: Graph-based multi-task self-supervised learning for EEG emotion recognition publication-title: IEEE Trans. Affect. Comput. doi: 10.1109/TAFFC.2022.3170428 – year: 2020 ident: 10.1016/j.asoc.2025.112731_b21 article-title: Language models are few-shot learners – year: 2021 ident: 10.1016/j.asoc.2025.112731_b33 – volume: 26 start-page: 563 issue: 3 year: 2018 ident: 10.1016/j.asoc.2025.112731_b5 article-title: A hybrid network for ERP detection and analysis based on restricted Boltzmann machine publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2018.2803066 – ident: 10.1016/j.asoc.2025.112731_b13 doi: 10.1109/ICASSP49357.2023.10097183 – volume: 50 start-page: 3033 issue: 7 year: 2020 ident: 10.1016/j.asoc.2025.112731_b27 article-title: Making sense of spatio-temporal preserving representations for EEG-based human intention recognition publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2019.2905157 – volume: 8 start-page: 93907 year: 2020 ident: 10.1016/j.asoc.2025.112731_b28 article-title: Self-supervised learning from multi-sensor data for sleep recognition publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2994593 – volume: 9 start-page: 70639 year: 2021 ident: 10.1016/j.asoc.2025.112731_b30 article-title: Complementary photoplethysmogram synthesis from electrocardiogram using generative adversarial network publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3078534 – volume: 35 start-page: 857 issue: 1 year: 2023 ident: 10.1016/j.asoc.2025.112731_b8 article-title: Self-supervised learning: Generative or contrastive publication-title: IEEE Trans. Knowl. Data Eng. – volume: 12 issue: 4 year: 2015 ident: 10.1016/j.asoc.2025.112731_b7 article-title: Enhancing performances of SSVEP-based brain-computer interfaces via exploiting inter-subject information publication-title: J. Neural Eng. doi: 10.1088/1741-2560/12/4/046006 – ident: 10.1016/j.asoc.2025.112731_b24 doi: 10.1007/978-3-031-16437-8_38 – volume: 28 start-page: 2687 issue: 5 year: 2024 ident: 10.1016/j.asoc.2025.112731_b32 article-title: MaskCAE: Masked convolutional AutoEncoder via sensor data reconstruction for self-supervised human activity recognition publication-title: IEEE J. Biomed. Health Inf. doi: 10.1109/JBHI.2024.3373019 – year: 2024 ident: 10.1016/j.asoc.2025.112731_b14 – volume: 8 issue: 5 year: 2019 ident: 10.1016/j.asoc.2025.112731_b34 article-title: EEG dataset and OpenBMI toolbox for three BCI paradigms: an investigation into BCI illiteracy publication-title: Gigascience |
| SSID | ssj0016928 |
| Score | 2.4361985 |
| Snippet | Deep learning methods currently represent the state-of-the-art (SOTA) in electroencephalography (EEG) decoding, primarily focusing on the development of... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 112731 |
| SubjectTerms | Fractional fourier transform (frFT) Masked autoencoder (MAE) Motor imagery (MI) Self-supervised learning (SSL) Steady-state visual evoked potential (SSVEP) |
| Title | EEG generalizable representations learning via masked fractional fourier domain modeling |
| URI | https://dx.doi.org/10.1016/j.asoc.2025.112731 |
| Volume | 170 |
| WOSCitedRecordID | wos001417868600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 1568-4946 databaseCode: AIEXJ dateStart: 20010601 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0016928 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELZgy4ELlJcoLcgHbquskjiO4-OqWkpRVXEosJwiO3ZK-siuNpuqP59xbCfsAhU9cIkiazx5zKfxZDLjD6H3WkSRojoJGA-zIJFUB5lKo6AMlemLhJC9K_n_esJOT7P5nH92f_Cbjk6A1XV2e8uX_9XUMAbGNq2z9zB3rxQG4ByMDkcwOxz_yfCz2ZHhRTa5JlOxdWV4UZZDk1HdeKaI8_FNJcbXormEoLNc2Q6Hrp_R0tipxbWoasuV4xc4v1-ti10bcOJdVXq79hIbSegfrax69E2tg1sMgidV26Goqou2F_umuwKD72Jx3gon69ISMfWVzIMnTcH23OUXvau1JCHOWUKox-wS8JsftymFi4kAiE6M-skgvLlp9tZi1pcY-uq1i9zoyI2O3Op4iHZiRnk2QjvT49n8U__TKeUdFW9_567HypYDbt_Jn-OYX2KTs130xH1U4KkFwzP0QNfP0VNP2IGd_36B5oANvIENvIUN7LGBARvYYgMP2MAOG9hiA3tsvERfPszODj8GjlojKEgYroNSsyiGx4g51bEMS1EUktBUwfd3pJOSKC1EqiihJOQqYSyTUhEapakkBS8jSV6hUb2o9WuEiRRMFgllmpOkLEvOQiFiBuoyknKS7qHIv6i8cPvOG_qTq_zvJtpD437O0u66cqc09e8_d3GjjQdzgNMd897c6yr76PGA8wM0Wq9a_RY9Km7WVbN657D0E-Wyj6Q |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=EEG+generalizable+representations+learning+via+masked+fractional+fourier+domain+modeling&rft.jtitle=Applied+soft+computing&rft.au=Zhang%2C+Shubin&rft.au=An%2C+Dong&rft.au=Liu%2C+Jincun&rft.au=Wei%2C+Yaoguang&rft.date=2025-02-01&rft.issn=1568-4946&rft.volume=170&rft.spage=112731&rft_id=info:doi/10.1016%2Fj.asoc.2025.112731&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_asoc_2025_112731 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1568-4946&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1568-4946&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1568-4946&client=summon |