Cauchy non-convex sparse feature selection method for the high-dimensional small-sample problem in motor imagery EEG decoding

The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is a...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Frontiers in neuroscience Ročník 17; s. 1292724
Hlavní autori:	Zhang, Shaorong, Wang, Qihui, Zhang, Benxin, Liang, Zhen, Zhang, Li, Li, Linling, Huang, Gan, Zhang, Zhiguo, Feng, Bao, Yu, Tianyou
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Lausanne Frontiers Research Foundation 03.11.2023 Frontiers Media S.A
Predmet:	Classification Datasets Deep learning EEG EEG decoding Electroencephalography Feature selection Frequency dependence high-dimensional small-sample Mental task performance motor imagery Motor task performance nonconvex regularization Regularization methods Signal processing Sparsity
ISSN:	1662-453X, 1662-4548, 1662-453X
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is an effective method for addressing this issue. However, the most commonly employed sparse regularization models in motor imagery decoding, such as the least absolute shrinkage and selection operator (LASSO), is a biased estimation method and leads to the loss of target feature information. In this paper, we propose a non-convex sparse regularization model that employs the Cauchy function. By designing a proximal gradient algorithm, our proposed model achieves closer-to-unbiased estimation than existing models. Therefore, it can learn more accurate, discriminative, and effective feature information. Additionally, the proposed method can perform feature selection and classification simultaneously, without requiring additional classifiers. We conducted experiments on two publicly available motor imagery EEG datasets. The proposed method achieved an average classification accuracy of 82.98% and 64.45% in subjectdependent and subject-independent decoding assessment methods, respectively. The experimental results show that the proposed method can significantly improve the performance of motor imagery decoding, with better classification performance than existing feature selection and deep learning methods. Furthermore, the proposed model shows better generalization capability, with parameter consistency over different datasets and robust classification across different training sample sizes. Compared with existing sparse regularization methods, the proposed method converges faster, and with shorter model training time.
AbstractList	IntroductionThe time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is an effective method for addressing this issue. However, the most commonly employed sparse regularization models in motor imagery decoding, such as the least absolute shrinkage and selection operator (LASSO), is a biased estimation method and leads to the loss of target feature information.MethodsIn this paper, we propose a non-convex sparse regularization model that employs the Cauchy function. By designing a proximal gradient algorithm, our proposed model achieves closer-to-unbiased estimation than existing sparse models. Therefore, it can learn more accurate, discriminative, and effective feature information. Additionally, the proposed method can perform feature selection and classification simultaneously, without requiring additional classifiers.ResultsWe conducted experiments on two publicly available motor imagery EEG datasets. The proposed method achieved an average classification accuracy of 82.98% and 64.45% in subject-dependent and subject-independent decoding assessment methods, respectively.ConclusionThe experimental results show that the proposed method can significantly improve the performance of motor imagery decoding, with better classification performance than existing feature selection and deep learning methods. Furthermore, the proposed model shows better generalization capability, with parameter consistency over different datasets and robust classification across different training sample sizes. Compared with existing sparse regularization methods, the proposed method converges faster, and with shorter model training time. The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is an effective method for addressing this issue. However, the most commonly employed sparse regularization models in motor imagery decoding, such as the least absolute shrinkage and selection operator (LASSO), is a biased estimation method and leads to the loss of target feature information.IntroductionThe time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is an effective method for addressing this issue. However, the most commonly employed sparse regularization models in motor imagery decoding, such as the least absolute shrinkage and selection operator (LASSO), is a biased estimation method and leads to the loss of target feature information.In this paper, we propose a non-convex sparse regularization model that employs the Cauchy function. By designing a proximal gradient algorithm, our proposed model achieves closer-to-unbiased estimation than existing sparse models. Therefore, it can learn more accurate, discriminative, and effective feature information. Additionally, the proposed method can perform feature selection and classification simultaneously, without requiring additional classifiers.MethodsIn this paper, we propose a non-convex sparse regularization model that employs the Cauchy function. By designing a proximal gradient algorithm, our proposed model achieves closer-to-unbiased estimation than existing sparse models. Therefore, it can learn more accurate, discriminative, and effective feature information. Additionally, the proposed method can perform feature selection and classification simultaneously, without requiring additional classifiers.We conducted experiments on two publicly available motor imagery EEG datasets. The proposed method achieved an average classification accuracy of 82.98% and 64.45% in subject-dependent and subject-independent decoding assessment methods, respectively.ResultsWe conducted experiments on two publicly available motor imagery EEG datasets. The proposed method achieved an average classification accuracy of 82.98% and 64.45% in subject-dependent and subject-independent decoding assessment methods, respectively.The experimental results show that the proposed method can significantly improve the performance of motor imagery decoding, with better classification performance than existing feature selection and deep learning methods. Furthermore, the proposed model shows better generalization capability, with parameter consistency over different datasets and robust classification across different training sample sizes. Compared with existing sparse regularization methods, the proposed method converges faster, and with shorter model training time.ConclusionThe experimental results show that the proposed method can significantly improve the performance of motor imagery decoding, with better classification performance than existing feature selection and deep learning methods. Furthermore, the proposed model shows better generalization capability, with parameter consistency over different datasets and robust classification across different training sample sizes. Compared with existing sparse regularization methods, the proposed method converges faster, and with shorter model training time. The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is an effective method for addressing this issue. However, the most commonly employed sparse regularization models in motor imagery decoding, such as the least absolute shrinkage and selection operator (LASSO), is a biased estimation method and leads to the loss of target feature information. In this paper, we propose a non-convex sparse regularization model that employs the Cauchy function. By designing a proximal gradient algorithm, our proposed model achieves closer-to-unbiased estimation than existing models. Therefore, it can learn more accurate, discriminative, and effective feature information. Additionally, the proposed method can perform feature selection and classification simultaneously, without requiring additional classifiers. We conducted experiments on two publicly available motor imagery EEG datasets. The proposed method achieved an average classification accuracy of 82.98% and 64.45% in subjectdependent and subject-independent decoding assessment methods, respectively. The experimental results show that the proposed method can significantly improve the performance of motor imagery decoding, with better classification performance than existing feature selection and deep learning methods. Furthermore, the proposed model shows better generalization capability, with parameter consistency over different datasets and robust classification across different training sample sizes. Compared with existing sparse regularization methods, the proposed method converges faster, and with shorter model training time.
Author	Liang, Zhen Li, Linling Zhang, Zhiguo Zhang, Shaorong Yu, Tianyou Zhang, Li Zhang, Benxin Wang, Qihui Feng, Bao Huang, Gan
Author_xml	– sequence: 1 givenname: Shaorong surname: Zhang fullname: Zhang, Shaorong – sequence: 2 givenname: Qihui surname: Wang fullname: Wang, Qihui – sequence: 3 givenname: Benxin surname: Zhang fullname: Zhang, Benxin – sequence: 4 givenname: Zhen surname: Liang fullname: Liang, Zhen – sequence: 5 givenname: Li surname: Zhang fullname: Zhang, Li – sequence: 6 givenname: Linling surname: Li fullname: Li, Linling – sequence: 7 givenname: Gan surname: Huang fullname: Huang, Gan – sequence: 8 givenname: Zhiguo surname: Zhang fullname: Zhang, Zhiguo – sequence: 9 givenname: Bao surname: Feng fullname: Feng, Bao – sequence: 10 givenname: Tianyou surname: Yu fullname: Yu, Tianyou
BookMark	eNp9kU9r3DAQxUVJock2XyAnQS-9eCNL_iMdy7JNA4FcGshNjOXxWotsbSW5dA_97tVmUyg59DRi9HuPmXlX5GL2MxJyU7K1EFLdDrOd45ozLtYlV7zl1TtyWTYNL6paPF_88_5ArmLcM9ZwWfFL8nsDixmPNPsVxs8_8ReNBwgR6YCQloA0okOTrJ_phGn0PR18oGlEOtrdWPR2wjnmX3A0TuBcEWE6OKSH4DuHE7VZ51OW2Al2GI50u72jPRrf23n3kbwfwEW8fq0r8vR1-33zrXh4vLvffHkoTFXKVLRt2zFQgFUnhBGlBBBoZKXKjhtZVlUnGe-6YRAdE6JWUqLhQqKCGmvToFiR-7Nv72GvDyHPEo7ag9UvDR92GkKyxqFmjPUliKZlqq-Y7GEwrGsHJngDqgeRvT6fvfKGPxaMSU82GnQOZvRL1FyqumVCqSajn96ge7-EfKoTJWshWZvJFZFnygQfY8BBG5vgdPEUwDpdMn3KWL9krE8Z69eMs5S_kf7d7T-iP2nGrvc
CitedBy_id	crossref_primary_10_1007_s11042_025_20605_8 crossref_primary_10_1080_15368378_2024_2415089 crossref_primary_10_3390_sym17060887
Cites_doi	10.1002/hbm.23730 10.1109/ACCESS.2018.2880454 10.3389/fnhum.2023.1117670 10.1016/j.ijepes.2012.04.048 10.1109/TBME.2010.2082539 10.1109/TNSRE.2017.2757519 10.1016/j.sigpro.2020.107631 10.1088/1741-2552/aace8c 10.1016/j.jneumeth.2007.03.005 10.1088/1741-2552/acbb2c 10.1016/j.patcog.2010.03.022 10.1109/TBME.2021.3137184 10.1007/s40747-021-00452-4 10.1109/MSP.2008.4408441 10.1109/JSEN.2020.3016402 10.3390/mi13060927 10.1016/j.bspc.2022.104066 10.1109/TBME.2022.3193277 10.1016/j.bspc.2022.103825 10.1088/1741-2552/ab405f 10.1109/JBHI.2018.2832538 10.1007/s10915-018-0801-z 10.1093/bioinformatics/btad135 10.3389/fnins.2019.01275 10.1016/j.bspc.2022.103634 10.1109/TPAMI.2022.3185773 10.1109/TSP.2020.3032231 10.1016/j.bspc.2021.102763 10.1016/j.neuroimage.2023.120209 10.1109/TIE.2018.2793271 10.1109/TNNLS.2018.2789927 10.1016/j.bspc.2020.102144 10.1109/TNSRE.2021.3071140 10.3390/informatics6020021 10.1109/TNNLS.2019.2946869
ContentType	Journal Article
Copyright	2023. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. Copyright © 2023 Zhang, Wang, Zhang, Liang, Zhang, Li, Huang, Zhang, Feng and Yu.
Copyright_xml	– notice: 2023. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: Copyright © 2023 Zhang, Wang, Zhang, Liang, Zhang, Li, Huang, Zhang, Feng and Yu.
DBID	AAYXX CITATION 3V. 7XB 88I 8FE 8FH 8FK ABUWG AFKRA AZQEC BBNVY BENPR BHPHI CCPQU DWQXO GNUQQ HCIFZ LK8 M2P M7P PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI Q9U 7X8 DOA
DOI	10.3389/fnins.2023.1292724
DatabaseName	CrossRef ProQuest Central (Corporate) ProQuest Central (purchase pre-March 2016) Science Database (Alumni Edition) ProQuest SciTech Collection ProQuest Natural Science Collection ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials - QC Biological Science Collection ProQuest Central ProQuest Natural Science Collection ProQuest One ProQuest Central ProQuest Central Student SciTech Premium Collection Biological Sciences Science Database Biological Science Database Proquest Central Premium ProQuest One Academic (New) ProQuest Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central Basic MEDLINE - Academic DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Publicly Available Content Database ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Natural Science Collection ProQuest Central ProQuest One Applied & Life Sciences Natural Science Collection ProQuest Central Korea Biological Science Collection ProQuest Central (New) ProQuest Science Journals (Alumni Edition) ProQuest Biological Science Collection ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition Biological Science Database ProQuest SciTech Collection ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic Publicly Available Content Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Anatomy & Physiology
EISSN	1662-453X
ExternalDocumentID	oai_doaj_org_article_000d1a36709d408dafc0b7f0326a9da3 10_3389_fnins_2023_1292724
GroupedDBID	--- 29H 2WC 53G 5GY 5VS 88I 8FE 8FH 9T4 AAFWJ AAYXX ABUWG ACGFO ACGFS ADRAZ AEGXH AENEX AFFHD AFKRA AFPKN AIAGR ALMA_UNASSIGNED_HOLDINGS AZQEC BBNVY BENPR BHPHI BPHCQ CCPQU CITATION CS3 DIK DU5 DWQXO E3Z EBS EJD EMOBN F5P FRP GNUQQ GROUPED_DOAJ GX1 HCIFZ HYE KQ8 LK8 M2P M48 M7P O5R O5S OK1 OVT P2P PGMZT PHGZM PHGZT PIMPY PQGLB PQQKQ PROAC RNS RPM W2D 3V. 7XB 8FK ACXDI PKEHL PQEST PQUKI Q9U 7X8
ID	FETCH-LOGICAL-c418t-777b0a9ae4b33c318aa3ec8491b2c8144b802bbff3b0335988ec238e9a5e5c6e3
IEDL.DBID	M7P
ISICitedReferencesCount	2
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001104087300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1662-453X 1662-4548
IngestDate	Fri Oct 03 12:44:46 EDT 2025 Sun Nov 09 09:45:03 EST 2025 Fri Jul 25 11:37:16 EDT 2025 Tue Nov 18 22:41:46 EST 2025 Sat Nov 29 04:31:14 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c418t-777b0a9ae4b33c318aa3ec8491b2c8144b802bbff3b0335988ec238e9a5e5c6e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
OpenAccessLink	https://www.proquest.com/docview/2885380770?pq-origsite=%requestingapplication%
PQID	2885380770
PQPubID	4424402
ParticipantIDs	doaj_primary_oai_doaj_org_article_000d1a36709d408dafc0b7f0326a9da3 proquest_miscellaneous_2895703996 proquest_journals_2885380770 crossref_citationtrail_10_3389_fnins_2023_1292724 crossref_primary_10_3389_fnins_2023_1292724
PublicationCentury	2000
PublicationDate	2023-11-03
PublicationDateYYYYMMDD	2023-11-03
PublicationDate_xml	– month: 11 year: 2023 text: 2023-11-03 day: 03
PublicationDecade	2020
PublicationPlace	Lausanne
PublicationPlace_xml	– name: Lausanne
PublicationTitle	Frontiers in neuroscience
PublicationYear	2023
Publisher	Frontiers Research Foundation Frontiers Media S.A
Publisher_xml	– name: Frontiers Research Foundation – name: Frontiers Media S.A
References	Dai (ref10) 2020; 17 Chadebec (ref5) 2022; 45 Miao (ref26) 2023; 276 Autthasan (ref2) 2021; 69 Kwon (ref17) 2019; 31 Jia (ref14) 2020 Wu (ref35) 2019; 13 You (ref36) 2019; 78 Lawhern (ref18) 2018; 15 Li (ref19) 2023; 79 Sakhavi (ref29) 2018; 29 Park (ref27) 2018; 26 Lotte (ref22) 2011; 58 Blankertz (ref4) 2008; 25 Zheng (ref42) 2022; 76 Hoffmann (ref13) 2008 Liao (ref20) 2023; 17 Mane (ref23) 2020 Zhang (ref41) 2021; 63 Karakuş (ref16) 2020; 68 Zhang (ref39) 2022; 77 Shen (ref31) 2022; 8 Miao (ref25) 2023 Wen (ref34) 2018; 6 Zhang (ref40) 2020; 174 Miao (ref24) 2021; 29 Ang (ref1) 2008 Zancanaro (ref37) 2021 Chen (ref7) 2023; 20 Chen (ref8) 2023; 39 Hoffmann (ref12) 2008; 167 Liu (ref21) 2022; 70 Schirrmeister (ref30) 2017; 38 Radman (ref28) 2021; 68 Datta (ref11) 2012; 42 Jiao (ref15) 2018; 23 Chopra (ref9) 2010; 43 Wang (ref33) 2018; 65 Bishop (ref3) 2006 Too (ref32) 2019; 6 Zhang (ref38) 2020; 21 Chang (ref6) 2022; 13
References_xml	– year: 2020 ident: ref23 – volume: 38 start-page: 5391 year: 2017 ident: ref30 article-title: Deep learning with convolutional neural networks for EEG decoding and visualization publication-title: Hum. Brain Mapp. doi: 10.1002/hbm.23730 – volume: 6 start-page: 69883 year: 2018 ident: ref34 article-title: A survey on non-convex regularization-based sparse and low-rank recovery in signal processing, statistics, and machine learning publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2880454 – volume: 17 start-page: 1117670 year: 2023 ident: ref20 article-title: Motor imagery brain-computer interface rehabilitation system enhances upper limb performance and improves brain activity in stroke patients: A clinical study publication-title: Front. Hum. Neurosci. doi: 10.3389/fnhum.2023.1117670 – year: 2008 ident: ref13 – volume: 42 start-page: 517 year: 2012 ident: ref11 article-title: A binary-real-coded differential evolution for unit commitment problem publication-title: Int. J. Electr. Power Energy Syst. doi: 10.1016/j.ijepes.2012.04.048 – volume: 58 start-page: 355 year: 2011 ident: ref22 article-title: Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2010.2082539 – volume: 26 start-page: 498 year: 2018 ident: ref27 article-title: Filter bank regularized common spatial pattern ensemble for small sample motor imagery classification publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2017.2757519 – volume: 174 start-page: 107631 year: 2020 ident: ref40 article-title: A TV-log non-convex approach for image deblurring with impulsive noise publication-title: Signal Process. doi: 10.1016/j.sigpro.2020.107631 – volume: 15 start-page: 056013 year: 2018 ident: ref18 article-title: EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces publication-title: J. Neural Eng. doi: 10.1088/1741-2552/aace8c – volume: 167 start-page: 115 year: 2008 ident: ref12 article-title: An efficient P300-based brain-computer interface for disabled subjects publication-title: J. Neurosci. Methods doi: 10.1016/j.jneumeth.2007.03.005 – volume: 20 start-page: 026001 year: 2023 ident: ref7 article-title: Filter bank sinc-convolutional network with channel self-attention for high performance motor imagery decoding publication-title: J. Neural Eng. doi: 10.1088/1741-2552/acbb2c – volume: 43 start-page: 2609 year: 2010 ident: ref9 article-title: Total variation, adaptive total variation and non-convex smoothly clipped absolute deviation penalty for denoising blocky images publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2010.03.022 – volume: 69 start-page: 2105 year: 2021 ident: ref2 article-title: MIN2net: end-to-end multi-task learning for subject-independent motor imagery EEG classification publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2021.3137184 – volume: 8 start-page: 2769 year: 2022 ident: ref31 article-title: Two-stage improved Grey wolf optimization algorithm for feature selection on high-dimensional classification publication-title: Complex Intell. Syst. doi: 10.1007/s40747-021-00452-4 – year: 2008 ident: ref1 – year: 2020 ident: ref14 – volume: 25 start-page: 41 year: 2008 ident: ref4 article-title: Optimizing spatial filters for robust EEG single-trial analysis publication-title: IEEE Signal Process. Mag. doi: 10.1109/MSP.2008.4408441 – volume: 21 start-page: 1764 year: 2020 ident: ref38 article-title: Fused group lasso: A new EEG classification model with spatial smooth constraint for motor imagery-based brain -computer interface publication-title: IEEE Sensors J. doi: 10.1109/JSEN.2020.3016402 – volume: 13 start-page: 927 year: 2022 ident: ref6 article-title: Motor imagery EEG classification based on transfer learning and multi-scale convolution network publication-title: Micromachines doi: 10.3390/mi13060927 – volume: 79 start-page: 104066 year: 2023 ident: ref19 article-title: A parallel multi-scale temporal-frequency block convolutional neural network based on channel attention module for motor imagery classification publication-title: Biomed. Signal Proces. Control doi: 10.1016/j.bspc.2022.104066 – volume: 70 start-page: 436 year: 2022 ident: ref21 article-title: FBMSNet: A filter-Bank multi-scale convolutional neural network for EEG-based motor imagery decoding publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2022.3193277 – volume: 77 start-page: 103825 year: 2022 ident: ref39 article-title: Overall optimization of CSP based on ensemble learning for motor imagery EEG decoding publication-title: Biomed. Signal Proces. Control doi: 10.1016/j.bspc.2022.103825 – volume: 17 start-page: 016025 year: 2020 ident: ref10 article-title: HS-CNN: a CNN with hybrid convolution scale for EEG motor imagery classification publication-title: J. Neural Eng. doi: 10.1088/1741-2552/ab405f – volume: 23 start-page: 631 year: 2018 ident: ref15 article-title: Sparse group representation model for motor imagery EEG classification publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2018.2832538 – volume: 78 start-page: 1063 year: 2019 ident: ref36 article-title: A non-convex model with minimax concave penalty for image restoration publication-title: J. Sci. Comput. doi: 10.1007/s10915-018-0801-z – volume: 39 start-page: btad 135 year: 2023 ident: ref8 article-title: Graph convolutional network-based feature selection for high-dimensional and low-sample size data publication-title: Bioinformatics doi: 10.1093/bioinformatics/btad135 – volume: 13 start-page: 1275 year: 2019 ident: ref35 article-title: A parallel multiscale filter bank convolutional neural networks for motor imagery EEG classification publication-title: Front. Neurosci. doi: 10.3389/fnins.2019.01275 – volume: 76 start-page: 103634 year: 2022 ident: ref42 article-title: Ensemble learning method based on temporal, spatial features with multi-scale filter banks for motor imagery EEG classification publication-title: Biomed. Signal Proces. Control doi: 10.1016/j.bspc.2022.103634 – volume: 45 start-page: 1 year: 2022 ident: ref5 article-title: Data augmentation in high dimensional low sample size setting using a geometry-based variational autoencoder publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2022.3185773 – volume-title: Pattern recognition and machine learning year: 2006 ident: ref3 – volume: 68 start-page: 6159 year: 2020 ident: ref16 article-title: Convergence guarantees for non-convex optimisation with cauchy-based penalties publication-title: IEEE Trans. Signal Process. doi: 10.1109/TSP.2020.3032231 – volume: 68 start-page: 102763 year: 2021 ident: ref28 article-title: Feature fusion for improving performance of motor imagery brain-computer interface system publication-title: Biomed. Signal Proces. Control doi: 10.1016/j.bspc.2021.102763 – volume: 276 start-page: 120209 year: 2023 ident: ref26 article-title: LMDA-net: A lightweight multi-dimensional attention network for general EEG-based brain-computer interfaces and interpretability publication-title: Neuro Image doi: 10.1016/j.neuroimage.2023.120209 – volume: 65 start-page: 7332 year: 2018 ident: ref33 article-title: Non-convex sparse regularization and convex optimization for bearing fault diagnosis publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2018.2793271 – year: 2021 ident: ref37 – year: 2023 ident: ref25 – volume: 29 start-page: 5619 year: 2018 ident: ref29 article-title: Learning temporal information for brain-computer interface using convolutional neural networks publication-title: IEEE Trans. Neural Networks Learn. Syst. doi: 10.1109/TNNLS.2018.2789927 – volume: 63 start-page: 102144 year: 2021 ident: ref41 article-title: Hybrid deep neural network using transfer learning for EEG motor imagery decoding publication-title: Biomed. Signal Proces. Control doi: 10.1016/j.bspc.2020.102144 – volume: 29 start-page: 699 year: 2021 ident: ref24 article-title: Learning common temporal-frequency-spatial patterns for motor imagery classification publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2021.3071140 – volume: 6 start-page: 21 year: 2019 ident: ref32 article-title: A new co-evolution binary particle swarm optimization with multiple inertia weight strategy for feature selection publication-title: Informatics. mdpi doi: 10.3390/informatics6020021 – volume: 31 start-page: 3839 year: 2019 ident: ref17 article-title: Subject-independent brain-computer interfaces based on deep convolutional neural networks publication-title: IEEE Trans. Neural Networks Learn. Syst. doi: 10.1109/TNNLS.2019.2946869
SSID	ssj0062842
Score	2.369257
Snippet	The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these... IntroductionThe time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these...
SourceID	doaj proquest crossref
SourceType	Open Website Aggregation Database Enrichment Source Index Database
StartPage	1292724
SubjectTerms	Classification Datasets Deep learning EEG EEG decoding Electroencephalography Feature selection Frequency dependence high-dimensional small-sample Mental task performance motor imagery Motor task performance nonconvex regularization Regularization methods Signal processing Sparsity
SummonAdditionalLinks	– databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrZ3Bb9MwFMatadqBCwLGtMJADwntgrw5thPbxzF1cJo4bNJuke04olKboaZF9MD_zntOWjFNGheuraMmfrbf96X27zH2UapKaW8Sr1ysuA664LatEi-Nl62rpA6Vz8UmzPW1vbtz3_4q9UV7wgY88NBxdNKgKXzGjDVa2Ma3UQTTCpQd3jU-cz5R9WzN1LAGV7joyuGIDFowd952s47Y3FKdYX6TRuoHaSjT-h8txjnDXL1gz0dpCBfDLb1ke6l7xQ4vOrTFiw2cQt6smd-CH7Lfl34dv28AzTvPG8d_AS4Nyz5BmzKqE_pc4AZ7HYYi0YDqFFDtAQGKeUNQ_wHIAf3Cz-e898QJhrHADMzwunv04zBbEOViA9PpF2jQq1Kue81ur6Y3l1_5WEmBR13YFUpoEwRxuHVQKuI09l6laLUrgowWPVWwQobQtioIRUw_myLm8uR8mcpYJXXE9vGB0jED70qNMiFZj31chjLERoqYZDDKo9axE1ZsO7aOI2acql3Ma7QbFIw6B6OmYNRjMCbs0-6aHwNk48nWnyleu5YEyM4f4LCpx2FT_2vYTNjJNtr1OGvxVyyKFyuMERP2Yfc1zjf6E8V36X5NbRxBy9Amvvkf9_GWPaNny6cb1QnbXy3X6R07iD9Xs375Pg_qP2oH_UQ priority: 102 providerName: Directory of Open Access Journals
Title	Cauchy non-convex sparse feature selection method for the high-dimensional small-sample problem in motor imagery EEG decoding
URI	https://www.proquest.com/docview/2885380770 https://www.proquest.com/docview/2895703996 https://doaj.org/article/000d1a36709d408dafc0b7f0326a9da3
Volume	17
WOSCitedRecordID	wos001104087300001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: DOA dateStart: 20070101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: M7P dateStart: 20230101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: BENPR dateStart: 20230101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: PIMPY dateStart: 20230101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database customDbUrl: eissn: 1662-453X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0062842 issn: 1662-453X databaseCode: M2P dateStart: 20230101 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Nb9MwGLbYxoELXwNRGJWREBdklthO7JzQNnXAYVWEQCqnyHacUalNRtMieuC_876OWwkh7cIlh8ROHD32--GP5yHkNRe5kEZ5lhcuZ9LKlOkm9yxThjdFzqXNTRCbUNOpns2KMk649XFb5c4mBkNddw7nyE-5BseiE6WS9zc_GKpG4epqlNA4IEfIkiDC1r1yZ4lzML1htTPHk0EQmg-HZiApK06bdt4iWzcX78DjccXlX44p8Pf_Y56Dz7l88L-tfUjux2iTng3d4xG549vH5PishUx7uaVvaNj_GSbWj8nvC7Nx37e07VoW9qL_omBtVr2njQ_sn7QPmjkAJB10pykEvBQCSIqcx6xGnYCB44P2S7NYsN4g9TCNmjV0DvU6SPHpfInEGVs6mXygNaS_6D6fkK-Xky8XH1kUZ2BOpnoNUbmyCVJ7SyuEA8tgjPBOyyK13GlI06xOuLVNI2wikCZQewfhgS9M5jOXe_GUHMIP-WeEmiKTgJ7XBgDLbGZdzRPnuVXCQPikRyTdIVO5yFyOAhqLCjIYRLMKaFaIZhXRHJG3-zo3A2_HraXPEfB9SeTcDje61XUVhzAu09epCYR3tUx0bRqXWNUkEACbojZiRE52faGKhgC-su8II_Jq_xiGMK7LmNZ3GyxTIA8aZJ7Pb3_FC3IPWx2OQooTcrhebfxLctf9XM_71ZgcqJkek6PzybT8PA6TC3C94uU4jAp4Un66Kr_9ATCBE5E
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3Pb9MwFH4aHRJc-DUQhQFGAi4oLLWdxDkgNEbHqm3VDkMap8x2HKjUJqNpgR74l_gbec9JKiGk3XbgmtiO4nx-P-Ln7wN4wUUspE5cEKc2DqSRg0AVsQuiRPMijbk0sfZiE8l4rM7O0pMN-N2dhaGyys4mekOdV5b-ke9whY5FhUkSvrv4FpBqFO2udhIaDSwO3eoHpmz129EH_L4vOd8fnu4dBK2qQGDlQC0wnExMSJzU0ghhEdJaC2eVTAeGW4X5hVEhN6YohAkF8dspZ9GvuVRHLrKxEzjuNdiUCHbVg82T0fHJ5872x2js_f5qTGeRMBlojulgGpjuFOWkJH5wLt6gj-UJl3-5Qq8Y8I9D8F5u__b_Nj934FYbT7PdZgHchQ1X3oOt3VIvqtmKvWK-wtVvHWzBrz29tF9XrKzKwFfb_2RoT-e1Y4Xz_Kas9qpACFXWKGszDOkZhsiMWJ2DnJQQGhYTVs_0dBrUmsiVWavKwybYr1pgl8mMqEFWbDj8yHJM8ClAuA-frmQiHkAPX8g9BKbTSGJs5ZRGgEQmMjbnoXXcJEJjgKj6MOiQkNmWm50kQqYZ5miEnsyjJyP0ZC16-vB63eeiYSa5tPV7Ati6JbGK-wvV_EvWGikqRMgH2lP65TJUuS5saJIixBBfp7kWfdjusJe1pg6fsgZeH56vb6ORop0nXbpqSW1SYnrD3PrR5UM8gxsHp8dH2dFofPgYbtIb-IOfYht6i_nSPYHr9vtiUs-ftiuPwflVg_kPKbBsIw
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9MwGLbGQIgLXwNRGGAk4IK8prYTOweExtbCNFT1ANJuwXYcqNQmo0mBHvhj_Dre10kqIaTdduCa2I7iPH4_4tfPQ8hzLhIhjfIsSV3CpJUjpovEs1gZXqQJlzYxQWxCTaf67Cyd7ZDf_VkYLKvsbWIw1Hnl8B_5kGtwLDpSKhoWXVnE7Hjy5vwbQwUp3Gnt5TRaiJz6zQ9I3-rXJ8fwrV9wPhl_PHrPOoUB5uRINxBaKhshP7W0QjiAtzHCOy3TkeVOQ65hdcStLQphI4Fcd9o78HE-NbGPXeIFjHuFXFVIWh7KBme9F0jA7Ied1gRPJUFa0B7YgYQwHRblvESmcC4OwNtyxeVfTjFoB_zjGoK_m9z6n2fqNrnZRdn0sF0Wd8iOL--SvcPSNNVyQ1_SUPcaNhT2yK8js3ZfN7SsShZq8H9SsLKr2tPCB9ZTWgetIAAwbfW2KQT6FAJnilzPLEd9hJbbhNZLs1iw2iDlMu20eugc-lUNdJkvkTBkQ8fjdzSHtB_Dhnvk06VMxH2yCy_kHxBq0lhCxOW1AbDENrYu55Hz3CphIGzUAzLqUZG5jrEdhUMWGWRuiKQsIClDJGUdkgbk1bbPectXcmHrtwi2bUvkGg8XqtWXrDNdWJ6Qj0wg-stlpHNTuMiqIoLA36S5EQOy3-Mw6wwgPGULwgF5tr0Npgv3o0zpqzW2SZH_DTLuhxcP8ZRcBwRnH06mp4_IDXyBcBpU7JPdZrX2j8k1972Z16snYQlS8vmykfwHGcVzYg
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=Cauchy+non-convex+sparse+feature+selection+method+for+the+high-dimensional+small-sample+problem+in+motor+imagery+EEG+decoding&rft.jtitle=Frontiers+in+neuroscience&rft.au=Zhang%2C+Shaorong&rft.au=Wang%2C+Qihui&rft.au=Zhang%2C+Benxin&rft.au=Liang%2C+Zhen&rft.date=2023-11-03&rft.issn=1662-4548&rft.volume=17&rft.spage=1292724&rft_id=info:doi/10.3389%2Ffnins.2023.1292724&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1662-453X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1662-453X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1662-453X&client=summon