Subject-invariant feature learning for mTBI identification using LSTM-based variational autoencoder with adversarial regularization
Developing models for identifying mild traumatic brain injury (mTBI) has often been challenging due to large variations in data from subjects, resulting in difficulties for the mTBI-identification models to generalize to data from unseen subjects. To tackle this problem, we present a long short-term...
Uloženo v:
| Vydáno v: | Frontiers in signal processing (Lausanne) Ročník 2 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Frontiers Media S.A
30.11.2022
|
| Témata: | |
| ISSN: | 2673-8198, 2673-8198 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Developing models for identifying mild traumatic brain injury (mTBI) has often been challenging due to large variations in data from subjects, resulting in difficulties for the mTBI-identification models to generalize to data from unseen subjects. To tackle this problem, we present a long short-term memory-based adversarial variational autoencoder (LSTM-AVAE) framework for subject-invariant mTBI feature extraction. In the proposed model, first, an LSTM variational autoencoder (LSTM-VAE) combines the representation learning ability of the variational autoencoder (VAE) with the temporal modeling characteristics of the LSTM to learn the latent space representations from neural activity. Then, to detach the subject’s individuality from neural feature representations, and make the model proper for cross-subject transfer learning, an adversary network is attached to the encoder in a discriminative setting. The model is trained using the 1 held-out approach. The trained encoder is then used to extract the representations from the held-out subject’s data. The extracted representations are then classified into normal and mTBI groups using different classifiers. The proposed model is evaluated on cortical recordings of Thy1-GCaMP6s transgenic mice obtained
via
widefield calcium imaging, prior to and after inducing injury. In cross-subject transfer learning experiment, the proposed LSTM-AVAE framework achieves classification accuracy results of 95.8% and 97.79%, without and with utilizing conditional VAE (cVAE), respectively, demonstrating that the proposed model is capable of learning invariant representations from mTBI data. |
|---|---|
| AbstractList | Developing models for identifying mild traumatic brain injury (mTBI) has often been challenging due to large variations in data from subjects, resulting in difficulties for the mTBI-identification models to generalize to data from unseen subjects. To tackle this problem, we present a long short-term memory-based adversarial variational autoencoder (LSTM-AVAE) framework for subject-invariant mTBI feature extraction. In the proposed model, first, an LSTM variational autoencoder (LSTM-VAE) combines the representation learning ability of the variational autoencoder (VAE) with the temporal modeling characteristics of the LSTM to learn the latent space representations from neural activity. Then, to detach the subject’s individuality from neural feature representations, and make the model proper for cross-subject transfer learning, an adversary network is attached to the encoder in a discriminative setting. The model is trained using the 1 held-out approach. The trained encoder is then used to extract the representations from the held-out subject’s data. The extracted representations are then classified into normal and mTBI groups using different classifiers. The proposed model is evaluated on cortical recordings of Thy1-GCaMP6s transgenic mice obtained
via
widefield calcium imaging, prior to and after inducing injury. In cross-subject transfer learning experiment, the proposed LSTM-AVAE framework achieves classification accuracy results of 95.8% and 97.79%, without and with utilizing conditional VAE (cVAE), respectively, demonstrating that the proposed model is capable of learning invariant representations from mTBI data. Developing models for identifying mild traumatic brain injury (mTBI) has often been challenging due to large variations in data from subjects, resulting in difficulties for the mTBI-identification models to generalize to data from unseen subjects. To tackle this problem, we present a long short-term memory-based adversarial variational autoencoder (LSTM-AVAE) framework for subject-invariant mTBI feature extraction. In the proposed model, first, an LSTM variational autoencoder (LSTM-VAE) combines the representation learning ability of the variational autoencoder (VAE) with the temporal modeling characteristics of the LSTM to learn the latent space representations from neural activity. Then, to detach the subject’s individuality from neural feature representations, and make the model proper for cross-subject transfer learning, an adversary network is attached to the encoder in a discriminative setting. The model is trained using the 1 held-out approach. The trained encoder is then used to extract the representations from the held-out subject’s data. The extracted representations are then classified into normal and mTBI groups using different classifiers. The proposed model is evaluated on cortical recordings of Thy1-GCaMP6s transgenic mice obtained via widefield calcium imaging, prior to and after inducing injury. In cross-subject transfer learning experiment, the proposed LSTM-AVAE framework achieves classification accuracy results of 95.8% and 97.79%, without and with utilizing conditional VAE (cVAE), respectively, demonstrating that the proposed model is capable of learning invariant representations from mTBI data. |
| Author | Salsabilian, Shiva Najafizadeh, Laleh |
| Author_xml | – sequence: 1 givenname: Shiva surname: Salsabilian fullname: Salsabilian, Shiva – sequence: 2 givenname: Laleh surname: Najafizadeh fullname: Najafizadeh, Laleh |
| BookMark | eNp9kc1uFDEQhK0oSISQF-DkF5jFf_PjI0RAVlrEIcvZ6rHbG68mdmR7guDKi7MziSLEgVO3uqq-Q9cbch5TRELecbaRctDvfS7hYSOYEBvOuBatPCMXoutlM3A9nP-1vyZXpRwZY6IflGDdBfl9O49HtLUJ8RFygFipR6hzRjoh5BjigfqU6f3-45YGh7EGHyzUkCKdy6LubvdfmxEKOroSFgkmCnNNGG1ymOmPUO8ouEfMZXFMNONhnk7rr9X9lrzyMBW8ep6X5PvnT_vrm2b37cv2-sOusbLtawMaZAsDa7kdZeus7UcUTPuuax1zqneddU6B9Fpq7CXrTk4h3MAVjlY7Jy_J9onrEhzNQw73kH-aBMGsh5QPBnINdkKjWmSeI5OdZYqBH_noh15oJZX0qhcnlnhi2ZxKyehfeJyZpRWztmKWVsxzK6fQ8E_Ihrq-oGYI0_-ifwDMsZjy |
| CitedBy_id | crossref_primary_10_1088_1741_2552_ad3eb3 crossref_primary_10_1109_TNSRE_2024_3391067 |
| Cites_doi | 10.1364/boe.9.003017 10.1162/neco_a_01199 10.1038/sj.jcbfm.9600497 10.1016/j.injury.2010.03.032 10.1038/s41598-021-02371-3 10.1038/s41536-020-00114-y 10.1093/arclin/acp006 10.1088/1741-2552/abce70 10.3389/fnbeh.2016.00200 10.1016/j.neucom.2021.04.089 10.1109/lsp.2020.3020215 10.1016/j.neuroimage.2015.02.015 10.1080/02699050050203559 10.4103/1673-5374.131568 10.1021/acs.jcim.9b00694 10.1109/jbhi.2021.3062335 10.1093/cercor/bhaa350 10.3390/math9182288 10.3389/fnins.2016.00430 10.3390/s20133738 10.14569/ijacsa.2017.081046 10.1088/1741-2552/abda0b 10.1364/BRAIN.2018.BTu2C.4 10.1016/j.ymssp.2019.05.005 10.1016/j.neuron.2015.11.031 10.1016/j.nicl.2013.12.009 10.1016/j.brainres.2019.146427 10.1364/BRAIN.2020.BW4C.3 10.1088/1741-2552/ab6df3 10.1109/EMBC46164.2021.9630205 10.1214/aoms/1177729694 10.1109/EMBC48229.2022.9871743 10.3390/s19030551 10.1007/978-3-319-59050-9_47 10.1242/dmm.026120 10.1109/tcds.2019.2949306 10.1088/1741-2552/ac1982 10.1016/s1474-4422(15)00002-2 10.1038/s42003-020-0961-x 10.1016/j.asoc.2019.105689 10.1016/j.eng.2019.03.010 10.1109/lra.2018.2801475 10.1088/1741-2552/ab9842 10.1109/access.2020.2971600 10.1016/j.patcog.2020.107335 10.1038/nrg.2017.19 10.1109/NER.2019.8716897 10.1016/j.neuroimage.2019.06.014 10.1109/tbme.2010.2082539 10.1109/EMBC44109.2020.9175800 10.1523/jneurosci.21-04-01370.2001 10.1016/j.neunet.2009.06.003 |
| ContentType | Journal Article |
| DBID | AAYXX CITATION DOA |
| DOI | 10.3389/frsip.2022.1019253 |
| DatabaseName | CrossRef DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2673-8198 |
| ExternalDocumentID | oai_doaj_org_article_45e0f1e036c040afb1bf87294343f472 10_3389_frsip_2022_1019253 |
| GroupedDBID | 9T4 AAFWJ AAYXX AFPKN ALMA_UNASSIGNED_HOLDINGS CITATION GROUPED_DOAJ M~E OK1 |
| ID | FETCH-LOGICAL-c357t-a9a35a8051cb35dcc7be209f665d0d47d6cdd4a3f939e730605122d814ebc9dd3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001063226400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2673-8198 |
| IngestDate | Fri Oct 03 12:44:46 EDT 2025 Tue Nov 18 21:21:49 EST 2025 Sat Nov 29 05:55:17 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c357t-a9a35a8051cb35dcc7be209f665d0d47d6cdd4a3f939e730605122d814ebc9dd3 |
| OpenAccessLink | https://doaj.org/article/45e0f1e036c040afb1bf87294343f472 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_45e0f1e036c040afb1bf87294343f472 crossref_primary_10_3389_frsip_2022_1019253 crossref_citationtrail_10_3389_frsip_2022_1019253 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-11-30 |
| PublicationDateYYYYMMDD | 2022-11-30 |
| PublicationDate_xml | – month: 11 year: 2022 text: 2022-11-30 day: 30 |
| PublicationDecade | 2020 |
| PublicationTitle | Frontiers in signal processing (Lausanne) |
| PublicationYear | 2022 |
| Publisher | Frontiers Media S.A |
| Publisher_xml | – name: Frontiers Media S.A |
| References | Cornblath (B7) 2020; 3 Wiltschko (B63) 2015; 88 Bethge (B5) Higgins (B20) Linkenkaer-Hansen (B33) 2001; 21 Breschi (B6) 2017; 18 Han (B17) 2021; 25 Kullback (B28) 1951; 22 Eierud (B11) 2014; 4 Zhu (B71) 2017 Morganti-Kossmann (B39) 2010; 41 Ming (B38) 2019; 84 Han (B18) 2020; 27 Salsabilian (B52) Niu (B41) 2020; 20 Shamsi (B56) 2021; 18 Waytowich (B62) 2016; 10 Goodfellow (B15) 2014; 27 Fazli (B13) 2009; 22 Higgins (B19) Salsabilian (B50) 2018 Bethge (B4) Özdenizci (B42) 2020; 8 Marshall (B37) 2019; 1724 Salsabilian (B51) Kou (B27) 2014; 9 Gu (B16) 2021; 31 Koochaki (B25) 2021 Dai (B9) 2019; 19 Srivastava (B58) 2015 Morioka (B40) 2015; 111 Salsabilian (B48) 2019 Makhzani (B36) 2015 Beauchamp (B3) 2022 Li (B32) 2019; 12 Lotte (B34) 2010; 58 Cramer (B59) 2022; 11 Cortes (B8) 2021; 6 Salsabilian (B53) 2020 Wu (B64) 2020 Cramer (B22) 2019; 199 Sohn (B57) 2015; 28 Lee (B30) 2020 Louppe (B35) 2017; 30 Ellenbroek (B12) 2016; 9 Salsabilian (B54) Hong (B21) 2019; 60 Iverson (B23) 2000; 14 Du (B14) 2019; 5 Kamnitsas (B24) 2017 Angjelichinoski (B2) 2020; 17 Koochaki (B26) 2020 Zhou (B69) 2021; 453 You (B66) 2007; 27 Ruff (B47) 2009; 24 Xie (B65) 2017; 30 Park (B44) 2018; 3 Yu (B67); 129 Levin (B31) 2015; 14 Perich (B45) 2021 Lee (B29) 2016; 10 Alhagry (B1) 2017; 8 Özdenizci (B43) 2019 Schmid (B55) 2021; 18 Doersch (B10) 2016 Peterson (B46) 2021; 18 Tortora (B61) 2020; 17 Zhu (B70) 2018; 9 Yu (B68); 31 Salsabilian (B49) Tahir (B60) 2021; 9 |
| References_xml | – volume-title: Tutorial on variational autoencoders year: 2016 ident: B10 – volume: 9 start-page: 3017 year: 2018 ident: B70 article-title: Decoding cortical brain states from widefield calcium imaging data using visibility graph publication-title: Biomed. Opt. Express doi: 10.1364/boe.9.003017 – volume: 31 start-page: 1235 ident: B68 article-title: A review of recurrent neural networks: LSTM cells and network architectures publication-title: Neural Comput. doi: 10.1162/neco_a_01199 – start-page: 467 volume-title: Brain Struct. Funct. year: 2020 ident: B30 article-title: Investigating learning-related neural circuitry with chronic in vivo optical imaging – volume: 27 start-page: 1954 year: 2007 ident: B66 article-title: Reduced tissue damage and improved recovery of motor function after traumatic brain injury in mice deficient in complement component c4 publication-title: J. Cereb. Blood Flow. Metab. doi: 10.1038/sj.jcbfm.9600497 – start-page: 843 volume-title: International conference on machine learning year: 2015 ident: B58 article-title: Unsupervised learning of video representations using LSTMs – volume: 41 start-page: S10 year: 2010 ident: B39 article-title: Animal models of traumatic brain injury: Is there an optimal model to reproduce human brain injury in the laboratory? publication-title: Injury doi: 10.1016/j.injury.2010.03.032 – volume: 11 start-page: 1 year: 2022 ident: B59 article-title: Wide-field calcium imaging reveals widespread changes in cortical connectivity following repetitive, mild traumatic brain injury in the mouse publication-title: bioRxiv doi: 10.1038/s41598-021-02371-3 – year: 2015 ident: B36 article-title: Adversarial autoencoders – volume: 6 start-page: 5 year: 2021 ident: B8 article-title: The genetic basis of inter-individual variation in recovery from traumatic brain injury publication-title: npj Regen. Med. doi: 10.1038/s41536-020-00114-y – volume: 24 start-page: 3 year: 2009 ident: B47 article-title: Recommendations for diagnosing a mild traumatic brain injury: A national academy of neuropsychology education paper publication-title: Archives Clin. neuropsychology doi: 10.1093/arclin/acp006 – volume: 18 start-page: 016015 year: 2021 ident: B56 article-title: Early classification of motor tasks using dynamic functional connectivity graphs from EEG publication-title: J. Neural Eng. doi: 10.1088/1741-2552/abce70 – volume: 10 start-page: 200 year: 2016 ident: B29 article-title: Pupil dynamics reflect behavioral choice and learning in a go/nogo tactile decision-making task in mice publication-title: Front. Behav. Neurosci. doi: 10.3389/fnbeh.2016.00200 – volume: 453 start-page: 131 year: 2021 ident: B69 article-title: VAE-based deep SVDD for anomaly detection publication-title: Neurocomputing doi: 10.1016/j.neucom.2021.04.089 – volume: 27 start-page: 1565 year: 2020 ident: B18 article-title: Disentangled adversarial autoencoder for subject-invariant physiological feature extraction publication-title: IEEE Signal Process. Lett. doi: 10.1109/lsp.2020.3020215 – volume: 111 start-page: 167 year: 2015 ident: B40 article-title: Learning a common dictionary for subject-transfer decoding with resting calibration publication-title: NeuroImage doi: 10.1016/j.neuroimage.2015.02.015 – volume: 14 start-page: 1057 year: 2000 ident: B23 article-title: Prevalence of abnormal CT-scans following mild head injury publication-title: Brain Inj. doi: 10.1080/02699050050203559 – volume: 30 year: 2017 ident: B35 article-title: Learning to pivot with adversarial networks publication-title: Adv. Neural Inf. Process. Syst. – volume: 9 start-page: 693 year: 2014 ident: B27 article-title: Imaging brain plasticity after trauma publication-title: Neural Regen. Res. doi: 10.4103/1673-5374.131568 – volume: 60 start-page: 29 year: 2019 ident: B21 article-title: Molecular generative model based on an adversarially regularized autoencoder publication-title: J. Chem. Inf. Model. doi: 10.1021/acs.jcim.9b00694 – volume: 27 year: 2014 ident: B15 article-title: Generative adversarial nets publication-title: Adv. Neural Inf. Process. Syst. – volume: 25 start-page: 2928 year: 2021 ident: B17 article-title: Universal physiological representation learning with soft-disentangled rateless autoencoders publication-title: IEEE J. Biomed. Health Inf. doi: 10.1109/jbhi.2021.3062335 – volume: 31 start-page: 2125 year: 2021 ident: B16 article-title: Temporal dynamics of functional brain states underlie cognitive performance publication-title: Cereb. Cortex doi: 10.1093/cercor/bhaa350 – ident: B19 article-title: Early visual concept learning with unsupervised deep learning – volume: 9 start-page: 2288 year: 2021 ident: B60 article-title: Voxel-based 3D object reconstruction from single 2D image using variational autoencoders publication-title: Mathematics doi: 10.3390/math9182288 – volume: 10 start-page: 430 year: 2016 ident: B62 article-title: Spectral transfer learning using information geometry for a user-independent brain-computer interface publication-title: Front. Neurosci. doi: 10.3389/fnins.2016.00430 – volume: 20 start-page: 3738 year: 2020 ident: B41 article-title: LSTM-based VAE-GAN for time-series anomaly detection publication-title: Sensors doi: 10.3390/s20133738 – volume: 8 year: 2017 ident: B1 article-title: Emotion recognition based on EEG using LSTM recurrent neural network publication-title: ijacsa. doi: 10.14569/ijacsa.2017.081046 – start-page: 412 volume-title: 10th international IEEE/EMBS conference on neural engineering year: 2021 ident: B25 article-title: A convolutional autoencoder for identification of mild traumatic brain injury – start-page: 408 volume-title: 10th international IEEE/EMBS conference on neural engineering ident: B52 article-title: An adversarial variational autoencoder approach toward transfer learning for mTBI identification – volume: 18 start-page: 026014 year: 2021 ident: B46 article-title: Generalized neural decoders for transfer learning across participants and recording modalities publication-title: J. Neural Eng. doi: 10.1088/1741-2552/abda0b – start-page: 5217 volume-title: 41st annual international conference of the IEEE engineering in medicine and Biology society year: 2019 ident: B48 article-title: Quantifying changes in brain function following injury via network measures – volume: 30 year: 2017 ident: B65 article-title: Controllable invariance through adversarial feature learning publication-title: Adv. Neural Inf. Process. Syst. – start-page: 1236 volume-title: ICASSP 2022 IEEE international conference on acoustics, speech and signal processing ident: B4 article-title: Domain-invariant representation learning from EEG with private encoders – volume-title: Optics and the brain year: 2018 ident: B50 article-title: Using connectivity to infer behavior from cortical activity recorded through widefield transcranial imaging doi: 10.1364/BRAIN.2018.BTu2C.4 – volume: 129 start-page: 764 ident: B67 article-title: Remaining useful life estimation using a bidirectional recurrent neural network based autoencoder scheme publication-title: Mech. Syst. Signal Process. doi: 10.1016/j.ymssp.2019.05.005 – volume: 88 start-page: 1121 year: 2015 ident: B63 article-title: Mapping sub-second structure in mouse behavior publication-title: Neuron doi: 10.1016/j.neuron.2015.11.031 – volume: 4 start-page: 283 year: 2014 ident: B11 article-title: Neuroimaging after mild traumatic brain injury: Review and meta-analysis publication-title: NeuroImage Clin. doi: 10.1016/j.nicl.2013.12.009 – volume: 1724 start-page: 146427 year: 2019 ident: B37 article-title: Mouse vs man: Organoid models of brain development & disease publication-title: Brain Res. doi: 10.1016/j.brainres.2019.146427 – volume-title: Optics and the brain ident: B49 article-title: Study of functional network topology alterations after injury via embedding methods doi: 10.1364/BRAIN.2020.BW4C.3 – start-page: 103940C volume-title: Wavelets and sparsity XVII year: 2017 ident: B71 article-title: Probing the dynamics of spontaneous cortical activities via widefield Ca+2 imaging in GCaMP6 transgenic mice – volume: 17 start-page: 016067 year: 2020 ident: B2 article-title: Cross-subject decoding of eye movement goals from local field potentials publication-title: J. Neural Eng. doi: 10.1088/1741-2552/ab6df3 – volume-title: 43rd annual international Conference of the IEEE Engineering in medicine & Biology society (EMBC) ident: B51 article-title: A variational encoder framework for decoding behavior choices from neural data doi: 10.1109/EMBC46164.2021.9630205 – ident: B20 article-title: beta-vae: Learning basic visual concepts with a constrained variational framework – volume: 22 start-page: 79 year: 1951 ident: B28 article-title: On information and sufficiency publication-title: Ann. Math. Stat. doi: 10.1214/aoms/1177729694 – volume-title: Exploiting multiple EEG data domains with adversarial learning ident: B5 doi: 10.1109/EMBC48229.2022.9871743 – volume: 19 start-page: 551 year: 2019 ident: B9 article-title: EEG classification of motor imagery using a novel deep learning framework publication-title: Sensors doi: 10.3390/s19030551 – start-page: 597 volume-title: International conference on information processing in medical imaging year: 2017 ident: B24 article-title: Unsupervised domain adaptation in brain lesion segmentation with adversarial networks doi: 10.1007/978-3-319-59050-9_47 – start-page: 2917 volume-title: 42nd annual international conference of the IEEE engineering in medicine & Biology society (EMBC) year: 2020 ident: B26 article-title: Detecting mTBI by learning spatio-temporal characteristics of widefield calcium imaging data using deep learning – volume: 9 start-page: 1079 year: 2016 ident: B12 article-title: Rodent models in neuroscience research: Is it a rat race? publication-title: Dis. models Mech. doi: 10.1242/dmm.026120 – volume: 12 start-page: 344 year: 2019 ident: B32 article-title: Domain adaptation for EEG emotion recognition based on latent representation similarity publication-title: IEEE Trans. Cogn. Dev. Syst. doi: 10.1109/tcds.2019.2949306 – volume: 18 start-page: 041006 year: 2021 ident: B55 article-title: Review of wearable technologies and machine learning methodologies for systematic detection of mild traumatic brain injuries publication-title: J. Neural Eng. doi: 10.1088/1741-2552/ac1982 – year: 2022 ident: B3 article-title: Whole-brain comparison of rodent and human brains using spatial transcriptomics publication-title: bioRxiv – volume: 14 start-page: 506 year: 2015 ident: B31 article-title: Diagnosis, prognosis, and clinical management of mild traumatic brain injury publication-title: Lancet Neurology doi: 10.1016/s1474-4422(15)00002-2 – volume: 28 year: 2015 ident: B57 article-title: Learning structured output representation using deep conditional generative models publication-title: Adv. neural Inf. Process. Syst. – volume: 3 start-page: 1 year: 2020 ident: B7 article-title: Temporal sequences of brain activity at rest are constrained by white matter structure and modulated by cognitive demands publication-title: Commun. Biol. doi: 10.1038/s42003-020-0961-x – volume: 84 start-page: 105689 year: 2019 ident: B38 article-title: Subject adaptation network for EEG data analysis publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2019.105689 – volume: 5 start-page: 948 year: 2019 ident: B14 article-title: Brain encoding and decoding in fMRI with bidirectional deep generative models publication-title: Engineering doi: 10.1016/j.eng.2019.03.010 – volume: 3 start-page: 1544 year: 2018 ident: B44 article-title: A multimodal anomaly detector for robot-assisted feeding using an lstm-based variational autoencoder publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/lra.2018.2801475 – volume: 17 start-page: 046011 year: 2020 ident: B61 article-title: Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network publication-title: J. Neural Eng. doi: 10.1088/1741-2552/ab9842 – volume: 8 start-page: 27074 year: 2020 ident: B42 article-title: Learning invariant representations from EEG via adversarial inference publication-title: IEEE access doi: 10.1109/access.2020.2971600 – volume-title: Modality-specific and shared generative adversarial network for cross-modal retrieval year: 2020 ident: B64 doi: 10.1016/j.patcog.2020.107335 – volume: 18 start-page: 425 year: 2017 ident: B6 article-title: Comparative transcriptomics in human and mouse publication-title: Nat. Rev. Genet. doi: 10.1038/nrg.2017.19 – volume-title: 2019 9th international IEEE/EMBS conference on neural engineering (NER) year: 2019 ident: B43 article-title: Transfer learning in brain-computer interfaces with adversarial variational autoencoders doi: 10.1109/NER.2019.8716897 – start-page: 1 year: 2021 ident: B45 article-title: Inferring brain-wide interactions using data-constrained recurrent neural network models publication-title: BioRxiv – volume: 199 start-page: 570 year: 2019 ident: B22 article-title: In vivo widefield calcium imaging of the mouse cortex for analysis of network connectivity in health and brain disease publication-title: Neuroimage doi: 10.1016/j.neuroimage.2019.06.014 – volume: 58 start-page: 355 year: 2010 ident: B34 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-title: 42st annual international conference of the IEEE engineering in medicine and Biology society (EMBC) year: 2020 ident: B53 article-title: Detection of mild traumatic brain injury via topological graph embedding and 2D convolutional neural networks doi: 10.1109/EMBC44109.2020.9175800 – start-page: 1 volume-title: IEEE international symposium on circuits and systems (ISCAS) ident: B54 article-title: Identifying task-related brain functional states via cortical networks – volume: 21 start-page: 1370 year: 2001 ident: B33 article-title: Long-range temporal correlations and scaling behavior in human brain oscillations publication-title: J. Neurosci. doi: 10.1523/jneurosci.21-04-01370.2001 – volume: 22 start-page: 1305 year: 2009 ident: B13 article-title: Subject-independent mental state classification in single trials publication-title: Neural Netw. doi: 10.1016/j.neunet.2009.06.003 |
| SSID | ssj0002784206 |
| Score | 2.2170904 |
| Snippet | Developing models for identifying mild traumatic brain injury (mTBI) has often been challenging due to large variations in data from subjects, resulting in... |
| SourceID | doaj crossref |
| SourceType | Open Website Enrichment Source Index Database |
| SubjectTerms | adversarial regularization cross-subject transfer learning LSTM-long short-term memory mild TBI (mTBI) variational autoencoder (VAE) |
| Title | Subject-invariant feature learning for mTBI identification using LSTM-based variational autoencoder with adversarial regularization |
| URI | https://doaj.org/article/45e0f1e036c040afb1bf87294343f472 |
| Volume | 2 |
| WOSCitedRecordID | wos001063226400001&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: 2673-8198 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002784206 issn: 2673-8198 databaseCode: DOA dateStart: 20210101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2673-8198 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002784206 issn: 2673-8198 databaseCode: M~E dateStart: 20210101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NSx0xFA1FXNRF8ROtVbJwJ8HJ12SyrPJEQUXwtbgbMvmQV-yzjM-37MY_3nszUZ4bu3EziyETwslNck8mOYeQg-Ar463TzFW-YSrUnDXSCaYazkPtdVdn2cWfF-bqqrm9tdcLVl94JmyQBx6AO1I6VolHmGg9xJtLHe9SAxkh3ohMyuTZF7KeBTL1q_xOE1U93JIBFmaPEnBv1KcUAgmrFVq-WYkWBPvzynK6Sr6UlJB-H5qyRj7F6TpZWRAK3CDPML5xw4RNpnMgt4AGTTFLctJi-3BHIfukv8fH53QSygmgDDrFk-139OJmfMlwyQo01zBsAVL3NHtAKcsQe4pbstShQfMjlrinffap78tNzU3y43Q0PjljxT6BeanNjDnrpHYNjDrfSR28N10UlU11rUMVlIGuCEE5may0EQY6EBsuRGi4ip23IcgtsjR9mMZtQoXxzilXNR4wV0q6Ds2GasGjS9oYuUP4C5StL9riaHFx3wLHQPjbDH-L8LcF_h1y-PrNn0FZ493Sx9hDryVRFTu_gFhpS6y0_4uVrx9RyS75jA0b5B-_kaVZ_xT3yLKfzyaP_X4OQ3he_h39A6TA5N4 |
| linkProvider | Directory of Open Access Journals |
| 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=Subject-invariant+feature+learning+for+mTBI+identification+using+LSTM-based+variational+autoencoder+with+adversarial+regularization&rft.jtitle=Frontiers+in+signal+processing+%28Lausanne%29&rft.au=Shiva+Salsabilian&rft.au=Laleh+Najafizadeh&rft.date=2022-11-30&rft.pub=Frontiers+Media+S.A&rft.eissn=2673-8198&rft.volume=2&rft_id=info:doi/10.3389%2Ffrsip.2022.1019253&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_45e0f1e036c040afb1bf87294343f472 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2673-8198&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2673-8198&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2673-8198&client=summon |