NEURAL ORDINARY DIFFERENTIAL EQUATIONS FOR TIME SERIES RECONSTRUCTION
Context. Neural Ordinary Differential Equations is a deep neural networks family that leverage numerical methods approaches for solving the problem of time series reconstruction, given small amount of unevenly distributed samples. Objective. The goal of the following research is the synthesis of a d...
Gespeichert in:
| Veröffentlicht in: | Radìoelektronika, informatika, upravlìnnâ H. 4; S. 69 |
|---|---|
| 1. Verfasser: | |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
24.12.2023
|
| ISSN: | 1607-3274, 2313-688X |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Context. Neural Ordinary Differential Equations is a deep neural networks family that leverage numerical methods approaches for solving the problem of time series reconstruction, given small amount of unevenly distributed samples.
Objective. The goal of the following research is the synthesis of a deep neural network that is able to solve input signal reconstruction and time series extrapolation task.
Method. The proposed method exhibits the benefits of solving time series extrapolation task over forecasting one. A model that implements encoder-decoder architecture with differential equation solving in latent space, is proposed. The latter approach was proven to demonstrate outstanding performance in solving time series reconstruction task given a small percentage of noisy and uneven distributed input signals. The proposed Latent Ordinary Differential Equations Variational Autoencoder (LODE-VAE) model was benchmarked on synthetic non-stationary data with added white noise and randomly sampled with random intervals between each signal.
Results. The proposed method was implemented via deep neural network to solve time series extrapolation task.
Conclusions. The conducted experiments have confirmed that proposed model solves the given task effectively and is recommended to apply it to solving real-world problems that require reconstructing dynamics of non-stationary processes. The prospects for further research may include the process of computational optimization of proposed models, as well as conducting additional experiments involving different baselines, e. g. Generative Adversarial Networks or attention Networks. |
|---|---|
| AbstractList | Context. Neural Ordinary Differential Equations is a deep neural networks family that leverage numerical methods approaches for solving the problem of time series reconstruction, given small amount of unevenly distributed samples.
Objective. The goal of the following research is the synthesis of a deep neural network that is able to solve input signal reconstruction and time series extrapolation task.
Method. The proposed method exhibits the benefits of solving time series extrapolation task over forecasting one. A model that implements encoder-decoder architecture with differential equation solving in latent space, is proposed. The latter approach was proven to demonstrate outstanding performance in solving time series reconstruction task given a small percentage of noisy and uneven distributed input signals. The proposed Latent Ordinary Differential Equations Variational Autoencoder (LODE-VAE) model was benchmarked on synthetic non-stationary data with added white noise and randomly sampled with random intervals between each signal.
Results. The proposed method was implemented via deep neural network to solve time series extrapolation task.
Conclusions. The conducted experiments have confirmed that proposed model solves the given task effectively and is recommended to apply it to solving real-world problems that require reconstructing dynamics of non-stationary processes. The prospects for further research may include the process of computational optimization of proposed models, as well as conducting additional experiments involving different baselines, e. g. Generative Adversarial Networks or attention Networks. |
| Author | Androsov, D. V. |
| Author_xml | – sequence: 1 givenname: D. V. surname: Androsov fullname: Androsov, D. V. |
| BookMark | eNo9kM1KxDAAhIOsYF33CbzkBaJJ89ceSzfVQG0xbUFPoUkTUHRXWi--vVsVTwMzHwMzl2BzOB4CANcE3xDOs-yWCCwRTSVDKU4pYkiegSSlhCKRZU8bkPwDF2C3LK8YY8IzQZhMgGrUYIoatmavm8I8w72uKmVU0-uTqx6Hotdt08GqNbDXDwp2ymjVQaPKk92boVzzK3Aex7cl7P50C4ZK9eU9qts7XRY18kSyTxRz4Tj2YZrCxPLcixDHyDimbpQhj8wJTiVlwjmMR-al4yeQTBF75lyYPN0C-tvr5-OyzCHaj_nlfZy_LMH25wy7brXrVrueYZmV9Bu0m088 |
| ContentType | Journal Article |
| DBID | AAYXX CITATION |
| DOI | 10.15588/1607-3274-2023-4-7 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2313-688X |
| ExternalDocumentID | 10_15588_1607_3274_2023_4_7 |
| GroupedDBID | AAYXX ADBBV ALMA_UNASSIGNED_HOLDINGS BCNDV CITATION GROUPED_DOAJ |
| ID | FETCH-LOGICAL-c174t-f96b50cedded499c6efaf4503ba7e9f4b6537346bb00a4c7b5ded1df0c4bbedc3 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001165038500016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1607-3274 |
| IngestDate | Sat Nov 29 05:06:08 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| License | https://creativecommons.org/licenses/by-sa/4.0 |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c174t-f96b50cedded499c6efaf4503ba7e9f4b6537346bb00a4c7b5ded1df0c4bbedc3 |
| OpenAccessLink | http://ric.zntu.edu.ua/article/download/294369/287145 |
| ParticipantIDs | crossref_primary_10_15588_1607_3274_2023_4_7 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-12-24 |
| PublicationDateYYYYMMDD | 2023-12-24 |
| PublicationDate_xml | – month: 12 year: 2023 text: 2023-12-24 day: 24 |
| PublicationDecade | 2020 |
| PublicationTitle | Radìoelektronika, informatika, upravlìnnâ |
| PublicationYear | 2023 |
| SSID | ssj0001586147 ssib018208917 ssib015895113 ssib044757822 |
| Score | 2.241844 |
| Snippet | Context. Neural Ordinary Differential Equations is a deep neural networks family that leverage numerical methods approaches for solving the problem of time... |
| SourceID | crossref |
| SourceType | Index Database |
| StartPage | 69 |
| Title | NEURAL ORDINARY DIFFERENTIAL EQUATIONS FOR TIME SERIES RECONSTRUCTION |
| WOSCitedRecordID | wos001165038500016&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: 2313-688X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001586147 issn: 1607-3274 databaseCode: DOA dateStart: 19990101 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: 2313-688X dateEnd: 99991231 omitProxy: false ssIdentifier: ssib044757822 issn: 1607-3274 databaseCode: M~E dateStart: 19990101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF5B4QAHxFNAAfnAzWxIvU8fq9QRkcBCjlOVk2Vv1hIqcqIkjfrzO7NrO4ZKiB642PFqNbY8X2a_Wc-DkI8xZktKK6lUtaEciBGN45pTJQ02ueJV5IrpnH9VaaovLuLvbUGFrWsnoJpGX1_H6_-qahgDZWPq7B3U3QuFAfgNSocjqB2O_6T4NFlkGM2Tnc3S0-xHeDabTpMsSfMZjCbAYH3iMHh_YT77loRzcOWSeZhhS8N5ni0m_aZVV7cbUICf0ycrWKIuXc-cS0c526Kru_byar0p97_8VGDFeO5DlzFucrVd7Z2JG4Xno-FuQ8QwcsMnObcGUuK-ZuQ764ysGwOKyKjUrkVwhxc-MIq-F8stWy2ExgSEXiJ19wOYHJam7nP8HytWH0eIHgyKKVBIgUIKFFLwQt0nDyIlYj3wssHEnAgNlPLAYLB8vR54rFj-UHUVDX2iuQYC41r0dM_Z1q7C-36-_fADfjMgKvlT8qT1MIJTj4xn5J5tnpPHg7qTL0jiMRJ0GAmGGAl6jASAkQAxEniMBL9j5CVZTJN88oW2_TSoAb9zR-tYVmJsLKxoS3B0jbR1WXMxZlWpLPxBKymYYlxWYIpLblQlYOLJsh4bXlV2adgrctSsGvuaBGUJTFOJpWLacKViXdlSmDrSJmI1U-IN-dS9hWLty6YUf1HW27tNPyaPDth8R452myv7njw0-93P7eaDU_gNicxNIw |
| 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=NEURAL+ORDINARY+DIFFERENTIAL+EQUATIONS+FOR+TIME+SERIES+RECONSTRUCTION&rft.jtitle=Rad%C3%ACoelektronika%2C+informatika%2C+upravl%C3%ACnn%C3%A2&rft.au=Androsov%2C+D.+V.&rft.date=2023-12-24&rft.issn=1607-3274&rft.eissn=2313-688X&rft.issue=4&rft.spage=69&rft_id=info:doi/10.15588%2F1607-3274-2023-4-7&rft.externalDBID=n%2Fa&rft.externalDocID=10_15588_1607_3274_2023_4_7 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1607-3274&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1607-3274&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1607-3274&client=summon |