Matches in SemOpenAlex for { <https://semopenalex.org/work/W4375929147> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4375929147 endingPage "12331" @default.
- W4375929147 startingPage "12326" @default.
- W4375929147 abstract "Estimation of the state of a discrete-time state-space model from noisy measurements is a crucial aspect of signal processing. The extended Kalman filter (EKF) is widely used as a low-complexity solution based on a state evolution and measurement model of the state-space model. However, obtaining precise information about these models can be difficult in practice, and model mismatch greatly reduces state estimation accuracy. In this paper, we introduce Split-KalmanNet, a robust EKF algorithm that utilizes the power of deep learning for state estimation. Split-KalmanNet is inspired by the recent KalmanNet and calculates the Kalman gain using the Jacobian matrix of a measurement function and two recurrent neural networks (RNNs) with a split structure. The RNNs independently learn the covariance matrices of the prior state estimate and the innovation from data. The proposed split structure in calculating the Kalman gain allows for compensation of both state and measurement model mismatch effects. Numerical simulations show that Split-KalmanNet outperforms traditional EKF and the state-of-the-art KalmanNet algorithm in various scenarios of model mismatch." @default.
- W4375929147 created "2023-05-10" @default.
- W4375929147 creator A5012405763 @default.
- W4375929147 creator A5014076559 @default.
- W4375929147 creator A5043029411 @default.
- W4375929147 creator A5046746368 @default.
- W4375929147 creator A5080663906 @default.
- W4375929147 date "2023-09-01" @default.
- W4375929147 modified "2023-09-27" @default.
- W4375929147 title "Split-KalmanNet: A Robust Model-Based Deep Learning Approach for State Estimation" @default.
- W4375929147 cites W2047448918 @default.
- W4375929147 cites W2054091988 @default.
- W4375929147 cites W2055936398 @default.
- W4375929147 cites W2098613108 @default.
- W4375929147 cites W2104524378 @default.
- W4375929147 cites W2105934661 @default.
- W4375929147 cites W2119033078 @default.
- W4375929147 cites W2123487311 @default.
- W4375929147 cites W2137585588 @default.
- W4375929147 cites W2162854795 @default.
- W4375929147 cites W2169346523 @default.
- W4375929147 cites W2335829695 @default.
- W4375929147 cites W2475771804 @default.
- W4375929147 cites W2591996318 @default.
- W4375929147 cites W2964314726 @default.
- W4375929147 cites W2998513956 @default.
- W4375929147 cites W3183282730 @default.
- W4375929147 cites W3205447877 @default.
- W4375929147 cites W3207180569 @default.
- W4375929147 cites W4312790010 @default.
- W4375929147 cites W745867715 @default.
- W4375929147 doi "https://doi.org/10.1109/tvt.2023.3270353" @default.
- W4375929147 hasPublicationYear "2023" @default.
- W4375929147 type Work @default.
- W4375929147 citedByCount "0" @default.
- W4375929147 crossrefType "journal-article" @default.
- W4375929147 hasAuthorship W4375929147A5012405763 @default.
- W4375929147 hasAuthorship W4375929147A5014076559 @default.
- W4375929147 hasAuthorship W4375929147A5043029411 @default.
- W4375929147 hasAuthorship W4375929147A5046746368 @default.
- W4375929147 hasAuthorship W4375929147A5080663906 @default.
- W4375929147 hasConcept C105795698 @default.
- W4375929147 hasConcept C11413529 @default.
- W4375929147 hasConcept C147168706 @default.
- W4375929147 hasConcept C154945302 @default.
- W4375929147 hasConcept C157286648 @default.
- W4375929147 hasConcept C178650346 @default.
- W4375929147 hasConcept C185142706 @default.
- W4375929147 hasConcept C200331156 @default.
- W4375929147 hasConcept C206833254 @default.
- W4375929147 hasConcept C2775924081 @default.
- W4375929147 hasConcept C28826006 @default.
- W4375929147 hasConcept C33923547 @default.
- W4375929147 hasConcept C41008148 @default.
- W4375929147 hasConcept C47446073 @default.
- W4375929147 hasConcept C48103436 @default.
- W4375929147 hasConcept C50644808 @default.
- W4375929147 hasConcept C52918065 @default.
- W4375929147 hasConcept C72434380 @default.
- W4375929147 hasConceptScore W4375929147C105795698 @default.
- W4375929147 hasConceptScore W4375929147C11413529 @default.
- W4375929147 hasConceptScore W4375929147C147168706 @default.
- W4375929147 hasConceptScore W4375929147C154945302 @default.
- W4375929147 hasConceptScore W4375929147C157286648 @default.
- W4375929147 hasConceptScore W4375929147C178650346 @default.
- W4375929147 hasConceptScore W4375929147C185142706 @default.
- W4375929147 hasConceptScore W4375929147C200331156 @default.
- W4375929147 hasConceptScore W4375929147C206833254 @default.
- W4375929147 hasConceptScore W4375929147C2775924081 @default.
- W4375929147 hasConceptScore W4375929147C28826006 @default.
- W4375929147 hasConceptScore W4375929147C33923547 @default.
- W4375929147 hasConceptScore W4375929147C41008148 @default.
- W4375929147 hasConceptScore W4375929147C47446073 @default.
- W4375929147 hasConceptScore W4375929147C48103436 @default.
- W4375929147 hasConceptScore W4375929147C50644808 @default.
- W4375929147 hasConceptScore W4375929147C52918065 @default.
- W4375929147 hasConceptScore W4375929147C72434380 @default.
- W4375929147 hasFunder F4320322120 @default.
- W4375929147 hasFunder F4320328359 @default.
- W4375929147 hasIssue "9" @default.
- W4375929147 hasLocation W43759291471 @default.
- W4375929147 hasOpenAccess W4375929147 @default.
- W4375929147 hasPrimaryLocation W43759291471 @default.
- W4375929147 hasRelatedWork W2000670602 @default.
- W4375929147 hasRelatedWork W2050490845 @default.
- W4375929147 hasRelatedWork W2094523859 @default.
- W4375929147 hasRelatedWork W2162717464 @default.
- W4375929147 hasRelatedWork W2970132737 @default.
- W4375929147 hasRelatedWork W3092329866 @default.
- W4375929147 hasRelatedWork W3125722836 @default.
- W4375929147 hasRelatedWork W3193646638 @default.
- W4375929147 hasRelatedWork W4242707909 @default.
- W4375929147 hasRelatedWork W4246357351 @default.
- W4375929147 hasVolume "72" @default.
- W4375929147 isParatext "false" @default.
- W4375929147 isRetracted "false" @default.
- W4375929147 workType "article" @default.