Matches in SemOpenAlex for { <https://semopenalex.org/work/W2282304611> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2282304611 endingPage "15" @default.
- W2282304611 startingPage "10" @default.
- W2282304611 abstract "The identification of nonlinear and chaotic systems is an important and challenging problem. Neural network models, particularly Recurrent Neural Networks (RNN) trained with suitable algorithms, have received particular attention in the area of nonlinear identification due to their potentialities to approximate any nonlinear behavior. A method of nonlinear identification based on the RNN model trained with improved nonlinear Kalman filter is proposed in this paper. The neural network weights are estimated using the Extended Kalman Filter(EKF) algorithm, augmented by the Expectation Maximization(EM) algorithm is used to derive the initial states and covariance of the Kalman filter. It was shown that not only could this chaotic approach provide an accurate identification, but it was also more effective in the sense that the approach had a smaller mean squares error (MSE). An experimental case study using the famous Venice lagoon time series is analyzed by the proposed algorithm. The minimum embedding dimension of the time series is calculated using the method of false nearest neighbors. The Lyapunov exponents of the model are calculated, from the state space evolution, The numerical results presented here indicate that the traditional Extended Kalman Filter algorithm combined with EM techniques are effective in building a good NN model for nonlinear identification. demonstrated. The Venice Lagoon time series is a measure of the level of water in the Lagoon in centimeters each hour along the years 1940-1990.Non linear stochastic models are used for modeling the system. Unusually high tides and other climatic conditions sometimes drive the time series to show chaotic nature. The recurrent architecture also generates the state space evolution, while trying to arrive at the model of the output time series. The parameters of the neural network are estimated using the Extended Kalman Filter (EKF) algorithm, by choosing the weights of the neural network as the states of the Extended Kalman Filter. Further, the Expectation Maximization algorithm is used to effectively arrive at the initial states and the state covariance, required in the EKF algorithm. The recurrent network, shown in Fig. 1. models the following system: xk+1 = f ( xk , W) (1)" @default.
- W2282304611 created "2016-06-24" @default.
- W2282304611 creator A5003352731 @default.
- W2282304611 creator A5020435422 @default.
- W2282304611 creator A5061459553 @default.
- W2282304611 date "2012-09-07" @default.
- W2282304611 modified "2023-09-26" @default.
- W2282304611 title "Modeling of Venice Lagoon Time series with Improved Kalman Filter based neural networks" @default.
- W2282304611 cites W1544266542 @default.
- W2282304611 cites W1646998587 @default.
- W2282304611 cites W2073129852 @default.
- W2282304611 cites W2123716044 @default.
- W2282304611 cites W2124776405 @default.
- W2282304611 cites W2138484437 @default.
- W2282304611 cites W2285257517 @default.
- W2282304611 hasPublicationYear "2012" @default.
- W2282304611 type Work @default.
- W2282304611 sameAs 2282304611 @default.
- W2282304611 citedByCount "1" @default.
- W2282304611 countsByYear W22823046112015 @default.
- W2282304611 crossrefType "journal-article" @default.
- W2282304611 hasAuthorship W2282304611A5003352731 @default.
- W2282304611 hasAuthorship W2282304611A5020435422 @default.
- W2282304611 hasAuthorship W2282304611A5061459553 @default.
- W2282304611 hasConcept C105795698 @default.
- W2282304611 hasConcept C106131492 @default.
- W2282304611 hasConcept C11413529 @default.
- W2282304611 hasConcept C119857082 @default.
- W2282304611 hasConcept C121332964 @default.
- W2282304611 hasConcept C143724316 @default.
- W2282304611 hasConcept C147168706 @default.
- W2282304611 hasConcept C151406439 @default.
- W2282304611 hasConcept C151730666 @default.
- W2282304611 hasConcept C154945302 @default.
- W2282304611 hasConcept C157286648 @default.
- W2282304611 hasConcept C158622935 @default.
- W2282304611 hasConcept C178650346 @default.
- W2282304611 hasConcept C206833254 @default.
- W2282304611 hasConcept C2775924081 @default.
- W2282304611 hasConcept C2777052490 @default.
- W2282304611 hasConcept C31972630 @default.
- W2282304611 hasConcept C33923547 @default.
- W2282304611 hasConcept C41008148 @default.
- W2282304611 hasConcept C47446073 @default.
- W2282304611 hasConcept C50644808 @default.
- W2282304611 hasConcept C62520636 @default.
- W2282304611 hasConcept C86803240 @default.
- W2282304611 hasConceptScore W2282304611C105795698 @default.
- W2282304611 hasConceptScore W2282304611C106131492 @default.
- W2282304611 hasConceptScore W2282304611C11413529 @default.
- W2282304611 hasConceptScore W2282304611C119857082 @default.
- W2282304611 hasConceptScore W2282304611C121332964 @default.
- W2282304611 hasConceptScore W2282304611C143724316 @default.
- W2282304611 hasConceptScore W2282304611C147168706 @default.
- W2282304611 hasConceptScore W2282304611C151406439 @default.
- W2282304611 hasConceptScore W2282304611C151730666 @default.
- W2282304611 hasConceptScore W2282304611C154945302 @default.
- W2282304611 hasConceptScore W2282304611C157286648 @default.
- W2282304611 hasConceptScore W2282304611C158622935 @default.
- W2282304611 hasConceptScore W2282304611C178650346 @default.
- W2282304611 hasConceptScore W2282304611C206833254 @default.
- W2282304611 hasConceptScore W2282304611C2775924081 @default.
- W2282304611 hasConceptScore W2282304611C2777052490 @default.
- W2282304611 hasConceptScore W2282304611C31972630 @default.
- W2282304611 hasConceptScore W2282304611C33923547 @default.
- W2282304611 hasConceptScore W2282304611C41008148 @default.
- W2282304611 hasConceptScore W2282304611C47446073 @default.
- W2282304611 hasConceptScore W2282304611C50644808 @default.
- W2282304611 hasConceptScore W2282304611C62520636 @default.
- W2282304611 hasConceptScore W2282304611C86803240 @default.
- W2282304611 hasIssue "5" @default.
- W2282304611 hasLocation W22823046111 @default.
- W2282304611 hasOpenAccess W2282304611 @default.
- W2282304611 hasPrimaryLocation W22823046111 @default.
- W2282304611 hasRelatedWork W1535441708 @default.
- W2282304611 hasRelatedWork W16940046 @default.
- W2282304611 hasRelatedWork W2035335744 @default.
- W2282304611 hasRelatedWork W2060130885 @default.
- W2282304611 hasRelatedWork W2084093969 @default.
- W2282304611 hasRelatedWork W2142133043 @default.
- W2282304611 hasRelatedWork W2182059946 @default.
- W2282304611 hasRelatedWork W2188627861 @default.
- W2282304611 hasRelatedWork W2531695493 @default.
- W2282304611 hasRelatedWork W2772525328 @default.
- W2282304611 hasRelatedWork W2794083847 @default.
- W2282304611 hasRelatedWork W2902283662 @default.
- W2282304611 hasRelatedWork W2903162480 @default.
- W2282304611 hasRelatedWork W2917624112 @default.
- W2282304611 hasRelatedWork W2996988305 @default.
- W2282304611 hasRelatedWork W2998096733 @default.
- W2282304611 hasRelatedWork W3012229929 @default.
- W2282304611 hasRelatedWork W3047822177 @default.
- W2282304611 hasRelatedWork W3088317923 @default.
- W2282304611 hasRelatedWork W3121249861 @default.
- W2282304611 isParatext "false" @default.
- W2282304611 isRetracted "false" @default.
- W2282304611 magId "2282304611" @default.
- W2282304611 workType "article" @default.