Filters








421 Hits in 4.1 sec

Recursive Least Squares and Quadratic Prediction in Continuous Multistep Problems [chapter]

Daniele Loiacono, Pier Luca Lanzi
2010 Lecture Notes in Computer Science  
In this paper we investigate this issue by analyzing the performance of XCSF with recursive least squares and with quadratic prediction on continuous multistep problems.  ...  In particular, a novel prediction update algorithm based on recursive least squares and the extension to polynomial prediction led to significant improvements of XCSF.  ...  EXPERIMENTAL DESIGN To study how the recursive least squares and the quadratic prediction affect the performance of XCSF on continuous multistep problems we considered a well known class of problems: the  ... 
doi:10.1007/978-3-642-17508-4_6 fatcat:y6ab7wss6rffphl6hrf4xlxsyy

Recursive least squares and quadratic prediction in continuous multistep problems

Daniele Loiacono, Pier Luca Lanzi
2008 Proceedings of the 2008 GECCO conference companion on Genetic and evolutionary computation - GECCO '08  
In this paper we investigate this issue by analyzing the performance of XCSF with recursive least squares and with quadratic prediction on continuous multistep problems.  ...  In particular, a novel prediction update algorithm based on recursive least squares and the extension to polynomial prediction led to significant improvements of XCSF.  ...  EXPERIMENTAL DESIGN To study how the recursive least squares and the quadratic prediction affect the performance of XCSF on continuous multistep problems we considered a well known class of problems: the  ... 
doi:10.1145/1388969.1389011 dblp:conf/gecco/LoiaconoL08 fatcat:l53s7xbneff5lcvcdlwrxttbyq

Generalization in the XCSF Classifier System: Analysis, Improvement, and Extension

Pier Luca Lanzi, Daniele Loiacono, Stewart W. Wilson, David E. Goldberg
2007 Evolutionary Computation  
linear-least square, and one based on the recursive * Contact Author. 1 version of linear-least square.  ...  XCSF is an extension of XCS in which the classifier prediction is computed as a linear combination of classifier inputs and a weight vector associated with each classifier.  ...  square and the recursive least square perform the same.  ... 
doi:10.1162/evco.2007.15.2.133 pmid:17535137 fatcat:3yw337woaja5rmqptzblcgln54

B-Spline Neural Networks Based PID Controller for Hammerstein Systems [chapter]

Xia Hong, Serdar Iplikci, Sheng Chen, Kevin Warwick
2012 Communications in Computer and Information Science  
In order to update the control signal, the multistep ahead predictions of the Hammerstein system based on the B-spline neural networks and the associated Jacobians matrix are calculated using the De Boor  ...  algorithms including both the functional and derivative recursions.  ...  Acknowledgement The authors would like to thank the financial support from UK EPSRC and the Council of Higher Education in Turkey.  ... 
doi:10.1007/978-3-642-31837-5_6 fatcat:mbg2yrekoze6nmq5jpoaeym2dq

Page 1779 of Mathematical Reviews Vol. , Issue 82d [page]

1982 Mathematical Reviews  
Amaral and L. Gimeno, Recursive multivariable least squares identification with bias estimation (pp. 505-512); A. Frosini, P. Piazzesi, A. Tiano and G.  ...  Gorez, Orthogonal transformations and square-root algorithms in linear-quadratic optimal control of discrete-time systems (pp. 192-200); S. P.  ... 

Page 2103 of Mathematical Reviews Vol. 51, Issue 6 [page]

1976 Mathematical Reviews  
The authors give a detailed treatment of the prob- lem of estimability using the methods of least mean-square, stochastic approximation, maximum likelihood and Bayes.  ...  He also deals with the problem of the quadratic linear optimal regulator and an identification problem. {For the entire collection see MR 50 #15983.} Yaakov Yavin (Beer Sheva) Barabanov, A.  ... 

A model-based PID controller for Hammerstein systems using B-spline neural networks

X. Hong, S. Iplikci, S. Chen, K. Warwick
2012 International Journal of Adaptive Control and Signal Processing  
In [11] , a least squares SVM model is used to tune PID parameters to control a nonlinear time-varying system.  ...  Both the parameters in the PID controller and the correction term are optimized on the basis of minimizing the multistep ahead prediction errors.  ...  ACKNOWLEDGEMENTS The authors would like to thank the financial support from UK EPSRC and the Council of Higher Education in Turkey.  ... 
doi:10.1002/acs.2293 fatcat:gfkyy6lpkzenbnphih3tt5mr2m

Soft-DTW: a Differentiable Loss Function for Time-Series [article]

Marco Cuturi, Mathieu Blondel
2018 arXiv   pre-print
We show in this paper that soft-DTW is a differentiable loss function, and that both its value and gradient can be computed with quadratic time/space complexity (DTW has quadratic time but linear space  ...  To compute DTW, one typically solves a minimal-cost alignment problem between two time series using dynamic programming.  ...  Multistep-ahead prediction experiments In this section, we present preliminary experiments for the task of multistep-ahead prediction, described in §3.4. Experimental setup.  ... 
arXiv:1703.01541v2 fatcat:orwlgow6gbbb3oswhrlt76ptii

Model Predictive Control of Nonlinear Processes [chapter]

Venkateswarlu Ch.
2010 Model Predictive Control  
as recursive least squares.  ...  The LMPC is implemented by adaptively updating the prediction model using recursive least squares.  ... 
doi:10.5772/46954 fatcat:f2rmzzm4zfg5de2upvicxtjcli

Finite-TimeH∞Filtering for Linear Continuous Time-Varying Systems with Uncertain Observations

Huihong Zhao, Chenghui Zhang
2012 Journal of Applied Mathematics  
The design of finite-timeH∞filter is equivalent to the problem that a certain indefinite quadratic form has a minimum and the filter is such that the minimum is positive.  ...  This paper is concerned with the finite-timeH∞filtering problem for linear continuous time-varying systems with uncertain observations andℒ2-norm bounded noise.  ...  This work is supported by the National Natural Science Foundation of China 60774004, 61034007, and 60874016 and the Independent Innovation Foundation of Shandong University, China 2010JC003 .  ... 
doi:10.1155/2012/710904 fatcat:t6a56rdignckjew6d45spbq7ca

A comparison of some adaptive-predictive fuzzy-control strategies

J. Valente de Oliveira, J.M. Lemos
2000 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
They begin from the current time instant and continue up to a given time horizon in the future. A fuzzy model of the plant is used for forecasting.  ...  algorithm used in on-line model identification.  ...  In this work, both the gradient method and the recursive least-squares (RLS) algorithm are considered for parameter estimation.  ... 
doi:10.1109/5326.827488 fatcat:llfxbjcsgjf7vgidtmpvnnlhpa

General Control Horizon Extension Method for Nonlinear Model Predictive Control

Hai-Tao Zhang, Han-Xiong Li
2007 Industrial & Engineering Chemistry Research  
We prove the closed-loop stability of the algorithm in the sense that the input and output series are both mean-square-bounded.  ...  In the nonlinear model predictive control (NMPC) field, it is well-known that the multistep control approach is superior to the single-step approach when examining high-order nonlinear systems.  ...  Fortunately, the model parameters c 0 , C, and D are in a linear regressive form, which can be easily estimated by least-squares estimation (LSE) 31 as follows: with According to eq 8, Φ(t) can be calculated  ... 
doi:10.1021/ie0703944 fatcat:bs5bwoe2rvblfbxiz4773uom3u

Predicting the volatility of the S&P-500 stock index via GARCH models: the role of asymmetries

Basel M.A. Awartani, Valentina Corradi
2005 International Journal of Forecasting  
Comparing predictive accuracy. Journal of Business and Economic Statistics, 13, 253-263 test statistic].  ...  In this paper, we examine the relative out of sample predictive ability of different GARCH models, with particular emphasis on the predictive content of the asymmetric component.  ...  Her current research focuses on densities forecast evaluation, bootstrap techniques for recursive and rolling schemes, testing and modelling volatility processes.  ... 
doi:10.1016/j.ijforecast.2004.08.003 fatcat:jw22vie3jbhijcez3yduyvthvu

Control Optimization of Stochastic Systems Based on Adaptive Correction CKF Algorithm

FengJun Hu, Qian Zhang, Gang Wu
2020 International Journal of Aerospace Engineering  
adding memory factor to the filter, and the disturbance factors in nonlinear time-varying discrete stochastic systems are eliminated by multistep feedback predictive control strategy, so as to improve  ...  adaptive correction CKF algorithm has good control accuracy and robustness in the UAV control test.  ...  Acknowledgments This work is supported by the National Natural Science LGG18F010007), and Young Academic Team Project of Zhejiang Shuren University.  ... 
doi:10.1155/2020/2096302 fatcat:pis26c4kzzgjvc3lwroz32c4sy

Two-Phase Model of Multistep Forecasting of Traffic State Reliability

Jufen Yang, Zhigang Liu, Guiyan Jiang, Lin Zhu
2018 Discrete Dynamics in Nature and Society  
The research results based on the principle of multistep prediction can provide more information about the traffic operating quality in advance.  ...  The average relative error of multistep prediction reached the lowest value, 8.91% and 12.01%, respectively, for weekday and weekend data used.  ...  Acknowledgments The authors greatly appreciate the support provided by the National Key Supplementary Materials The flow chart of the two-phase model of multistep prediction based on wavelet neural  ... 
doi:10.1155/2018/7650928 fatcat:5rlnrmqq2fegvmvpmrfiztqjiu
« Previous Showing results 1 — 15 out of 421 results