Search
Search results for: BASIS FUNCTIONS IDENTIFICATION AND SMOOTHING OF NONSTATIONARY SYSTEMS SAVITZKY–GOLAY FILTERS
-
Generalized Savitzky–Golay filters for identification of nonstationary systems
PublicationThe problem of identification of nonstationary systems using noncausal estimation schemes is consid-ered and a new class of identification algorithms, combining the basis functions approach with localestimationtechnique,isdescribed.Unliketheclassicalbasisfunctionestimationschemes,theproposedlocal basis function estimators are not used to obtain interval approximations of the parametertrajectory, but provide a sequence of point...
-
Application of regularized Savitzky–Golay filters to identification of time-varying systems
PublicationSavitzky–Golay (SG) filtering is a classical signal smoothing technique based on the local least squares approximation of the analyzed signal by a linear combination of known functions of time (originally — powers of time, which corresponds to polynomial approximation). It is shown that the regularized version of the SG algorithm can be successfully applied to identification of time-varying finite impulse response (FIR) systems....
-
Local basis function estimators for identification of nonstationary systems
PublicationThe problem of identification of a nonstationary stochastic system is considered and solved using local basis function approximation of system parameter trajectories. Unlike the classical basis function approach, which yields parameter estimates in the entire analysis interval, the proposed new identification procedure is operated in a sliding window mode and provides a sequence of point (rather than interval) estimates. It is...
-
Locally Adaptive Cooperative Kalman Smoothing and Its Application to Identification of Nonstationary Stochastic Systems
PublicationOne of the central problems of the stochastic approximation theory is the proper adjustment of the smoothing algorithm to the unknown, and possibly time-varying, rate and mode of variation of the estimated signals/parameters. In this paper we propose a novel locally adaptive parallel estimation scheme which can be used to solve the problem of fixed-interval Kalman smoothing in the presence of model uncertainty. The proposed solution...
-
Fully Adaptive Savitzky-Golay Type Smoothers
PublicationThe problem of adaptive signal smoothing is consid-ered and solved using the weighted basis function approach. Inthe special case of polynomial basis and uniform weighting theproposed method reduces down to the celebrated Savitzky-Golaysmoother. Data adaptiveness is achieved via parallel estimation.It is shown that for the polynomial and harmonic bases andcosinusoidal weighting sequences, the competing signal estimatescan be computed...
-
Regularized Local Basis Function Approach to Identification of Nonstationary Processes
PublicationThe problem of identification of nonstationary stochastic processes (systems or signals) is considered and a new class of identification algorithms, combining the basis functions approach with local estimation technique, is described. Unlike the classical basis function estimation schemes, the proposed regularized local basis function estimators are not used to obtain interval approximations of the parameter trajectory, but provide...
-
On noncausal identification of nonstationary stochastic systems
PublicationIn this paper we consider the problem of noncausal identification of nonstationary,linear stochastic systems, i.e., identification based on prerecorded input/output data. We show how several competing weighted least squares parameter smoothers, differing in memory settings, can be combined together to yield a better and more reliable smoothing algorithm. The resulting parallel estimation scheme automatically adjusts its smoothing...
-
On the preestimation technique and its application to identification of nonstationary systems
PublicationThe problem of noncausal identification of a nonstationary stochastic FIR (finite impulse response) sys- tem is reformulated, and solved, as a problem of smoothing of preestimated parameter trajectories. Three approaches to preestimation are critically analyzed and compared. It is shown that optimization of the smoothing operation can be performed adaptively using the parallel estimation technique. The new approach is computationally...
-
Towards Robust Identification of Nonstationary Systems
PublicationThe article proposes a fast, two-stage method for the identification of nonstationary systems. The method uses iterative reweighting to robustify the identification process against the outliers in the measurement noise and against the numerical errors that may occur at the first stage of identification. We also propose an adaptive algorithm to optimize the values of the hyperparameters that are crucial for this new method.
-
On ''cheap smoothing'' opportunities in identification of time-varying systems
PublicationIn certain applications of nonstationary system identification the model-based decisions can be postponed, i.e. executed with a delay. This allows one to incorporate into the identification process not only the currently available information, but also a number of ''future'' data points. The resulting estimation schemes, which involve smoothing, are not causal. Despite the possible performance improvements, the existing smoothing...
-
On noncausal weighted least squares identification of nonstationary stochastic systems
PublicationIn this paper, we consider the problem of noncausal identification of nonstationary, linear stochastic systems, i.e., identification based on prerecorded input/output data. We show how several competing weighted (windowed) least squares parameter smoothers, differing in memory settings, can be combined together to yield a better and more reliable smoothing algorithm. The resulting parallel estimation scheme automatically adjusts...
-
On the lower smoothing bound in identification of time-varying systems
PublicationIn certain applications of nonstationary system identification the model-based decisions can be postponed, i.e. executed with a delay. This allows one to incorporate in the identification process not only the currently available information, but also a number of ''future'' data points. The resulting estimation schemes, which involve smoothing, are not causal. Assuming that the infinite observation history is available, the paper...
-
Fast Basis Function Estimators for Identification of Nonstationary Stochastic Processes
PublicationThe problem of identification of a linear nonsta-tionary stochastic process is considered and solved using theapproach based on functional series approximation of time-varying parameter trajectories. The proposed fast basis func-tion estimators are computationally attractive and yield resultsthat are better than those provided by the local least squaresalgorithms. It is shown that two...
-
Locally-adaptive Kalman smoothing approach to identification of nonstationary stochastic systems
Publication -
New approach to noncausal identification of nonstationary stochastic systems subject to both smooth and abrupt parameter changes
PublicationIn this paper we consider the problem of finiteintervalparameter smoothing for a class of nonstationary linearstochastic systems subject to both smooth and abrupt parameterchanges. The proposed parallel estimation scheme combines theestimates yielded by several exponentially weighted basis functionalgorithms. The resulting smoother automatically adjustsits smoothing bandwidth to the type and rate of nonstationarityof the identified...
-
A new look at the statistical identification of nonstationary systems
PublicationThe paper presents a new, two-stage approach to identification of linear time-varying stochastic systems, based on the concepts of preestimation and postfiltering. The proposed preestimated parameter trajectories are unbiased but have large variability. Hence, to obtain reliable estimates of system parameters, the preestimated trajectories must be further filtered (postfiltered). It is shown how one can design and optimize such...
-
Medley filters - simple tools for efficient signal smoothing
PublicationMedley filters are defined as convex combinations of elementary smoothing filters (averaging, median) with different smoothing bandwidths. It is shown that when adaptive weights of such a mixture are evaluated using the recently proposed Bayesian rules, one obtains a tool which often outperforms the state-of-the-art wavelet-based smoothing algorithms. Additionally, unlike wavelet-based procedures, medley filters can easily cope...
-
New Approach to Noncasual Identification of Nonstationary Stochastic FIR Systems Subject to Both Smooth and Abrupt Parameter Changes
PublicationIn this technical note, we consider the problem of finite-interval parameter smoothing for a class of nonstationary linear stochastic systems subject to both smooth and abrupt parameter changes. The proposed parallel estimation scheme combines the estimates yielded by several exponentially weighted basis function algorithms. The resulting smoother automatically adjusts its smoothing bandwidth to the type and rate of nonstationarity...
-
Generalized adaptive comb filters/smoothers and their application to the identification of quasi-periodically varying systems and signals
PublicationThe problem of both causal and noncausal identification of linear stochastic systems with quasiharmonically varying parameters is considered. The quasi-harmonic description allows one to model nonsinusoidal quasi-periodic parameter changes. The proposed identification algorithms are called generalized adaptive comb filters/smoothers because in the special signal case they reduce down to adaptive comb algorithms used to enhance...
-
Optimally regularized local basis function approach to identification of time-varying systems
PublicationAccurate identification of stochastic systems with fast-varying parameters is a challenging task which cannot be accomplished using model-free estimation methods, such as weighted least squares, which assume only that system coefficients can be regarded as locally constant. The current state of the art solutions are based on the assumption that system parameters can be locally approximated by a linear combination of appropriately...
-
On Noncausal Identification of Nonstationary Multivariate Autoregressive Processes
PublicationThe problem of identification of nonstationary multivariate autoregressive processes using noncausal local estimation schemes is considered and a new approach to joint selection of the model order and the estimation bandwidth is proposed. The new selection rule, based on evaluation of pseudoprediction errors, is compared with the previously proposed one, based on the modified Akaike’s final prediction error criterion.
-
Identification of nonstationary processes using noncausal bidirectional lattice filtering
PublicationThe problem of off-line identification of a nonstationary autoregressive process with a time-varying order and a time-varying degree of nonstationarity is considered and solved using the parallel estimation approach. The proposed parallel estimation scheme is made up of several bidirectional (noncausal) exponentially weighted lattice algorithms with different estimation memory and order settings. It is shown that optimization of...
-
On joint order and bandwidth selection for identification of nonstationary autoregressive processes
PublicationWhen identifying a nonstationary autoregressive process, e.g. for the purpose of signal prediction or parametric spectrum estimation, two important decisions must be taken. First, one should choose the appropriate order of the autoregressive model, i.e., the number of autoregressive coefficients that will be estimated. Second, if identification is carried out using the local estimation technique, such as the localized version of...
-
Optimal and suboptimal algorithms for identification of time-varying systems with randomly drifting parameters
PublicationNoncausal estimation algorithms, which involve smoothing, can be used for off-line identification of nonstationary systems. Since smoothingis based on both past and future data, it offers increased accuracy compared to causal (tracking) estimation schemes, incorporating past data only. It is shown that efficient smoothing variants of the popular exponentially weighted least squares and Kalman filter-based parameter trackers can...
-
Identification of quasi-periodically varying systems with quasi-linear frequency changes
PublicationThe problem of identification of linear quasi-periodically varying systems is considered. This problem can be solved using generalized adaptive notch filtering (GANF) algorithms. It is shown that accuracy of system parameter estimation can be increased if the results obtained from GANF are further processed using a cascade of appropriately designed filters. The resulting generalized adaptive notch smoothing (GANS) algorithms can...
-
Zdzisław Kowalczuk prof. dr hab. inż.
PeopleZdzislaw Kowalczuk received his M.Sc. degree in 1978 and Ph.D. degree in 1986, both in Automatic Control from Technical University of Gdańsk (TUG), Gdańsk, Poland. In 1993 he received his D.Sc. degree (Dr Habilitus) in Automatic Control from Silesian Technical University, Gliwice, Poland, and the title of Professor from the President of Poland in 2003. Since 1978 he has been with Faculty of Electronics, Telecommunications and Informatics...
-
A New Method of Noncausal Identification of Time-varying Systems
PublicationThe paper shows that the problem of noncausal identification of a time-varying FIR (finite impulse response) sys- tem can be reformulated, and solved, as a problem of smoothing of the preestimated parameter trajectories. Characteristics of the smoothing filter should be chosen so as to provide the best trade- off between the bias and variance of the resulting estimates. It is shown that optimization of the smoothing operation can...
-
Generalized adaptive notch filters with frequency debiasing for tracking of polynomial phase systems
PublicationGeneralized adaptive notch filters are used for identification/tracking of quasi-periodically varying dynamic systems and can be considered an extension, to the system case, of classical adaptive notch filters. For general patterns of frequency variation the generalized adaptive notch filtering algorithms yield biased frequency estimates. We show that when system frequencies change slowly in a smooth way, the estimation bias can...
-
Variable-structure algorithm for identification of quasi-periodically varying systems
PublicationThe paper presents a variable-structure version of a generalized notchfiltering (GANF) algorithm. Generalized notch filters are used for identification of quasi-periodically varying dynamic systems and can be considered an extension, to the system case, of classical adaptive notch filters. The proposed algorithm is a cascade of two GANF filters: a multiple-frequency "precise" filter bank, used for precise system tracking, and a...
-
The consideration to the dynamic systems parameter identification
PublicationIn this paper, a concept for continuous-time dynamic systems parameter identification using modulating function approach is presented. It refers to linear as well as selected non-linear systems. It shows the possibility of direct application without converting differential equation. In particular cases direct application can decrease the amount of computation in non-linear system identification, which generally requires Fourier...
-
Generalized adaptive notch and comb filters for identification of quasi-periodically varying systems
PublicationW artykule wprowadzono pojęcie obiektów pseudookresowych o parametrach będących liczbami rzeczywistymi. Pokazanometody oparte na metodzie funkcji bazowych pozwalające na identyfikację takich obiektów. Przedstawiono związekpomiędzy zaprojektowanymi algorytmami a klasycznymi filtrami wycinającymi typu notch.
-
Mutually polarizable QM/MM model with in situ optimized localized basis functions
PublicationWe extend our recently developed quantum-mechanical/molecular mechanics (QM/MM) approach [Dziedzic et al., J. Chem. Phys. 145, 124106 (2016)] to enable in situ optimization of the localized orbitals. The quantum subsystem is described with ONETEP linear-scaling density functional theory and the classical subsystem – with the AMOEBA polarizable force field. The two subsystems interact via multipolar electrostatics and are fully...
-
Classification of Urban Regeneration Participants as a Basis for Identification of Construction Investment's Risk Sources
PublicationOn the basis of the conducted research it can be concluded that the majority of the existing urban regeneration problems are revealed by the lack of an in-depth analysis of sources and risk factors. For the above reasons, the subject of this study is classification of urban regeneration's participants as a basis for identification of construction investment's risk sources. The research methodology is based on an in-depth analysis...
-
Mesh-free approach to Helmholtz equation on radial basis functions
PublicationMetoda radialnych funkcji bazowych (RBF) jest coraz czesciej stosowana przy rozwiazywaniu rownan rozniczkowych czastkowych oraz zagadnien wlasnych. W szczegolnosci znalazla ona zastosowanie w problemach elektrodynamiki obliczeniowej. W publikacji zastosowano RBF do rozwiazania rownania Helmholtza. Wprowadzono nowy algorytm - adaptacyjny do wyznaczania centrow interpolacyjnych. Przedstawiona metode zastosowano do wyznaczenia rozkladow...
-
On bidirectional preestimates and their application to identification of fast time-varying systems
PublicationWhen applied to the identification of time-varying systems, such as rapidly fading telecommunication channels, adaptive estimation algorithms built on the local basis function (LBF) principle yield excellent tracking performance but are computationally demanding. The subsequently proposed fast LBF (fLBF) algorithms, based on the preestimation principle, allow a substantial reduction in complexity without significant performance...
-
Mesh-free approach to Helmholtz equation based on radial basis functions.
PublicationW artykule zastosowano metodę radialnych funkcji bazowych do rozwiązania równania Helmholthza oraz zaproponowano nowy (adaptacyjny) algorytm wyznaczania centrów interpolacyjnych. W oparciu o prezentowany schemat wyznaczono długości fal odcięcia dla różnych kształtów przekrojów poprzecznych falowodów cylindrycznych.
-
Road Restraint Systems as a Basis for Roadside Safety Improvement
PublicationRoadside-related crashes occur when vehicles run off the road. The majority of the crashes have severe outcomes, especially when an object is hit (tree, pole, supports, front wall of a culvert, barrier). These accidents represent app. 19% of all of Poland's road deaths. Roadside crashes involve: hitting a tree, hitting a barrier, hitting a sign or utility pole, vehicle roll-over on the roadside, vehicle roll-over on a slope and...
-
Tracking Moving Objects in Video Surveillance Systems with Kalman and Particle Filters – A Practical Approach
PublicationThis Chapter focuses on the first type of object tracking algorithms, namely on Kalman and particle filters. A theory of these algorithms may be found in many publications, there are also reports on implementation of these approaches to object tracking in video. However, developers of VCA systems still face two important problems. The first one is related to obtaining accurate measurements of positions and sizes of the tracked...
-
Automotive Validation Functions for On-line Test Evaluation of Hybrid Real-time Systems
PublicationThe aim of this paper is to present the means of black-box on-line test evaluation for hybrid real-time systems. The described procedures can be used for the model-based testing process so as to improve its effectiveness. In particular, intelligent automotive validation functions are considered, which are divided into different types depending on the nature of the evaluated issue. All provided definitions are specified on the meta-model...
-
Modelling of Objects Behaviour for Their Re-identification in Multi-camera Surveillance System Employing Particle Filters and Flow Graphs
PublicationAn extension of the re-identification method of modeling objects behavior in muti-camera surveillance systems, related to adding a particle filter to the decision-making algorithm is covered by the paper. A variety of tracking methods related to a single FOV (Field of Vision) are known, proven to be quite different for inter-camera tracking, especially in case of non-overlapping FOVs. The re-identification methods refer to the...
-
Identification of nonstationary multivariate autoregressive processes– Comparison of competitive and collaborative strategies for joint selection of estimation bandwidth and model order
PublicationThe problem of identification of multivariate autoregressive processes (systems or signals) with unknown and possibly time-varying model order and time-varying rate of parameter variation is considered and solved using parallel estimation approach. Under this approach, several local estimation algorithms, with different order and bandwidth settings, are run simultaneously and compared based on their predictive performance. First,...
-
CAD-model construction based on adaptive radial basis functions interpolation technique.
PublicationZaprezentowana jest nowa metoda konstrukcji modeli układów mikrofalowych. Modele tworzone sa na podstawie wyników symulacji pełnofalowej przy użyciu funkcji radialnych. Zaletą użycia funkcji radialnych jest gwarantowana nieosobliwość problemu interpolacyjnego. Dodatkowo zastosowany został algorytm adaptacyjnego próbkowania minimalizujący liczbę próbek potrzebnych do konstrukcji modelu.
-
Raw data for the paper "Mutually polarizable QM/MM model with in situ optimized localized basis functions"
Open Research DataThis dataset contains raw data used to generate plots in the paper Mutually polarizable QM/MM model with in situ optimized localized basis functions. The paper is devoted to a second generation of the TINKTEP model -- an QM/MM approach combining linear-scaling DFT (ONETEP) and a polarizable force field (AMOEBA).
-
Regularized identification of fast time-varying systems - comparison of two regularization strategies
PublicationThe problem of identification of a time-varying FIR system is considered and solved using the local basis function approach. It is shown that the estimation (tracking) results can be improved by means of regularization. Two variants of regularization are proposed and compared: the classical L2 (ridge) regularization and a new, reweighted L2 one. It is shown that the new approach can outperform the classical one and is computationally...
-
Fast Algorithms for Identification of Time-Varying Systems with Both Smooth and Discontinuous Parameter Changes
PublicationThe problem of noncausal identification of a time-varying linear system subject to both smooth and occasional jump-type changes is considered and solved using the preestimation technique combined with the basis function approach to modeling the variability of system parameters. The proposed estimation algorithms yield very good parameter tracking results and are computationally attractive.
-
Regularized Identification of Time-Varying FIR Systems Based on Generalized Cross-Validation
PublicationA new regularization method is proposed and applied to identification of time-varying finite impulse response systems. We show, that by a careful design of the regularization constraint, one can improve estimation results, especially in the presence of strong measurement noise. We also show that the the most appropriate regularization gain can be found by direct optimization of the generalized cross-validation criterion.
-
Fast recursive basis function estimators for identification of time-varying processes
PublicationW pracy wprowadzono nową kategorię filtrów adaptacyjnych opartych na metodzie funkcji bazowych i wykorzystujących koncepcję postfiltracji. Proponowane algorytmy pozwalają połączyć niską złożoność obliczeniową i dobre właściwości śledzące.
-
Novel Fault Identification for Electromechanical Systems via Spectral Technique and Electrical Data Processing
PublicationIt is proposed, developed, investigated, and validated by experiments and modelling for the first time in worldwide terms new data processing technologies, higher order spectral multiple correlation technologies for fault identification for electromechanical systems via electrical data processing. Investigation of the higher order spectral triple correlation technology via modelling has shown that the proposed data processing technology...
-
Gradient based basis function algorithms for identification of quasi periodically varying processes.
PublicationW pracy przedstawiono problem identyfikacji systemów, których parametry zmieniają się w sposób pseudookresowy. Pokazano sposób, w jaki można modelować takie systemy przy zastosowaniu metody harmonicznych funkcji bazowych.Przedstawiono dwa sposoby dekompozycji (struktura szeregowa i równoległa) takich układów na elementy związane z poszczególnymi funkcjami bazowymi. Zaprezentowany został sposób śledzenia częstotliwości funkcji...
-
Discrete identification of continuous non-linear and non-stationary dynamical systems that is insensitive to noise correlation and measurement outliers
PublicationThe paper uses specific parameter estimation methods to identify the coefficients of continuous-time models represented by linear and non-linear ordinary differential equations. The necessary approximation of such systems in discrete time in the form of utility models is achieved by the use of properly tuned `integrating filters' of the FIR type. The resulting discrete-time descriptions retain the original continuous parameterization...