19 results on '"Nonstationary random processes"'
Search Results
2. Variance of a Nonstationary Random Process.
- Author
-
Galleani, Lorenzo and Cohen, Leon
- Subjects
- *
RANDOM fields , *WIGNER distribution , *WIENER processes , *ANALYSIS of variance , *STOCHASTIC differential equations , *LANGEVIN equations , *F-distribution - Abstract
We show how to obtain the instantaneous variance of a nonstationary random process by way of the Wigner spectrum. This is done by transforming the governing differential equation into the time-frequency domain and by finding the second conditional moment of frequency. We illustrate the method with Brownian motion. © 2006 American Institute of Physics [ABSTRACT FROM AUTHOR]
- Published
- 2006
- Full Text
- View/download PDF
3. Locally Stationary Noise and Random Processes.
- Author
-
Galleani, Lorenzo, Cohen, Leon, and Suter, Bruce
- Subjects
- *
NOISE , *STOCHASTIC processes , *WIGNER distribution , *DISTRIBUTION (Probability theory) , *STATIONARY processes , *FOURIER transforms , *RANDOM noise theory - Abstract
We obtain a criteria for “local stationarity” for a stochastic process. By a process being locally stationary we mean that has stationary properties in an interval of time. We argue that a random process is locally stationary when its time-varying spectrum is approximately factorable into its marginals at the time point of interest. In addition, we also define local stationarity in frequency and time-frequency. © 2006 American Institute of Physics [ABSTRACT FROM AUTHOR]
- Published
- 2006
- Full Text
- View/download PDF
4. A probabilistic performance-based approach for mitigating the seismic pounding risk between adjacent buildings.
- Author
-
Barbato, M. and Tubaldi, E.
- Subjects
EARTHQUAKE hazard analysis ,EARTHQUAKE engineering ,EARTHQUAKE resistant design ,MULTI-degree of freedom ,STRUCTURAL dynamics ,STRUCTURAL analysis (Engineering) - Abstract
ABSTRACT Existing design procedures for determining the separation distance between adjacent buildings subjected to seismic pounding risk are based on approximations of the buildings' peak relative displacement. These procedures are characterized by unknown safety levels and thus are not suitable for use within a performance-based earthquake engineering framework. This paper introduces an innovative reliability-based methodology for the design of the separation distance between adjacent buildings. The proposed methodology, which is naturally integrated into modern performance-based design procedures, provides the value of the separation distance corresponding to a target probability of pounding during the design life of the buildings. It recasts the inverse reliability problem of the determination of the design separation distance as a zero-finding problem and involves the use of analytical techniques in order to evaluate the statistics of the dynamic response of the buildings. Both uncertainty in the seismic intensity and record-to-record variability are taken into account. The proposed methodology is applied to several different buildings modeled as linear elastic single-degree-of-freedom (SDOF) and multi-degree-of-freedom (MDOF) systems, as well as SDOF nonlinear hysteretic systems. The design separation distances obtained are compared with the corresponding estimates that are based on several response combination rules suggested in the seismic design codes and in the literature. In contrast to current seismic code design procedures, the newly proposed methodology provides consistent safety levels for different building properties and different seismic hazard conditions. Copyright © 2012 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]
- Published
- 2013
- Full Text
- View/download PDF
5. Time–Frequency Analysis of the Endocavitarian Signal in Paroxysmal Atrial Fibrillation.
- Author
-
Pagana, Guido, Galleani, Lorenzo, Gross, Stefano, Roch, Massimo Ruo, Pastore, Erica, Poggio, Mauro, and Quaranta, Greta
- Subjects
- *
ATRIAL fibrillation , *TIME-frequency analysis , *CATHETER ablation , *STOCHASTIC processes , *HEART beat measurement , *ELECTRONOGRAPHY - Abstract
We apply the time–frequency analysis to the endocavitarian signal of patients suffering from paroxysmal atrial fibrillation. The time–frequency spectrum reveals the components of the endocavitarian signal. These components are located in the regions of the time–frequency domain that differ for in-rhythm and in-atrial fibrillation signals. By using experimental data, we perform a statistical study of these regions, and we obtain their average value. The difference in the shape of these regions is caused by the re-entry circuits that characterize atrial fibrillation. We propose a propagation model for atrial fibrillation based on the re-entry circuits, which explains the shape of the time–frequency spectrum. [ABSTRACT FROM PUBLISHER]
- Published
- 2012
- Full Text
- View/download PDF
6. Wavelet Packets of Nonstationary Random Processes: Contributing Factors for Stationarity and Decorrelation.
- Author
-
Atto, Abdourrahmane M. and Berthoumieu, Yannick
- Subjects
- *
WAVELETS (Mathematics) , *STOCHASTIC processes , *STATISTICAL correlation , *POLYNOMIALS , *MATHEMATICAL decomposition , *MATHEMATICAL models , *TIME series analysis , *PARAMETER estimation - Abstract
The paper addresses the analysis and interpretation of second order random processes by using the wavelet packet transform. It is shown that statistical properties of the wavelet packet coefficients are specific to the filtering sequences characterizing wavelet packet paths. These statistical properties also depend on the wavelet order and the form of the cumulants of the input random process. The analysis performed points out the wavelet packet paths for which stationarization, decorrelation and higher order dependency reduction are effective among the coefficients associated with these paths. This analysis also highlights the presence of singular wavelet packet paths: the paths such that stationarization does not occur and those for which dependency reduction is not expected through successive decompositions. The focus of the paper is on understanding the role played by the parameters that govern stationarization and dependency reduction in the wavelet packet domain. This is addressed with respect to semi-analytical cumulant expansions for modeling different types of nonstatonarity and correlation structures. The characterization obtained eases the interpretation of random signals and time series with respect to the statistical properties of their coefficients on the different wavelet packet paths. [ABSTRACT FROM PUBLISHER]
- Published
- 2012
- Full Text
- View/download PDF
7. A Comparison Between Different Discrete Ambiguity Domain Definitions in Stochastic Time-Frequency Analysis.
- Author
-
Sandberg, Johan and Hansson-Sandsten, Maria
- Subjects
- *
TIME-frequency analysis , *DISCRETE-time systems , *STOCHASTIC analysis , *SPECTRUM analysis , *STOCHASTIC processes , *DISTRIBUTION (Probability theory) , *KERNEL functions , *ANALYSIS of covariance - Abstract
The ambiguity domain plays a central role in estimating the time-varying spectrum and in estimating the covariance function of nonstationary random processes in continuous time. For processes indiscrete time, there exist different definitions of the ambiguity domain, but it is well known that neither of these definitions perfectly resembles the usefulness of the continuous ambiguity domain. In this paper, we present some of the most frequently used definitions of the ambiguity domain in discrete time: the Claasen-Mecklenbräuker, the Jeong-Williams, and the Nuttall definitions. For the first time, we prove their equivalence within some necessary conditions and we present theorems that justify their usage. [ABSTRACT FROM AUTHOR]
- Published
- 2009
- Full Text
- View/download PDF
8. Fast Approximate Joint Diagonalization Incorporating Weight Matrices.
- Author
-
Tichavský, Petr and Yeredor, Arie
- Subjects
- *
SYMMETRIC matrices , *ALGORITHMS , *GAUSSIAN processes , *STOCHASTIC processes , *BLIND source separation , *TIME-frequency analysis , *LARGE scale systems , *LEAST squares , *ANALYSIS of covariance - Abstract
We propose a new low-complexity approximate joint diagonalization (AJD) algorithm, which incorporates nontrivial block-diagonal weight matrices into a weighted least-squares (WLS) AJD criterion. Often in blind source separation (BSS), when the sources are nearly separated, the optimal weight matrix for WLS-based AJD takes a (nearly) block-diagonal form. Based on this observation, we show how the new algorithm can be utilized in an iteratively reweighted separation scheme, thereby giving rise to fast implementation of asymptotically optimal BSS algorithms in various scenarios. In particular, we consider three specific (yet common) scenarios, involving stationary or block-stationary Gaussian sources, for which the optimal weight matrices can be readily estimated from the sample covariance matrices (which are also the target-matrices for the AJD). Comparative simulation results demonstrate the advantages in both speed and accuracy, as well as compliance with the theoretically predicted asymptotic optimality of the resulting BSS algorithms based on the weighted AJD, both on large scale problems with matrices of the size 100 x 100. [ABSTRACT FROM AUTHOR]
- Published
- 2009
- Full Text
- View/download PDF
9. CHARACTERIZATION OF NONSTATIONARY ATOMIC CLOCKS.
- Author
-
Galleani, Lorenzo and Tavella, Patrizia
- Subjects
- *
ATOMIC clocks , *ATOMIC frequency standards , *FREQUENCY standards , *STOCHASTIC processes , *ANALYSIS of variance - Abstract
Atomic clocks are the core of a navigation system. Since an error in time results in an error in the user localization, it is fundamental that the stability is very high and constant with time. In this paper we discuss the dynamic Allan variance, or DAVAR, a representation of the time-varying stability of an atomic clock. We show by simulation its effectiveness in tracking common nonstationary behaviors of a clock. [ABSTRACT FROM AUTHOR]
- Published
- 2007
- Full Text
- View/download PDF
10. Comments on "The Generalized Wiener Process for Colored Noise.".
- Author
-
Loughlin, Patrick J.
- Subjects
STOCHASTIC processes ,DIFFERENTIAL equations ,WIENER integrals ,GENERALIZED integrals ,PHASE space ,AUTOCORRELATION (Statistics) - Abstract
Galleani and Cohen have developed a new approach to the study of random differential equations. Recently, they applied their method to the interesting case that they called the generalized Wiener process. We show that while the phase space equation they derived is correct, their solution to the equation is not the full solution but holds only under certain conditions. We obtain the general solution and discuss under what circumstances their solution is exact, and under what circumstances their solution is a good approximation to the exact solution. In addition, we pinpoint where in their method of solution they neglected a term, and give the correction. In many cases, their approach may be accurate enough, and hence preferable, as it is a simpler calculation than the exact solution. However, for processes with long correlation times (i.e., autocorrelation functions that do not decay rapidly to zero), the complete method of solution presented here may be required. [ABSTRACT FROM AUTHOR]
- Published
- 2007
- Full Text
- View/download PDF
11. The Generalized Wiener Process for Colored Noise.
- Author
-
Galleani, Lorenzo and Cohen, Leon
- Subjects
WIENER processes ,DIFFERENTIAL equations ,RANDOM noise theory ,STOCHASTIC processes ,AUTOCORRELATION (Statistics) - Abstract
We define the generalized Wiener process as the output of a first-order differential equation when the input is an arbitrary stochastic input. This is in contrast to the standard Wiener process, where the input is white Gaussian noise. We obtain a simple explicit result for any input wide sense stationary random process, namely, that the Wigner spectrum of the output random process is the product of the power spectrum of the input process times a simple universal function of time and frequency. We also obtain the impulse response function wherein the output of the generalized process is expressed as the impulse response function integrated with the input random process. Various limiting values are derived. We apply the method to the case where the driving stochastic process has an exponentially decaying autocorrelation function [ABSTRACT FROM AUTHOR]
- Published
- 2006
- Full Text
- View/download PDF
12. Nonstationary Spectral Analysis Based on Time-Frequency Operator Symbols and Underspread Approximations.
- Author
-
Matz, Gerald and Hlawatsch, Franz
- Subjects
- *
APPROXIMATION theory , *SPECTRUM analysis , *STOCHASTIC processes , *GABOR transforms , *FOURIER transforms , *CALCULUS , *INFORMATION theory , *MATHEMATICAL analysis , *ALGEBRA - Abstract
We present a unified framework for time-varying or time-frequency (TF) spectra of nonstationary random processes in terms of TF operator symbols. We provide axiomatic definitions and TF operator symbol formulations for two broad classes of TF spectra, one of which is new. These classes contain all major existing TF spectra such as the Wigner-Ville, evolutionary, instantaneous power, and physical spectrum. Our subsequent analysis focuses on the practically important case of nonstationary processes with negligible high-lag TF correlations (so-called underspread processes). We demonstrate that for underspread processes all TF spectra yield effectively identical results and satisfy several desirable properties at least approximately. We also show that Gabor frames provide approximate Karhunen-Loève (KL) functions of underspread processes and TF spectra provide a corresponding approximate KL spectrum. Finally, we formulate simple approximate input-output relations for the TF spectra of underspread processes that are passed through underspread linear time-varying systems. All approximations are substantiated mathematically by upper bounds on the associated approximation errors. Our results establish a TF calculus for the second-order analysis and time-varying filtering of underspread processes that is as simple as the conventional spectral calculus for stationary processes. [ABSTRACT FROM AUTHOR]
- Published
- 2006
- Full Text
- View/download PDF
13. Wigner distributions (nearly) everywhere: time–frequency analysis of signals, systems, random processes, signal spaces, and frames
- Author
-
Matz, Gerald and Hlawatsch, Franz
- Subjects
- *
SIGNAL processing , *LINEAR time invariant systems - Abstract
The Wigner distribution (WD) is perhaps the most prominent quadratic time–frequency signal representation. In this paper, which has mainly tutorial character but also contains some new results, we describe extensions of the WD concept to multidimensional vector signals, nonstationary random processes, linear time-varying systems (deterministic and random), linear signal spaces, and frames. We discuss the interpretation and properties of these WD extensions and various relations connecting them. Some application examples are also provided. [Copyright &y& Elsevier]
- Published
- 2003
- Full Text
- View/download PDF
14. Time-Frequency Representation of MIMO Dynamical Systems
- Author
-
Lorenzo Galleani
- Subjects
Signal processing ,Stationary process ,Dynamical systems theory ,Stochastic process ,MIMO ,Nonstationary signals ,Topology ,Noise (electronics) ,MIMO systems ,Time-frequency analysis ,Control theory ,Frequency domain ,Signal Processing ,Nonstationary random processes ,Time domain ,Electrical and Electronic Engineering ,Mathematics - Abstract
Many deterministic and random physical signals can be modeled as the output of a multi-input-multi-output (MIMO) dynamical system. Since physical signals are typically nonstationary, their frequency content changes with time. To understand this time variation, we transform the MIMO system to the time-frequency domain. The result is a time-frequency MIMO dynamical system, whose input and output are the time-frequency spectra of the original input and output signals in the time domain. The time-frequency system reveals the spectral mechanisms involved in the generation of nonstationary signals. We apply our method to the case of a MIMO system with two vibrational modes and a nonstationary noise at the input. We obtain the time-frequency spectrum of the output, which shows how the spectrum of the modes changes with time. This result cannot be achieved with classical spectral techniques, because they require the input random process to be wide sense stationary.
- Published
- 2013
- Full Text
- View/download PDF
15. Моделювання процесів з детермінованими і стохастичними трендами
- Subjects
Information technology, system analysis and guidance ,Інформаційні технології, системний аналіз та керування ,Nonstationary random processes ,Deterministic and stochastic trends ,Mathematical modeling ,Model constructing methodology ,Информационные технологии, системный анализ и управление ,Нестаціонарні випадкові процеси ,Детерміновані та випадкові тренди ,Математичне моделювання ,Методика побудови моделі ,Нестационарные случайные процессы ,Детерминированные и стохастические тренды ,Математическое моделирование ,Методика построения модели - Abstract
Most of actual financial and economic processes exhibit nonstationary behavior. Their mathematical expectation and/or variance are functions of time what requires constructing of adequate forecasting models for the processes of this class. The purpose of the work is review of deterministic trends models and their applications, the study of possibilities for application of stochastic processes combinations for describing stochastic trends, as well as development of recommendations for modeling stochastic trends. As the examples of deterministic trends models we used time polynomials, exponents, splines and combinations of harmonic functions. To describe stochastic trends the following combinations of random processes were used: random walk, random walk with noise and shift, and the model of linear local trend. The procedure proposed for mathematical description of stochastic trends provides a possibility for constructing adequate candidate models for estimating of short and medium period forecasts. The study of the modeling procedure proposed with the use of heteroskedastic processes models for forecasting nonstationary process variance provide a possibility for reaching acceptable forecasting quality for stochastic trends. The mean absolute percentage errors for the generated forecasts was in the following limits: 7 – 20%., Большинство финансово-экономических процессов имеют нестационарный характер – их математическое ожидание и/или дисперсия являются функциями времени. Поэтому существует актуальная задача построения адекватных прогнозирующих моделей процессов такого класса. Целью работы является обзор моделей детерминированных трендов и их применение, исследование возможности использования комбинаций случайных процессов для описания стохастических трендов, а также для выработки рекомендаций по моделированию процессов со случайными трендами. В качестве примеров моделей детерминированных трендов рассмотрены полиномы от времени, экспонента, сплайны и комбинации гармонических функций. Для описания стохастических трендов применены комбинации случайных процессов: модель случайного блуждания, модель случайного блуждания с шумом и дрейфом, а также модель линейного локального тренда. Предложенная процедура математического описания стохастических трендов обеспечивает возможность получения адекватных моделей-кандидатов для дальнейшего оценивания кратко- и среднесрочных прогнозов. Исследование предложенной процедуры с использованием моделей гетероскедастических процессов для прогнозирования нестационарной дисперсии исследуемого процесса свидетельствует о возможности достижения приемлемого качества прогнозирования стохастических трендов. При этом средняя абсолютная ошибка прогнозов в процентах находилась в пределах 7–20 %., Більшість фінансово-економічних процесів мають нестаціонарний характер – їх математичне сподівання та/або дисперсія є функціями часу, а тому існує актуальна задача побудови адекватних прогнозуючих моделей процесів такого класу. Метою роботи є огляд моделей детермінованих трендів та їх застосування, дослідження можливості використання комбінацій випадкових процесів для опису стохастичних трендів, а також вироблення рекомендації стосовно моделювання процесів з випадковими трендами. За приклади моделей детермінованих трендів використано поліноми стосовно часу, експоненту, сплайни і комбінації гармонічних функцій. Для опису стохастичних трендів використано комбінації випадкових процесів: модель випадкового кроку, модель випадкового кроку з шумом та дрейфом і модель лінійного локального тренду. Запропонована процедура математичного опису стохастичних трендів забезпечує отримання адекватних моделей-кандидатів для подальшого оцінювання коротко- і середньострокових прогнозів. Дослідження запропонованої процедури з використанням моделей гетероскедастичних процесів для прогнозування змінної у часі дисперсії досліджуваного процесу свідчать про можливість досягнення прийнятної якості прогнозування стохастичних трендів. При цьому середня абсолютна похибка прогнозів у процентах була в межах 7–20 %.
- Published
- 2015
16. Modeling the Processes with Deterministic and Stochastic Trends
- Author
-
Trofymchuk, Oleksandr M. and Kutovyj, Taras Yu.
- Subjects
model constructing methodology ,методика побудови моделі ,детерміновані та випадкові тренди ,методика построения модели ,mathematical modeling ,нестаціонарні випадкові процеси ,нестационарные случайные процессы ,детерминированные и стохастические тренды ,004.942 + 519.766 ,математичне моделювання ,nonstationary random processes ,deterministic and stochastic trends ,математическое моделирование - Abstract
Більшість фінансово-економічних процесів мають нестаціонарний характер - їх математичне сподівання та/або дисперсія є функціями часу, а тому існує актуальна задача побудови адекватних прогнозуючих моделей процесів такого класу. Метою роботи є огляд моделей детермінованих трендів та їх застосування, дослідження можливості використання комбінацій випадкових процесів для опису стохастичних трендів, а також вироблення рекомендації стосовно моделювання процесів з випадковими трендами. За приклади моделей детермінованих трендів використано поліноми стосовно часу, експоненту, сплайни і комбінації гармонічних функцій. Для опису стохастичних трендів використано комбінації випадкових процесів: модель випадкового кроку, модель випадкового кроку з шумом та дрейфом і модель лінійного локального тренду. Запропонована процедура математичного опису стохастичних трендів забезпечує отримання адекватних моделей-кандидатів для подальшого оцінювання коротко- і середньострокових прогнозів. Дослідження запропонованої процедури з використанням моделей гетероскедастичних процесів для прогнозування змінної у часі дисперсії досліджуваного процесу свідчать про можливість досягнення прийнятної якості прогнозування стохастичних трендів. При цьому середня абсолютна похибка прогнозів у процентах була в межах 7-20 %. Most of actual financial and economic processes exhibit nonstationary behavior. Their mathematical expectation and/or variance are functions of time what requires constructing of adequate forecasting models for the processes of this class. The purpose of the work is review of deterministic trends models and their applications, the study of possibilities for application of stochastic processes combinations for describing stochastic trends, as well as development of recommendations for modeling stochastic trends. As the examples of deterministic trends models we used time polynomials, exponents, splines and combinations of harmonic functions. To describe stochastic trends the following combinations of random processes were used: random walk, random walk with noise and shift, and the model of linear local trend. The procedure proposed for mathematical description of stochastic trends provides a possibility for constructing adequate candidate models for estimating of short and medium period forecasts. The study of the modeling procedure proposed with the use of heteroskedastic processes models for forecasting nonstationary process variance provide a possibility for reaching acceptable forecasting quality for stochastic trends. The mean absolute percentage errors for the generated forecasts was in the following limits: 7-20%. Большинство финансово-экономических процессов имеют нестационарный характер - их математическое ожидание и/или дисперсия являются функциями времени. Поэтому существует актуальная задача построения адекватных прогнозирующих моделей процессов такого класса. Целью работы является обзор моделей детерминированных трендов и их применение, исследование возможности использования комбинаций случайных процессов для описания стохастических трендов, а также для выработки рекомендаций по моделированию процессов со случайными трендами. В качестве примеров моделей детерминированных трендов рассмотрены полиномы от времени, экспонента, сплайны и комбинации гармонических функций. Для описания стохастических трендов применены комбинации случайных процессов: модель случайного блуждания, модель случайного блуждания с шумом и дрейфом, а также модель линейного локального тренда. Предложенная процедура математического описания стохастических трендов обеспечивает возможность получения адекватных моделей-кандидатов для дальнейшего оценивания кратко- и среднесрочных прогнозов. Исследование предложенной процедуры с использованием моделей гетероскедастических процессов для прогнозирования нестационарной дисперсии исследуемого процесса свидетельствует о возможности достижения приемлемого качества прогнозирования стохастических трендов. При этом средняя абсолютная ошибка прогнозов в процентах находилась в пределах 7-20 %.
- Published
- 2015
17. Modeling the Processes with Deterministic and Stochastic Trends
- Author
-
Трофимчук, Олександр Миколайович; Institute of Telecommunications and Global Information Space at NAS of Ukraine, Кутовий, Тарас Юрійович; NTUU “KPI”, Трофимчук, Олександр Миколайович; Institute of Telecommunications and Global Information Space at NAS of Ukraine, and Кутовий, Тарас Юрійович; NTUU “KPI”
- Abstract
Most of actual financial and economic processes exhibit nonstationary behavior. Their mathematical expectation and/or variance are functions of time what requires constructing of adequate forecasting models for the processes of this class. The purpose of the work is review of deterministic trends models and their applications, the study of possibilities for application of stochastic processes combinations for describing stochastic trends, as well as development of recommendations for modeling stochastic trends. As the examples of deterministic trends models we used time polynomials, exponents, splines and combinations of harmonic functions. To describe stochastic trends the following combinations of random processes were used: random walk, random walk with noise and shift, and the model of linear local trend. The procedure proposed for mathematical description of stochastic trends provides a possibility for constructing adequate candidate models for estimating of short and medium period forecasts. The study of the modeling procedure proposed with the use of heteroskedastic processes models for forecasting nonstationary process variance provide a possibility for reaching acceptable forecasting quality for stochastic trends. The mean absolute percentage errors for the generated forecasts was in the following limits: 7 – 20%., Большинство финансово-экономических процессов имеют нестационарный характер – их математическое ожидание и/или дисперсия являются функциями времени. Поэтому существует актуальная задача построения адекватных прогнозирующих моделей процессов такого класса. Целью работы является обзор моделей детерминированных трендов и их применение, исследование возможности использования комбинаций случайных процессов для описания стохастических трендов, а также для выработки рекомендаций по моделированию процессов со случайными трендами. В качестве примеров моделей детерминированных трендов рассмотрены полиномы от времени, экспонента, сплайны и комбинации гармонических функций. Для описания стохастических трендов применены комбинации случайных процессов: модель случайного блуждания, модель случайного блуждания с шумом и дрейфом, а также модель линейного локального тренда. Предложенная процедура математического описания стохастических трендов обеспечивает возможность получения адекватных моделей-кандидатов для дальнейшего оценивания кратко- и среднесрочных прогнозов. Исследование предложенной процедуры с использованием моделей гетероскедастических процессов для прогнозирования нестационарной дисперсии исследуемого процесса свидетельствует о возможности достижения приемлемого качества прогнозирования стохастических трендов. При этом средняя абсолютная ошибка прогнозов в процентах находилась в пределах 7–20 %., Більшість фінансово-економічних процесів мають нестаціонарний характер – їх математичне сподівання та/або дисперсія є функціями часу, а тому існує актуальна задача побудови адекватних прогнозуючих моделей процесів такого класу. Метою роботи є огляд моделей детермінованих трендів та їх застосування, дослідження можливості використання комбінацій випадкових процесів для опису стохастичних трендів, а також вироблення рекомендації стосовно моделювання процесів з випадковими трендами. За приклади моделей детермінованих трендів використано поліноми стосовно часу, експоненту, сплайни і комбінації гармонічних функцій. Для опису стохастичних трендів використано комбінації випадкових процесів: модель випадкового кроку, модель випадкового кроку з шумом та дрейфом і модель лінійного локального тренду. Запропонована процедура математичного опису стохастичних трендів забезпечує отримання адекватних моделей-кандидатів для подальшого оцінювання коротко- і середньострокових прогнозів. Дослідження запропонованої процедури з використанням моделей гетероскедастичних процесів для прогнозування змінної у часі дисперсії досліджуваного процесу свідчать про можливість досягнення прийнятної якості прогнозування стохастичних трендів. При цьому середня абсолютна похибка прогнозів у процентах була в межах 7–20 %.
- Published
- 2015
18. Representation of nonstationary narrowband random processes and their application and effectiveness as jamming signals in spread spectrum communication systems
- Author
-
Bukofzer, Daniel C., Myers, Glen A., Naval Postgraduate School (U.S.), Electrical and Computer Engineering, Low, Kah Meng, Bukofzer, Daniel C., Myers, Glen A., Naval Postgraduate School (U.S.), Electrical and Computer Engineering, and Low, Kah Meng
- Abstract
A representation of nonstationary narrowband random processes in terms of nonstationary quadrature components is proposed in a form analogous to that used to represent wide sense stationary narrowband random processes. The representation is then applied to a specific case in which the nonstationary narrowband random process is generated by the product of white noise and a deterministic periodic signal and then is processed by a narrowband filter. This representation is used in the modeling of a bi-level pulsed noise jammer which is assumed to be present in a communication channel. The effect of such a jammer on a direct sequence, binary phase shift keyed (DS-BPSK) spread spectrum communication receiver is evaluated and characterized in terms of the error rate performance of the receiver. Families of performance curves are plotted to demonstrate the effect of various parameters, namely signal-to-noise ratio, jammer power to signal power ratio, and processing gain, on the error rate of the complete spread spectrum receiver. The analysis carried out differentiates between two cases, namely fast jammers and slow jammers. However, the analytical tools developed make it possible to consider either one of the two cases without resorting to quasi-stationary arguments as has been done in the past., http://archive.org/details/representationof1094522458, Civilian, Singapore Ministry of Defense, Approved for public release; distribution is unlimited.
19. Representation of nonstationary narrowband random processes and their application and effectiveness as jamming signals in spread spectrum communication systems
- Author
-
Low, Kah Meng, Bukofzer, Daniel C., Myers, Glen A., Naval Postgraduate School (U.S.), and Electrical and Computer Engineering
- Subjects
Pulsed noise jammer ,Electrical and computer engineering ,Nonstationary random processes ,Spread spectrum communication - Abstract
A representation of nonstationary narrowband random processes in terms of nonstationary quadrature components is proposed in a form analogous to that used to represent wide sense stationary narrowband random processes. The representation is then applied to a specific case in which the nonstationary narrowband random process is generated by the product of white noise and a deterministic periodic signal and then is processed by a narrowband filter. This representation is used in the modeling of a bi-level pulsed noise jammer which is assumed to be present in a communication channel. The effect of such a jammer on a direct sequence, binary phase shift keyed (DS-BPSK) spread spectrum communication receiver is evaluated and characterized in terms of the error rate performance of the receiver. Families of performance curves are plotted to demonstrate the effect of various parameters, namely signal-to-noise ratio, jammer power to signal power ratio, and processing gain, on the error rate of the complete spread spectrum receiver. The analysis carried out differentiates between two cases, namely fast jammers and slow jammers. However, the analytical tools developed make it possible to consider either one of the two cases without resorting to quasi-stationary arguments as has been done in the past. http://archive.org/details/representationof1094522458 Civilian, Singapore Ministry of Defense Approved for public release; distribution is unlimited.
- Published
- 1987
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.