scholarly journals Second-order gravitational effects of local inhomogeneities on CMB anisotropies and non-Gaussian signatures

2005 ◽  
Vol 72 (10) ◽  
Author(s):  
Kenji Tomita
Keyword(s):  
Second Order ◽  
Gravitational Effects ◽  
Non Gaussian

Non‐Gaussian Properties of Second‐Order Random Waves

1993 ◽  
Vol 119 (2) ◽  
pp. 344-364 ◽  
Author(s):  
Sau‐Lon James Hu ◽  
Dongsheng Zhao
Keyword(s):  
Second Order ◽  
Random Waves ◽  
Non Gaussian

Maximum Correntropy Criterion Constrained Kalman Filter

2017 ◽  
Author(s):  
Seyed Fakoorian ◽  
Mahmoud Moosavi ◽  
Reza Izanloo ◽  
Vahid Azimi ◽  
Dan Simon
Keyword(s):  
Kalman Filter ◽  
Gaussian Noise ◽  
State Constraints ◽  
Statistical Information ◽  
Second Order ◽  
System Model ◽  
Error Covariance ◽  
Inequality State ◽  
Maximum Correntropy Criterion ◽  
Non Gaussian

Non-Gaussian noise may degrade the performance of the Kalman filter because the Kalman filter uses only second-order statistical information, so it is not optimal in non-Gaussian noise environments. Also, many systems include equality or inequality state constraints that are not directly included in the system model, and thus are not incorporated in the Kalman filter. To address these combined issues, we propose a robust Kalman-type filter in the presence of non-Gaussian noise that uses information from state constraints. The proposed filter, called the maximum correntropy criterion constrained Kalman filter (MCC-CKF), uses a correntropy metric to quantify not only second-order information but also higher-order moments of the non-Gaussian process and measurement noise, and also enforces constraints on the state estimates. We analytically prove that our newly derived MCC-CKF is an unbiased estimator and has a smaller error covariance than the standard Kalman filter under certain conditions. Simulation results show the superiority of the MCC-CKF compared with other estimators when the system measurement is disturbed by non-Gaussian noise and when the states are constrained.

Neural Networks and HOS for Power Quality Evaluation

2011 ◽  
pp. 1226-1231
Author(s):  
Juan J. González De la Rosa ◽  
Carlos G. Puntonet ◽  
A. Moreno-Muñoz
Keyword(s):  
Signal Processing ◽  
Power Quality ◽  
Wavelet Transforms ◽  
Learning Rule ◽  
Higher Order ◽  
Second Order ◽  
Voltage Waveform ◽  
Long Duration ◽  
Non Linear Load ◽  
Non Gaussian

Power quality (PQ) event detection and classification is gaining importance due to worldwide use of delicate electronic devices. Things like lightning, large switching loads, non-linear load stresses, inadequate or incorrect wiring and grounding or accidents involving electric lines, can create problems to sensitive equipment, if it is designed to operate within narrow voltage limits, or if it does not incorporate the capability of filtering fluctuations in the electrical supply (Gerek et. al., 2006; Moreno et. al., 2006). The solution for a PQ problem implies the acquisition and monitoring of long data records from the energy distribution system, along with an automated detection and classification strategy which allows identify the cause of these voltage anomalies. Signal processing tools have been widely used for this purpose, and are mainly based in spectral analysis and wavelet transforms. These second-order methods, the most familiar to the scientific community, are based on the independence of the spectral components and evolution of the spectrum in the time domain. Other tools are threshold-based algorithms, linear classifiers and Bayesian networks. The goal of the signal processing analysis is to get a feature vector from the data record under study, which constitute the input to the computational intelligence modulus, which has the task of classification. Some recent works bring a different strategy, based in higher-order statistics (HOS), in dealing with the analysis of transients within PQ analysis (Gerek et. al., 2006; Moreno et. al., 2006) and other fields of Science (De la Rosa et. al., 2004, 2005, 2007). Without perturbation, the 50-Hz of the voltage waveform exhibits a Gaussian behaviour. Deviations from Gaussianity can be detected and characterized via HOS. Non-Gaussian processes need third and fourth order statistical characterization in order to be recognized. In order words, second-order moments and cumulants could be not capable of differentiate non-Gaussian events. The situation described matches the problem of differentiating between a transient of long duration named fault (within a signal period), and a short duration transient (25 per cent of a cycle). This one could also bring the 50-Hz voltage to zero instantly and, generally affects the sinusoid dramatically. By the contrary, the long-duration transient could be considered as a modulating signal (the 50-Hz signal is the carrier). These transients are intrinsically non-stationary, so it is necessary a battery of observations (sample registers) to obtain a reliable characterization. The main contribution of this work consists of the application of higher-order central cumulants to characterize PQ events, along with the use of a competitive layer as the classification tool. Results reveal that two different clusters, associated to both types of transients, can be recognized in the 2D graph. The successful results convey the idea that the physical underlying processes associated to the analyzed transients, generate different types of deviations from the typical effects that the noise cause in the 50-Hz sinusoid voltage waveform. The paper is organized as follows: Section on higher-order cumulants summarizes the main equations of the cumulants used in the paper. Then, we recall the competitive layer’s foundations, along with the Kohonen learning rule. The experience is described then, and the conclusions are drawn.

Information Theoretic Learning

2011 ◽  
pp. 902-909 ◽  
Author(s):  
Deniz Erdogmus ◽  
Jose C. Principe
Keyword(s):  
Neural Network ◽  
Least Squares ◽  
Adaptive Systems ◽  
Mean Squared Error ◽  
Learning Algorithms ◽  
Optimal Solution ◽  
Principal Component ◽  
Second Order ◽  
Linear Discriminant ◽  
Non Gaussian

Learning systems depend on three interrelated components: topologies, cost/performance functions, and learning algorithms. Topologies provide the constraints for the mapping, and the learning algorithms offer the means to find an optimal solution; but the solution is optimal with respect to what? Optimality is characterized by the criterion and in neural network literature, this is the least addressed component, yet it has a decisive influence in generalization performance. Certainly, the assumptions behind the selection of a criterion should be better understood and investigated. Traditionally, least squares has been the benchmark criterion for regression problems; considering classification as a regression problem towards estimating class posterior probabilities, least squares has been employed to train neural network and other classifier topologies to approximate correct labels. The main motivation to utilize least squares in regression simply comes from the intellectual comfort this criterion provides due to its success in traditional linear least squares regression applications – which can be reduced to solving a system of linear equations. For nonlinear regression, the assumption of Gaussianity for the measurement error combined with the maximum likelihood principle could be emphasized to promote this criterion. In nonparametric regression, least squares principle leads to the conditional expectation solution, which is intuitively appealing. Although these are good reasons to use the mean squared error as the cost, it is inherently linked to the assumptions and habits stated above. Consequently, there is information in the error signal that is not captured during the training of nonlinear adaptive systems under non-Gaussian distribution conditions when one insists on second-order statistical criteria. This argument extends to other linear-second-order techniques such as principal component analysis (PCA), linear discriminant analysis (LDA), and canonical correlation analysis (CCA). Recent work tries to generalize these techniques to nonlinear scenarios by utilizing kernel techniques or other heuristics. This begs the question: what other alternative cost functions could be used to train adaptive systems and how could we establish rigorous techniques for extending useful concepts from linear and second-order statistical techniques to nonlinear and higher-order statistical learning methodologies?

scholarly journals A Second-Order Exact Ensemble Square Root Filter for Nonlinear Data Assimilation

2015 ◽  
Vol 143 (4) ◽  
pp. 1347-1367 ◽  
Author(s):  
Julian Tödter ◽  
Bodo Ahrens
Keyword(s):  
Kalman Filter ◽  
Data Assimilation ◽  
Second Order ◽  
Square Root ◽  
Computationally Efficient ◽  
Research Activities ◽  
Wide Range ◽  
Matrix Square Root ◽  
Non Gaussian ◽  
Ensemble Transform

Abstract The ensemble Kalman filter (EnKF) and its deterministic variants, mostly square root filters such as the ensemble transform Kalman filter (ETKF), represent a popular alternative to variational data assimilation schemes and are applied in a wide range of operational and research activities. Their forecast step employs an ensemble integration that fully respects the nonlinear nature of the analyzed system. In the analysis step, they implicitly assume the prior state and observation errors to be Gaussian. Consequently, in nonlinear systems, the analysis mean and covariance are biased, and these filters remain suboptimal. In contrast, the fully nonlinear, non-Gaussian particle filter (PF) only relies on Bayes’s theorem, which guarantees an exact asymptotic behavior, but because of the so-called curse of dimensionality it is exposed to weight collapse. Here, it is shown how to obtain a new analysis ensemble whose mean and covariance exactly match the Bayesian estimates. This is achieved by a deterministic matrix square root transformation of the forecast ensemble, and subsequently a suitable random rotation that significantly contributes to filter stability while preserving the required second-order statistics. The properties and performance of the proposed algorithm are further investigated via a set of experiments. They indicate that such a filter formulation can increase the analysis quality, even for relatively small ensemble sizes, compared to other ensemble filters in nonlinear, non-Gaussian scenarios. Localization enhances the potential applicability of this PF-inspired scheme in larger-dimensional systems. The proposed algorithm, which is fairly easy to implement and computationally efficient, is referred to as the nonlinear ensemble transform filter (NETF).

Non-Gaussian Random Wave Simulation by Two-Dimensional Fourier Transform and Linear Oscillator Response to Morison Force

2007 ◽  
Vol 129 (4) ◽  
pp. 327-334 ◽  
Author(s):  
Xiang Yuan Zheng ◽  
Torgeir Moan ◽  
Ser Tong Quek
Keyword(s):  
Fourier Transform ◽  
Time Domain ◽  
Two Dimensions ◽  
Second Order ◽  
Linear Oscillator ◽  
Interaction Matrix ◽  
Random Wave ◽  
Two Dimensional ◽  
Near Surface ◽  
Non Gaussian

The one-dimensional fast Fourier transform (FFT) has been applied extensively to simulate Gaussian random wave elevations and water particle kinematics. The actual sea elevations/kinematics exhibit non-Gaussian characteristics that can be represented mathematically by a second-order random wave theory. The elevations/kinematics formulations contain frequency sum and difference terms that usually lead to expensive time-domain dynamic analyses of offshore structural responses. This study aims at a direct and efficient two-dimensional FFT algorithm for simulating the frequency sum terms. For the frequency-difference terms, inverse FFT and forward FFT are implemented, respectively, across the two dimensions of the wave interaction matrix. Given specified wave conditions, the statistics of simulated elevations/kinematics compare well with not only the empirical fits but also the analytical solutions based on a modified eigenvalue/eigenvector approach, while the computational effort of simulation is very economical. In addition, the stochastic analyses in both time domain and frequency domain show that, attributable to the second-order nonlinear wave effects, the near-surface Morison force and induced linear oscillator response are more non-Gaussian than those subjected to Gaussian random waves.

Approximation of Crossing Intensities for Non Linear Responses Subjected to Non Gaussian Loadings

2010 ◽  
Author(s):  
Thomas Galtier ◽  
Sayan Gupta ◽  
Igor Rychlik
Keyword(s):  
Heavy Tails ◽  
Moving Average ◽  
Ocean Waves ◽  
Response Characteristic ◽  
Second Order ◽  
Computationally Efficient ◽  
Marine Structures ◽  
Efficient Manner ◽  
New Class ◽  
Non Gaussian

Crossing intensity constitute an important response characteristic for randomly vibrating structures, especially if one is interested in estimating the risk against failures. This paper focusses on developing approximations by which estimates of the crossing intensities for response of marine structures can be obtained in a computationally efficient manner, when the loads are modeled as a special class of non-Gaussian processes, namely as LMA processes. Ocean waves exhibit considerable non-Gaussianity as marked by their skewed marginal distributions and heavy tails. Here, a new class of processes-the Laplace driven Moving Average (LMA) processes are used to model the ocean waves. LMA processes are non-Gaussian, strictly stationary, can model in principle any spectrum and have the additional flexibility to model the skewness and the kurtosis of the marginal distribution. The structure behavior assumed is limited to quadratic systems characterized by second order kernels, which is common for marine structures. Thus, an estimation of the crossing intensities of the response involves studying the crossing characteristics of a LMA process passing through a second order filter. A new computationally efficient hybrid method, which uses the saddle point approximations along with limited Monte Carlo simulations, is developed to compute crossing intensity of the response. The proposed method is illustrated through numerical examples.

Sign in / Sign up

Export Citation Format

Share Document