Search

This paper deals with parameter estimation problem of large‐scale systems. A recursive distributed parameter estimation algorithm, based on the minimization of the prediction estimation error method, is developed. Specifically, the class of large‐scale systems that are composed of several interconnected sub‐systems is considered. Each interconnected sub‐system is modelled by a linear discrete‐time state space mathematical model with unknown parameters. The convergence analysis is then achieved using the Lyapunov approach. The theoretical analysis and simulation results prove the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Abstract: Classifier combination methods have proved to be an effective tool to increase the performance of classification techniques that can be used in any pattern recognition applications. Despite a significant number of publications describing successful classifier combination implementations, the theoretical basis is still not matured enough and achieved improvements are inconsistent. In this paper, we propose a novel statistical validation technique known as correlation‐based classifier combination technique for combining classifier in any pattern recognition problem. This validation has significant influence on the performance of combinations, and their utilization is necessary for complete theoretical understanding of combination algorithms. The analysis presented is statistical in nature but promises to lead to a class of algorithms for rank‐based decision combination. The potentials of the theoretical and practical issues in implementation are illustrated by applying it on 2 standard datasets in pattern recognition domain, namely, handwritten digit recognition and letter image recognition datasets taken from UCI Machine Learning Database Repository ( http://www.ics.uci.edu/_mlearn). An empirical evaluation using 8 well‐known distinct classifiers confirms the validity of our approach compared to some other combinations of multiple classifiers algorithms. Finally, we also suggest a methodology for determining the best mix of individual classifiers. [ABSTRACT FROM AUTHOR]

In this paper, we propose variable selection and estimation in generalized linear models using the seamless $L_0$ (SELO) penalized likelihood approach. The SELO penalty is a smooth function that very closely resembles the discontinuous $L_0$ penalty. We develop an efficient algorithm to fit the model, and show that the SELO-GLM procedure has the oracle property in the presence of a diverging number of variables. We propose a Bayesian information criterion (BIC) to select the tuning parameter. We show that under some regularity conditions, the proposed SELO-GLM/BIC procedure consistently selects the true model. We perform simulation studies to evaluate the finite sample performance of the proposed methods. Our simulation studies show that the proposed SELO-GLM procedure has a better finite sample performance than several existing methods, especially when the number of variables is large and the signals are weak. We apply the SELO-GLM to analyze a breast cancer genetic dataset to identify the SNPs that are associated with breast cancer risk. The Canadian Journal of Statistics 40: 745-769; 2012 © 2012 Statistical Society of Canada [ABSTRACT FROM AUTHOR]

In this paper, we show how the construction of a trans-dimensional equivalent of the Gibbs sampler can be used to obtain a powerful suite of adaptive algorithms suitable for trans-dimensional MCMC samplers. These algorithms adapt at the local scale, optimizing performance at each iteration in contrast to the globally adaptive scheme proposed by others for the fixeddimensional problem. Our adaptive scheme ensures suitably high acceptance rates for MCMC and RJMCMC proposals without the need for (often prohibitively) time-consuming pilot-tuning exercises. We illustrate our methods using the problem of Bayesian model discrimination for the important class of autoregressive time series models and, through the use of a variety of prior and proposal structures, demonstrate their ability to provide powerful and effective adaptive sampling schemes. [ABSTRACT FROM AUTHOR]

A nonparametric mixture model specifies that observations arise from a mixture distribution, ∫ f(x, θ) dG(θ), where the mixing distribution G is completely unspecified. A number of algorithms have been developed to obtain unconstrained maximum-likelihood estimates of G, but none of these algorithms lead to estimates when functional constraints are present. In many cases, there is a natural interest in functional ϕ( G), such as the mean and variance, of the mixing distribution, and profile likelihoods and confidence intervals for ϕ( G) are desired. In this paper we develop a penalized generalization of the ISDM algorithm of Kalbfleisch and Lesperance (1992) that can be used to solve the problem of constrained estimation. We also discuss its use in various different applications. Convergence results and numerical examples are given for the generalized ISDM algorithm, and asymptotic results are developed for the likelihood-ratio test statistics in the multinomial case. [ABSTRACT FROM AUTHOR]

ABSTRACT. Ibrahim (1990) used the EM-algorithm to obtain maximum likelihood estimates of the regression parameters in generalized linear models with partially missing covariates. The technique was termed EM by the method of weights. In this paper, we generalize this technique to Cox regression analysis with missing values in the covariates. We specify a full model letting the unobserved covariate values be random and then maximize the observed likelihood. The asymptotic covariance matrix is estimated by the inverse information matrix. The missing data are allowed to be missing at random but also the nonignorable non-response situation may in principle be considered. Simulation studies indicate that the proposed method is more efficient than the method suggested by Paik & Tsai (1997). We apply the procedure to a clinical trials example with six covariates with three of them having missing values. [ABSTRACT FROM AUTHOR]

Recent works in domain-independent plan merging have shown that the optimal plan-merging problem is NP-hard, and heuristic algorithms have been proposed to generate near-optimal solutions. These works have shown heuristic algorithms which assume that the mergeability of two actions can be determined by considering only the actions themselves. In this paper, we show that it is often that case that the surrounding actions in the plan must also be considered when determining the mergeability of two or more actions; therefore, the context in which the actions are used affects their mergeability. To address this problem, we have developed a plan-merging methodology that merges partial-order plans based on the the notion of plan fragments, which encapsulate actions with the context in which they are being utilized. This methodology applies to a class of planning domains, called decomposable domains, which consist of actions that follow all or some portion of a type sequence. Merging is performed hierarchically by action type. We also investigate the previously unexplored notion of alternative actions in domain-independent plan merging, which can improve the quality of the resulting merged plan. A novel approach is presented for removing cyclic dependencies that may occur during the plan-merging process. A key part of the methodology is the computation of a minimum cost cover of plan fragments. We provide theoretical analyses of two optimal algorithms and a greedy-based algorithm for computing the minimum cost cover. We support the theoretical analysis of these algorithms with experimental data to show that the greedy approach is near-optimal and efficient. [ABSTRACT FROM AUTHOR]