- Financial Risk and Volatility Modeling
- Statistical Methods and Inference
- Image Retrieval and Classification Techniques
- Image and Signal Denoising Methods
- Bayesian Methods and Mixture Models
- Medical Image Segmentation Techniques
- Advanced Statistical Methods and Models
- Probability and Risk Models
- Stochastic processes and financial applications
- Neural Networks and Applications
- Statistical Distribution Estimation and Applications
- Advanced Image and Video Retrieval Techniques
- Remote-Sensing Image Classification
- Complex Systems and Time Series Analysis
- Advanced Statistical Process Monitoring
- Hydrology and Drought Analysis
- Control Systems and Identification
- Supply Chain and Inventory Management
- Blind Source Separation Techniques
- Noise Effects and Management
- Opinion Dynamics and Social Influence
- Advanced Data Compression Techniques
- Video Analysis and Summarization
- Image Enhancement Techniques
- Statistical and numerical algorithms
Washington State University
2013-2024
University of Florida
2021
University of Patras
2003-2014
Decision Sciences (United States)
1999-2006
University of North Carolina at Chapel Hill
1993
Birkbeck, University of London
1983
University of Liverpool
1981
Incipient motion criteria based solely on time-averaged bed shear stress may underpredict sediment transport. The focus of this study is the stochastic aspect problem incipient motion. Specifically, role near-bed turbulent structures and packing density commencement investigated. cornerstone proposed model concept that particle governed by intermittent nature turbulence. Based mechanism, in article we provide a quantitative for predicting entrainment first time under three representative...
The article reviews methods of inference for single and multiple change‐points in time series, when data are retrospective (off‐line) type. inferential reviewed a change‐point series include likelihood, Bayes, Bayes‐type some relevant non‐parametric methods. Inference requires that can handle large sets be implemented efficiently estimating the number as well their locations. Our review this important area focuses on recent advances direction. Greater emphasis is placed multivariate while...
Manufacturing systems have become increasingly complex over recent years. This volume presents a collection of chapters which reflect the development probabilistic models and methodologies that either been motivated by manufacturing research or demonstrated to significant potential in such research. The editor has invited number leading experts present detailed expositions specific topics. These include: Jackson networks, fluid models, diffusion strong approximations, GSMP framework,...
This paper proposes a methodology that incorporates principles from cluster analysis and graph representation to achieve efficient image segmentation results. More specifically, feature-based, inter-region dissimilarity relation is considered here in order determine the matrix graph-based scheme. The calculation of function between adjacent elementary regions based on proximity each region's feature vector main clusters are formed by samples space. In contrast typical approaches literature,...
Synopsis: Classical Optimisation Techniques, and Inequalities, Numerical Methods of Optimisation, Linear Programming Non-linear Dynamic Methods, Variational Stochastic Approximation Procedures, in Simulation, Function Spaces Techniques: Preliminaries, Necessary Sufficient Conditions for an Extremum, Constrained - Lagrange Multipliers, Statistical Applications Inequalities: Matrix Optimisation: Evaluation Roots Equations, Direct Search Gradient Convergence Regression Other Algorithms Problem,...
A multiresolution color image segmentation approach is presented that incorporates the main principles of region-based and cluster-analysis approaches. The contribution This work may be divided into two parts. In first part, a multiscale dissimilarity measure proposed makes use feature transformation operation to interregion relations with respect their proximity clusters image. As part this process, an original also generate representation information using nonparametric clustering. second...
Twenty years have elapsed since the Shapiro-Wilk statistic $W$ for testing normality of a sample first appeared. In that time number statistics are close relatives been found to common (known) asymptotic distribution. It was assumed, therefore, must We show this be case and examine norming constants used with all statistics. addition consistency test is established.
In this study, a conceptually simple, yet flexible and extendable strategy to contrast two different color images is introduced. The proposed approach based on the multivariate Wald-Wolfowitz test, nonparametric test that assesses commonality between sets of observations. It provides an aggregate gauge match images, taking into consideration all (selected) low-level characteristics, while alleviating correspondence issues. We show powerful measure similarity can emerge from statistical...
We derive exact computable expressions for the asymptotic distribution of change-point mle when a change in mean occurred at an unknown point sequence time-ordered independent Gaussian random variables. The derivation, which assumes that nuisance parameters such as amount and variance are known, is based on ladder heights walks hitting half-line. then show easily extends to occurs vector multivariate process. perform simulations examine accuracy derived have be estimated well robustness...
In this article we describe a signal-processing framework for mining information from event-related recordings. Pattern-analytic tools are combined with graph-theoretic techniques and signal understanding methodologies in user-friendly environment the scope of learning, parameterization, representation ST data manifold. Through first part, provide general outline our methodological approach while trying to demonstrate all different stages, where DM can be applied. second more detailed...