A novel MAP-MRF approach for multispectral image contextual classification using combination of suboptimal iterative algorithms

In this paper we present a novel approach for multispectral image contextual classification by combining iterative combinatorial optimization algorithms. The pixel-wise decision rule is defined using a Bayesian approach to combine two MRF models: a Gaussian Markov Random Field (GMRF) for the observations (likelihood) and a Potts model for the a priori knowledge, to regularize the solution in the presence of noisy data. Hence, the classification problem is stated according to a Maximum a Posteriori (MAP) framework. In order to approximate the MAP solution we apply several combinatorial optimization methods using multiple simultaneous initializations, making the solution less sensitive to the initial conditions and reducing both computational cost and time in comparison to Simulated Annealing, often unfeasible in many real image processing applications. Markov Random Field model parameters are estimated by Maximum Pseudo-Likelihood (MPL) approach, avoiding manual adjustments in the choice of the regularization parameters. Asymptotic evaluations assess the accuracy of the proposed parameter estimation procedure. To test and evaluate the proposed classification method, we adopt metrics for quantitative performance assessment (Cohen`s Kappa coefficient), allowing a robust and accurate statistical analysis. The obtained results clearly show that combining sub-optimal contextual algorithms significantly improves the classification performance, indicating the effectiveness of the proposed methodology. (C) 2010 Elsevier B.V. All rights reserved.

A Markov random field model for combining optimum-path forest classifiers using decision graphs and game strategy approach

The research on multiple classifiers systems includes the creation of an ensemble of classifiers and the proper combination of the decisions. In order to combine the decisions given by classifiers, methods related to fixed rules and decision templates are often used. Therefore, the influence and relationship between classifier decisions are often not considered in the combination schemes. In this paper we propose a framework to combine classifiers using a decision graph under a random field model and a game strategy approach to obtain the final decision. The results of combining Optimum-Path Forest (OPF) classifiers using the proposed model are reported, obtaining good performance in experiments using simulated and real data sets. The results encourage the combination of OPF ensembles and the framework to design multiple classifier systems. © 2011 Springer-Verlag.

Sensitivity and specificity of machine learning classifiers for glaucoma diagnosis using Spectral Domain OCT and standard automated perimetry

PURPOSE: To evaluate the sensitivity and specificity of machine learning classifiers (MLCs) for glaucoma diagnosis using Spectral Domain OCT (SD-OCT) and standard automated perimetry (SAP). METHODS: Observational cross-sectional study. Sixty two glaucoma patients and 48 healthy individuals were included. All patients underwent a complete ophthalmologic examination, achromatic standard automated perimetry (SAP) and retinal nerve fiber layer (RNFL) imaging with SD-OCT (Cirrus HD-OCT; Carl Zeiss Meditec Inc., Dublin, California). Receiver operating characteristic (ROC) curves were obtained for all SD-OCT parameters and global indices of SAP. Subsequently, the following MLCs were tested using parameters from the SD-OCT and SAP: Bagging (BAG), Naive-Bayes (NB), Multilayer Perceptron (MLP), Radial Basis Function (RBF), Random Forest (RAN), Ensemble Selection (ENS), Classification Tree (CTREE), Ada Boost M1(ADA),Support Vector Machine Linear (SVML) and Support Vector Machine Gaussian (SVMG). Areas under the receiver operating characteristic curves (aROC) obtained for isolated SAP and OCT parameters were compared with MLCs using OCT+SAP data. RESULTS: Combining OCT and SAP data, MLCs' aROCs varied from 0.777(CTREE) to 0.946 (RAN).The best OCT+SAP aROC obtained with RAN (0.946) was significantly larger the best single OCT parameter (p<0.05), but was not significantly different from the aROC obtained with the best single SAP parameter (p=0.19). CONCLUSION: Machine learning classifiers trained on OCT and SAP data can successfully discriminate between healthy and glaucomatous eyes. The combination of OCT and SAP measurements improved the diagnostic accuracy compared with OCT data alone.

Robot visual localization through local feature fusion: an evaluation of multiple classifiers combination approaches

In the last decade, local image features have been widely used in robot visual localization. In order to assess image similarity, a strategy exploiting these features compares raw descriptors extracted from the current image with those in the models of places. This paper addresses the ensuing step in this process, where a combining function must be used to aggregate results and assign each place a score. Casting the problem in the multiple classifier systems framework, in this paper we compare several candidate combiners with respect to their performance in the visual localization task. For this evaluation, we selected the most popular methods in the class of non-trained combiners, namely the sum rule and product rule. A deeper insight into the potential of these combiners is provided through a discriminativity analysis involving the algebraic rules and two extensions of these methods: the threshold, as well as the weighted modifications. In addition, a voting method, previously used in robot visual localization, is assessed. Furthermore, we address the process of constructing a model of the environment by describing how the model granularity impacts upon performance. All combiners are tested on a visual localization task, carried out on a public dataset. It is experimentally demonstrated that the sum rule extensions globally achieve the best performance, confirming the general agreement on the robustness of this rule in other classification problems. The voting method, whilst competitive with the product rule in its standard form, is shown to be outperformed by its modified versions.

AWSum-Combining Classification with Knowledge Aquisition

Many classifiers achieve high levels of accuracy but have limited applicability in real world situations because they do not lead to a greater understanding or insight into the^way features influence the classification. In areas such as health informatics a classifier that clearly identifies the influences on classification can be used to direct research and formulate interventions. This research investigates the practical applications of Automated Weighted Sum, (AWSum), a classifier that provides accuracy comparable to other techniques whilst providing insight into the data. This is achieved by calculating a weight for each feature value that represents its influence on the class value. The merits of this approach in classification and insight are evaluated on a Cystic Fibrosis and Diabetes datasets with positive results.

Multi-sensor background subtraction by fusing multiple region-based probabilistic classifiers

In the recent years, the computer vision community has shown great interest on depth-based applications thanks to the performance and flexibility of the new generation of RGB-D imagery. In this paper, we present an efficient background subtraction algorithm based on the fusion of multiple region-based classifiers that processes depth and color data provided by RGB-D cameras. Foreground objects are detected by combining a region-based foreground prediction (based on depth data) with different background models (based on a Mixture of Gaussian algorithm) providing color and depth descriptions of the scene at pixel and region level. The information given by these modules is fused in a mixture of experts fashion to improve the foreground detection accuracy. The main contributions of the paper are the region-based models of both background and foreground, built from the depth and color data. The obtained results using different database sequences demonstrate that the proposed approach leads to a higher detection accuracy with respect to existing state-of-the-art techniques.

Combining Xanthan And Chitosan Membranes To Multipotent Mesenchymal Stromal Cells As Bioactive Dressings For Dermo-epidermal Wounds.

The association between tridimensional scaffolds to cells of interest has provided excellent perspectives for obtaining viable complex tissues in vitro, such as skin, resulting in impressive advances in the field of tissue engineering applied to regenerative therapies. The use of multipotent mesenchymal stromal cells in the treatment of dermo-epidermal wounds is particularly promising due to several relevant properties of these cells, such as high capacity of proliferation in culture, potential of differentiation in multiple skin cell types, important paracrine and immunomodulatory effects, among others. Membranes of chitosan complexed with xanthan may be potentially useful as scaffolds for multipotent mesenchymal stromal cells, given that they present suitable physico-chemical characteristics and have adequate tridimensional structure for the adhesion, growth, and maintenance of cell function. Therefore, the purpose of this work was to assess the applicability of bioactive dressings associating dense and porous chitosan-xanthan membranes to multipotent mesenchymal stromal cells for the treatment of skin wounds. The membranes showed to be non-mutagenic and allowed efficient adhesion and proliferation of the mesenchymal stromal cells in vitro. In vivo assays performed with mesenchymal stromal cells grown on the surface of the dense membranes showed acceleration of wound healing in Wistar rats, thus indicating that the use of this cell-scaffold association for tissue engineering purposes is feasible and attractive.

Classification of breast masses using a committee machine of artificial neural networks

This work proposes a new approach using a committee machine of artificial neural networks to classify masses found in mammograms as benign or malignant. Three shape factors, three edge-sharpness measures, and 14 texture measures are used for the classification of 20 regions of interest (ROIs) related to malignant tumors and 37 ROIs related to benign masses. A group of multilayer perceptrons (MLPs) is employed as a committee machine of neural network classifiers. The classification results are reached by combining the responses of the individual classifiers. Experiments involving changes in the learning algorithm of the committee machine are conducted. The classification accuracy is evaluated using the area A. under the receiver operating characteristics (ROC) curve. The A, result for the committee machine is compared with the A, results obtained using MLPs and single-layer perceptrons (SLPs), as well as a linear discriminant analysis (LDA) classifier Tests are carried out using the student's t-distribution. The committee machine classifier outperforms the MLP SLP, and LDA classifiers in the following cases: with the shape measure of spiculation index, the A, values of the four methods are, in order 0.93, 0.84, 0.75, and 0.76; and with the edge-sharpness measure of acutance, the values are 0.79, 0.70, 0.69, and 0.74. Although the features with which improvement is obtained with the committee machines are not the same as those that provided the maximal value of A(z) (A(z) = 0.99 with some shape features, with or without the committee machine), they correspond to features that are not critically dependent on the accuracy of the boundaries of the masses, which is an important result. (c) 2008 SPIE and IS&T.

Combining Legendre's Polynomials and Genetic Algorithm in the Solution of Nonlinear Initial-Value Problems

This work develops a method for solving ordinary differential equations, that is, initial-value problems, with solutions approximated by using Legendre's polynomials. An iterative procedure for the adjustment of the polynomial coefficients is developed, based on the genetic algorithm. This procedure is applied to several examples providing comparisons between its results and the best polynomial fitting when numerical solutions by the traditional Runge-Kutta or Adams methods are available. The resulting algorithm provides reliable solutions even if the numerical solutions are not available, that is, when the mass matrix is singular or the equation produces unstable running processes.

DECISION TREE CLASSIFIERS FOR STAR/GALAXY SEPARATION

We study the star/galaxy classification efficiency of 13 different decision tree algorithms applied to photometric objects in the Sloan Digital Sky Survey Data Release Seven (SDSS-DR7). Each algorithm is defined by a set of parameters which, when varied, produce different final classification trees. We extensively explore the parameter space of each algorithm, using the set of 884,126 SDSS objects with spectroscopic data as the training set. The efficiency of star-galaxy separation is measured using the completeness function. We find that the Functional Tree algorithm (FT) yields the best results as measured by the mean completeness in two magnitude intervals: 14 <= r <= 21 (85.2%) and r >= 19 (82.1%). We compare the performance of the tree generated with the optimal FT configuration to the classifications provided by the SDSS parametric classifier, 2DPHOT, and Ball et al. We find that our FT classifier is comparable to or better in completeness over the full magnitude range 15 <= r <= 21, with much lower contamination than all but the Ball et al. classifier. At the faintest magnitudes (r > 19), our classifier is the only one that maintains high completeness (> 80%) while simultaneously achieving low contamination (similar to 2.5%). We also examine the SDSS parametric classifier (psfMag - modelMag) to see if the dividing line between stars and galaxies can be adjusted to improve the classifier. We find that currently stars in close pairs are often misclassified as galaxies, and suggest a new cut to improve the classifier. Finally, we apply our FT classifier to separate stars from galaxies in the full set of 69,545,326 SDSS photometric objects in the magnitude range 14 <= r <= 21.

Combining Monte Carlo simulation and density-functional theory to describe the spectral changes of Na(2) in liquid helium

Spectral changes of Na(2) in liquid helium were studied using the sequential Monte Carlo-quantum mechanics method. Configurations composed by Na(2) surrounded by explicit helium atoms sampled from the Monte Carlo simulation were submitted to time-dependent density-functional theory calculations of the electronic absorption spectrum using different functionals. Attention is given to both line shift and line broadening. The Perdew, Burke, and Ernzerhof (PBE1PBE, also known as PBE0) functional, with the PBE1PBE/6-311++G(2d,2p) basis set, gives the spectral shift, compared to gas phase, of 500 cm(-1) for the allowed X (1)Sigma(+)(g) -> B (1)Pi(u) transition, in very good agreement with the experimental value (700 cm(-1)). For comparison, cluster calculations were also performed and the first X (1)Sigma(+)(g) -> A (1)Sigma(+)(u) transition was also considered.

Study of the optical and magnetic properties of pyrimidine in water combining PCM and QM/MM methodologies

The solvent effects on the low-lying absorption spectrum and on the (15)N chemical shielding of pyrimidine in water are calculated using the combined and sequential Monte Carlo simulation and quantum mechanical calculations. Special attention is devoted to the solute polarization. This is included by an iterative procedure previously developed where the solute is electrostatically equilibrated with the solvent. In addition, we verify the simple yet unexplored alternative of combining the polarizable continuum model (PCM) and the hybrid QM/MM method. We use PCM to obtain the average solute polarization and include this in the MM part of the sequential QM/MM methodology, PCM-MM/QM. These procedures are compared and further used in the discrete and the explicit solvent models. The use of the PCM polarization implemented in the MM part seems to generate a very good description of the average solute polarization leading to very good results for the n-pi* excitation energy and the (15)N nuclear chemical shield of pyrimidine in aqueous environment. The best results obtained here using the solute pyrimidine surrounded by 28 explicit water molecules embedded in the electrostatic field of the remaining 472 molecules give the statistically converged values for the low lying n-pi* absorption transition in water of 36 900 +/- 100 (PCM polarization) and 36 950 +/- 100 cm(-1) (iterative polarization), in excellent agreement among one another and with the experimental value observed with a band maximum at 36 900 cm(-1). For the nuclear shielding (15)N the corresponding gas-water chemical shift obtained using the solute pyrimidine surrounded by 9 explicit water molecules embedded in the electrostatic field of the remaining 491 molecules give the statistically converged values of 24.4 +/- 0.8 and 28.5 +/- 0.8 ppm, compared with the inferred experimental value of 19 +/- 2 ppm. Considering the simplicity of the PCM over the iterative polarization this is an important aspect and the computational savings point to the possibility of dealing with larger solute molecules. This PCM-MM/QM approach reconciles the simplicity of the PCM model with the reliability of the combined QM/MM approaches.

Combining Mager and Steinmetz: The Effect of Grain Size and Maximum Induction on Hysteresis Energy Loss

Twelve samples with different grain sizes were prepared by normal grain growth and by primary recrystallization, and the hysteresis dissipated energy was measured by a quasi-static method. Results showed a linear relation between hysteresis energy loss and the inverse of grain size, which is here called Mager`s law, for maximum inductions from 0.6 to 1.5 T, and a Steinmetz power law relation between hysteresis loss and maximum induction for all samples. The combined effect is better described by a Mager`s law where the coefficients follow Steinmetz law.

Combining GIS and Expert Opinion to Model Landscapes for a Smallholder Forest Extension Program in Leyte, the Philippines

A Geographic Information System (GIS) was used to model datasets of Leyte Island, the Philippines, to identify land which was suitable for a forest extension program on the island. The datasets were modelled to provide maps of the distance of land from cities and towns, land which was a suitable elevation and slope for smallholder forestry and land of various soil types. An expert group was used to assign numeric site suitabilities to the soil types and maps of site suitability were used to assist the selection of municipalities for the provision of extension assistance to smallholders. Modelling of the datasets was facilitated by recent developments of the ArcGIS® suite of computer programs and derivation of elevation and slope was assisted by the availability of digital elevation models (DEM) produced by the Shuttle Radar Topography (SRTM) mission. The usefulness of GIS software as a decision support tool for small-scale forestry extension programs is discussed.