Mean field methods for classification with Gaussian processes

We discuss the Application of TAP mean field methods known from Statistical Mechanics of disordered systems to Bayesian classification with Gaussian processes. In contrast to previous applications, no knowledge about the distribution of inputs is needed. Simulation results for the Sonar data set are given.

The application of methods of uncertain reasoning to the biological classification of river water quality

This thesis presents an investigation into the application of methods of uncertain reasoning to the biological classification of river water quality. Existing biological methods for reporting river water quality are critically evaluated, and the adoption of a discrete biological classification scheme advocated. Reasoning methods for managing uncertainty are explained, in which the Bayesian and Dempster-Shafer calculi are cited as primary numerical schemes. Elicitation of qualitative knowledge on benthic invertebrates is described. The specificity of benthic response to changes in water quality leads to the adoption of a sensor model of data interpretation, in which a reference set of taxa provide probabilistic support for the biological classes. The significance of sensor states, including that of absence, is shown. Novel techniques of directly eliciting the required uncertainty measures are presented. Bayesian and Dempster-Shafer calculi were used to combine the evidence provided by the sensors. The performance of these automatic classifiers was compared with the expert's own discrete classification of sampled sites. Variations of sensor data weighting, combination order and belief representation were examined for their effect on classification performance. The behaviour of the calculi under evidential conflict and alternative combination rules was investigated. Small variations in evidential weight and the inclusion of evidence from sensors absent from a sample improved classification performance of Bayesian belief and support for singleton hypotheses. For simple support, inclusion of absent evidence decreased classification rate. The performance of Dempster-Shafer classification using consonant belief functions was comparable to Bayesian and singleton belief. Recommendations are made for further work in biological classification using uncertain reasoning methods, including the combination of multiple-expert opinion, the use of Bayesian networks, and the integration of classification software within a decision support system for water quality assessment.

Interactions between landcover pattern and geospatial processing methods:effects on landscape metrics and classification accuracy

Remote sensing data is routinely used in ecology to investigate the relationship between landscape pattern as characterised by land use and land cover maps, and ecological processes. Multiple factors related to the representation of geographic phenomenon have been shown to affect characterisation of landscape pattern resulting in spatial uncertainty. This study investigated the effect of the interaction between landscape spatial pattern and geospatial processing methods statistically; unlike most papers which consider the effect of each factor in isolation only. This is important since data used to calculate landscape metrics typically undergo a series of data abstraction processing tasks and are rarely performed in isolation. The geospatial processing methods tested were the aggregation method and the choice of pixel size used to aggregate data. These were compared to two components of landscape pattern, spatial heterogeneity and the proportion of landcover class area. The interactions and their effect on the final landcover map were described using landscape metrics to measure landscape pattern and classification accuracy (response variables). All landscape metrics and classification accuracy were shown to be affected by both landscape pattern and by processing methods. Large variability in the response of those variables and interactions between the explanatory variables were observed. However, even though interactions occurred, this only affected the magnitude of the difference in landscape metric values. Thus, provided that the same processing methods are used, landscapes should retain their ranking when their landscape metrics are compared. For example, highly fragmented landscapes will always have larger values for the landscape metric "number of patches" than less fragmented landscapes. But the magnitude of difference between the landscapes may change and therefore absolute values of landscape metrics may need to be interpreted with caution. The explanatory variables which had the largest effects were spatial heterogeneity and pixel size. These explanatory variables tended to result in large main effects and large interactions. The high variability in the response variables and the interaction of the explanatory variables indicate it would be difficult to make generalisations about the impact of processing on landscape pattern as only two processing methods were tested and it is likely that untested processing methods will potentially result in even greater spatial uncertainty. © 2013 Elsevier B.V.

The classification of HLA supertypes by GRID/CPCA and hierarchical clustering methods

Biological experiments often produce enormous amount of data, which are usually analyzed by data clustering. Cluster analysis refers to statistical methods that are used to assign data with similar properties into several smaller, more meaningful groups. Two commonly used clustering techniques are introduced in the following section: principal component analysis (PCA) and hierarchical clustering. PCA calculates the variance between variables and groups them into a few uncorrelated groups or principal components (PCs) that are orthogonal to each other. Hierarchical clustering is carried out by separating data into many clusters and merging similar clusters together. Here, we use an example of human leukocyte antigen (HLA) supertype classification to demonstrate the usage of the two methods. Two programs, Generating Optimal Linear Partial Least Square Estimations (GOLPE) and Sybyl, are used for PCA and hierarchical clustering, respectively. However, the reader should bear in mind that the methods have been incorporated into other software as well, such as SIMCA, statistiXL, and R.

A közszolgálati szervezetek értékelési módszereinek osztályozása (Classification of evaluation methods of public sector organizations)

Az utóbbi évtizedekben egyre gyakrabban merült fel a közszolgálati szervezetek értékelésének igénye, és egyre újabb módszerek jelentek meg, amelyek felvetették ezek rendszerezésének szükségességét mind a gyakorlatban, mind a kutatásokban. A szerző a szakirodalomban fellelhető osztályozási kísérleteknek és az értékelés szakterülete szempontjainak figyelembevételével javaslatot tesz a közszolgálati szervezetek értékelési módszereinek osztályozási keretrendszerére. Az osztályozási szempontok között szerepel az értékelő helyzete, az értékelés szerepe és a megismerés módszere. Az osztályozási keretrendszer tartalmát a szerző példákkal is illusztrálja, amely jelzi a modell gyakorlati alkalmazhatóságát. Ugyanakkor a keretrendszer a kutatások fókuszának és érvényességi körének meghatározásában is segítséget nyújthat. _____ In the last decades the need of the evaluation of public sector organizations has emerged more and more often, and many new methods have shown up that has raised the need of their classification in practice and in research, as well. Based on literature review and the literature of evaluation the author makes a proposal on the classification framework of the evaluation methods of public sector organizations. The dimensions of the classification include the situation of evaluator, the role of evaluation and the approach of knowledge. The author illustrates the content of the framework with examples referring to the applicability of the model in practice. At the same time, the framework is also useful in determining the focus or the scope of research projects.

Statistical methods for polyhedral shape classification with incomplete data - application to cryo-electron tomographic images

A certain type of bacterial inclusion, known as a bacterial microcompartment, was recently identified and imaged through cryo-electron tomography. A reconstructed 3D object from single-axis limited angle tilt-series cryo-electron tomography contains missing regions and this problem is known as the missing wedge problem. Due to missing regions on the reconstructed images, analyzing their 3D structures is a challenging problem. The existing methods overcome this problem by aligning and averaging several similar shaped objects. These schemes work well if the objects are symmetric and several objects with almost similar shapes and sizes are available. Since the bacterial inclusions studied here are not symmetric, are deformed, and show a wide range of shapes and sizes, the existing approaches are not appropriate. This research develops new statistical methods for analyzing geometric properties, such as volume, symmetry, aspect ratio, polyhedral structures etc., of these bacterial inclusions in presence of missing data. These methods work with deformed and non-symmetric varied shaped objects and do not necessitate multiple objects for handling the missing wedge problem. The developed methods and contributions include: (a) an improved method for manual image segmentation, (b) a new approach to 'complete' the segmented and reconstructed incomplete 3D images, (c) a polyhedral structural distance model to predict the polyhedral shapes of these microstructures, (d) a new shape descriptor for polyhedral shapes, named as polyhedron profile statistic, and (e) the Bayes classifier, linear discriminant analysis and support vector machine based classifiers for supervised incomplete polyhedral shape classification. Finally, the predicted 3D shapes for these bacterial microstructures belong to the Johnson solids family, and these shapes along with their other geometric properties are important for better understanding of their chemical and biological characteristics.

Advancing Bag-of-visual-words Representations For Lesion Classification In Retinal Images.

Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 ± 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors.

Neural networks and statistical analysis for classification of corneal videokeratography maps based on Zernike coefficients: a quantitative comparison

PURPOSE: The main goal of this study was to develop and compare two different techniques for classification of specific types of corneal shapes when Zernike coefficients are used as inputs. A feed-forward artificial Neural Network (NN) and discriminant analysis (DA) techniques were used. METHODS: The inputs both for the NN and DA were the first 15 standard Zernike coefficients for 80 previously classified corneal elevation data files from an Eyesys System 2000 Videokeratograph (VK), installed at the Departamento de Oftalmologia of the Escola Paulista de Medicina, São Paulo. The NN had 5 output neurons which were associated with 5 typical corneal shapes: keratoconus, with-the-rule astigmatism, against-the-rule astigmatism, "regular" or "normal" shape and post-PRK. RESULTS: The NN and DA responses were statistically analyzed in terms of precision ([true positive+true negative]/total number of cases). Mean overall results for all cases for the NN and DA techniques were, respectively, 94% and 84.8%. CONCLUSION: Although we used a relatively small database, results obtained in the present study indicate that Zernike polynomials as descriptors of corneal shape may be a reliable parameter as input data for diagnostic automation of VK maps, using either NN or DA.

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.

Automated supervised classification of variable stars in the CoRoT programme Method and application to the first four exoplanet fields

Aims. In this work, we describe the pipeline for the fast supervised classification of light curves observed by the CoRoT exoplanet CCDs. We present the classification results obtained for the first four measured fields, which represent a one-year in-orbit operation. Methods. The basis of the adopted supervised classification methodology has been described in detail in a previous paper, as is its application to the OGLE database. Here, we present the modifications of the algorithms and of the training set to optimize the performance when applied to the CoRoT data. Results. Classification results are presented for the observed fields IRa01, SRc01, LRc01, and LRa01 of the CoRoT mission. Statistics on the number of variables and the number of objects per class are given and typical light curves of high-probability candidates are shown. We also report on new stellar variability types discovered in the CoRoT data. The full classification results are publicly available.

A Brazilian registry of juvenile dermatomyositis: onset features and classification of 189 cases

Objective To describe onset features, classification and treatment of juvenile dermatomyositis (JDM) and juvenile polymyositis (JPM) from a multicentre registry. Methods Inclusion criteria were onset age lower than 18 years and a diagnosis of any idiopathic inflammatory myopathy (IIM) by attending physician. Bohan & Peter (1975) criteria categorisation was established by a scoring algorithm to define JDM and JPM based oil clinical protocol data. Results Of the 189 cases included, 178 were classified as JDM, 9 as JPM (19.8: 1) and 2 did not fit the criteria; 6.9% had features of chronic arthritis and connective tissue disease overlap. Diagnosis classification agreement occurred in 66.1%. Medial? onset age was 7 years, median follow-up duration was 3.6 years. Malignancy was described in 2 (1.1%) cases. Muscle weakness occurred in 95.8%; heliotrope rash 83.5%; Gottron plaques 83.1%; 92% had at least one abnormal muscle enzyme result. Muscle biopsy performed in 74.6% was abnormal in 91.5% and electromyogram performed in 39.2% resulted abnormal in 93.2%. Logistic regression analysis was done in 66 cases with all parameters assessed and only aldolase resulted significant, as independent variable for definite JDM (OR=5.4, 95%CI 1.2-24.4, p=0.03). Regarding treatment, 97.9% received steroids; 72% had in addition at least one: methotrexate (75.7%), hydroxychloroquine (64.7%), cyclosporine A (20.6%), IV immunoglobulin (20.6%), azathioprine (10.3%) or cyclophosphamide (9.6%). In this series 24.3% developed calcinosis and mortality rate was 4.2%. Conclusion Evaluation of predefined criteria set for a valid diagnosis indicated aldolase as the most important parameter associated with de, methotrexate combination, was the most indicated treatment.

Intrinsic Dissolution as a Tool for Evaluating Drug Solubility in Accordance with the Biopharmaceutics Classification System

The Biopharmaceutics Classification System (BCS) is a tool that was created to categorize drugs into different groups according to their solubility and permeability characteristics. Through a combination of these factors and physiological parameters, it is possible to understand the absorption behavior of a drug in the gastrointestinal tract, thus contributing to cost and time reductions in drug development, as well as reducing exposure of human subjects during in vivo trials. Solubility is attained by determining the equilibrium under conditions of physiological pH, while different methods may be employed for evaluating permeability. On the other hand, the intrinsic dissolution rate (IDR), which is defined as the rate of dissolution of a pure substance under constant temperature, pH, and surface area conditions, among others, may present greater correlation to the in vivo dissolution dynamic than the solubility test. The purpose of this work is to discuss the intrinsic dissolution test as a tool for determining the solubility of drugs within the scope of the Biopharmaceutics Classification System (BCS).