In article possible approaches to clustering of large city schools of the Russian Federation by results of their educational activity are studied. The extent to which a school has entered a particular cluster is determined by a number of objective conditions in which schools operate. Significant indicators of conditions affecting the EGE-results in schools were identified. It is shown that the studied indexes of the working conditions of schools are not sufficient for the correct clustering of schools according to the aggregated EGE-indicators.
Different methods of feature selection are used to improve the performance of remote sensing images classification. In this work two methods of feature selection are examined. The first one is based on the discriminant analysis, and the second one rests on building the regression model. Histogram and textural features are considered as characteristics of an image. The experiments on the remote sensing dataset UC Merced Land Use show the effectiveness of these methods. As the result, the largest fraction of correctly classified images accounts for the 95%. Dimension of the initial feature space consisting of 18 features has been reduced to 3 features.
The article gives an overview of the main approaches to verification of the internal rating methods of analysis of the creditworthiness. The article gives practical advice on the application of these techniques by an example of real internal rating technique.
In this work a problem is studied of classification of respondents into classes accepting and not participation in a charity actions. An optimal (in Bayes sense) decisive discriminant rule of division of objects on two classes is constructed for the case when all indicators of observable objects are measured in a nominal scale, and there are signs of dependence between them . Using ROC-analysis methods, comparison of the developed rule with a rule implemented in the software package SPSS (Fisher’s discriminant rule), «naive» Bayesian classifier, a rule based on support vector machines (SVM) method and implemented in SPSS package binary logistic regression classifier is made. Results of the ROC-analysis have shown that the proposed rule has higher quality than all other mentioned rules of classification of respondents.