A new text categorization problem is introduced. As in the classical problem, there is a set of documents and a set of categories. However, in addition to being assigned to a specific category, each document belongs to a certain sequence of documents, referred to as a case. It is assumed that all documents in the same case belong to the same category. An example may be a set of news articles. Their categories may be sport, politics, entertainment, etc. In each category there exist cases, i.e., sequences of documents describing, for example evolution of some events. The problem considered is how to classify a document to a proper category and a proper case within this category. In the paper we formalize the problem and discuss two approaches to its solution.

The study is concerned with the nonparametric kernel estimation to determine the soil porosity and pore size distribution. The kernel density estimation, the kernel estimation of cumulative distribution function, and the kernel estimator of quantile are considered. After a short description of the method, practical aspects and applications in agricultural science are presented. The nonparametric kernel estimation does not require a priori assumptions relating to the choice of the density function shape. Moreover, its natural interpretation together with its suitable properties makes them an adequate tool among others in estimation methods.

The paper gives an overview of various bacterial type evolutionary algorithms used for fuzzy rule based identification. In order to find an optimal rule base from the input-output training data set, several improved algorithms have been developed in recent years. The task is to increase the models’ accuracy and convergence speeds by modifying a part of the Mamdani-type inference system.

The paper summarizes models and methods of data center resource management for VPS hosting. The approach for the allocation of computing resources in the form of particles of a predetermined size (virtual nodes) was proposed. Different cases of this problem for both an excess and a lack of computing resources were considered. These problems belong to the classes of linear and nonlinear Boolean programming. To solve the mentioned problems, heuristic and guided genetic algorithms have been proposed. A comparison of their effectiveness was carried out.

The classical inexact Newton method was presented as a tool for solving nonlinear differential algebraic equations (DAEs) in a fully implicit form F(y, y, t) = 0. This is especially in chemical engineering where describing the DAE system in a different form can be difficult or even impossible to realize. The appropriate rewriting of the DAEs using the backward Euler method makes it possible to present the differentialalgebraic system as a large-scale system of nonlinear equations. To solve the obtained system of nonlinear equations, the inexact Newton backtracking method was proposed. Because the convergence of the inexact Newton algorithm is strongly affected by the choice of the forcing terms, new variants of the inexact Newton method were presented and tested on the catalyst mixing problem.

Intelligent robot path planning require have very complex decision-making and computational processes. Collecting and calculating a high amount of data is one of the weakest points of a such system. In addition, it is necessarily processed in real-time on a limited computational capacity. In this paper, we propose some novel algorithms for coping with these problems and give some information about Fuzzy Situational Maps and their use as a multidimensional extension of Fuzzy Signatures. An example takes to the field of path planning map pre-optimization by Fuzzy Situational Map.

The clustering problem is one of the main problems which can be encountered in a data analysis. This problem can be modelled by means of a graph; finding clusters means finding cliques in the graph. Often there is a need to find clusters (cliques) in a graph in different ways and to construct a list of clusters. This paper describes two such ways, these can be stated as the cluster minimum covering problem and the vertex cluster minimum partitioning problem. This paper describes new ant algorithms which were used in order to make a list of clusters in both presented problems, and also discusses the results of their comparison.

The paper presents the modified model for video upscaling based on the preservation of structural information from the input sequence in the adaptive trained filters. Additionally, it is proposed to make soft truncation of the result pixel value during the interpolation process. The evaluation of the proposed algorithm has shown good resulting for a variety of test sequences. The best results are obtained for a sequence with average bitrate and movement of the scene. Received results prove the algorithm is valuable for upscaling tasks.

This paper summarizes the basic concept of the designed a fuzzy-based character recognition algorithm family and the results of the optimization of its rule-base with two various meta-heuristic methods, the Imperialist Competitive Algorithm and the bacterial evolutionary algorithm. The results are presented and compared with two other methods from literature after a short overview of the recognition algorithm.

Bipolar linguistic summaries of data are assumed to be an extension of the ‘classical’ linguistic summarization, a data mining technique revealing complex patterns present in data in a human consistent form. The extension proposal is based on the possibilistic interpretation of the ‘and possibly’ operator and introduced notion of context, which results in the introduction of the new ‘contextual and possibly’ operator. As the end user is expecting the most relevant summaries, ways of determining the quality of summary propositions (quality measures) needs to be developed. Here we focus on specific insights into the quality measures of proposed bipolar linguistic summaries of data and present some basic examples of their correctness and necessity of introduction.