Abstract: The automatic processing of unstructured texts in natural languages is one of the relevant problems of computer analysis and text synthesis. Within this problem, the author singles out a task of text normalization, which usually suggests such processes as tokenization, stemming, and lemmatization. The existing stemming algorithms for the most part are oriented towards the synthetic languages with inflectional morphemes. The Uzbek language represents an example of agglutinative language, characterized by polysemanticity of affixal and auxiliary morphemes. Although the Uzbek language largely differs from, for example, English language, it is successfully processed by stemming algorithms. There are virtually no examples of effective implementation of stemming algorithms for the Uzbek language; therefore, this questions is the subject of scientific interest and defines the goal of this work. In the course of this research, the author solved the task of bringing the given texts in the Uzbek language to normal form, which on the preliminary stage were tokenized and cleared of stop words. To author developed the method of normalization of texts in the Uzbek language based on the stemming algorithm. The development of stemming algorithm employed hybrid approach with application of algorithmic method, lexicon of linguistic rules and database of the normal word forms of the Uzbek language. The precision of the proposed algorithm depends on the precision of tokenization algorithm. At the same time, the article did not explore the question of finding the roots of paired words separated by spaces, as this task is solved at the stage of tokenization. The algorithm can be integrated into various automated systems for machine translation, information extraction, data retrieval, etc.

Keywords: affix, repeating words, paired words, difficult words, simple words, lemmatization, stemming, tokenization, algorithm, normal form

Abstract: This article explores certain aspects of the process of numerical solution of the tasks of continuous medium mechanics in the conditions of ongoing chemical reactions. Such tasks are usually characterized by the presence of multiple local areas with elevated temperature, which position in space is relatively unstable. In such conditions, rigidly stable methods of integration with step control, which in the “elevated temperature” areas that have higher time input comparing to other areas. In terms of using geometric parallelism, this fact leads to substantial imbalance of CPU load, which reduces the overall effectiveness of parallelization. Therefore, this article examines the problem of CPU load balancing in the context of parallel solution of the aforementioned tasks. The other offers a new modification of the algorithm of large-block distributed balancing with improved time prediction of the numerical integration of chemical kinetics equations, which is most effective in the conditions of drift of the areas with “elevated temperatures”. The improvement consists in application of the linear perceptron, which analyzes several previous values of time integration (the basic version of the algorithm uses only one previous spot from the history of time integration). This allows working in the conditions of fast and slow drift of the areas with “elevated temperatures”. The effectiveness of this approach is demonstrated on the task of modeling the flow-around the building with high-temperature combustion on its roof. It is indicated that the application of modified algorithm increases the effectiveness of parallelization by 2.1% compared to the initial algorithm.

Keywords: numerical simulation, distributed balancing, continuous medium mechanics, chemical kinetics, linear perceptron, load balancing, parallel computations, numerical experiment, approbation, geometrical parallelizing

Abstract: The subject of this research is medical chest X-ray images. After fundamental pre-processing, the accumulated database of such images can be used for training deep convolutional neural networks that have become one of the most significant innovations in recent years. The trained network carries out preliminary binary classification of the incoming images and serve as an assistant to the radiotherapist. For this purpose, it is necessary to train the neural network to carefully minimize type I and type II errors. Possible approach towards improving the effectiveness of application of neural networks, by the criteria of reducing computational complexity and quality of image classification, is the auxiliary approaches: image pre-processing and preliminary calculation of entropy of the fragments. The article provides the algorithm for X-ray image pre-processing, its fragmentation, and calculation of the entropy of separate fragments. In the course of pre-processing, the region of lungs and spine is selected, which comprises approximately 30-40% of the entire image. Then the image is divided into the matrix of fragments, calculating the entropy of separate fragments in accordance with Shannon’s formula based pm the analysis of individual pixels. Determination of the rate of occurrence of each of the 255 colors allows calculating the total entropy. The use of entropy for detecting pathologies is based on the assumption that its values differ for separate fragments and overall picture of its distribution between the images with the norm and pathologies. The article analyzes the statistical values: standard deviation of error, dispersion. A fully connected neural network is used for determining the patterns in distribution of entropy and its statistical characteristics on various fragments of the chest X-ray image.

Keywords: matrix of elements, computational experiment, x-rays images, machine learning, deep convolutional neural network, fragments, image entropy, image preprocessing, statistical analysis, binary classification

Abstract: The subject of this article is the numerical optimization techniques used in training neural networks that serve as predicate components in certain modern eddy viscosity models. Qualitative solution to the problem of training (minimization of the functional of neural network offsets) often requires significant computational costs, which necessitates to increase the speed of such training based on combination of numerical methods and parallelization of calculations. The Marquardt method draws particular interest, as it contains  the parameter that allows speeding up the solution by switching the method from the descent away from the solution to the Newton’s method of approximate solution. The article offers modification of the Marquardt method, which uses the limited series of random samples for improving the current point and calculate the parameter of the method. The author demonstrate descent characteristics of the method in numerical experiments, both on the test functions of Himmelblau and Rosenbrock, as well as the actual task of training the neural network predictor applies in modeling of the turbulent flows. The use of this method may significantly speed up the training of neural network predictor in corrective models of eddy viscosity. The method is less time-consuming in comparison with random search, namely in terms of a small amount of compute kernels; however, it provides solution that is close to the result of random search and is better than the original Marquardt method.

Keywords: approbation, optimization methods, numerical experiment, model of turbulent viscosity, Marquardt method, learning, deep neural network, random probes, parameter tuning, neural network predictor

Abstract: This article explores the walking robots that are used or assist in nondeterministic environment, such as rescue operations. This required carrying out in-depth analysis of the existing models to acquire relevant information on the robots with walking mechanisms in accordance with several criteria: parameters, weight, degrees of freedom, speed of movement, input energy, runtime, maximum load, advantages and disadvantages of the reviewed models. Using the methods of comparative and critical analysis, the author analyzed the available materials for the past 5 years, which allowed accomplishing the set tasks. The results consist in compiling a summary table for largely generalized groups of walking robots and three tables for the models under review, which summarize their advantages and weaknesses. Such data would broaden the knowledge of the researchers dealing with the walking robots, analyze both national and foreign studies on the topic, apply this experience in further work, focus on solution of the problems, and emphasize the uniqueness and relevance of their developments. This article determines the peculiarities of utilization of walking robots specifically in rescue operations; however, the scope of their applicability can be broader. The author also describes the nontraditional locomotors of walking robots, which are widely known in media, video hosting, and other tools of receiving information.

Keywords: anthropomorphic vehicles, dignity, advantages, limitations, problems, rescue operation, walking robot, robot, quadruped robot, hexapod