ABSTRACT. Breast cancer is the most common in the world and its rates could be increased from 2 million in 2018 to 3 million in 2040, and the death rate from 600 thousand to nearly 1 million per year. Histopathological analysis is used for diagnosis of almost all cancer types. Nowadays histopathological tissue analysis and evaluat-ing the microscopic appearance of a biopsied tissue sample are provided by a pathologist. The paper is devoted to the problem of histopathological analysis au-tomatization using a region-based convolutional neural network (R-CNN). The purpose of the research is to automatizate the tumor nuclei detection in the histo-pathological images, because detection can be used as qualitative and quantitative analysis. In the research breast cancer histopathological annotation and diagnosis dataset is used (BreCaHAD). The classification accuracy for SVM classifier, which uses features, extracted by CNN, is 0.96. The object detection heatmap was built. It is obtained that the average precision for tumor nuclei detection is 0.338. The theory of deep learning neural networks and mathematical statistics methods are used in the research.

ABSTRACT. This paper focuses on the need to evaluate the sustainability of Analytic hierarchy process at the Ranking of more than 10 alternatives. The proposed method is based on simulation modeling of the process of improving expert pair-wise comparison judgments. The represented method provides a stepwise improvement of the pair-wise comparison matrix transitivity. The average discrepancy and coincidence of ranks in multiple modeling are proposed as es-timates of the rating stability. The application of the developed method was studied on a statistical sample formed according to the final tables of the Eng-land, Germany and Spain football championships. The method for determining probability of some alternatives ranks is developed. It is possible to modify the method for predicting the results of sports competitions and for the case of ranking with partially missing expert ratings

ABSTRACT. Informational Management Systems (IMS) which are based on legacy systems have a significant problem of dirty data. The data cleansing problem solution in such systems usually starts with the search of similar tuples' clusters. After that for each cluster the reference tuple should be formed for saving in a data warehouse of IMS. Moreover, fail tuples should be returned to the source subsystem with the indication of error location, i. e. concrete invalid requisite. The necessary of such a deep diagnosis determined by the following fact: the reference tuple can be not just one of the existent, but as well the combination of several different tuples requisites. Considering one obtained cluster of similar tuples, a certain multiset can be composed from all of the certain attribute values. The paper represents the method of the multiset's diagnostic in terms of faultless and correctionability, based on the majority principle. The method provides the minimum time required for establishing the fact of multiset's incorrectness, moreover it allow defining valid (reference) and failed elements of the multiset.

ABSTRACT. Running software in a distributed manner is a common practice nowadays. This approach produces a lot of new challenges which should be thought in advance. This paper is the next step on understanding systems such as distributed datastores by using statistical estimation for violation of guarantees from Brewer's Conjecture. The paper focuses on finding ways for simplification of theoretical and practical modelling of a system of a distributed datastore. Considering that real-world distributed datastore consists of nodes with a different distribution of fail and recovery time it is proposed to substitute every node of distributed datastore with nodes with one common distribution of fail and one common distribution of recovery time. The verification of the approach is done by modelling systems and statistically comparing their violation of guarantees from Brewer's Conjecture. The results allow us to define cases where we can substitute one system with another without losing perception of its behaviour

ABSTRACT. Business process management has become the most widely-used and reliable approach to organizational management over the last decades. It is also considered as a part of quality management system in an organization. Business process modeling is the core of business process management, which is used for visualization, analysis, and improvement of organizational activities. Moreover, business process modeling plays an important role in the context of business process management maturity of an overall enterprise. Therefore, this paper is focused on the problem of business process model quality evaluation. Existing approaches based on the process modeling guidelines, metrics and corresponding thresholds are reviewed, as well as the refined process modeling rules, cor-responding quality criteria, the generalized quality criterion, and thresholds for its translation into linguistic values are proposed. The data model and software prototype are developed and the validation results are outlined.

ABSTRACT. This research is aimed to analyze the state of science digitization in Ukraine and also identifies the main problems and priority directions for the further development of science digitization as a major factor in the information society development and digital economy in our country. The authors propose definitions of digitization in general and digitization of science in particular. It is noted that the problems of digitization in Ukraine are directly related to the general problems of national science, which in its turn are caused by the difficult and unstable economic and social situation in the country. One of the main problems hampering the digitization process is the gradual reduction in the cost of science funding over the last years, which is illustrated by official statistics, leading to a reduction in overall scientific activity. The authors have developed a list of recommendations for overcoming existing problems and further development of the digitization of science in Ukraine.

ABSTRACT. The article considers the possibility of students to build their individual educational trajectories, the importance of independently determining the path of their self-development. The relevance of this topic is determined by the implementation of the student-centered learning paradigm. Building an individual educational trajectory is reduced to the tasks of analyzing student motivation and identifying the disciplines that will make up the variant part of a student's individual curriculum. Content analysis of students' motivation letters is used to analyze motivations. Information about a student's priority area of knowledge and directions of his activity is the result of content analysis. Academic disciplines are determined on the basis of latent-semantic analysis (LSA). The results of content analysis of motivation letters, student surveys on professional orientation, the results of tests students' knowledge come at the entrance of LSA. The list of knowledge areas for the profession indicated by the student is the result of applying LSA. The subject domain ontology is constructed for representation the knowledge model. The authors use Latent Dirichle allocation to determine the keywords of topics selected by the student subject areas. The identified keywords are the criteria for choosing the discipline that will make up the individual student's curriculum. Testing of the proposed information technology has shown its reliability.

ABSTRACT. Collecting the scientific publications to write the Related Work section, keeping up-to-date expertise in the topic of interest, or studying new scientific direction requires the search activity that has low specificity of the information need. Such a kind of need does not allow certainty about its fulfillment and about the completeness of search results.

The controlled snowball method suggested by authors in the previous papers was extended with the objective criterion of the result completeness that allows stopping the search as soon as the criterion is met avoiding unnecessary time consumption.

The criterion is based on the assumption that the ideal ordered document set contains all terms describing the topic of interest. As a result, the completeness of the terms comes out as terminological saturation that is stability the terms with respect to extending the document set with new documents.

In the experiments, we study four ordered sets of pubications describing the topic "Ontologies (computer science)". The sets were collected with controlled snowball method using "Microsoft Academic" search API, with topic search in "Microsoft Academic" database, with a keyword search in Google Scholar database, and with browsing ACM digital library using author keywords.

For each of the sets, the automatic term extraction was performed, the existence of terminological saturation is tested, and, if the saturation detected, the minimal size of the saturated publication set was noticed. It was shown that terminological saturation is observed for the sets collected with controlled snowball method and with topic search in "Microsoft Academic" database. Moreover, the proposed controlled snowball provides the 10% smaller document set.

ABSTRACT. We develop the method for fast building the text-based online “adventure” games for medical education. The starting point is the set of proven algorithms for diagnostic and treatment. The algorithms may build accordingly to the principles of evidence-based medicine. We check the accuracy of the algorithms, make the diagrams according by ISO standard, formulate test questions for all for all steps of algorithms and prepare distractors for the questions. We discuss the possibilities of switching to graphical screens in the future iterations.

ABSTRACT. In this paper, machine learning technology for neoplasm segmentation on brain MRI scans is analyzed. This analysis allows to choose the most appropriate machine learning architecture and various preprocessing techniques to increase the precision of tumor instance segmentation. Understanding the image and extracting information from it to accomplish some result is an important area of application in digital image technology. Image segmentation has quickly found its use in medicine, and specifically oncology. Precise segmentation masks may not be critical in other cases, but marginal segmen-tation errors in medical images caused the results to be unreliable in clinical settings. Therefore, biomedical problems require a much higher boundary detection precision to improve further analysis. Comparison of different machine learning algorithms, neural network architectures will achieve the highest accuracy of recognition and segmentation. Python was chosen as the programming language, including Scikit-learn library for basic machine learning algorithms and PyTorch as a deep learning framework.

ABSTRACT. The presented paper conducts the research on the topic of System-on-Chip (SoC) configuration in cloud environment. The main focus is devoted to the configuration of the SoC that includes Field-Programmable Gate Array as a composing part of the chip. The proposed approach is based on the assumption that each part of the system should support remote configuration by matching software artifact. We consider each component for SoC individually and provide a complex solution for its configuration when all of them are running as a system. Moreover, the settings of running machine can be changed dynamically according to the devised information technology. Peculiar attention is paid to the configuration of programmable logic within the framework. As cloud providers also establish services that involve configuration of FPGA and its further usage of an accelerator for specific tasks, the information technology can be used as a basis for software manager responsible for configuration of the SoC.

ABSTRACT. The impact of introducing a CRM system in the enterprise are discusses. The analysis of enterprise business-processes is carried out and the processes requiring improvement are identified. The calculation of the effectiveness of the enterprise before and after the implementation of the system.

ABSTRACT. In the article, we propose to consider the reliability of flexible automated production and justify the need for functional decomposition of automated systems, followed by the description of processes in the form of functional networks. We have developed the principles of variant modeling for flexible production systems, the structure, and information and software of information technology for reliable design of automated production. The test proved the effectiveness of the proposed toolkit.

ABSTRACT. In the paper, authors analyze information and communication technology (ICT) for planning and optimization of transport routes with time windows. This analysis helps to choose the method for solving a vehicle routing problem with time windows (VRPTW) with optimal result for decision-maker, as well as determine the influence of the internal parameters of the selected method on the result of its application. Currently, there are several well-known methods and algorithms in ICT for planning and optimization of transport routes with time windows, in particular: saving and sweeping algorithms, ant colony optimization (ACO) method, artificial bee colony (ABC) method, etc. The result of the analysis showed that: a) the speed and quality of the search for solutions can be improved by adjusting internal parameters of researched methods, b) depending on the size and specificity of the incoming data, a different methods can be more or less suitable. In this paper, the authors discussed the features of using the ACO method and the ABC method to solve VRPTW and influence of their application on the optimality of the results. Simulation results show the need and feasibility of using ICT in VRPTW.

ABSTRACT. In recent years, a significant number of ICT indices have been developed by various international organizations / companies to assess the state of development of the information (digital) society, each based on selected research priorities. However, none of the established international meth-odologies with the proposed indicators can be directly transferred to assess the state of development of the information society in Ukraine, and even more so to reflect the situation of digital transformation of domestic business structures. The current state of digital technology in domestic business is dramatically different from the world. As there is currently a problem with the low digital literacy of society and business executives at all levels, the use of a European methodology for determining the digital intensity index with appropriate indicators is not entirely acceptable for domestic businesses. Due to the lack of data on the ownership of certain digital technologies by 2017, it is not clear whether the domestic business is ready to integrate the global trends of digital development. That is why it is necessary to develop your own methodology for determining the index of digital business transformation with appropriate indicators, which would take into account the current state of affairs. The methodology should reflect an in-depth analysis of the level of digital transformation of business structures, while being flexible in order to be able to respond quickly to new phenomena and the emergence of new digital tools and technologies. In the future, the developed methodology should be harmonized with international methods for comparing Ukraine's digital transformation with the most developed countries of the world