The program system of the management of assessment tools for educational process described in the article. The system reduces the time that the teacher spends on the preparation of test materials, allowing you to create a set of assessment documents in a semi-automatic mode. The system implements the ability to create and manage task banks. Each task in the bank has a set of attributes that are involved in the process of generating assessment documents. The system also implements the ability to automatically generate the required number of variants of the assessment documents. At the same time, the algorithm for gen-erating a set of assessment documents works in such a way that, on the one hand, one set includes the most similar variants of assessment documents in structure, and on the other hand, each assessment document in the set is unique. The algorithm for generating a set of assessment documents is based on the clustering algorithm for categorical data. In this paper a modification of the CLOPE algorithm was submitted, which allows you to automatically determine the required number of clusters, depending on the input data. Also, this modification solves the problem of small clusters and the problem of categorical clustering of numerical attributes. The paper also describes an iterative algorithm for the generation of a set of assessment documents.

Kotlin is a statically typed programming language that supports object-oriented and functional programming. It sup-ports JVM, JS and native platforms via LLVM (Kotlin / Native). The first two targets are backed with well-developed virtual machines that can perform advanced program optimizations at runtime. However, for native platforms, all optimizations must be performed at compile time. Currently Kotlin / Native lacks many optimizations, which is why the performance of the generated code is poor in many cases. This paper describes a way to solve this problem by introducing an additional SSA-based intermediate representation and implementing escape analysis using it. Experimental results have shown that this approach can significantly improve performance.

The importance of the biological properties of proteins to cells cause actively exploring their amino acid composition (primary structure). The versatile tool of cell proteome exploring is mass-spectroscopy. The interpretation of mass-spectroscopy data is complex challenge because it remains uncertain peptide dissociation mechanisms and external factor influence to peptide fragmentation process. Moreover, a lot of mass-spectroscopy data is required to enhancement existing or development novel algorithms to interpret peptide mass-spectra. The article describes development of algorithm for in silico generation peptide mass-spectra covered the problem of influence noncanonical amino acid composition and posttranslational modifications to dissociation process. Developed algorithm was compared with analogues and evaluated over experimental data.

Currently, quantum technologies are at the forefront of scientific thought. Large corporations are creating their own quantum supercomputers, developing quantum analogues of classical algorithms, and research is being conducted in the field of quantum cryptography. But since quantum computers have not yet become widespread, the question becomes relevant: how can ordinary users, scientists and researchers keep up with the development of science? One possible solution is to use various kinds of tools to emulate quantum computing on a local non-quantum computer. In addition, there is also the opportunity to have several qubits of IBM's quantum supercomputer available. As a rule, such tools are implemented in the form of libraries for various programming languages. Due to the fact that working with real quantum computers is available only to a narrow circle of researchers, emulators are simply necessary to test hypotheses or algorithms. This article examined the most popular quantum emulators used for quantum computing and allowing emulating the process of a quantum computer. Work was carried out to study quantum emulators, to identify and describe their individual characteristics, to make recommendations for a more convenient start to work with them, as well as to describe their advantages and disadvantages. A review of several libraries for the JavaScript, Python, C / C ++ languages was made, as well as a tool with a web interface (Quantum Programming Studio) and a set of tools from Microsoft (Microsoft Quantum Development Kit), the main language of which is Q #, is examined. At the end of the article, a conclusion is made regarding the considered tools.

This paper presents a computer vision clothing auto-tagging algorithm. Tagging is highly demanded in e-commerce as a tool to create a rich uniform set of annotations. The annotations improve catalog organization, statistics, and can be used for interactive catalog search by consumer photos. The proposed algorithm predicts length, design, and color attributes for an arbitrary number of clothing items in an image. The modular structure of the proposed system allows reconfiguration for other sets of tags and tagging tasks not related to clothing.

Auto-completion is an essential feature of any popular text editor for some language. It allows users to avoid the process of annoying typing of long expressions in their projects. There are a lot of different works in this direction in scientific research and commercial products. These works are very different and either use some special features and heuristics to improve code completion or use machine learning techniques. Most of these approaches rely on synthetic data and do not take into account the behavior of real users. The article proposes an approach to improve the automatic code completion mechanism for the Python language by collecting information about usage of this mechanism by real users. The obtained data is used to train the model to rank completion variants with machine learning algorithms. To train the model, two types of features are used: contextual and elemental. Contextual features describe information about the code next to the cursor position in a text editor. Elemental features describe the characteristics of the proposed variant, for example, the length of the matching prefix. When building a model, it is important to take into account the limits of the response time of the model and its size. Also, in the paper, various approaches of assessing the quality of the final model are considered.

The aim of the work is to develop a model for describing and evaluating technological risks of an industrial enterprise, which allows you to manage risks based on their assessment and reasonably adjust the actual technical operation of the equipment. A technique for assessing the criticality of equipment is proposed and a scale for identifying the consequences of risks for the technical equipment of the enterprise is described. An algorithm for analyzing technological risks has been developed and recommendations have been formulated for the further operation of the facility.