This paper proposes the model that is used to describe relations between verb and set expressions during analysis of the sentence in the Russian language. It describes the developed knowledge base that is used to describe syntactic units of the Russian language. The model is used to objects identification and knowledge extraction from the text in Russian language.
Nowadays the computer adaptive testing plays the main role in massive educational testing. This partly causes the growing interest to computerized forms of testing. In its turn, data transfer between item banks and test systems has become the topic of high actuality this last few years. This paper address questions about the interoperability of educational testing systems. The most popular text and XML-formats of the test questions (including rapidly developed QTI/APIP) were studied. The review of existing converters demonstrated that there is no freely accessed converter, which supports several questions’ types, has adequate Russian interface or allows internationalization, and offers authoring tools for the questions of different types. Consequently, the architectural and functional software requirements on test questions’ converter were determined and listed. As a result, the paper presents the web-API prototype, which was design and implemented according to collected requirements.
The problems co-ordinate of data set from others sources are considered. Co-ordinate of data is impossible without preliminary data scrubbing. Some formal recognition methods of address data based on phonetic unification, list metric and finite–state automations are proposed. Results of using these methods for address data scrubbing are described.
The objects studied in the article are finite words over some finite alphabet. These words are symbolical codes of the investigated objects and processes that are analyzed further. A formalization of the entropy on words function is proposed that is based on the of the entropy of discrete distributions. Using the results of analysis of sets of words with fixed length over a given alphabet, a notion of entropy function majorant is proposed. The entropy on words function and the majorant form the basis for the forms of a characteristic functional proposed in the article, which give a quantitative estimation of the proximity of the tested finite word to a subword of the same length, randomly selected from a random infinite word over the same alphabet. The proposed forms of the functional may be used for solving different tasks of data analysis, including clustering and pattern recognition tasks.
The article is devoted to defining goals, objectives and content of training on the professional-oriented discipline "Group dynamics and communication in professional software engineering practice", which is included in the curriculum of preparation of bachelors in the direction "Software engineering". We propose an innovative approach to teaching the discipline, which was based on team development of software projects.
Huge computer networks composed of infected machines so called botnets are currently the one of the most dangerous threats for global society. Botnets are a brilliant tool for organizing distributed denial of service attacks, sending spam and phishing email, stealing sensitive information and money from various accounts. Hackers create botnets from any kind of electronic devices connected to the Internet. The most widely used devices are: personal computers with windows operating system, smartphones with Android OS, IoT devices with public IP addresses and open vulnerabilities (IPTV cameras, for example). There are a lot of options for botnet hiring on the darknet. It is possible to hire a botnet, buy a builder kit or any other service in hacker-to-hacker manner. The easiest way to build a botnet is a creation of central server for spreading commands and creation of clients (bots) that will connect to this server. Such botnets are so called traditional botnets. Traditional botnets with centralized command and control mechanism are vulnerable to the wide range of attacks. For example, if one particular bot is captured by the security analyst the IP address of command and control server will be compromised with very high probability. Without central command and control server botnet is useless because the malefactor is unable to spread commands over infected network. In order to make botnets more robust and steady the peer-to-peer botnet architecture was introduced. P2P architectures could be divided on 3 main categories: pure, moderated and hybrid. The aim of the current papers is covering peer to peer botnets and its architecture.
This research investigates the effects of training sample balancing while solving intrusion classification task with convolution neural network. Using two convolutional neural networks with similar architecture, we conduct comparative analysis of classification task solution quality with and without training sample balancing. Experiments illustrate the efficiency of using training sample balancing in case of significant differences in the amount of samples in different classes.
The features of virtual laboratory stands in education. An example of the virtual laboratory stand developed with NI LabVIEW.
The paper deals with the applicability of modern machine learning methods to the problem of automatic generation of UDC for scientific articles. As the classifiers, such models as artificial neural networks, logistic regression and boosting are considered. Graph algorithms and a prototype software module to generate UDC are designed.
The article deals with the stages of the decision-making process when choosing a computer networks project. The authors propose a mathematical apparatus for the evaluation of project solutions and selection of network equipment. The work considers questions of selecting the most preferred company-integrator, based on it’s assessment of the project solutions, network equipment, vendors, developers, and complex project presentation. It is shown that at the first stage (formation of the integrators list, their evaluation and ranking criteria) the use of methods based on information on allowable values, criteria: method of expanding the set of satisfactory and unsatisfactory or methods of lexicographic ordering and semi-ordering will be effective to reduce the of alternatives number. As the main method for evaluation and selection of alternative design decisions the decision maker proposes the use of the analytic hierarchy process.
The article consider the case when the decision maker can specify the relative evaluation of the alternatives, it is advisable to enlist the expert group The method of ranking alternatives is advisable to use for decision-making on integrated assessment of the project. The method of permutations is suggested for detailed consideration by experts of the projects quality offered by the integrators. The method allows project comparison on several criteria (calculation criteria weights on the basis of the procedure from the analytic hierarchy process).