Search

This paper aims to provide a solution for malicious network traffic detection and categorization. Remote attacks on computer systems are becoming more common and more dangerous nowadays. This is due to several factors, some of which are as follows: first of all, the usage of computer networks and network infrastructure overall is on the rise, with tools such as messengers, email, and so on. Second, alongside increased usage, the amount of sensitive information being transmitted over networks has also grown. Third, the usage of computer networks for complex systems, such as grid and cloud computing, as well as IoT and “smart” locations (e.g., “smart city”) has also seen an increase. Detecting malicious network traffic is the first step in defending against a remote attack. Historically, this was handled by a variety of algorithms, including machine learning algorithms such as clustering. However, these algorithms require a large amount of sample data to be effective against a given attack. This means that defending against zero‑day attacks or attacks with high variance in input data proves difficult for such algorithms. In this paper, we propose a semi‑supervised generative adversarial network (GAN) to train a discriminator model to categorize malicious traffic as well as identify malicious and non‑malicious traffic. The proposed solution consists of a GAN generator that creates tabular data representing network traffic from a remote attack and a classifier deep neural network for said traffic. The main goal is to achieve accurate categorization of malicious traffic with a few labeled examples. This can also, in theory, improve classification accuracy compared to fully supervised models. It may also improve the model’s performance against completely new types of attacks. The resulting model shows a prediction accuracy of 91 %, which is lower than a conventional deep learning model; however, this accuracy is achieved with a small sample of data (under 1000 labeled examples). As such, the results of this research may be used to improve computer system security, for example, by using dynamic firewall rule adjustments based on the results of incoming traffic classification. The proposed model was implemented and tested in the Python programming language and the TensorFlow framework. The dataset used for testing is the NSL‑KDD dataset.

The paper presents an example of using new technology to solve the problem of promoting goods and services according to the 7P concept. The technology was called virtual promotion. The reason for its occurrence is a decrease in the effectiveness of the currently classical search engine optimization methodology on the Internet. The task of the latter is to bring the given corporate WEB resource to the first place in the search server’s answers to the requests of potential buyers. Virtual promotion is based on two ideas. The first is based on marketing theory when to sell a product or service, you need to build a marketing channel. The second is that a search server is an intelligent machine. Then, to get the first position, we need to teach the virtual space, which consists of Internet nodes, to activate in such a way that the number of links to the WEB page with the desired product is maximum. To implement these ideas, two objects are synthesized as part of the virtual promotion: a semantic kernel and a promotion map. A semantic kernel is a description of a product or service or a training sequence of keywords. A map is a set of nodes on the Internet, where the semantic core should be placed to attract the maximum number of buyers of the product. The map is also a variant of marketing channels on the Internet. The paper considers an example of a situation where a semantic core and a minimal map have already been created using the classical approach (search optimization). In this case, the classic approach gave an increase in the number of visits to the WEB site, but there was not a single buyer of the product for six months. That is, the classical approach improved the key performance indicator, but it did not affect the sales performance in any way. The paper demonstrates how virtual promotion forms such a modification of the map that gives a given result in a given period. At the same time, it is not enough to synthesize a new map. It is necessary to apply a special mechanism for its implementation. For this purpose, the paper shows a real task of inter-functional coordination, which makes it possible to implement a promotion map. Real data for 2021, which was used to promote the product on the Ukrainian market, is given. The introduction of the new version of the map resulted in the first two orders within the first two weeks.

This paper considers the problem of quality measurement of business process models using the n-dimensional space distances. Business process models are graphical schemes similar to flowcharts or activity diagrams utilized in software engineering, usually represented using the BPMN (Business Process Model and Notation) or EPC (Event-driven Process Chain) notations. Business process modeling aims to capture current enterprise workflows for their analysis and then improvement using automation through IT (Information Technology) systems deployment. Therefore, designed business process models should be of high quality, so all “weak spots” of described organizational workflows could be properly identified and replaced with more efficient solutions. Whereas process models, which are not understandable, un-structured, and/or uncertain, may cause even more issues when used to improve organizational activities. Therefore, this study proposes quality measures and a software tool that can be used to detect errors in BPMN and EPC business process models using distances in n-dimensional space. The formal problem statement based on the graph-based description of business process models was given. Business process model quality characteristics and measures that consider features of both BPMN and EPC notations were proposed. Distances in n-dimensional space were suggested for usage to measure the quality of business process models. The algorithm for business process model quality measurement was proposed. The software tool to measure the quality of BPMN and EPC business process models was designed and developed. The quality of sample business process models was measured using the software tool. Obtained results were analyzed and discussed. This paper considers the Euclidean distance only, while other existing n-dimensional space distance measures or, on the opposite, similarity measures, can be used to evaluate business process model quality in further research.

Business process modeling is one of the main tools of the BPM (Business Process Management) concept. With the help of business process modeling, business scenarios can be presented in the form of graphical models that can be easily understood by both information technology (IT) professionals and non-IT professionals – business analysts, software customers, department heads, top managers, and other stakeholders interested in business process improvement. Business process improvement is usually done through the automation of activities, which were identified as “bottlenecks” after analysis. However, it is possible to analyze a business process model only if it is clear and correct in terms of compliance with both the notation used and the real business process it depicts. This paper considers the analysis of BPMN (Business Process Model and Notation) business process model structural measures. It is assumed that business process models, which by their structural features violate rules of business process modeling, are neither understandable nor suitable for further work with them, which also can lead to various errors occurring at the stage of business process analysis, as well as at the stage of its improvement and implementation of proposed changes, i.e., during development, testing and maintenance of distinct software components, information system modules or BPM-system scenarios that ensure business process execution. Therefore, in this paper, we propose to identify the main elements of BPMN business process models and their structural measures that affect models’ understandability and maintainability and could be sources of errors. Considering selected measures, it is proposed to calculate respective values for a large collection of BPMN business process models, and then study compliance with theoretical business process modeling guidelines on practice when real business process models are designed. In order to provide efficient storage and processing of a large collection of BPMN business process models data, there were developed a database, and a software component. Results of analysis of BPMN business process model structural measures obtained using developed database and software component are demonstrated and discussed. The conclusion is made, as well as future research directions in this field are formulated.

An approach to the mathematical description of the criterion for the effectiveness of a new object of research – virtual promotion is presented in the paper. The emergence of this new object of research is connected, on the one hand, with the classical theory of marketing, and on the other with modern Internet technologies. Marketing is based on the 4P principle: product, price, location and promotion. Promotion is a component of this principle. But in modern conditions, this phenomenon is changing under the influence of the Internet. Now this 4P component is becoming a fully virtual instrument. The traditional scheme of promotion functioning is as follows. A message is created to a potential buyer and the delivery channel of this message undergoes a change. It is based on the principle: money – goods – money. While the new sales scheme is described by the scheme: we attract a client, make money on a client, we spend money. In the new scheme, we deal with product knowledge in the form of the so-called semantic core of web content. Knowledge describes for a potential client how a given product can cover his need for something. Using the logistic principles of the transfer of goods, this semantic core is loaded into the specified Internet nodes. That is, virtual promotion is formed as two channels: logistics and marketing. The first one performs three operations: concentration, formatting and distribution of semantic cores on the Internet. The second manages this process, forming a virtual promotion map. This map is a graph of Internet nodes. It is required to define such a tree of Internet nodes so that virtual promotion has maximum efficiency. The paper analyzes modern metrics related to the processes of search engine optimization on the Internet. Unfortunately, these metrics evaluate only statistically after the fact of visiting a web resource or the budget of the Internet site in which the advertising message about the product was placed. Therefore, based on the conversion metric, a criterion for the effectiveness of virtual promotion was proposed in the work, which takes into account both the attractiveness of the semantic core and the attractiveness of the Internet site where the semantic core will be located. The criterion reflects the income that we receive depending on the attractiveness of the semantic kernel and the Internet site.

There is a lot of routine work in any organization, including in recruitment agencies. Effective management organization and automation of activities of employees of recruiting agencies is not an easy task. The system should automate the routine actions of workers of recruiting agencies and be convenient for their clients. This paper proposes an approach to automating the selection of necessary medical staff. Not all information systems used by recruiting agencies can compare candidates and generate results that include several of the best candidates. Based on the analysis of the subject area, groups of parameters that significantly affect the choice of medical personnel were determined. The proposed approach is to analyze the request from the client, and then in the system find requests of other clients similar to it in terms of parameters, for which a candidate has already been found. The next step is to take the profiles of healthcare professionals that have been suggested for these requests (they act as benchmarks) to further compare them with existing candidates. Each employee profile parameter has its own similarity function. Available candidates will receive scores and will be ranked. We also additionally adjust the assessment by comparing candidates with the current request. Software was developed to automate the selection of medical personnel. For its implementation, a three-level client-server architecture is proposed. MVC (Model View Controller) architecture was chosen for the server part. The Single Page Application architectural template is used for the client part. The server part is divided into three layers, which further demarcate and structure the responsibilities of the system components. .NET technologies are used to implement business logic. SQL Server is used for the server and database provider. The use of the software implementation of the developed system demonstrated quite good results. The average time for selecting the 10 best candidates out of 500 is 0.4 seconds, and the processing of only 1 resume by a person takes several minutes.

The article presents a new concept of “Management of knowledge about virtual promotion” on the Internet. Usually a real produ ct or service is being divided into four components (product, price, promotion and place) in accordance with the theory of marketing. One of the components is a product promotion. But now this element is becoming a fully virtual tool. It is necessary to consider product promotion as an image or a copy of a real product in a virtual space that lives in parallel on the network. Therefore, the objective of the paper is the presentation of a new object of research based on the experience of more than thirty real projects performed in Ukraine, USA, Europe and Canada. We regard the promotion as a software product, which works according to principles of knowledge management and machine learning. It is proposed that virtual promotion is characterized by four views: customer or user, data, technology and marketing. Thus, the structure of virtual promotion business process was presented. It includes four steps: selection of hypertext sources, knowledge representation and extraction, semantic kernel building and quality criterion evaluation to stop the process. Based on the process structure the research tasks were identified. The central task is semantic kernel forming. Then the software architecture was developed. IT solution contains CRM system as accounting tool and Web site as an image of virtual promotion. CRM plays main role as a commander center. Here we form semantic kernel and then send it via marketing channels such as Web site, telegram or viber accounts. Another part of IT solution is Web service such as Bing API or Google API. They help us to build the kernel. Also the paper demonstrates the list of future tasks that should be solved and the example of real project of proposed approach.

The problem of information searching is very common in the age of the internet and Big Data. Usually, there are huge collections of documents and only multiple percent of them are relevant. In this setup brute-force methods are useless. Search engines help to solve this problem optimally. Most engines are based on learning to rank methods, i.e. first of all algorithm produce scores for documents based on they feature and after that sorts them according to the score in an appropriate order. There are a lot of algorithms in this area, but one of the most fastest and a robust algorithm for ranking is LambdaMART. This algorithm is based on boosting and developed only for supervised learning, where each document in the collection has a rank estimated by an expert. But usually, in this area, collections contain tons of documents and their annotation requires a lot of resources like time, money, experts, etc. In this case, semi-supervised learning is a powerful approach. Semi-supervised learning is an approach to machine learning that combines a small amount of labeled data with a large amount of unlabeled data during training. Unlabeled data, when used in combination with a small quantity of labeled data, can produce significant improvement in learning accuracy. This paper is dedicated to the adaptation of LambdaMART to semi-supervised learning. The author proposes to add different weights for labeled and unlabeled data during the training procedure to achieve higher robustness and accuracy. The proposed algorithm was implemented using Python programming language and LightGBM framework that already has supervised the implementation of LambdaMART. For testing purposes, multiple datasets were used. One synthetic 2D dataset for a visual explanation of results and two real-world datasets MSLR-WEB10K by Microsoft and Yahoo LTRC.

Mixing processes are found in the chemical, pharmaceutical and food industries. Fluid mixing is one of the fundamental scientific problems associated with modern concepts of regular and chaotic dynamics. The paper considers the problem of mathematical modeling of the quasi-stationary process of mixing a viscous mixture. This problem consists of two sub-problems: determination of the velocity field in the flow region (Eulerian formalism) and investigation of the trajectories of individual fluid particles (Lagrange formalism). To solve the first subproblem, it is proposed to jointly use the principle of superposition, the structural method (method of R-functions) and the Ritz variational method. The methods of nonlinear dynamics and qualitative theory of differential equations are used to solve the second subproblem. A plane quasi-steady flow is considered in a rectangular region and it is assumed that the side walls are at rest, and the upper and lower walls move alternately according to the given laws. According to the method of R-functions, the structures of the solutions were built and the use of the Ritz variational method for the approximation of the uncertain components of the structures was justified. The operation of the proposed method is illustrated by the results of a computational experiment, which was conducted for different modes of wall motion. The practical interest of the considered regimes is due to the fact that they lead to the emergence of chaotic behavior when mixing occurs most efficiently. Using the methods of nonlinear dynamics, the location of periodic (hyperbolic and elliptical) points was investigated and the Poincaré section was constructed. Further research with the help of the method proposed in the work can be related to the consideration of flows in more geometrically complex regions and more complex mixing regimes, as well as in the application to the calculation of industrial problems.

The effectiveness of solving the problem of identifying the system state significantly depends on the number of controlled parameters and the degree of their informativeness. The traditional method for assessing the informativeness of these parameters is based on the measure of distance between the probability distributions of the values of the controlled parameter for different states of the system proposed by Kullback. The shortcomings of Kullback measure have been revealed. Firstly, the value of this measure is not normalised and is not limited from above. Secondly, this measure is asymmetric, i.e. its numerical value depends on the way its components enter the calculation ratio. The method for calculating the informativeness criterion proposed in this paper takes into account the uncertainty that arises due to the fuzzy description of the boundaries of the areas of possible values of the controlled parameters for each of the possible states of the system. An important enhancement of the known methods for assessing the informativeness of the controlled parameters is to take into account the real existing inaccuracy in estimating the values of the results of measuring these parameters themselves. These circumstances determine the subject and purpose of the study that is the development of a method for calculating the distance between the distributions of fuzzy values of the controlled parameter, free from the shortcomings of the Kullback measure. To calculate the measure of the distance between the distributions of the values of the controlled parameter under conditions of uncertainty of the initial data, described in terms of fuzzy mathematics, a symmetric criterion is proposed, which is easily calculated. Examples of the criterion calculation are given. The possibilities of increasing the level of informativeness of the criterion using analytical descriptions of membership functions of fuzzy values of the controlled parameter for different states of the system are considered.

Business process models are essential business process management artifacts that help describe visually ongoing business activities to facilitate communication between information technology and business stakeholders. Business process models are used to find inefficient spots within described workflows and resolve detected shortcomings by automation via configurable software solutions or unified workflow engines. However, this is impossible when using syntactically or semantically poor business process models. It is the same as building a house using the blueprint with windows on the floor and typos in text labels. Therefore, it is extremely important to keep created business process models clear and relevant to the actual workflows they describe. Hence, in this paper, we propose the approach and the software tool to calculate semantic quality measures of business process models. The proposed approach uses a special procedure to extract the modeling domain statements using natural language processing techniques. According to the proposed approach, the initial textual descriptions of business process models should be tokenized. Then obtained tokens should be turned to the lower case style and cleansed to remove non-alphabetic tokens and stop words. Finally, the remaining tokens should be stemmed and the existing duplicates should be removed. The same procedure is then repeated for text labels attached to the business process model activities. Then, tokens present in the result of textual description’s processing but missing in the result of labels’ processing are considered incomplete (i.e. incorrect in the modeling domain). Similarly, tokens present in the result of labels’ processing but missing in the result of textual description’s processing are considered invalid (i.e. irrelevant to the modeling domain). Therefore, respective semantic quality measures can be calculated. The software tool is created using the Python programming language because of its powerful natural language processing packages.

Currently, the question of state, formation and development of the information source interaction system, the scientific interaction and users' requests in certain fields of activity remains relevant under the conditions of the development of the use of Internet services. Recommendation systems are one of the types of artificial intelligence technologies for predicting parameters and capabilities. Due to the rapid increase in data on the Internet, it is becoming more difficult to find something really useful. And the recommendations offered by the service itself may not always correspond to the user's preferences. The relevance of the topic is to develop a personal recommendation system for searching books, which will not only reduce time and amount of unnecessary information, but also meet the user's preferences based on the analysis of their assessments and be able to provide the necessary information at the right time. All this makes resources based on referral mechanisms attractive to the user. Such a system of recommendations will be of interest to producers and sellers of books, because it is an opportunity to provide personal recommendations to customers according to their preferences. The paper considers algorithms for providing recommender systems (collaborative and content filtering systems) and their disadvantages. Combinations of these algorithms using a hybrid algorithm are also described. It is proposed to use a method that combines several hybrids in one system and consists of two elements: switching and feature strengthening. This made it possible to avoid problems arising from the use of each of the algorithms separately. A literature web application was developed using Python using the Django and Bootstrap frameworks, as well as SQLite databases, and a system of recommendations was implemented to provide the most accurate suggestion. During the testing of the developed software, the work of the literature service was checked, which calculates personal recommendations for users using the method of hybrid filtering. The recommendation system was tested successfully and showed high efficiency.

We substantiate the structure of the efficient numerical axis segment an active experiment on which allows finding estimates of the coefficients for nonlinear terms of univariate polynomial regression with high accuracy using normalized orthogonal Forsyth polynomials with a sufficiently small number of experiments. For the case when an active experiment can be executed on a numerical axis segment that does not satisfy these conditions, we substantiate the possibility of conducting a virtual active experiment on an efficient interval of the numerical axis. According to the results of the experiment, we find estimates for nonlinear terms of the univariate polynomial regression under research as a solution of a linear equalities system with an upper non-degenerate triangular matrix of constraints. Thus, to solve the problem of estimating the coefficients for nonlinear terms of univariate polynomial regression, it is necessary to choose an efficient interval of the numerical axis, set the minimum required number of values of the scalar variable which belong to this segment and guarantee a given value of the variance of estimates for nonlinear terms of univariate polynomial regression using normalized orthogonal polynomials of Forsythe. Next, it is necessary to find with sufficient accuracy all the coefficients of the normalized orthogonal polynomials of Forsythe for the given values of the scalar variable. The resulting set of normalized orthogonal polynomials of Forsythe allows us to estimate with a given accuracy the coefficients of nonlinear terms of univariate polynomial regression in an arbitrary limited active experiment: the range of the scalar variable values can be an arbitrary segment of the numerical axis. We propose to find an estimate of the constant and of the coefficient at the linear term of univariate polynomial regression by solving the linear univariate regression problem using ordinary least squares method in active experiment conditions. Author and his students shown in previous publications that the estimation of the coefficients for nonlinear terms of multivariate polynomial regression is reduced to the sequential construction of univariate regressions and the solution of the corresponding systems of linear equalities. Thus, the results of the paper qualitatively increase the efficiency of finding estimates of the coefficients for nonlinear terms of multivariate polynomial regression given by a redundant representation.

Applications architecture is the baseline of any organizational activity, which main goal is to provide the executional environment for business processes in order to deliver products or services to satisfy customer needs and generate revenue. Nowadays, large software engineering projects always begin with the architecture design phase, despite the waterfall or agile methodology is used by a software development team. Applications architecture design is the most important and, at the same time, error-prone stage of the whole software engineering project. It is well-known that design shortcomings made on the design phase may increase drastically to testing and maintenance phases. Further costs to defects fixing may be hundred times higher in the later project stages in compare to the design stage on which applications architecture is defined. Common system design solutions, which were proven on practice and used in many projects, are known as architectural patterns. Software architecture patterns are considered as building block for system implementation. The most popular and efficient way to share architectural patterns are graphical models that used as any other blueprints of engineering solutions. Applications architecture models are built to represent system design, whereas, such models are already based on certain patterns as the industry best practices. Hence, in this paper we consider a relevant problem of applications architecture models analysis, which relevance is defined by those fact that designed blueprints of information systems and other software solutions should be carefully checked for all presumable inefficiencies in order to avoid extra efforts and related costs for defects fixing in the later project stages. It is proposed to use ArchiMate enterprise architecture modeling language, since it can be used not only to represent applications architecture, but is connection to business and technology layers. In order to evaluate applications architecture models, respective ArchiMate metamodel is considered and represented as labeled directed graph, and coupling software metric is selected for analysis. Sample calculations are demonstrated, obtained results are discussed, conclusion and future work directions are formulated.

The paper is dedicated to the development and comparative experimental analysis of semi-supervised learning approaches based on a mix of unsupervised and supervised approaches for the classification of datasets with a small amount of labeled data, namely, identifying to which of a set of categories a new observation belongs using a training set of data containing observations whose category membership is known. Semi-supervised learning is an approach to machine learning that combines a small amount of labeled data with a large amount of unlabeled data during training. Unlabeled data, when used in combination with a small quantity of labeled data, can produce significant improvement in learning accuracy. The goal is semi-supervised methods development and analysis along with comparing their accuracy and robustness on different synthetics datasets. The proposed approach is based on the unsupervised K-medoids methods, also known as the Partitioning Around Medoid algorithm, however, unlike Kmedoids the proposed algorithm first calculates medoids using only labeled data and next process unlabeled classes – assign labels of nearest medoid. Another proposed approach is the mix of the supervised method of K-nearest neighbor and unsupervised K-Means. Thus, the proposed learning algorithm uses information about both the nearest points and classes centers of mass. The methods have been implemented using Python programming language and experimentally investigated for solving classification problems using datasets with different distribution and spatial characteristics. Datasets were generated using the scikit-learn library. Was compared the developed approaches to find average accuracy on all these datasets. It was shown, that even small amounts of labeled data allow us to use semi-supervised learning, and proposed modifications ensure to improve accuracy and algorithm performance, which was demonstrated during experiments. And with the increase of available label information accuracy of the algorithms grows up. Thus, the developed algorithms are using a distance metric that considers available label information. Keywords: Unsupervised learning, supervised learning. semi-supervised learning, clustering, distance, distance function, nearest neighbor, medoid, center of mass.

The paper discusses the issues of increasing the efficiency of the functioning of an intelligent business system by reducing its losses by creating an integrated set of models for assessing the level of its current strategic potential and the degree of achievement of its fixed target state. The object of the analysis is an intelligent business system of the IT industry that produces software products, the results of which depend on the well-established abilities of its personnel, who has effective intelligent information technologies. The task of assessing the strategic potential, determined by the totality of available resources (human, material, intellectual) that can be put into action, mobilized to achieve the target state of the enterprise, this calculation is based on estimates of the material and intellectual potential of the business system. We will build a complex of models for determining estimates of material and intellectual potential based on the significance and intensity of the influence of the strengths and weaknesses of the material, human, intellectual resources of the functional zones of the business system. Development of a subject technology for assessing the strategic potential of an intelligent business system, assessing the degree to which it reaches a fixed target state. Obtaining the results can serve as a theoretical basis for creating information technology for assessing the strategic potential of an enterprise in the IT industry.

The paper discusses the issues of increasing the efficiency of production activities of an intelligent business system operating in a dynamic environment by reducing its losses by creating a subject technology for reliable identification of problem situations in the process of functional diagnostics of a business system. The object of the research is an intelligent business system of the IT industry, which produces intelligent products, the results of which depend on the mental abilities of its personnel, who own effective intelligent information technologies. The problem-containing environment was chosen as the basis for analyzing the problem situation, in the depths of which the problem situation arises, develops and manifests itself. A problem-containing environment is characterized by structure and behavior. The behavior of the problem-containing environment is determined by the multidimensionality of the ongoing business processes, their interaction and dynamics. To identify deterministic and non-deterministic problem situations, it is proposed to set them by bipartite graphs and use the technology of inference based on precedents, which has serious advantages over the method of inference based on knowledge. In this work, a cognitive method is used to analyze problem situations of an intelligent business system. The basis of cognitive analysis is formed by the problem-containing environment, in the depths of which the problem situation arises. To study the problem-containing environment, the method of analysis of hierarchies is used, the basis of which is a hierarchy which is a system of levels, each of which consists of elements, factors of the problem-containing environment and an intelligent business system. A complex of models has been developed to construct a bipartite graph of a problem situation and to analyze its problem-containing environment. On the basis of a complex of models, a subject technology for identifying problem situations arising in the process of functional diagnostics of intelligent business systems has been created. The results obtained can be used as a theoretical platform for creating an information technology for functional diagnostics of intelligent business systems operating in a dynamic environment.

This paper considers the problem of software requirements capturing for business process model evaluation and recommendations generation to suggest how detected modeling errors may be eliminated in order to improve business process model correctness. Existing software tools for business process model analysis are based on metrics and thresholds that allow assume presence of errors in business process models, but they are not capable to recommend structural changes required to eliminate detected modeling errors. Therefore, business process model analysis and improvement tasks become relevant, since early detection and elimination of possible errors presented in business process models may allow organizations avoid extra costs that may occur on any of the steps of business process lifecycle. Since business process models are shared organizational assets, it is also necessary to consider the capabilities of collaborative and concurrent usage of business process models by multiple stakeholders. Hence, the workflow of business process model analysis and improvement was analyzed and its key steps, which describe expected user and software behavior, were formalized using the IDEF0 functional model. Functional software requirements were captured in the form of user stories according to modern agile practices of software development. These user stories are based on features and drawbacks of existing software tools for business process model analysis. Captured user stories were formalized using the use case modeling. Non-functional software requirements were also captured; they include maintainability, readability, testability, understandability, integrability, and complexity requirements. Captured requirements can be used to design and develop business process model analysis and improvement software capable to provide recommendations to eliminate detected modeling errors.

This research paper considers the problem of dashboard design as part of the Business Process Management lifecycle, where it is become necessary to monitor and control the current state of the organizational business processes. Therefore, designed dashboards should fully correspond to the features of the considered business processes, such as Key Performance Indicators and possible stakeholders, which are considered here as users of the developed Business Intelligence dashboard application. At the same time, according to the state-of-the-art in the field of data visualization, it is required to choose data visualization techniques, which are clear, easy interpretable, space efficient, attractive, and legible. In general, the dashboard design problem requires placing various visualization tools in a relatively small place, such as a screen of a computer, a laptop, a tablet, or even a smart phone, while keeping them accessible and easy to understand. At first, as part of the related work review and analysis, we have considered the core architecture of the dashboards and reporting applications. It is outlined that modern dashboards might use various big data chunks, such as databases of enterprise information systems of different types, spreadsheets data, and even unstructured documents. In order to summarize all the raw data from these data sources, the Data Warehouse should be built and, moreover, it should correspond to the metrics and indicators of business processes that should be demonstrated on a dashboard. We have also considered main principles, common mistakes, and graphs and charts that might be used to design a dashboard for business analytics purposes. Using the existing research in this field, the levels of informativeness were defined for each visualization tool, as well as the best practices of mapping various data types to graphs and charts are outlined. Proposed model of the da shboard design is based on the mathematical optimization. It is used to provide recommendations on which visualization tool should be used to display a certain Key Performance Indicator on a dashboard that corresponds to a certain user role. Development and usage of the software solution that implements the proposed model is outlined, as well as the obtained results of validation of the proposed software solution are shown and discussed.

Keeping employees aligned with modern trends and developments in their professional areas is the main focus of a lifelong lea rning approach. That becomes even more important for such dynamic industries like Information Technology. Therefore, it’s crucial to extend existing e-learning management system with an adaptive training component that enables the effective study of on-demand skills, leading to a broader range of candidates available for project management to select from and consequently improving the overall performance of an IT company. To improve the existing learning process according to company's and employee's needs the overview of a typical learning management system functionality is given in this paper. The main benefits from the adoption of a learning management system in small and medium-sized IT-companies were discussed, analysis of their features and problems was given. The adjustment plan for the typical learning management system to be suitable for the information technology domain including module of the adaptive learning content selection using the basic principles of graph theory was proposed to reduce the time of the learning process. LMS OpenOLAT was reworked according to the adjustment plan which is reflected by the number of diagrams such as sequence diagram, IDEF0 business process description, activity diagram that shows search algorithm steps and application component diagram. Also, GUI was adjusted to provide user with a good look and feel. The benefits of the proposed approach in business processes of IT-company are shown using “Academy – Smart”. To prove the efficiency of the proposed algorithm, real courses were used. Based on the learning material, provided by “Coursera”, a number of test cases was formed and analyzed. After applying adaptive content selection algorithm according to the models of “Academy – Smart” employees, learning time was reduced and optimized. This investigation has shown significant improvement in the resource management process and acceleration of the learning process for employees.

The results of effectiveness evaluating of machine learning methods for sentiment analysis of social network messages are presented in this paper. The importance of the sentiment analysis problem as one of the important tasks of natural language processing in general and textual information processing in particular is substantiated. A review of existing methods and software for sentiment analysis are made. The choice of classifiers for sentiment analysis of texts for this research is substantiated. The principles of functioning of a Naïve Bayesian Classifier and classifier based on a recurrent neural network are described. Classifiers were sequentially trained in two corpuses: first, in the RuTweetCorp corpus, the corpus of short messages from the social network Twitter, and then on the Slang corpus, the corpus of messages from social networks Facebook and Instagram and posts from the Pikabu website, second corpus have been marked up the tonality of slang words. Information about the tonality of slang words was taken from the youth slang dictionary obtained as a result of the survey of users. The separation of texts by tonality was carried out into three classes: positive, negative and neutral. The efficiency of these classifiers was evaluated. Efficiency evaluation was carried out according to standard metrics Recall, Precision, F-measure, Accuracy. For the naive Bayesian classifier, after training on the first corpus, the following metric values were obtained: Recall = 0,853; Precision = 0,869; F-measure = 0,861; Accuracy = 0,855; and after training on the second corpus such values were obtained: Recall = 0,948; Precision = 0,975; F-measure = 0,961; Accuracy = 0,960. For the classifier based on a recurrent neural network, after training on the first corpus, the following metric values were obtained: Recall = 0,870; Precision = 0,878; F-measure = 0,874; Accuracy = 0,861; and after training on the second corpus such values were obtained: Recall = 0,965; Precision = 0,982; F-measure = 0,973; Accuracy = 0,973. These results prove that additional training on the second corpus increased the efficiency of classifiers by 10–11%.

The paper considers the problem of estimating the state of the enterprise (on example of the IT company). The problem is presented in the form of two problems. The first problem is the aggregation of the initial information and the second problem is the identification of the state of a complex system. Authors formulated the problem and selected methods for solution of the problem. It is possible to form software for solving research problems. To solve the problem of aggregation of initial data authors used the fuzzy cluster analysis, namely the fuzzy k-means method. A numerical research was carried out and a test case was figured out in the MATLAB environment. In this test case the source data was reduced to a dimensionless form. Thereafter, already reduced to the same scale, the initial attributes were reduced to fuzziness. The results allow to formalize linguistic variables, which are characterized by the term-sets and definition range. The numerical results were approximated by analytical membership functions. The solution of the first task allows to generate a set of possible fuzzy reference situations, which reflect the possible state of the system. Each situation is characterized by the reference informational granule, which contains information about formalized linguistic variables. The second problem was solved by using the method of fuzzy logic in the MATLAB environment. The test case was calculated. In this test case, the search of the situation in which the IT-company is located was performed. At this stage, the current situation belongs to comparison with each reference situation. In this way, authors determined the most similar reference situation to the current situation. An analysis of the resulting situation allows to argue the state of the IT company. The solution of the second task allowed to establish assessment of IT company state. The theoretical and practical results can improve the efficiency of complex system management.

The objects and situations recognition is important problem in such areas as the definition of the types of air objects according to various sources of information, diagnosis of patients on the results of the survey and analysis, diagnostics of different equipment or technic types. Under the recognition refers to the process of obtaining the initial information about the affiliation of each studied element to a class based on analyze of the incoming information about studied elements of the environment, using methods to transform input data environment into output. The paper presents a model of the recognition process, which is characterized by the decision making of the class object based on the analysis of a set of quantitative and qualitative characteristics of which information can be obtained from various sources. The article presents a formalized set-theoretic model of the recognition process. According to the model, to attribute an object or situation to a certain class, it is necessary to define a set of feature groups of different types that allow to identify objects (situations) of a particular class. To perform recognition process experts based on experience or on the basis of statistical data must define a fuzzy affiliation function of the object of observation to each class with a set of values [0,1]. In the article shown representation of such function for quantitative characteristic in the form of a histogram. For qualitative attributes determined own values for each value. The new result of researches is a data structure for storing of the recognition process model, which allows to store together diverse characteristics and affiliation functions of different types at the same database tables. The proposed structure can be used in the process of the development of recognition systems software. It should be noted that will provide increased reliability of data storage by reducing the components of the database structure but also increased the complexity of the procedures and algorithms for saving and selecting the data.

Link prediction is an important area of study in network analysis and graph theory which tries to answer the question of whether two nodes in the graph might have an association in the future. Nowadays, graphs are ubiquitously present in our lives (social networks, circuits, roads etc.), which is why the problem is crucial to the development of intelligent applications. In the past, there have been proposed methods of solving link prediction problem through algebraic formulations and heuristics, however, their expressive power and transferability fell short. Recently, graph embedding methods have risen to popularity because of their effectiveness and the ability to transfer knowledge between tasks. Inspired by the famous in machine learning and natural language processing research Word2Vec approach, these methods try to learn a distributed vector representation, called an embedding, of graph nodes. After that a binary classifier given a pair of embeddings predicts the probability of the existence of a link between the encoded nodes. In this paper, we review several graph embedding approaches for the problem of Wikipedia link prediction, namely Wikipedia2vec, Role2vec, AttentionWalk and Walkets. Wikipedia link prediction tries to find pages that should be interlinked due to some semantic relation. We evaluate prediction accuracy on a hold-out set of links and show which one proves to be better at mining associations between Wikipedia concepts. The results include qualitative (principal component analysis dimensionality reduction and visualization) and quantitative (accuracy) differences between the proposed methods. As a part of the conclusion, further research questions are provided, including new embedding architectures and the creation of a graph embedding algorithms benchmark.

Internet technologies are an integral part of the relationship that arises in modern society. The rapid introduction and convenience of electronic platforms triggered the projected growth in demand in the market for IT products for recommender systems.The article discusses various limitations of current recommender methods and discusses possible extensions that can improve the recommender capabilities and make them more valuable for a wide range of applications. These extensions include improving the perception of users and elements, including contextual information in the recommendatory process, supporting multi-criteria ratings and providing more flexible and at the same time less intrusive types of recommendations.When integrating the relevant information technology to develop a commodity proposals environment, it is therefore necessary to consider the personalization requirements of the proposal to ensure that the technology achieves its intended result. This study therefore sought to apply context aware technology and recommendation algorithms to develop a system realize personalized goals in a context aware manner and improve commodity proposals effectiveness.In order to offer context-aware and personalized information, intelligent processing techniques are necessary. Different initiatives considering many contexts have been proposed, but users preferences need to be learned to offer contextualized and personalized services, products or information. Therefore, this paper proposes an agent-based architecture for context-aware and personalized event recommendation based on ontology and the spreading algorithm. The use of ontology allows to define the domain knowledge model, while the spreading activation algorithm learns user patterns by discovering user interests.Also from the statistical observation, it is found that there exists a higher level agreement towards the system between the participants of both end users and experts.

The methods of inversion of dynamical systems are widely used for solving the problems of controlling mechanical and electrical systems. The inverting of dynamic systems is an effective way of implementing processes of control according to disturbance, as well as in combined control systems with a predictive model. In solving the problems of inversion, there are number of difficulties related to the high sensitivity of the results in relation to accuracy of specifying the parameters of a mathematical model of an object, the instability in the control of non-minimal-phase objects, and the violation of physical feasibility conditions. The paper suggests an approximate method for solving the inversion problem for linear stationary dynamical systems that is largely free of the indicated disadvantages. The method is based on the representation of input and output signals by their approximations in the linear space of quasiharmonic functions of time. Consider mathematical models of linear dynamical systems in the form "input-output". The systems under consideration must satisfy the requirements of asymptotic stability, and also the condition of equality of dimension of the input and output vectors. A feature of the proposed method of inversion of dynamical systems is the representation of multidimensional polynomials, approximating input and output signals, in the form of a product of rectangular matrices and a vector of power of time. Such a representation allowed reducing most of the statements of inversion problems to the solution of linear systems of matrix algebraic equations. The computer implementation of the proposed approach to the inverting of the linear system is developed for "square" linear scalar systems in conditions of polynomial signal and contains blocks of approximation of the output assignment; the formation of matrices of linear systems and right-hand sides of linear algebraic equations; estimation of the condition number of the solution of the linear system and the block of comparison the result of the inversion with the assignment based on the direct integration of the differential equations of the mathematical model.

The paper proposes an approach to the detection of abnormalities in the behavior of knowledge-capacity business processes on the basis of comparative analysis of tracks in the log of events logging. The approach takes into account the temporal and object aspects of the implementation of the business process. The temporal aspect defines the sequence of events that reflect the execution of the business process. Object defines the characteristics of objects that use the business process when performing these actions. When searching for abnormal fragments, the distance between paths in the attribute event space is calculated. As an indicator of the beginning and end of an abnormal fragment, the angle of deviation between the tracks is used. The approach defines the set of attributes of objects associated with the execution of an anomalous fragment, as well as the values of these attributes, which can then be used to improve the business process.

The article examines an architectural solution of a software application for building an enterprise strategy map. It gives a short review of existing software products at the IT-market, which is used in strategic enterprise performance management. Much attention is dedicated to the separate stage of the development program formation, i.e. strategy map building. For building such a map it is proposed to formulate general enterprise strategic goals on the basis of an analysis of the development direction priorities and then check them for their feasibility. Next, the selected goals are decomposed into goals by the perspectives in accordance with the balanced storecard. The goals are analyzed for the impact of key success factors. Based on the success factors, bunch of strategic key performance indicators are formed. The paper examines problems that need to be solved at each stage of the map building, and proposes mathematical methods for their solving such as the analytic hierarchy process, the trajectory approach in conjunction with the system optimization and the cognitive analysis. The author suggests using service-oriented architecture for EPM-system implementation and microservice architecture for the implementation of the strategic map application. As result the study identifies four services that implement the following business functions: an identification of priority directions for the enterprise development and general strategic goals; a verification of the feasibility of common strategic goals and planned targets formation; a definition of the goals by the perspectives, KSF definition and building of the strategy map; a definition of KPI by the perspectives. The structure of the software application is presented as a component diagram.

A three-dimensional field with properties of stationary, normality and Markov process is considered. In the paper is considered a three-dimensional field, which has the properties of stationarity, normality, and process of Markov. The analysis is based on the equation of motion of the amplitude of a three-dimensional field with a generating three-dimensional field possessing the properties of three-dimensional white noise. For a random variable, the amplitudes of a three-dimensional normal Markov field of the first order in the volume, transition conditional probability density densities are obtained together with the unconditional probability distribution density. On their basis, an algorithm for generating such a field in a parallelepiped is constructed and justified. A numerical example of the implementation of the proposed algorithm is given.