Architecture of modern platforms for big data analytics

Big data is one of modern tools that have impacted the world industry a lot of. It also plays an important role in determining the ways in which businesses and organizations formulate their strategies and policies. However, very limited academic researches has been conducted into forecasting based on big data due to the difficulties in capturing, collecting, handling, and modeling of unstructured data, which is normally characterized by it’s confidential. We define big data in the context of ecosystem for future forecasting in business decision-making. It can be difficult for a single organization to possess all of the necessary capabilities to derive strategic business value from their findings. That’s why different organizations will build, and operate their own analytics ecosystems or tap into existing ones. An analytics ecosystem comprising a symbiosis of data, applications, platforms, talent, partnerships, and third-party service providers lets organizations be more agile and adapt to changing demands. Organizations participating in analytics ecosystems can examine, learn from, and influence not only their own business processes, but those of their partners. Architectures of popular platforms for forecasting based on big data are presented in this issue.

Comparison of methods of ranking scientists based on the Hirsch and PageRank indices: contradictory situations

Experiments aimed at comparing different methods of estimating and ranking scientists and researchers on the base of their publication activity are reported. Scientometric indicators based on h-index and PageRank are being compared. For such a comparison, a graph of citations represented by a matrix was applied. An example when different methods lead to opposite results was described. For example, authors having the best PageRank-based estimations may have the least h-indices. Such a situation is possible when a high-cited author managed to obtain a key result cited by all the other authors but this author has few papers. A comparison with methods of expert estimations was carried out, which appears to be very useful for building automated systems combining various methods of algorithmic estimating and ranking. The Analytic Hierarchy Process was applied. For building pairwise comparison matrices, transitive scales with a parameter representing how much times the next level of advantage is bigger than the previous one were harnessed.

Intelligent support system for agro-technological decisions for sowing fields

The are crop planning problems exist in a modern agriculture of Ukraine. With the help of the intelligent support system for agro-technological decisions proposed by the authors, it is possible to simplify the planning process by using the concept of precision farming. Modern fields monitoring methods were analyzed and methods that will be used in the intelligent system are identified. The k-means method is one of them and will be applied to field clustering. The authors analyzed modern research and publications related to the concept of precision farming and the problem of implementing modern innovative information systems in agriculture of Ukraine. The decomposition of the intelligent system was carried out. Six main subsystems were identified, functional requirements were developed for each of them. Modern methods of fields monitoring are analyzed and methods that will be used in the intelligent system are identified, one of which is the k-means method, which will be applied to field clustering. Based on the already developed requirements, the authors have developed the general architecture of the system. The notation TOGAF was applied for the graphical display of the architecture. Based on the proposed architecture, intelligent system software was created. As a result of testing the soft-ware of the intelligent system, it is possible to draw a conclusion about its efficiency and readiness for implementation. The designed and developed system allows to carry out intellectual analysis of historical data of crops, to display results in the form of tables and graphs, to carry out planning of crops, agrotechnological operations and fertilizer application. The introduction of this system will improve the quality of management decisions and productivity of agricultural activities.

Modeling of thermophysiological state of man

This article presents an analysis of mathematical models that can be used to predict the thermophysiological state of man in different environmental conditions in the development of information systems for its life support. The basic element of all considered models is the equation of heat balance. According to this equation, the total heat transfer of the organism must be equal to its heat output. The article considers continuous and discrete-vascular models, analyzes their advantages and disadvantages. Continuous models are, in essence, a simplified notation of biothermal equations. In these models, the effect of blood flow on each individual vessel is neglected, and the blood supply is averaged over the volume studied. Discrete-vascular models are a set of biothermal equations that describe the blood flow in each individual vessel. Discrete-vascular models of the thermophysiological state of man are not very applicable today, due to the complex and insufficiently studied vascular geometry. More common are continuum models, for the construction of which a multi-compartmental approach is used. As a result, the article presents a comparative table of continuous models and information systems that use these models.

Models of proactive change management of projects for the creation and development of distributed information systems

This article considers approaches to the formation of models of proactive management of projects for the creation and development of distributed information systems. Features of distributed IT projects as a complex adaptive system that develops under numerous interrelated constraints are considered. It is concluded that the projects themselves are distributed. The main trends in the development of such systems were analyzed, the main patterns and problems were identified. The focus is on the consideration of the basic components of such systems and formalized models are proposed to describe their interaction. Attention is paid to the formation and implementation of projects to create complex systems based on distributed information systems, where the main features are the action of a significant number of complex influences from the turbulent external environment. The issues of project reactions to the effects of these changes were investigated. To address the management of such complex projects, a proactive approach is proposed. The consequences of changes in the processes of creating such systems are studied. A mathematical model of minimizing the effects of changes on project elements in the management of complex projects is proposed and an approach to the configuration management of such projects is proposed, which in general allows to build a scheme of effective project management.

Choosing the best parameters for method of deformed stars in n-dimensional space

This paper is devoted to the problem of optimization of a function in -dimensional space, which, in general case, is polyextreme and undifferentiated. The new method of deformed stars in n-dimensional space was proposed. It is built on the ideas and principles of the evolutionary paradigm. Method of deformed stars is based on the assumption of using potential solutions groups. There by it allows to increase the rate of the accuracy and the convergence of the achieved result. Populations of potential solutions are used to optimize the multivariable function. In contrast to the classical method of deformed stars, we obtained a method that solves problems in -dimensional space, where the population of solutions consists of 3-, 4-, and 5-point groups. The advantages of the developed method over genetic algorithm, differential evolution and evolutionary strategy as the most typical evolutionary algorithms are shown. Also, experiments were performed to investigate the best configuration of method of deformed stars parameters.

Intelligent module for recognizing emotions by voice

Speech is the main way of communication for people, and people can receive not only semantic but also emotional information from speech. Recognition of emotions by voice is relevant to areas such as psychological care, security systems development, lie detection, customer relationship analysis, video game development. Because the recognition of emotions by a person is subjective, and therefore inexact and time consuming, there is a need to create software that could solve this problem. The article considers the state of the problem of recognizing human emotions by voice. Modern publications, the approaches used in them, namely models of emotions, data sets, methods of extraction of signs, classifiers are analyzed. It is determined that existing developments have an average accuracy of about 0.75. The general structure of the system of recognition of human emotions by voice is analyzed, the corresponding intellectual module is designed and developed. A Unified Modeling Language (UML) is used to create a component diagram and a class diagram. RAVDESS and TESS datasets were selected as datasets to diversify the training sample. A discrete model of emotions (joy, sadness, anger, disgust, fear, surprise, calm, neutral emotion), MFCC (Mel Frequency Cepstral Coefficients) method for extracting signs, convolutional neural network for classification were used. . The neural network was developed using the TensorFlow and Keras machine learning libraries. The spectrogram and graphs of the audio signal, as well as graphs of accuracy and recognition errors are constructed. As a result of the software implementation of the intelligent module for recognizing emotions by voice, the accuracy of validation has been increased to 0.8.

Project management models to create IT company in the field of Data Science

The basis for the emergence of projects to create IT companies in the field of Data Science is considered. The relevance of such projects is substantiated. The feasibility of their study using models and methods of project management is proven. Literary sources in three directions are analyzed. Such areas include classical project management, flexible approaches to project management, value-oriented management. Insufficient research of the described subject is proved. Groups of models and methods are described that describe the relevant areas of project management knowledge that will be necessary and minimally sufficient to develop the scientific basis of the IT company creation project in the field of Data Science. Namely: project team management, project value management, project concept development, project content management, project communications management, flexible project management tools. In the analysis of each area, the relevant models and methods are highlighted. Their applicability to the researched project is analyzed. A model for selecting a set of models and methods within the identified key knowledge areas for the research project in the form of a convolution of criteria is proposed. SWOT-analysis of the proposed approach was performed. The strengths, weaknesses, opportunities and threats associated with the proposed approach are highlighted. Conclusions to the study are formulated. Prospects for further research in the chosen direction are outlined.

Customer-oriented optimization of healthcare facilities staff is considered

The problem of developing information technology for customer-oriented optimization of healthcare facilities staff is considered. It is determined that the key tasks in the development of personnel decisions in the formation of personnel policy in medical institutions are assessing such current characteristics of staff as to regulatory and actual workload and the task of forecasting needs for medical services in future periods. To effectively perform such a forecast, it is proposed to consistently solve clustering, identification, and forecasting problems. A mathematical model of the multicriteria optimization problem for the formation of many variants of solutions for the formation of personnel policy in health care facilities is built. The model of search of optimum distribution of services between employees of establishment in the form of a problem of integer linear programming is executed. Production rules have been developed to analyze the results of solving the formulated problem. A model for developing variants of decisions on changes in the staff of a medical institution to ensure the completeness of medical services is proposed. To assess the effectiveness of the options made, the customer orientation index is used, which is calculated by the principles of egalitarianism. Experimental verification of the developed models and methods is performed.

Analysis of visual object tracking algorithms for real-time systems

The article analyzes the latest achievements and decisions in the process of visual support of the target object in the field of computer vision, considers approaches to the choice of algorithm for visual support of objects on video sequences, highlights the main visual features that can be based on tracking object. The criteria that influence the choice of the target object-tracking algorithm in real time are defined. However, for real-time tracking with limited computing resources, the choice of the appropriate algorithm is crucial. The choice of visual tracking algorithm is also influenced by the requirements and limitations for the monitored objects and prior knowledge or assumptions about them. As a result of the analysis, the Staple tracking algorithm was preferred, according to the criterion of speed, which is a crucial indicator in the design and development of software and hardware for automated visual support of the object in real-time video stream for various surveillance and security systems, monitoring traffic, activity recognition and other embedded systems.