previous day
next day
all days

View: session overviewtalk overview

09:00-10:30 Session 11: Plenary Session: Keynote
Location: Assembly Hall
Unlocking Value from Ubiquitous Data


Short Bio

Rajendra Akerkar is a professor of Information Technology at Western Norway Research Institute. He leads big data research at the institute. He has 26 years of experience in knowledge representation and reasoning, data science, intelligent systems and requirement engineering. His recent research focuses on application of big data methods to real-world challenges, and social media analysis in a wide set of semantic dimensions. He is coordinating projects funded by European Commission (Horizon 2020 programme) and the Research Council of Norway on different topics: ubiquitous data-driven urban mobility and emergency management. He is actively involved in several international ICT initiatives for more than 18 years.

Keynote Abstract

Data is growing at an alarming rate. This growth is spurred by varied array of sources, such as embedded sensors, social media sites, video cameras, the quantified-self and the internet-of-things. This is changing our reliance on data for making decisions, or data analytics, from being mostly carried out by an individual and in limited settings to taking place while on-the-move and in the field of action. Unlocking value from data directs that it must be assessed from multiple dimensions. Data’s value can be primarily classified as “information,” “knowledge” or “wisdom”. Data analytics addresses such matters as what and why, as well as what will and what should be done. In recent days, data analytics is moving from being reserved for domain experts to becoming necessary for the end-user. However, data availability is both a pertinent issue and a great opportunity for global businesses. In effect, data ubiquity is helping manufacturers, retailers, mobility sector and logistics firms, for example, foster an integrated decision-making environment supporting real-time, information-based business networks. New IT architectures enabled by big data, internet-of-things, cloud computing, and other technologies are helping optimize a business environment with common real-time data, workflow, and alerting capabilities. Business success will be centered around the timely and effective analysis of the large-scale data sets generated by business and sensor networks and the ways in which organizational insights are used to assess and affect potential impacts and risks to their business. This talk will present recent examples from work in our research team on ubiquitous data analytics and open up to a discussion on key questions relating methodologies, tools and frameworks to improve ubiquitous data team effectiveness as well as the potential goals for a ubiquitous data process methodology. Finally, we give an outlook on the future of data analytics, suggesting a few research topics, applications, opportunities and challenges.

10:30-11:00Coffee Break
11:00-12:30 Session 12A: Advances in ICT Research
Location: Assembly Hall
Machine Learning in Estimating of SME Investment Potential in Ukraine
SPEAKER: unknown

ABSTRACT. The aim of this research is to develop a model of SME investment potential assessment, using some of machine learning approaches. The structure of investment potential for SMEs was defined underlining their main characteristic features. It was revealed that the SME investment potential depends on factors of business environment measured by indicators of annual Doing Business Reports developed by World Bank Group. The methodology for assessing the impact of business environment factors on the SMEs investment potential was developed. This methodology is based on the algorithm of machine learning, which is used to design a model for forecasting the investment potential of SMEs. This model allows to determine the degree of influence of parameters on the formation of the SMEs investment potential. It is recommended to use computer language Python for optimization of time and human resources. It provides the opportunity to study the effects of the main drivers (both enhancement and reduction) of SME investment potential aimed at its improvement. The authors examined that estimation results could become the basis for elaboration of recommendations regarding improvement of business environment in Ukraine.

Universal Properties of the General Agent-Based Market Model through Computational Experiments

ABSTRACT. Research goals and objectives: to synthesize and investigate the general heterogeneous agent-based model of competitive market in accordance with agent based computational economics paradigm using a desktop application Model developed during our investigations. Object of research: microeconomics system with heterogeneous agents. Subject of research: heterogeneous agent-based model of market of general view investigated using specially developed desktop application. Research methods: optimization methods, bifurcation analysis, stability analysis, simulation methods, game theory. Results of the research: a market moves from stability to dynamic chaos with an increase in number of firms. The crucial factor which ensures market stability is the adaptive approach of firms’ competitive strategy. If no less than two-thirds of industry output is planned under naive expectations, then the state of dynamic chaos will appear in the market. The profits ratio and quantity outputs ratio of firms remains almost unchanged in chaotic state.

Recognition of Price Discrimination in the Online Sale of Airline tickets
SPEAKER: unknown

ABSTRACT. This paper deals with the recognition of price discrimination types in the online sale of tickets by Ukrainian airline companies. A set of technical tools, such as VPN, are used to create different user profiles in order to check several hypotheses on user features, which can make companies set different prices for one type of tickets. A set of hypotheses is taken from already existing researches on price discrimination. Moreover, a new hypothesis about price discrimination based on geographical location of a customer will be tested.

11:00-12:30 Session 12B: Information Systems: Technology and Applications
Location: 112
The Neuromarketing ICT Technique for Assessing Buyer Emotional Fatigue

ABSTRACT. The typical consumer receives a steady stream of information at purchase process. In the process of perception of this information he/she must not only find necessary data for him, but also process, analyses it, evaluate and weigh the pros and cons, relate it to his own needs, and at the end to make a decision: to buy or not to buy a certain product. All named factors cause consumer’s fatigue, stress and even aggression. In this case, the buyer can make the wrong choice and the quality of his decisions would deteriorate and it is difficult to make a decision about the purchase in such conditions. The research is aimed at assessing the impact of the elements of the process of purchases on the emotional state of the buyer in the urban retailer. The method to assess the emotional fatigue using GSR and HR has been presented. The elements of purchase process and stimuli affecting the buyer were assessed to find overall fatigue in current shop visiting.

The construction of the algorithm study based on the mathematical model of motion
SPEAKER: Maryna Graf

ABSTRACT. The purpose of this work is the construction of the algorithm study a neural network based on the mathematical model of the motion in remotely piloted aircraft systems (RPAS) or unmanned vehicle aircraft (UAV). Information technologies are considered in the UAV control system to provide two-way information transfer between the on-board computer UAV and the operator. The problem arises in the analysis of big amounts of data with information which come from the operator to the on-board computer and in the opposite direction, as well as with a constant change under the influence of external factors. In case of distorted data transmission or collision with obstacles a hang-up and drop of the UAV is possible. Taking into account the rapid growth of UAV usage for civilian and military purposes, the neural network training algorithm for processing the input signal is offered. It can facilitate the task of data analysis and reduce the likelihood of uncertain situations. This algorithm is designed to predict the development of the situation, increase accuracy, the rate of information transfer and its reliability.

Optimization of the activity of operators of critical systems by methods of regulating operational-tempo tension

ABSTRACT. The model of the influence of the available time on the tension of operators and the infallibility of their activity is considered. The productions and methods of solving possible optimization problems are developed to search for ergonomic reserves to increase the efficiency of critical systems.

Fuzzy technology-based cause detection of structural cracks of stone buildings
SPEAKER: unknown

ABSTRACT. The article presents a hierarchical fuzzy rule base for intelligent support of decision making about cause of structural crack of stone building. According to civil engineering practice the causes of structural cracks are classified by the followings diagnoses: static overload; dynamic overload; especial overload; defects of basis and foundation; temperature influence; breach of technological process during the building. Source information needed for decision making is the data of visual investigation of building, icluding simple measuremnts. For decision making 42 input attributes are taking into account. The hierarchical system ties 9 fuzzy knowledge bases, which contain 151 rules in total. Cause detection of the crack is carrying out by max-min fuzzy inference with hierarchical knowledge base. Learning of fuzzy rules by genetic algorithms provided a good concordance between real causes of cracks and modeling results.

12:30-14:00Lunch Break
14:00-15:30 Session 13A: ICT in Education
Location: Assembly Hall
Adaptive Technology for Students' Knowledge Assessment as a Prerequisite for Effective Education Process Management
SPEAKER: Oleh Suprun

ABSTRACT. Despite the rapid development of intellectual systems and their implementation in education process, the knowledge assessment technologies are almost the same as decades ago. This paper presents an intellectual system approach to the students’ knowledge evaluation process, based on adaptive mechanisms development. It is an individual directed systems and it allows to correct the questions complexity levels in real time, depending on the average students’ score and to reduce the examiner’s influence to the evaluation process. Besides, the proposed system allows to consider not only the testing result itself, but also different criteria, like time, used by a student to answer the question. According to this idea, the education assessment should demonstrate not only student’s pure knowledge, but also his skills and ability to use obtained knowledge in different situations. The experimental results that show the system’s effectiveness are presented.


ABSTRACT. The article substantiates the use of dynamic mathematics software as effective means of formation of the functional thinking of pupils, which directly impact on the quality of mathematical education. The constructive approaches to solving mathematical problems by GeoGebra, which reduce the weight of analytical calculations and put forward the need for skills to simulate the desired construction, take into account the dependencies between its parameters, visualize positions of possible results, even "see" the desired function, for which you want to define extreme, are described. The authors use GeoGebra in solving extreme problems using methods based on constructing an empirical graph of the relations between the values and defining of extremum, and on the visualisation of spreadsheets of the values of the empirical function and their analysis. The effectiveness of the proposed approach was tested during 2015-2017 and was experimentally confirmed in the work on the research topic "The use of information technology in education" through the organization of math group works for pupils in the Sumy region. We tracked the overall level of academic achievement and its dynamics. Since the scale had two positions (right/wrong) and the results of educational achievements were not dependent on each other, we used the sign test. The statistical check at the significance level of 0.05 confirmed the positive impact of the group works on the quality of mathematical preparation of pupils.

IoT Information-Communication in the “Smart Cities” Projects

ABSTRACT. In the computing environment of the "smart cities" projects actually a number of complex devices are operating. They are implemented in physical objects connected to the Internet. They, in turn, support a set of diverse communication means and protocols for data exchange. Such system integration ensures efficient supply of a wide range of services, forming due to the combination of both virtual and real physical devices, innovative services formed on the basis of modern information and communication technologies. The authors analyzed existing in modern “smart cities” projects implementations and architectures developed on the basis of the IoT,, generalized them and defined the principles of their complex application with information technologies of other classes such as cloud computing, Big Data, analytical data processing technologies, as well as their integration with information models of heterogeneous processes and systems presented in the form of databases, stores and data spaces. The authors designed and implemented the information-technological platform for telemetric accounting of water, heat, gas and electricity consumption focused on the implementation in the "smart cities" projects. Several generations of digital devices for telemetry data transmission with the ability of connection to the Internet network by means of network interfaces (LANs) and mobile network are used in the base version of the offered platform. The data concerning the implementation in the leading Ukraine technical universities of the specialty "Information Systems and Technologies" majoring in "Internet of Things" with the curricula providing the study of "Internet of things for smart cities" subject are given.

14:00-15:30 Session 13B: PhD Symposium I
Location: 112
Selecting Cloud Service for Healthcare Applications: From Hardware to Cloud Across Machine Learning
SPEAKER: Ivan Kuzlo

ABSTRACT. The paper deals with the process of creating IoT healthcare applications and selection environment to deploy it. The proposition of cloud service based on research of application architecture for healthcare proposed in the paper. It draws our attention to complex architecture with using different sources of medical data like external medical databases, medical equipment and wearable medical and non-medical devices. Much attention is given to us-ing machine learning in process in detection of health problems. Paper de-scribes two levels of machine learning: one for detecting single problems with heals and second for predictions complex reports and providing treat-ment plan based on data from first level. The main emphasis in the choice of cloud service is made on scalability and the ability to create multiple neural networks for processing data.

Analysis of the possibilities of unauthorized access in content management systems using attack trees
SPEAKER: Artem Tetskyi

ABSTRACT. The reasons for attacks on content management systems are considered. Frequent attack scenarios for obtaining unauthorized access are investigated. The method for assessing the probability of a successful attack on a content management system is proposed. Described method uses the attack tree, audit results, source code analysis results, and statistical data. Combinations of basic events for high probability of successful attack are defined. The differences of the proposed method from existing methods of security assessment are shown.

Bank attractiveness evaluation method based on soft computing in the analytic hierarchy process

ABSTRACT. The article offers a methodology for solving the problem of allocating investments to optimize the work of the bank. For this, a hierarchy of criteria is formed based on the use of expert information. After that, a formalized presentation of the problem is given: how to allocate the amount of investment according to the criteria in the optimal way. Due to the fact that the evalua-tion criteria are contradictory, a utility func-tion is built on the basis of the mathematical apparatus of fuzzy sets to solve the problem. The result of the work is a mathematical model for solving the problem of distribu-tion of investments.

An Approach to Forming Dashboards for Business Process Indicators Analysis using Fuzzy and Semantic Technologies
SPEAKER: Andrii Kopp

ABSTRACT. This article considers development of the approach to forming dashboards for business process indicators analysis. The approach idea is based on the dashboard design problem, outlined in analyzed works, which propose a lot of recommendations and best practices, but have a lack of formal approaches to dashboard design definition for specific business process indicators. This study considers application of fuzzy and semantic technologies in order to provide description and analysis of relations between analyzed business process indicators, indicator’s types, and visualization tools. It also considers event log processing of a workflow system, used to execute business processes, which indicators are measured. As a result of implementation and application of the proposed approach, recommendations for a dashboard’s design, based on specific business processes and their performance indicators to be analyzed, can be obtained and implemented. The theoretical essentials, workflow scheme, and early results of the proposed approach are given, future research is outlined.

Towards Requirements Variability in Agile Software Product Line Development

ABSTRACT. This article proposes an approach to support an agile development of software product lines (SPL) using requirements variability management within a Scrum methodology. The main aim is to classify all requirements in 3 types according to the typical SPL-components: core, variable and new ones, and in this way to reduce a sprint backlog for any Scrum iteration. An information base for this approach is structured, its role in common Scrum method is shown, and a conceptual scheme for requirements variability management is proposed.

15:30-16:00Coffee Break
16:00-18:00 Session 14A: ICT in Education
Location: Assembly Hall
How Participation in an Intensive Project can Increase 3d Level Students' Awareness of Entrepreneurship
SPEAKER: unknown

ABSTRACT. Teaching entrepreneurial skills to third level students is becoming increasingly recognised as a necessary skill for them to thrive in the 21st century. Across the E.U. and globally, the teaching of entrepreneurial skills is progressively being incorporated into the core syllabus that students take during their time in third level education. However, despite the efforts of policy makers and educators, entrepreneurship is still not widespread among graduates.

This paper discusses the impact on student attitudes toward entrepreneurship of an E.U. intensive programme (called WalkAbout) that has run for the past two years. In the first year, 28% of the projects were developed further at the request of external stake holders. In the second year, 40% of the projects were developed further. In this paper we discuss the reasons as to why this programme is so successful in motivating students to further develop their projects in an entrepreneurial fashion.

Scientific E-conference as a Tool of Development Students Research Competences: Local Study
SPEAKER: unknown

ABSTRACT. The article offers the systematic approach to the formation and development of research competencies of university students by means of scientific e-conferences. The concept and structure of research competencies are analyzed. The process of formation of research competencies of students in the process of preparing the publication and presentation of a participant in a scientific e-conference is substantiated. Established compliance of the developed competencies of the standard ISTE2016 for students. The indicators of measuring the acquired research competencies are offered. The efficiency of the use of scientific e-conferences as an instrument for the development of research competencies of students is substantiated.

Optimization of training content for future engineers-teachers after the criterion of maximizing the generalized significance
SPEAKER: unknown

ABSTRACT. In the article, the use of a universal recursive model of the content of professional training for formalizing of interdisciplinary connections of the curriculum is proposed. The method of optimizing the curriculum for future engineers-teachers training after the criterion of maximizing the generalized significance considering the connectivity of modules is worked out. The advantage of the proposed method is the development of computer tools, which accelerate the process of optimizing the curriculum for engineer-teachers training after the criterion of maximizing the generalized significance considering the connectivity of modules.


ABSTRACT. IRT profiles scheme using average interpolating polygons. The article deals with the construction characteristics of the aggregate quality of tests using average interpolating linear splines. It was found that the use of splines with free node allows to build an integral characteristic quality of compilation of tests task.

16:00-18:00 Session 14B: PhD Symposium II
Location: 112
Efficient search in short documents

ABSTRACT. This paper presents the first results on the way of building Multimodal Search System. It describes important aspects of building search engines and focuses on the efficient and correct implementation of Okapi-BM25 for k-grams. This extended abstract should be treated as a part of Master's thesis in System Analysis and Control. This work emphasizes the importance of getting high performance in Information Retrieval. Since Okapi-BM25 requires the usage of several general-purpose algorithms, it is important to choose the best version of the existing algorithms in order to squeeze every bit of the hardware.

Software Module Representing Geometry Tasks in Mathematical Systems of Educational Appointment
SPEAKER: Denys Melnyk

ABSTRACT. The article describes the main functional features of mathematical systems for educational purposes. A short description and analysis of existing and most frequently used mathematical systems of educational appointment of geometry are present. The main functional requirements for the software module for representing geometrical tasks in mathematical systems for educational purposes is described

Development of the universal data transfer protocol: mobile solution

ABSTRACT. The paper deals with the process of development of the universal data transfer protocol for IOT projects. It describes the reasons for the mobile solution is needed. All main ways of communication are every IOT system are described. It is spoken in details about different ways to transfer data on the mobile side. WIFI, Bluetooth and Bluetooth Low Energy are noted as main existed protocols. Much attention is given to Bluetooth Low Energy as the main protocol for the universal solution to base on. The method proposed explained with the example of the common healthcare project’s system. The main data buses are defined.

Markov Model of FPGA Resources as a Service Considering Hardware Failures

ABSTRACT. The FaaS architecture is analyzed. Based on information on the structure and principles of the architecture, Markov model is presented, considering possible hardware failures.

Evaluating the Fitness of a Domain Ontology to Formalized Stakeholder Requirements

ABSTRACT. This paper presents the Ph.D. project, by the first author, aimed at developing the methodological and formal approaches, and also software tools for evaluating the fitness of a domain ontology to the formalized stakeholder requirements in a domain. The paper describes the objectives and presents the vision of the solution to be developed as a three-step process including analysis, mapping, and fitness evaluation. The paper also presents the initial steps in finding the relevant techniques that may help attack the outlined problems. The project plans to develop novel approaches and techniques, in particular, for formalized requirements analysis, extending a mapping language, fitness com- putation and visualization. These approaches will be implemented in a software solution that will help knowledge engineers evaluate their results more effi- ciently and effectively and also prioritize their ontology refinement work based on objective fitness measures. The software will be experimentally validated as presented in the paper.

Conceptualizing and Formalizing Requirements for Ontology Engineering

ABSTRACT. This paper presents the PhD project, by the first author, that devel- ops, in frame of the OntoElect methodology, the methods, techniques, and software tools for conceptualizing and formalizing the requirements for engi- neering an ontology in an arbitrary domain. It takes in the terms extracted from a representative collection of high-quality textual documents written by the ex- perts in the target domain and therefore describing this domain. It produces the representative set of the requirements by the knowledge stakeholders as onto- logical fragments conceptualized as UML class diagrams and formalized in OWL+SWRL. The paper presents the vision of the solution and the plan to- wards building it based on the background knowledge and related work in the fields of Conceptual Modeling and Ontology Engineering. It also outlines the plan for experimental evaluation and validation of the solution.

18:00-19:00 Session 15: Poster Session II
Location: Hall
Recommendations based on visual content
SPEAKER: Taras Hnot

ABSTRACT. There is a large number of algorithms to do recommendations for cus- tomers of online platforms. All depends on data sources we have. Widely used approaches are based on transactional data and “ratings” matrixes. For such kind of products as clothes, furniture, hand clocks it is very important to take into account not only some metadata characteristics, but also their “visual look”. Peo- ple always buy clothes not based on only size, sleeves lengths, textile type and so on, but based on how it looks in general. In this thesis, we will show how features vectors of visual content could be extracted and used to enhance recom- mendations.

Development of the Ateb-Gabor filtration method in biometric protection systems

ABSTRACT. The Gabor filter for biometric images has been investigated. Introduced a new Ateb-Gabor filter to improve the quality of fingerprint images. The sequence of filtration and recognition of biometric data is developed. For reliable fingerprint recognition, image correction is required, since interference caused by scanning may distort the lines of the imprints, which creates errors in recognition. The mathematical apparatus of the Ateb-functions provides additional functions for controlling Gabor's filtration, since it has a wider range of filtering options. It has been shown that the use of the Ateb-Gabor filter has a more controlling influence on the image, because in addition there are two parameters of rational numbers that considerably extends the filtration process. The method of filtering images based on the Gabor filter using Ateb-functions is developed. At present, work is being done on the application of a new filter to biometric images, bringing it to a finished software product. A two-dimensional Gabor filter is also developed, which in the future will allow people to recognize their faces.

Mobile Supplement to Determine the Severity of Salmonellosis Disease

ABSTRACT. The paper deals with studying the use of mobile devices while diagnosing in medicine, working out the element of medical students’ electronic teaching and applying the mobile supplement in learning infectious diseases, namely, salmonellosis. The amount of people infected with this disease have been increasing year by year. The complexity of curing the medium serious and serious diseases depends on the timeliness of determining the patient’s condition. The authors have statistically researched how four indices of clinical blood test that affect the course of disease are significant. The supplement for mobile devices that enables the prompt and accurate determination of the salmonellosis disease severity without extra time and financial expenditures has been worked out. It can be used by students in the academic process, by doctors while rendering the first aid to patients, as well as for the independent disease course control by a patient himself / herself.

Classification of Multifractal Time Series by Decision Tree Methods
SPEAKER: unknown

ABSTRACT. Recent scientific studies indicate that many natural, informational and technical time series have self-similar and multifractal properties. The article considers classification task of fractal time series by the methods of machine learning. To classify the series, it is proposed to use the meta algorithms based on decision trees. To construct model fractal time series, binomial stochastic cascade processes derived from the beta distribution were chosen. Classification of time series by the selected methods is carried out. The analysis indicate that the best results are obtained by the methods of random forest and bagging, which use regression trees.

Cryptocurrencies Prices Forecasting with Anaconda Tool Using Machine Learning Techniques
SPEAKER: unknown

ABSTRACT. Research goals and objective: to study criteria which affect the price of cryptocurrency and their usage for the price forecasting using Machine Learning techniques. The object of research: the cryptocurrencies prices. The subject of research: forecasting of most famous cryptocurrency Bitcoin using the most popular Python Data Science Platform - Anaconda. Research Methods are machine learning, data analysis, and multiple regres-sion. Results of the research: a set of criteria which affect the price of the crypto-currency were defined based on the analysis of public information. The cor-rectness of criteria was tested using Machine Learning Multiple Regression algorithms. As a result of simulation experiment through the application using real data from open sources we have found that that combination of criterion can explain 61% of cryptocurrencies prices variation. Difficulty per block for mined cryptocurrencies has the direct dependence on the price of bitcoins. In contrast supply of bitcoins, the general number of mined bitcoins with the price of bitcoins has inverse dependence. The more trust to bitcoins, the more mined cryptocurrency and the less the price of bitcoin.

Automation of assessing the reliability of operator's activities in contact centers that provide access to information resources
SPEAKER: unknown

ABSTRACT. Aautomated systems with many active operators such as contact center of providing internet and television services are researched. To describe the activities the functional structural theory of ergotechnical systems of Prof. A.I. Gubinsky was used. Estimation model of the human-operator reliability were obtained. Computer experiments were conducted. Results will be useful in improving the ergonomic properties of contact-center of providing internet and television services.