The Quality of Software Metrics
Vol. 11 No. 1 (2021): JITA – APEIRON Dragoljub Pilipović, Dejan Simeunović The Quality of Software Metrics Original scientific paper DOI:https://doi.org/ 10.7251/JIT2101061P Download Article PDF Abstract This paper discusses the definition, types, characteristic and construction of software metrics in the field of software development. Finally, an overview is given regarding the use of a software tool in software development in relation to software metrics in the field of banking. Keywords: software engineering, software metrics, SEI, CISQ, ISO/IEC, banking. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators.
Software Application Development Using ContainerTechnology
Vol. 11 No. 1 (2021): JITA – APEIRON Dražen Marinković, Velimir Kojić, Zoran Ž. Avramović Software Application Development Using Container Technology Original scientific paper DOI:https://doi.org/10.7251/JIT2101054M Download Article PDF Abstract The paper will give an example and an overview of how we can set up and maintain web applications using a Docker. We will define what Docker is, what containers are and how to use them. Developers often find themselves in a situation where their program works properly on a computer in the laboratory environment in which the application was developed, but after installing the program on the production server, the program does not work as expected. In such circumstances, it is difficult for a programmer to determine why a program is not working. Docker solves this problem by placing applications and virtual containers that run on the same operating system. Keywords: Docker, Devops,Virtual machine, Container technology. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators.
Four-Layered Structure of E-Government Systems
Vol. 11 No. 1 (2021): JITA – APEIRON Dalibor P. Drljača, Dušan Starčević, Siniša Tomić Four-Layered Structure of E-Government Systems Original scientific paper DOI:https://doi.org/10.7251/JIT2101044D Download Article PDF Abstract The structure of the e-government systems plays a vital role for provision of quality of e-services offered. These systems are quite complex deploying the most advanced technologies and developed and rich countries minimised this complexity with centralised systems. However, the less developed and countries with limited financial support are creating distributed and decentralised systems trying to keep the pace with more developed in provision of e-government services. The common identifier for both types of the systems is four-layered structure, which provides quality of service provision. This paper discusses the fourlayered structure of e-government systems on cases of Estonia, Serbia and Bosnia and Herzegovina. The four-layered structure was found as the quality solution for distributed and decentralised e-government systems. Keywords: e-government, quality, structure, four-layer, X-tee, X-road. Introduction Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators.
Making Decisions in Monitoring by Using Decision-MakingMethod, Knowledge Bases and New it Solutions
Vol. 11 No. 1 (2021): JITA – APEIRON Jefto Džino, Branko Latinović, Zoran Ž. Avramović Making Decisions in Monitoring by Using Decision-Making Method, Knowledge Bases and New it Solutions Original scientific paper DOI:https://doi.org/ 10.7251/JIT2101033D Download Article PDF Abstract In this paper we deal with decision-making processes in monitoring with the use of new technological solutions. This is an area where decision-makers in monitoring face a large number of different challenges and need appropriate specific knowledge. We give an example of a method for making complex decisions. Here we propose the application of the semantic web and knowledge bases that can provide decision-makers with a quick access to the necessary knowledge in the decision-making process. To update some of the knowledge we will use the Protégé editor, an open source platform. Our goal is not to update all the necessary knowledge needed by those who make decisions in monitoring, but only to propose a new concept to their faster fullfilment and more efficient use. Keywords: monitoring, decision-making, knowledge base, efficient use of knowledge, methods, facilitation, business intelligence. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators.
Implementation of User Authentication System in SmartHospitals Useful in the Age of the Covid-19 Pandemic
Vol. 11 No. 1 (2021): JITA – APEIRON Nenad Badovinac Implementation of User Authentication System in Smart Hospitals Useful in the Age of the Covid-19 Pandemic Original scientific paper DOI:https://doi.org/10.7251/JIT2101024B Download Article PDF Abstract The security system for authentication and user records in a smart hospital is part of an integrated security system consisting of various authentication devices. The security system should be adapted to different characteristics of users, their user processes, but also to periods when the possibility of infection is increased due to a virus pandemic and contamination during multiple touches of different persons on authentication devices. The use of gloves and a medical face mask during a pandemic limits biometric scanning of fingerprints and facial images. During a virus pandemic, some authentication devices have limitations that need to be considered when creating an integrated security system that will have the purpose of securing doctors, staff, patients, information, and things in a smart hospital. In this paper, the parameters on the basis of which it is possible to design an optimally integrated security system are recommended. Keywords: smart hospital, access control, user authentication, virus pandemic. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators.
Impact of Pointing Errors on the Performances of DoubleRician FSO Channels
Vol. 11 No. 1 (2021): JITA – APEIRON Stefan Panić, Negovan Stamenković Impact of Pointing Errors on the Performances of Double Rician FSO Channels Original scientific paper DOI:https://doi.org/10.7251/JIT2101017P Download Article PDF Abstract In this paper we will propose new analytically traceable probability density function (PDF) model for free space optics (FSO) turbulence, obtained as a generalization of double Ricean turbulence model, that encompasses both large-scale and smallscale turbulence eddy effects along by taking into account performance decreasing influence of misalignment introduced through boresight pointing error model. Consequently, after delivering the closed-form expressions for the newly introduced double FSO model, we obtain the analytical expressions for the bit error rate (BER) performance for the Double Rician distribution affected by misalignment. Numerical results will show the impact of system parameters on FSO link performance and we will provide full performance analysis. © 2021. Keywords: free space optics (FSO), atmospheric turbulence, pointing error, bit error rate (BER). Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators.
Arduino Sensor Integrated Drone for Weather Indices: APrototype for Pre-flight Preparation
Vol. 11 No. 1 (2021): JITA – APEIRON Theodore Karachalios, Dimitris Kanellopoulos, Fotis Lazarinis Arduino Sensor Integrated Drone for Weather Indices: A Prototype for Pre-flight Preparation Original scientific paper DOI:https://doi.org/10.7251/JIT2101005K Download Article PDF Abstract Commercial weather stations can effectively collect weather data for a specified area. However, their ground sensors limit the amount of data that can be logged, thus failing to collect precise meteorological data in a local area such as a micro-scale region. This happens because weather conditions at a micro-scale region can vary greatly even with small altitude changes. For now, drone operators must check the local weather conditions to ensure a safe and successful flight. This task is often a part of pre-flight preparations. Since flight conditions (and most important flight safety) are greatly affected by weather, drone operators need a more accurate localized weather map reading for the flight area. In this paper, we present the Arduino Sensor Integrated Drone (ASID) with a built-in meteorological station that logs the weather conditions in the vertical area where the drone will be deployed. ASID is an autonomous drone-based system that monitors weather conditions for pre-flight preparation. The operation of the ASID system is based on the Arduino microcontroller running automatic flight profiles to record meteorological data such as temperature, barometric pressure, humidity, etc. The Arduino microcontroller also takes photos of the horizon for an objective assessment of the visibility, the base, and the number of clouds. Keywords: Unmanned Aerial Vehicles; Drones; Arduino; Sensor; Weather data; Flight Level. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators.
Application of Information Technologiesin New Forms of Teaching Processes
Vol. 11 No. 2 (2021): JITA – APEIRON Slavojka Lazić, Tijana Talić Application of Information Technologies in New Forms of Teaching Processes Original scientific paper DOI:https://doi.org/10.7251/JIT2102131L Download Article PDF Abstract Educating young people is one of the most beautiful and humane vocations. The transfer of knowledge to young people and their introduction into the world of science requires a well-prepared and organized educator. The application of information technologies in education has become an everyday tool, so that its role in the educational process has come to the fore during the last two years. The Covid 19 pandemic brought new challenges to the education system in Republika Srpska. The best solutions for the teaching process were sought. At the beginning, the classes were conducted at a distance, last year in classrooms with classes shortened to 20 minutes, and this year the classes again last 45 minutes, with respect to protection measures. The paper will show how the students coped with all these changes and how much their knowledge of information technology helped them in all this. The research includes an analysis of data collected by a survey of high school students and refers to their attitudes towards the performance of the teaching process in the past few years. Keywords: education, teaching process, IT. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators.
Architecture of GIS Solutions for Detection andDevelopment of Wildfire Database
Vol. 11 No. 2 (2021): JITA – APEIRON Saša Ljubojević, Zoran Ž. Avramović Architecture of GIS Solutions for Detection and Development of Wildfire Database Original scientific paper DOI:https://doi.org/10.7251/JIT2102123L Download Article PDF Abstract This research paper presents organization of the business environment for work with geographic information systems (GIS) which are based on open source. The solution is completely open source: operating system, working environment and supporting apps. The architecture consists of: server, workstations, mobile devices and sensors. Software packages for each architecture segment will be displayed. The goal is to achieve a complete business environment for work with open source GIS, thus minimizing the costs of system development and maintenance. The illustrated example shows the possibility of applying GIS within a forestry company, in the field of wildfire monitoring and data collection and registering the possibility of wildfire occurrence using IoT. Keywords: GIS, open source, IoT, wildfires, wildfire detection. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators.
Accelerated Process of Digital Transformation – TheImpact and Consequences of Covid-19
Vol. 11 No. 2 (2021): JITA – APEIRON Mihajlo Travar, Igor Dugonjić, Saša Ristić Accelerated Process of Digital Transformation – The Impact and Consequences of Covid-19 Original scientific paper DOI:https://doi.org/10.7251/JIT2102116T Download Article PDF Abstract Due to the current pandemic caused by the COVID-19 virus, the world is changing rapidly along with digital technologies that transform every aspect of life, society and the economy. To prevent a complete collapse and suspension of all business processes, companies were forced to organize remote work, i.e. workers perform their daily work activities from their homes. The situation in which the world is currently in clearly indicates that digital transformation is something that should be a priority. Digital transformation is changing the way of doing and developing the business, new opportunities for economic progress in the public and private sectors. It allows companies to survive and focus on innovation, increasing their competitiveness. We can say with certainty that digital transformation means much more than complete integration of digital technologies. It also means digitalization and business processes and models automation, marketing, sales, digital purchase, Big Data, and related processes, and is based on five different areas, which include customers, competition, value, innovation and data. Keywords: Digital transformation, Information technology, Business process, Impact, Pandemic Covid-19. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators. Vol. 26 No. 2 (2023): JITA – APEIRON Igor Shubinsky, Alexey Ozerov Application of Artificial Intelligence Methods for the Prediction of Hazardous Failures Original scientific paper DOI: https://doi.org/10.7251/JIT2302061S Download Article PDF Abstract The availability of real-time data on the state of railway facilities and the state-of-the art technologies for data collection and analysis allow transition to the fourth generation maintenance. It is based on the prediction of the facility functional safety and dependability and the risk-oriented facility management. The article describes an approach to assessing the risks of hazardous facility failures using the latest digital data processing methods. The implementation of this approach will help set maintenance objectives and contribute to the efficient use of resources and the reduction of railway facility managers’ expenditures. Keywords: predictive analysis, maintenance, functional safety, Big Data, Data Science, risk indicators.