Online evaluation of recommender system with MovieLens dataset
Vol. 6 No. 1 (2018): JITA – APEIRON Asmir Handžić Online evaluation of recommender system with MovieLens dataset Original scientific paper DOI: https://doi.org/10.7251/JIT16020H Download Article PDF Abstract The purpose of this paper is to explore the advantages of recommender systems based on the matrix factorization in respect to classical first neighbor recommender systems to real users through A/B test, as these studies are more significant. The results presented in this paper confirms the hypothesis that the recommender systems based on the models of matrix factorization are superior in relation to classical nearest-neighbor recommender systems. Keywords: Recommender systems, online evaluation, MovieLens, A/B test. 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.
VirtualSign Translator as a Base for a Serious Game
Vol. 6 No. 1 (2018): JITA – APEIRON Paula Maria de Sá VirtualSign Translator as a Base for a Serious Game Original scientific paper DOI: https://doi.org/10.7251/JIT16012S Download Article PDF Abstract The goal of this paper is to present the development of a game aimed at making the process of learning sign language enjoyable and interactive, using the VirtualSign Translator. This game aims to make the process of learning sign language easier and enjoyable. In the game the player can control an avatar and interact with several objects and Non-player characters in order to obtain signs. Through the connection with VirtualSign Translator the data gloves and Kinect support, this interaction and the gestures can then be represented by the character. This allows for the user to visualize and learn or train the various existing configurations of gestures. To improve the interactivity and to make the game more interesting and motivating, several checkpoints were placed along game levels. The game has as an inventory system where the signs are kept and can be checked allowing for the user to visualize and learn or train the various existing configurations of gestures. A High Scores system was also created, as well as a History option, to ensure that the game is a continuous and motivating learning process. Keywords: VirtualSign, Serious Games, Portuguese Sign Language, Kinect. 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.
Cluster formation techniques in hierarchical routing protocols for Wireless Sensor Networks
Vol. 6 No. 1 (2018): JITA – APEIRON Goran Popović, Goran Đukanović Cluster formation techniques in hierarchical routing protocols for Wireless Sensor Networks Original scientific paper DOI: https://doi.org/10.7251/JIT16005P Download Article PDF Abstract Wireless sensors are an irreplaceable link in the chain of global networking today. There is almost no area of human activity where they are still not used, and they will be used in the near future almost everywhere. Wireless sensor networks consist of a large number of sensor nodes that are arranged (usually randomly) in an area. The main problem is the limited power supply. Sensors are usually powered by the battery which is not possible to replace. The lifetime of the network depends on the duration of battery power of sensor nodes. The largest part of the consumed energy goes for communication with the rest of the network. Therefore, the selection of good routing protocol is essential for the long life-span of the network. There are a large number of proposed protocols and they can be divided into several groups, depending on the approach to the problem. In this paper we present a family of hierarchical protocols, their common features and specific implementation, we will present advantages and disadvantages as well as possible directions of further development. Keywords: LEACH, CH, Clustering, Wireless Sensor Network. 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.
The Impact of Felder’s Learning Styles Index on Motivation and Adoption of Information Through E-Learning
Vol. 6 No. 2 (2018): JITA – APEIRON Željko Pekić, Srđan Jovanovski, Nađa Pekić The Impact of Felder’s Learning Styles Index on Motivation and Adoption of Information Through E-Learning Original scientific paper DOI: https://doi.org/10.7251/JIT1602093P Download Article PDF Abstract In this paper, we examined the nature and distribution (direction and intensity) of motivation for using e-learning, focusing the connection between the independent variables on one side and the Felder’s learning style on the other. The most relevant information that we wanted to examine and present is the individual ways of the respondents in adopting the same material. We were also interested in the ways to technically adjust the information delivery. The results confirm the statistical significance of the initial idea. Keywords: e-Learning, motivation, learning style, placement of materials, adoption of information. 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.
Using open source software for web application security testing
Vol. 6 No. 2 (2018): JITA – APEIRON Ksenija Živković, Ivan Milenković, Dejan Simić Using open source software for web application security testing Original scientific paper DOI: https://doi.org/10.7251/JIT1602086Z Download Article PDF Abstract Web applications are a standard part of our everyday lives. Their purpose can vary significantly, from e-banking to social networks. However, one thing is similar – users have generally high expectations from different web applications. To assure such high expectations, proper web application testing is necessary. Non-functional testing is an important part of web application testing. As technology advances and requirements become more complex, the importance of non-functional application aspects becomes even greater. It is necessary to identify non-functional requirements of web applications which are important to users, implement those requirements and test them. Keywords: non-functional testing, web applications, testing tools. 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.
Frameworks for Audit of an Information System in Practice
Vol. 6 No. 2 (2018): JITA – APEIRON Dalibor Drljača, Branko Latinović Frameworks for Audit of an Information System in Practice Original scientific paper DOI: https://doi.org/10.7251/JIT1602078D Download Article PDF Abstract The IT function became the backbone of the company and the central driving force of the entire operations of an organization. Modern electronic commerce is very dependent on the quality of information system supported with information technology. Safety aspects of business and electronic transactions transfer (Internet-supported), particularly in the banking sector, require a more complex audit of the organization, both financial and the information system audit. This paper presents the basic and in practice most frequently applied standards and guidelines for checking of security controls in information systems. The work presents the COBIT and ITIL as the two most prevalent methodologies for quality audit of information systems with the presentation of two ISO 27000 series of standards on information security. Keywords: audit frameworks, IT audit, IT Governance, COBIT, ITIL, ISO27000. 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.
Biometric System To Secure The Internet Of Things
Vol. 6 No. 2 (2018): JITA – APEIRON Olja Latinović Biometric System To Secure The Internet Of Things Original scientific paper DOI: https://doi.org/10.7251/JIT1602073L Download Article PDF Abstract Today, Internet of Things (IoT) is becoming part of a diverse organization, from academic to large enterprises. Also, we use IoT in our daily lives like home appliances, security monitoring such as baby, smoke detectors, health product measure exercise, traffic systems, industrial uses, etc. Biometric is an important segment of IoT, because it proves user’s identity. Biometric security plays the main role in IoT. This paper presents how biometric system secures the Internet of Things and architecture proposal based on one system that connects biometric system and components of Internet of Things. Keywords: biometrics, Internet of Things, security, authentication. 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.
MANET vs. ZigBee: Some simulation experiments at the seaport environment
Vol. 6 No. 2 (2018): JITA – APEIRON Sanja Bauk, Diego Garcia Gonzalez, Anke Schmeink, Zoran Ž Avramović MANET vs. ZigBee: Some simulation experiments at the seaport environment Original scientific paper DOI: https://doi.org/10.7251/JIT1602063B Download Article PDF Abstract The paper presents the results of some OPNET simulation experiments realized with an aim to benchmark MANET and ZigBee networks’ performances at the seaport environment. The MANET is formed among workers’ and supervisors’ personal digital assistants (PDAs). On the other side, the ZigBee is established between end-nodes or employees’ body central units (BCUs), which collect signals from several active and passive devices embedded into ID badges and personal protective equipment (PPE) pieces; several moving and fixed routers; and the coordinator mounted at the appropriate seaport location. The simulation experiments are realized over the layout of the Port of Bar (Montenegro) container and general cargo terminal by taking into account the real number of workers and supervisors engaged at the terminal per each shift. This research work should give an insight to the seaport’s managers and stakeholders into some advantages and disadvantages of these two considered wireless networks’ schemes, and to motivate them to provide conditions for implementing these or similar on seaport and backend info-communication solutions for uprising the level of occupational safety and overall seaport’s environmental management system. Keywords: MANET, ZigBee, seaport, occupational safety. 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.
Time Complexity Analysis of the Binary Tree Roll Algorithm
Vol. 6 No. 2 (2018): JITA – APEIRON Adrijan Božinovski, George Tanev, Biljana Stojčevska, Veno Pačovski, Nevena Ackovska Time Complexity Analysis of the Binary Tree Roll Algorithm Original scientific paper DOI: https://doi.org/10.7251/JIT1602053B Download Article PDF Abstract This paper presents the time complexity analysis of the Binary Tree Roll algorithm. The time complexity is analyzed theoretically and the results are then confirmed empirically. The theoretical analysis consists of finding recurrence relations for the time complexity, and solving them using various methods. The empirical analysis consists of exhaustively testing all trees with given numbers of nodes and counting the minimum and maximum steps necessary to complete the roll algorithm. The time complexity is shown, both theoretically and empirically, to be linear in the best case and quadratic in the worst case, whereas its average case is shown to be dominantly linear for trees with a relatively small number of nodes and dominantly quadratic otherwise. Keywords: Binary Tree Roll Algorithm, time complexity, theoretical analysis, empirical analysis. 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.
COMPARISON OF PERCEIVED INTERACTIVITY MEASURES OF ACTUAL WEBSITES INTERACTIVITY
Vol. 7 No. 1 (2018): JITA – APEIRON Velimir Štavljanin, Milica Jevremović COMPARISON OF PERCEIVED INTERACTIVITY MEASURES OF ACTUAL WEBSITES INTERACTIVITY Original scientific paper DOI: https://doi.org/10.7251/JIT1701042S Download Article PDF Abstract Interactivity is a concept of enormous importance for digital marketing. It was recognized as a key feature of website, a hub of all digital marketing activities. But, almost all interactivity measures were conceptualized one or two decades ago. In the meantime, technological novelties changed the face of websites. Also, a number of interactivity features increased exponentially. Those changes had a huge impact on practice and could influence user’s perception of interactivity. Aim of this paper is to explore whether several selected existing measures of perceived interactivity could cope with those changes. Paper reports a study in which two websites of low and high interactivity were developed and in an experimental setting as stimuli used to test three perceived interactivity measures. Results show that all measures estimated perceived interactivity of a high interactivity website better than of a low interactivity website. Also, results show that particular dimensions of a model could be used to estimate overall interactivity. Keywords: website interactivity, perceptual interactivity, actual interactivity, interactivity measures, website design. 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.