Prva međunarodna naučna konferencija

BEZBJEDNO

URBANO

MOBILNO

Vol. 10 No. 2 (2020): JITA - APEIRON

Željko Račić, Zoran Ž. Avramović, Đuro Mikić

Nonlinear Prediction Models in Data Analysis

Original scientific paper

DOI:https://doi.org/10.7251/JIT2002106R

Abstract

The modern entrepreneurial sensibility of the company’s business implies directing the right information to the appropriate parts of the company at the right time. That is why it is necessary to digitalize processes as much as possible and make the organization “intelligent”, and its human resources, to the greatest extent, the knowledge workers. The application of neural networks, i.e. nonlinear prediction models, enables systematic analysis of data in the function of evaluating the behavior of the system. Neural networks are a powerful tool, especially for forecasting trends and forecasting based on historical data. The grouping method, i.e., the k-mean value algorithm, is used as a precursor to neural networks.

Keywords: neural networks, Back-propagation neural network, grouping methods, k-mean algorithm.

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

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

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.