R-Language Based Analytics System For Monitoring Railway Disasters

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    The everyday workplace of railroads is backbreaking and frequently includes high-hazard activities. These operations has its impact on railways crew and public people who lives along the town and cities. To avoid the employees and public's exposure to risk, railway companies uses safety training programs[1] , advanced technology concepts like data analytics and machine learning to analyze about frequent accident occurring zones and safety precautions to be taken in advance. So in this paper we are proposing an visualization model for identifying the frequent occurrence of railway accident zones so as to take enough precautions to avoid them. Here we will be collecting the data on the frequently occurring railway accidents and the causes for it. After the data is been collected, we will be analyzing the data and presenting the information about most frequent and less frequent accident prone areas using visualization tools which provides the clear picture of incidents so as certain precautions or counter measures will be taken at proper times to minimize railway accidents. The results of the analysis done can be used to make and communicate decisions about accidents so as to minimize them.


  • Keywords

    railways, data analytics, visualization ,machine learning, R-language

  • References

      [1] Lira W.P. Alves, R. ; Costa, J.M.R. ; Pessin, G. ; Galvao, L. ; Cardoso, A.C. ; De Souza, C.R.B.,”A Visual-Analytics System for Railway Safety Management”,Computer Graphics and Applications, IEEE (Volume:34, Issue: 5 ),26th July 2014,pp. 52-57.

      [2] https://en.wikipedia.org/wiki/List_of_Indian_rail_accidents#2017

      [3] https://ppiaf.org/sites/ppiaf.org/files/documents/toolkits/railways_toolkit/PDFs/RR 20Toolkit 20EN 20New 202017 2012 2027 20CASE6 20INDIA.pdf

      [4] http://www.mospi.gov.in/statistical-year-book-india/2016/188

      [5] https://analyticsindiamag.com/indian-railways-embrace-data-analytics-monetize-available-data/

      [6] Sergio Saponara, Luca Fanucci, Fabio Bernardo, Alessandro Falciani, "Predictive Diagnosis of High-Power Transformer Faults by Networking Vibration Measuring Nodes With Integrated Signal Processing", Instrumentation and Measurement IEEE Transactions on, vol. 65, pp. 1749-1760, 2016, ISSN 0018-9456.




Article ID: 20238
DOI: 10.14419/ijet.v7i4.6.20238

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.