Using visual analytics to make sense of railway Close Calls

In the big data era, large and complex data sets will exceed scientists’ capacity to make sense of them in the traditional way. New approaches in data analysis, supported by computer science, will be necessary to address the problems that emerge with the rise of big data. The analysis of the Close Call database, which is a text-based database for near-miss reporting on the GB railways, provides a test case. The traditional analysis of Close Calls is time consuming and prone to differences in interpretation. This paper investigates the use of visual analytics techniques, based on network text analysis, to conduct data analysis and extract safety knowledge from 500 randomly selected Close Call records relating to worker slips, trips and falls. The results demonstrate a straightforward, yet effective, way to identify hazardous conditions without having to read each report individually. This opens up new ways to perform data analysis in safety science.

[1]  Guy H. Walker,et al.  WESTT (workload, error, situational awareness, time and teamwork): an analytical prototyping system for command and control , 2008, Cognition, Technology & Work.

[2]  Hadley Wickham,et al.  A Cognitive Interpretation of Data Analysis , 2014 .

[3]  Maria Grazia Gnoni,et al.  Near-miss management systems: A methodological comparison , 2012 .

[4]  Nicolas Dugué,et al.  Identifying the community roles of social capitalists in the Twitter network , 2014, 2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014).

[5]  Chris Harrison,et al.  Big Data Risk Analysis for rail safety , 2015 .

[6]  L. Freeman.  Centrality in social networks conceptual clarification , 1978 .

[7]  A. Tversky,et al.  Judgment under Uncertainty: Heuristics and Biases , 1974, Science.

[8]  Ben Shneiderman,et al.  Readings in information visualization - using vision to think , 1999 .

[9]  Mark Newman,et al.  Networks: An Introduction , 2010 .

[10]  Mathieu Bastian,et al.  Gephi: An Open Source Software for Exploring and Manipulating Networks , 2009, ICWSM.

[11]  Melanie Tory,et al.  Human factors in visualization research , 2004, IEEE Transactions on Visualization and Computer Graphics.

[12]  Roel Popping,et al.  Knowledge Graphs and Network Text Analysis , 2003 .

[13]  Yiannis Kompatsiaris,et al.  Community detection in Social Media , 2012, Data Mining and Knowledge Discovery.

[14]  工業講話会.  安全装置工業事故豫防法 = Industrial accident prevention , 1918 .

[15]  A. Tversky,et al.  The framing of decisions and the psychology of choice. , 1981, Science.

[16]  Ruud H. Teunter,et al.  Safety and Reliability of Complex Engineered Systems , 2015 .

[17]  Daniel A. Keim,et al.  Visual Analytics: Definition, Process, and Challenges , 2008, Information Visualization.

[18]  James P. Bliss,et al.  What are close calls? A proposed taxonomy to inform risk communication research , 2014 .

[19]  Carl Macrae,et al.  Close Calls: Managing Risk and Resilience in Airline Flight Safety , 2014 .

[20]  Miguel Figueres-Esteban,et al.  Learning from text-based close call data , 2016 .

[21]  W. Cleveland,et al.  Graphical Perception: Theory, Experimentation, and Application to the Development of Graphical Methods , 1984 .

[22]  Erik Hollnagel,et al.  Barriers And Accident Prevention , 2004 .

[23]  Roel Popping,et al.  Computer-assisted text analysis , 2000 .

[24]  Philipp Drieger,et al.  Semantic Network Analysis as a Method for Visual Text Analytics , 2013 .

[25]  Neville A Stanton,et al.  Cognitive compatibility of motorcyclists and car drivers. , 2011, Accident; analysis and prevention.

[26]  Ewan Klein,et al.  Natural Language Processing with Python , 2009 .

[27]  Jean-Loup Guillaume,et al.  Fast unfolding of community hierarchies in large networks , 2008, ArXiv.

[28]  Dmitry Paranyushkin,et al.  Identifying the Pathways for Meaning Circulation using Text Network Analysis , 2011 .