Rail Accidents Analysing By Text Mining

Abstract

Death costs and injuries caused by rail accidents have a significant impact on society. As part of our effort to understand the characteristics of past rail accidents, this article presents an analysis of major rail accidents worldwide from 2000 to 2015. The theory of gross sets and related rules are applied to analyze data . collected. The results show that, although most derived rules are unique, some rules deserve to be highlighted. Collision accidents generally result in lower accidents than derailment accidents, and the most common cause of accidents is human error. In addition, most train accidents occur during the summer. These findings can provide train leaders with lessons and resolutions from past accidents, facilitating the creation of a safer rail operating environment around the world. Accident investigation and analysis are essential to strengthen and improve rail safety. Many railway accidents have been caused by degraded human performance and human error, and the tasks of train drivers and markers have remained essentially the same. Although new technologies and equipment have progressively reduced railway operational accidents, no research has been conducted to determine whether the factors influencing rail performance (PRW) attributed to deteriorating human performance have changed. or have remained constant. The results show that the predictive accuracy of accident costs is significantly improved by using features found in text mining and that predictive accuracy is further improved by the use of modern sets. It is important to note that this study also shows through case examples how the results of textual exploration of narratives can improve the understanding of railway accident contributors in an impossible way through a fixed field analysis of accident reports.