Data mining on Chinese train accidents to derive associated rules

Abstract

The costs of fatalities and injuries from train accidents have a great impact on society. As part of our effort to understand the characteristics of past train accidents, this paper presents an analysis of significant train accidents occurring in China from 1954 to 2014. Rough set theory and associated rules approaches are applied in analyzing the collected data. The results show that although most derived rules are unique, some rules are worth noting. Collision accidents generally lead to more casualties than derailment accidents, and the most frequent cause of accidents is human error. Additionally, most train accidents occur during summer. These findings can provide railway leaders with lessons and rules learned from past accidents, thus facilitating the establishment of a safer railway operation environment in China.

An Association Rule Mining Model for the Assessment of the Correlations Between the Attributes of Severe Accidents

“…Furthermore, work zone crashes (Weng et al, 2016), vehicle-pedestrian crashes in Louisiana (Das et al, 2018), and crashes occurring during rainy weather (Das & Sun, 2014) were explicitly focused. Other researchers tried to discover meaningful relationships, patterns, and trends for railway accidents in China (Chen et al, 2017) and in Iran (Mirabadi & Sharifian, 2010). Likewise, Zhang and Liu (2011) established a primary database for marine traffic accidents and employed ARM to determine dependency on the factors behind these accidents.…”

Los accidentes de tránsito desde la perspectiva de la minería de datos. Una revisión de la literatura.

“…El comportamiento de los conductores, por ejemplo, manejo imprudente, desconocer las normas de tránsito, falta de experiencia al volante, o permanecer bajo los efectos del alcohol o sustancias sicotrópicas, fue objeto de estudio a través de algoritmos como como Reglas de Asociación, Árboles de regresión, Árboles de clasificación, Random Forest y Clustering [47][48][49] [56][57]. El estudio de Chen et al [41] analizó los datos históricos ferroviarios y mediante Reglas de Asociación, identificó como motivo principal de los accidentes el error humano y causas externas como el clima; además se evidencio que los accidentes de colisión causan más víctimas que los accidentes de descarrilamiento. En la investigación de Pakgohar et al [58] usaron la minería de datos para analizar la base de datos de la policía de tránsito a través de regresión logística multinomial y Árboles de Regresión y clasificación para predecir la gravedad de los accidentes de tráfico; los resultados mostraron además la incidencia de factores humanos como el permiso de conducir y el uso del cinturón en la gravedad de los accidentes viales.…”

Quantitative causal analysis of mainline passenger train accidents in the United States

“…Chen et al. 66 used the Associated Rule and other data mining techniques to analyze Chinese passenger train accidents. Britton et al.…”

“…33,37,43,46,84 For passenger trains, casualties are another important metric of accident severity. 62,66,68–71 In this research, casualties are defined as the total number of onboard passenger and crew injuries and fatalities, and were used as the primary severity indicator.…”