A Study of Risk Relevance Reasoning Based on a Context Ontology of Railway Accidents

Abstract

With the application of risk management and accident response in the railway domain, risk detection and prevention have become key research topics. Many dangers and associated risk sources must be considered in collaborative scenarios of heavy‐haul railways. In these scenarios, (1) various risk sources are involved in different data sources, and context affects their occurrence, (2) the relationships between contexts and risk sources in the accident cause mechanism need to be explicitly defined, and (3) risk knowledge reasoning needs to integrate knowledge from multiple data sources to achieve comprehensive results. To express the association rules among core concepts, this article constructs two ontologies: The accident‐risk ontology and the context ontology. Concept analysis is based on railway domain knowledge and accident analysis reports. To sustainably integrate knowledge, an integrated evolutionary model called scenario‐risk‐accident chain ontology (SRAC) is constructed by introducing new data sources. The SRAC is integrated through expert rules between the two ontologies, and its evolution process involves new knowledge through a new risk source database. After three versions of the upgrade process, potential risk sources can be mined and evaluated in specific contexts. To evaluate the risk source level, a long short‐term memory (LSTM) neural network model is used to capture context and risk text features. A model comparison for different neural network structures is performed to find the optimal evaluation results. Finally, new concepts, such as risk source level, and new instances are updated in the context‐aware risk knowledge reasoning framework.

A novel textual track‐data‐based approach for estimating individual infection risk of COVID‐19

“…Based on an early effort made by Ginsberg et al (2009), data analytics have played an important role in risk identification and assessment. Recently, with the development of text-mining technology (Cao et al, 2020;Feldman & Hart, 2018), analysis of massive amounts of textual data containing valuable risk information has been introduced into many fields of risk management, such as finance (Ronnqvist & Sarlin, 2014;Wei et al, 2019a) and energy (Li et al, 2018;Wei et al, 2019b), as well as health and safety (Ajayi et al, 2019). The use of textual data has enriched quantitative risk measures and improved the effectiveness of risk management.…”

Classification Trees in the Assessment of the Road–Railway Accidents Mortality

“…Railroad transport safety is an important factor taken into account when evaluating the operation of this branch of transport. Due to the importance, scope and consequences for society and economy of the low level of traffic safety, it is the subject of many studies and analyses and is systematically evaluated [1][2][3]. According to the latest annual reports/statistics from the International Union of Railways (UIC), the number of railroad accidents is decreasing [4,5].…”

Project portfolio risk analysis with the consideration of project interdependencies

“…There are many existing network research methods for risk assessment, such as artificial neural networks (Paltrinieri et al, 2019), social network analysis (Yu et al, 2017) and Bayesian networks (BNs) (Cao et al, 2020). An artificial neural network is a numerical and mathematical model that mimics the neural structure of the human brain, requires considerable data to train and cannot visualize the causal relationship between risks.…”

“…BN can model and analyze the interdependencies among risks increased by the complexity associated with PPs (Fang and Marle, 2011). As a result, in our study, a BN is developed to calculate the risk probability and diagnose the cause of different PPR scenarios (Cao et al, 2020). Nevertheless, due to the high uncertainty and insufficient data in typical PPR analysis, it is difficult for experts to make judgments with crisp and precise probability (Flores et al, 2011;Wang and Chen, 2017).…”