Identifying characteristics that impact motor carrier safety using Bayesian networks

A Dynamic Bayesian Network model to evaluate the availability of machinery systems in Maritime Autonomous Surface Ships

With their complex structure, multiple failure modes and lack of maintenance crew, the safety problem of Maritime Autonomous Surface Ships' (MASS) machinery systems are becoming an important research topic. The present study presents an availability model for ship machinery systems incorporating a maintenance strategy based on Dynamic Bayesian Networks (DBN). First, the availability of conventional ship machinery systems is evaluated and used as a benchmark based on the configuration and planned maintenance strategy. Secondly, the availability of MASS machinery systems is compared to the benchmark, before the introduction of any changes to the ship's configuration and planned maintenance strategy. Finally, the availability improvement strategies, including redundant designs and planned maintenance strategies at port, are proposed based on sensitivity analysis and planned maintenance cost minimization. To exemplify the model's application, a case study of a cooling water system is explored. Based on a sensitivity analysis using the model, it is possible to decide which components need to be redundant. Different redundancy designs and corresponding planned maintenance strategies can be adopted to meet the availability demand. It is also shown that redundancy and enhanced detection capabilities reduce much of the planned maintenance cost. This framework can be used in the early design stages to determine whether the MASS machinery systems' availability is at least equivalent to that of conventional ships, and has certain reference significance for redundant configuration designs and MASS planned maintenance strategy schedule.

Bayesian network predicted variables for good neurological outcomes in patients with out-of-hospital cardiac arrest

Out-of-hospital cardiac arrest (OHCA) is linked to a poor prognosis and remains a public health concern. Several studies have predicted good neurological outcomes of OHCA. In this study, we used the Bayesian network to identify variables closely associated with good neurological survival outcomes in patients with OHCA. This was a retrospective observational study using the Japan Association for Acute Medicine OHCA registry. Fifteen explanatory variables were used, and the outcome was one-month survival with Glasgow-Pittsburgh cerebral performance category (CPC) 1-2. The 2014-2018 dataset was used as training data. The variables selected were identified and a sensitivity analysis was performed. The 2019 dataset was used for the validation analysis. Four variables were identified, including the motor response component of the Glasgow Coma Scale (GCS M), initial rhythm, age, and absence of epinephrine. Estimated probabilities were increased in the following order: GCS M score: 2-6; epinephrine: non-administered; initial rhythm: spontaneous rhythm and shockable; and age: <58 and 59-70 years. The validation showed a sensitivity of 75.4% and a specificity of 95.4%. We identified GCS M score of 2-6, initial rhythm (spontaneous rhythm and shockable), younger age, and absence of epinephrine as variables associated with one-month survival with CPC 1-2. These variables may help clinicians in the decision-making process while treating patients with OHCA.

A data-driven Bayesian network for probabilistic crash risk assessment of individual driver with traffic violation and crash records

In recent years, individual drivers' crash risk assessments have received much attention for identifying high-risk drivers. To this end, we propose a probabilistic assessment method of crash risks with a reproducible long-term dataset (i.e., traffic violations, license, and crash records). In developing this method, we used 7.75 million violations and crashes of 5.5 million individual drivers in Seoul, South Korea, from June 2013 to June 2017 (four years). The stochastic process of the Bayesian network (BN), whose structure is optimized by tabu-search, successfully evaluates individual drivers' crash and violation probability. In addition, the cluster analysis classifies drivers into five distinctive groups according to their estimated violation and crash probabilities. As a result, this study found that the estimated average crash rate within a cluster converges with the actual crash rate by the proposed framework without privacy issues. We also confirm that violation records and expected crash probability are strongly correlated, and there is a direct relationship between a driver's previous violations and crash record and the future at-fault crash. The proposed assessment method is valuable in developing proactive driver education programs and safety countermeasures, including adjusting the penalty system and developing user-based insurance by recognizing dangerous drivers and identifying their properties.

Predicting online participation through Bayesian network analysis

Despite the fact that preconditions of political participation were thoroughly examined before, there is still not enough understanding of which factors directly affect political participation and which factors correlate with participation due to common background variables. This article scrutinises the causal relations between the variables associated with participation in online activism and introduces a three-step approach in learning a reliable structure of the participation preconditions' network to predict political participation. Using Bayesian network analysis and structural equation modeling to stabilise the structure of the causal relations, the analysis showed that only age, political interest, internal political efficacy and no other factors, highlighted by the previous political participation research, have direct effects on participation in online activism. Moreover, the direct effect of political interest is mediated by the indirect effects of internal political efficacy and age via political interest. After fitting the parameters of the Bayesian network dependent on the received structure, it became evident that given prior knowledge of the explanatory factors that proved to be most important in terms of direct effects, the predictive performance of the model increases significantly. Despite this fact, there is still uncertainty when it comes to predicting online participation. This result suggests that there remains a lot to be done in participation research when it comes to identifying and distinguishing factors that stimulate new types of political activities.

A data-driven feature learning approach based on Copula-Bayesian Network and its application in comparative investigation on risky lane-changing and car-following maneuvers

The era of 'Big Data' provides opportunities for researchers to have deep insights into traffic safety. By taking advantages of 'Big Data', this study proposes a data-driven method to develop a Copula-Bayesian Network (Copula-BN) using a large-scale naturalistic driving dataset with multiple features. The Copula-BN is able to explain the causality of a risky driving maneuver. As compared with conventional BNs, the Copula-BN developed in this study has the following advantages: the Copula-BN 1. Has a more rational and explainable structure; 2. Is less likely to be over-fitting and can attain more satisfactory prediction performance; and 3. Can handle not only discrete but also continuous features. In terms of technical innovations, Shapley Additive Explanation (SHAP) is used for feature selection, while Gaussian Copula function is employed to build the dependency structure of the Copula-BN. As for applications, the Copula-BNs are used to investigate the causality of risky lane-changing (LC) and car-following (CF) maneuvers, upon which the comparisons are made between the two essential but risky driving maneuvers. In this study, the Copula-BNs are developed based on the Second Highway Research Program (SHRP2) Naturalistic Driving Study (NDS) database. Upon network evaluation, the Copula-BNs for both risky LC and CF maneuvers demonstrate satisfactory structure performance and promising prediction performance. Feature inferences are conducted based on the Copula-BNs to respectively illustrate the causation of the two risky maneuvers. Several interesting findings related to features' contribution are discussed in this paper. To a certain extent, the Copula-BN developed using the data-driven method makes a trade-off between prediction and causality within the 'Big Data'. The comparison between risky LC and CF maneuvers also provides a valuable reference for crash risk evaluation, road safety policy-making, etc. In the future, the achievements of this study could be applied in Advanced Driver-Assistance System (ADAS) and accident diagnosis system to enhance road traffic safety.

A method of railway system safety analysis based on cusp catastrophe model

For rail transit systems, safety is one of the most important goals that need to be guaranteed. We build a method of railway system safety analysis based on the cusp catastrophe model. This method describes the continuous changing process of railway system safety and considers the emergent property of safety. This method solves the problem that the outputs of most static analysis methods of railway system safety do not have continuity and avoids the complex analysis process and heavy computation burden brought by using some dynamic models such as state transition models. The quantitative case study of the continuous changing process of system safety in the evolution process of the Yong-Wen railway accident shows that the visualized outputs obtained by using this method are consistent with the actual situation. This method has the potential to be applied in the real-time monitoring of railway system safety and the early warning of train accidents.