Modeling accident scenarios from databases with missing data: A probabilistic approach for safety-related systems design

This paper combines Bayesian networks (BN) and information theory to model the likelihood of severe loss of separation (LOS) near accidents, which are considered mid-air collision (MAC) precursors. BN is used to analyze LOS contributing factors and the multi-dependent relationship of causal factors, while Information Theory is used to identify the LOS precursors that provide the most information. The combination of the two techniques allows us to use data on LOS causes and precursors to define warning scenarios that could forecast a major LOS with severity A or a near accident, and consequently the likelihood of a MAC. The methodology is illustrated with a case study that encompasses the analysis of LOS that have taken place within the Spanish airspace during a period of four years.

show abstract

“…, An}. Such distribution could be continued or discrete, based on the conditional independency and chain rule [32] included in the network as…”

Section: Development and Validation Of A Bn Modelmentioning

confidence: 99%

Application of Bayesian Networks and Information Theory to Estimate the Occurrence of Mid-Air Collisions Based on Accident Precursors

Valdés

Cheng

Comendador

et al. 2018

Entropy

View full text Add to dashboard Cite

show abstract

“…The coding of the R-based multi-fill method is detailed in Section 2.2, where the m value defaults to 5 [20], which can be taken as 3 to 5 [21], 5 to 10 [22], or 5 to 20, or even higher [23]; the larger the value, the better, but the size of the calculation amount should also be considered. Therefore, the value of m needs to be discussed on a case-by-case basis, and should not be too large or too small, which may make the filling inaccurate and affect the research results.…”

Section: Introductionmentioning

confidence: 99%

Research and Application of Improved Multiple Imputation Based on R Language in Fire Prediction

Wang

Jiang

et al. 2023

Fire

View full text Add to dashboard Cite

An improved multiple imputation based on R language is proposed to deal with the miss of data in a fire prediction model, which can affect the accuracy of the prediction results. Hazard and operability (HAZOP) is used to accurately find the data related to the research purpose, and exclude data with a missing rate greater than 80% and small differences in characteristics. Then, by changing the m value in the mice package under the R language (R-mice), the relevant parameters of the complete filling factor set under different m values are obtained. The value of m is determined after observing and comparing the parameters. The proposed method fully considers the randomness of filling and the difference between the generated dataset. Taking Hubei Province as an example, the data processed by this method are used as the input of the Bayesian network, and the fire trend is used as the output. The results show that the improved multiple imputation based on R-mice can solve the problem of missing data very well, and have a high prediction effect (AUC = 94.0800). In addition, the results of the predictive reasoning and sensitivity analysis show that the government’s supervision has a vital influence on the trend of fires in Hubei Province.

show abstract

“…From a fatality perspective, construction accounted for 40 fatal injuries to workers in 2019/20; the cost of occupational injuries and new cases of occupational ill health being estimated at £1.2 billion [1]. Whilst improving safety can broadly be divided into the pre-construction and in-construction phase [2], it is acknowledged that pre-construction approaches can reduce risks involved in construction, operation and maintenance: many accidents being predictable and preventable during design, if appropriate approaches, tools and technologies are utilized [3][4][5]. Designers can therefore play a significant role in accident reduction [6].…”

Section: Introductionmentioning

confidence: 99%

BIM-based construction safety risk library

Collinge

Farghaly²,

Mosleh³

et al. 2022

Automation in Construction

View full text Add to dashboard Cite

Modeling accident scenarios from databases with missing data: A probabilistic approach for safety-related systems design

Cited by 13 publications

References 28 publications

Application of Bayesian Networks and Information Theory to Estimate the Occurrence of Mid-Air Collisions Based on Accident Precursors

Application of Bayesian Networks and Information Theory to Estimate the Occurrence of Mid-Air Collisions Based on Accident Precursors

Research and Application of Improved Multiple Imputation Based on R Language in Fire Prediction

BIM-based construction safety risk library

Contact Info

Product

Resources

About