Estimating runway veer-off risk using a Bayesian network with flight data

Barry, David

doi:10.1016/j.trc.2021.103180

Cited by 23 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Linear Discriminant Analysis (LDA) [123] Quadratic Discriminant Analysis (QDA) [123] Gaussian Mixture Model (GMM) [153,190-195] [196-198] Autoencoder [199] Fuzzy Logic [200] [117,201,202] [ [203][204][205][206][207] Logistic Regression [131,150] [126,208] Bayesian Network [30,[209][210][211] Multi-Layer Perceptron (MLP) [125,163,251] Graph-Theoretic Clustering [253] Hidden Markov Model (HMM) [254] Markov Decision Process (MDP) [78,235,240,255] Not referenced [256,257] [258]…”

Section: Categorisation Insightsmentioning

confidence: 99%

A Survey on Artificial Intelligence (AI) and eXplainable AI in Air Traffic Management: Current Trends and Development with Future Research Trajectory

et al. 2022

View full text Add to dashboard Cite

Air Traffic Management (ATM) will be more complex in the coming decades due to the growth and increased complexity of aviation and has to be improved in order to maintain aviation safety. It is agreed that without significant improvement in this domain, the safety objectives defined by international organisations cannot be achieved and a risk of more incidents/accidents is envisaged. Nowadays, computer science plays a major role in data management and decisions made in ATM. Nonetheless, despite this, Artificial Intelligence (AI), which is one of the most researched topics in computer science, has not quite reached end users in ATM domain. In this paper, we analyse the state of the art with regards to usefulness of AI within aviation/ATM domain. It includes research work of the last decade of AI in ATM, the extraction of relevant trends and features, and the extraction of representative dimensions. We analysed how the general and ATM eXplainable Artificial Intelligence (XAI) works, analysing where and why XAI is needed, how it is currently provided, and the limitations, then synthesise the findings into a conceptual framework, named the DPP (Descriptive, Predictive, Prescriptive) model, and provide an example of its application in a scenario in 2030. It concludes that AI systems within ATM need further research for their acceptance by end-users. The development of appropriate XAI methods including the validation by appropriate authorities and end-users are key issues that needs to be addressed.

show abstract

Section: Categorisation Insightsmentioning

confidence: 99%

A Survey on Artificial Intelligence (AI) and eXplainable AI in Air Traffic Management: Current Trends and Development with Future Research Trajectory

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Cox further argues that matrices consist of ambiguous inputs and outputs. Barry (2021) also argues that there has not been a lot of research looking into their validity, effectiveness and also evaluation of their performance in improving risk management decisions. Probabilities of occurrence require subjective interpretation and different users may obtain differing ratings of the same quantitative risk depending on their operational experience and national culture.…”

Section: Motivation and Research Problem Statementmentioning

confidence: 99%

“…Airlines receive a lot of data from Flight Data Recorders (FDR) and Quick Access Recorders (QAR). In his research paper, "Estimating runway veer-off risk using a Bayesian network with flight data", Barry (2021) argues that risk assessments in airline operations are mostly qualitative in nature and this is despite the availability of large amounts of data from programmes such as Flight Data Monitoring (FDM), employee safety reporting systems and Flight Operations Quality Assurance (FOQA).…”

Section: Motivation and Research Problem Statementmentioning

confidence: 99%

Application, Utility and Acceptability of Data Analytics in Safety Risk Management of Airline Operations

2022

View full text Add to dashboard Cite

One area the aviation industry is grappling with is the quantification of the probability of occurrence of safety incidents. Currently, aviation professionals involved in safety risk management mostly rely on collective experience to determine probability of incident occurrences and apply it to the International Civil Aviation Organisation (ICAO) matrix or equivalent to evaluate the risk. A number of limitations linked to the use of risk matrices will be explored in this paper. It is the aim of this paper to explore statistical methods that can be used to determine the probability of safety occurrences and come up with an algorithm that can be used by airlines using available safety data. The novelty of this research is that it combines the exploration of use of statistical techniques to quantitatively assess risk using Flight Data Monitoring (FDM) and other data, with acceptability of Safety Risk Management (SRM) data analytics by operational personnel. The paper also explores the contributory factors leading to the reluctance of operational personnel to use data analytics to inform their risk assessments despite the increasing availability of operational data and advancement in technology.

show abstract

“…Because of the seriousness of the consequences of accidents, there are currently many ''reactive'' studies on accident trends and accident causation, which use quantitative methods such as descriptive statistics, correlation tests, and regression analysis (8,(19)(20)(21)(22). Similarly, with the rapid development of machine learning and artificial intelligence, many predictive studies on flight data have emerged in recent years to predict the probability of occurrence of certain unsafe events or to suggest operational safety improvements at the microlevel of flight operations (23)(24)(25)(26)(27). These studies provide more granular information on accident prevention through advanced data analysis methods, or suggest operational safety improvements at the operational level.…”

Section: A Brief Literature Review On Aviation Safety Managementmentioning

confidence: 99%

Trends and Characteristics of Incidents in China Civil Aviation: 1994–2020

Sun

2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Safety is of great importance to the sustainable development of air transportation. Because aviation accidents rarely occur, the traditional indexes based on fatal accidents and fatality could not provide enough information for accident prevention and continuous safety improvement. This paper collected data on 6,357 incidents in China civil aviation from 1994 to 2020. Afterward, a whole picture was drawn to reflect the detailed safety situation by analyzing the characteristics and trend of incidents. From 1994 to 2008, the annual number of incidents in China civil aviation remained relatively stable. After 2008, the number of incidents exhibited an obvious growth trend, but the incidents per million flight hours remained stable. From the direct cause of incidents, operator and mechanic are no longer the leading causes. Presently, 63.4% of incidents are caused by environmental factors, showing an increasing trend. From the operation phase, most incidents occurred during the cruise phase (29.8%), followed by the approach phase (19.4%), and the take-off phase (16.0%). In addition, there have been many incidents that occurred during uncertain phase. From the typical incidents, bird strikes and lightning strikes account for 43.8% and 6.7% of the total incidents, respectively, showing an annually ascending trend. Engine shutdown accounts for 9.4% but the number exhibits a descending trend. As an important index of safety, the trend and characteristics of incidents can specifically reflect the safety situation of the aviation industry, and provide a reference for accident prevention and continuous safety improvement.

show abstract

Estimating runway veer-off risk using a Bayesian network with flight data

Cited by 23 publications

References 28 publications

A Survey on Artificial Intelligence (AI) and eXplainable AI in Air Traffic Management: Current Trends and Development with Future Research Trajectory

A Survey on Artificial Intelligence (AI) and eXplainable AI in Air Traffic Management: Current Trends and Development with Future Research Trajectory

Application, Utility and Acceptability of Data Analytics in Safety Risk Management of Airline Operations

Trends and Characteristics of Incidents in China Civil Aviation: 1994–2020

Contact Info

Product

Resources

About