運用資料探勘技術於航安風險因素分析

機構典藏 > College of Business and Management > Graduate Institute & Department of Information Management > Thesis > Item 987654321/102395

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/102395

Title:	運用資料探勘技術於航安風險因素分析
Other Titles:	Apply data mining techniques to analyze flight safety risk factors
Authors:	許珉豪;Hsu, Min-Hao
Contributors:	淡江大學資訊管理學系碩士班徐煥智
Keywords:	資料探勘;航安風險;風險因素;data mining;Flight Safety risk;Risk Factors
Date:	2014
Issue Date:	2015-05-04 09:54:43 (UTC+8)
Abstract:	飛行操作風險評估系統(Flight Operation Risk Assessment System, FORAS)將影響航班飛行之一系列相關風險因素利用階層式架構模型描述彼此之間的關聯性：並透過此模型來推估每一航班在起飛或降落時所可能面臨之風險程度。本研究利用多種的資料探勘技術分析國內某國際航空公司已建置之FORAS系統中已被定義之70多種飛行風險因素。本研究發現依據實際航班資料分析，有將近40％左右的風險因素可被考量由原模型中去除，以簡化模型之複雜度及加強風險因素對風險值預估的敏感度。此外，本研究亦利用分群分析法協助航空公司了解其所屬不同機隊與飛行航段較普遍存在的風險因素為何，以作為航空公司在差異化風險管理的依據。 The FORAS (Flight Operation Risk Assessment System) model is to represent the risk of a flight as a chain of the flight operations in terms of risk factors using a hierarchical structure which breaks down the concerned operation risk of the flight, e.g. approach and landing risk, to its causal operation risks.The importance of risk factors defined in a FORAS system, which is currently developed by an international airline, has been analyzed by data mining techniques in this study. The original system considers more than 70 risk factors to create risk inference model.However, in this study, it has been suggested that around 40% of risk factors need to be reconsidered or removed from the original model. In additional, cluster analysis has been applied to figure out the patterns of potential higher risk areas for various fleets and flight regions.
Appears in Collections:	[Graduate Institute & Department of Information Management] Thesis

Files in This Item:

File	Size	Format
index.html	0Kb	HTML	206	View/Open

Loading...