進階搜尋


下載電子全文  
系統識別號 U0026-1708201815313300
論文名稱(中文) 利用航空數據分析探討航空飛航管理應用
論文名稱(英文) Application of Airline Data in Aviation Flight Management
校院名稱 成功大學
系所名稱(中) 航空太空工程學系
系所名稱(英) Department of Aeronautics & Astronautics
學年度 106
學期 2
出版年 107
研究生(中文) 江奇勳
研究生(英文) Chi-Hsun Chiang
學號 P46041267
學位類別 碩士
語文別 英文
論文頁數 52頁
口試委員 指導教授-林清一
口試委員-詹劭勳
口試委員-李志清
中文關鍵字 大數據,隨機森林  廣播式自動回報監視  航空數據 
英文關鍵字 Big Data  Random Forest  ADS-B  Aviation Data 
學科別分類
中文摘要 大數據分析近年來蓬勃發展,各領域試著把新思維帶入企業中,以提升營收效益並找到潛在因子。大數據基礎來自於大量、多樣化、快速產生的數據量,必須經過充分蒐集、分析及應用才能展現它的價值。航空業對於數據產生、保存上更是鉅細靡遺,現行發展非常多的公開資訊廣泛地經全球性之衛星定位(GPS) 獲得航機位置資訊並且搭配航空公司實際飛航準時及延遲資訊,甚至是氣象局提供之天氣、風向、水氣等天然因素。資料蒐集較過去精準且完整,將會使得航空業成為更安全、更有效率的產業。本文章的目的是提供有關機器學習分析方法和軟體工具的運用可以幫助航空公司將其數據轉化為有價值的信息,從而提高安全性並利於航空之管理。
隨機森林是機器學習中其中一個熱門的演算法,它是由多棵決策樹所組成的模型,再由投票的方式決定最後的預測結果。以R軟體Random Forest套件作分析,是一個十分完整且方便的模型。由於航空業資料瞬息萬變,以隨機森林模型可探討各種狀況的假設,若能蒐集更多外部即時資訊更能增進模型精準度。本論文將這套隨機森林演算法運用在航空業資料,以預測延遲班機作為目標,利用美國運輸部所提供的飛航數據建立模型並探討,找出其影響延遲之關鍵。未來數據分析會持續受到重視,培養判斷力與直覺,將成為強而有力的洞見。
英文摘要 Big data analysis has rapid develop recently. In various fields are trying to bring the new insight into their enterprise for increasing revenue or finding potential patterns. Basis for big data analysis is on the volume, variety, velocity, and veracity of data. It needs to be well collected, analyzed, and applied that can reveal its value. For aviation, there is a strict regulation for collecting, preserving data. Nowadays, many public information including event reports and digital flight data depends on accurate global satellite positioning (GPS) to obtain aircraft location and the airline has the flight arrival data including on-time or delay information. Moreover, Weather bureau has situation of the weather, wind direction, moisture and so on. There is more accurate, reliable and comprehensive. It will make the aviation more efficient and security. The purpose of this guide is to provide information on existing analytical methods and tools that can help the airline community turn their data into valuable information to improve safety and flight management.
Random Forest is a popular machine learning algorithms. It is a decision tree model consists of multiple trees. Then we predict the final result by majority voting of the results. Random forest in R software package “random forest” is very easy and comprehensive to use. Due to the data rapidly changing in the aviation, random forest models can be used to explore the assumptions of various conditions. If we can collect more external information, the model can improve the degree of accuracy. In this study, based on random forest algorithm applied in aviation data to predict delayed flights as the target. The data is collected by the US Department of Transportation and use it to build the model and explore the important features to find the delay flight. In the future, data analysis will continue to receive attention. If we cultivate judgment and intuition will become strong and generate great insights.
論文目次 摘要 I
Abstract II
謝誌 IV
Contents V
List of Tables VII
List of Figures VIII
Chapter 1 INTRODUCTION 1
1.1 Motivation 1
1.2 Goal 4
1.3 Framework 5
Chapter 2 LITERATURE REVIEW 6
2.1 Previous studies and Applications of flight delays 6
2.2 Aviation Data and Factors affecting flight delays 8
2.3 Data collection method 9
Chapter 3 METHODOLOGY 11
3.1 Basic introduction of ADS-B 11
3.1.1 ADS-B system 11
3.2 Basic introduction of Data Mining 12
3.2.1 Background 12
3.2.2 Data mining 13
3.2.3 Big Data 14
3.2.4 Machine Learning 17
3.3 Basic introduction of Random Forest 20
3.3.1 Algorithm 21
3.3.2 Variable Importance Measures 25
3.3.3 Features 27
3.4 Procedure to Random Forest on the Flight Delay 28
3.5 Random Forest in R 29
3.5.1 Introduction in R 29
3.5.2 R Package: Random Forest 30
Chapter 4 RESULTS AND DISCUSSION 34
4.1 Expected outcomes 34
4.2 Collection of the Aviation database 35
4.3 Data pre-processing 38
4.3.1 Descriptive statistics 38
4.3.2 Classify and label the delay flight of the data 42
4.4 Model Building 42
4.5 Model Evaluation 44
Chapter 5 CONCLUSIONS 48
References 50
參考文獻 [1] Mayer, Christopher and Todd Sinai. (2003a). Network Effects, Congestion Externalities, and Air Traffic Delays: or Why All Delays Are Not Evil, American Economic Review, 93:4, p. 1194-1215.
[2] Mayer, Christopher and Todd Sinai. (2003b). Why Do Airline Schedules Systematically Underestimate Travel Time?, working paper, Wharton School of Business.
[3] Mazzeo, Michael J. (2003). Competition and Service Quality in the U.S. Airline Industry, Review of Industrial Organization, 22:4, p. 275-96
[4] Rupp, Nicholas G. and George M. Holmes. (2006). An Investigation Into the Determinants of Flight Cancellations, Economica, 73:292, p. 749-84.
[5] Starr, M. (2001). Safety and security: Critical qualities call for refocusing POM. Production and Operations Management, 10(4), 361-362. http://dx.doi.org/10.1111/j.1937-5956.2001.tb00081.x
[6] Talia, D, Trunfio, P. (2012). Service-Oriented Distributed Knowledge Discovery. Boca Raton, FL, USA: Chapman & Hall/CRC.
[7] Ball, M., Barnhart, C., Dresner, M., Hansen, M., Neels, K., Odoni, A & Zou, B. (2010). Total delay impact study: a comprehensive assessment of the costs and impacts of flight delay in the United States.
[8] Abdelghany, K. F., Shah, S. S., Raina, S., Abdelghany, A. F.(2004). A Model for Projecting Flight Delays during Irregular Operation Conditions. Journal of Air Transport Management,10(6),385-394.
[9] Abdel-Aty, M., Lee, C., Bai, Y., Li, X., & Michalak, M. (2007). Detecting periodic patterns of arrival delay. Journal of Air Transport Management, 13(6), 355-361.
[10] Adrian Alexander Arteche Simmons. (2015). Flight Delay Forecast due to weather using data mining.
[11] Lawson, Dieterich; Castillo, William. (2012). Predicting Flight Delays.
[12] http://www.datawrangling.com/how¬flightcaster¬squeezes¬predictions¬from¬flight¬data
[13] Brett Naul. (2008). Airline Departure Delay Prediction.
[14] Mike de Waard. (2017). Machine learning based aircraft arrival / departure registrations
[15] FlightAware. (2017). Do you want to build your own flight aware piaware ads-b ground station? https://flightaware.com/adsb/piaware/build.
[16] Air Traffic Management. (2016). Nz satellite-based aircraft tracking on the way. http://www.airtrafficmanagement.net/2016/09/ nz-satellite based-aircraft-tracking-on-the-way.
[17] Jason Brownlee. (2015). Basic Concepts in Machine Learning.
[18] Jason Brownlee (2013). A Tour of Machine Learning Algorithms.
[19] Ajitesh Kumar. (2018). Dummies Notes – Supervised vs Unsupervised Learning.
[20] Maloof, Marcus A. (2006). Machine Learning and Data Mining for Computer Security. Springer.
[21] Breiman, L., Random Forests. Machine Learning. (2001). 45(1): p. 5-32.
[22] Breiman, L., Bagging predictors. Machine Learning. (1996). 24(2): p. 123-140.
[23] James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013). An Introduction to Statistical Learning with Applications in R, http://www-bcf.usc.edu/˜gareth/ISL/.
[24] Segal, M.R., Machine learning benchmarks and random forest regression. (2004).
[25] Deng, H., G. Runger, and E. Tuv, Bias of importance measures for multi-valued attributes and solutions. (2011). p. 293-300.
[26] Chen, C., A. Liaw, and L. Breiman. (2004). Using random forest to learn imbalanced data.
[27] A Programming Environment for Data Analysis and Graphics Version 3.5.0 (2018).
https://cran.r-project.org/doc/manuals/r-release/R-intro.pdf
[28] Fortran original by Leo Breiman and Adele Cutler, R port by Andy Liaw and Matthew Wiener. (2018). Package randomForest.
[29] The U.S. Department of Transportation's (DOT) Bureau of Transportation Statistics (BTS https://www.bts.gov/
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2018-08-27起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2018-08-27起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw