Air Traffic Flow Management Data Mining and Analysis for In-flight Cost Optimization

As the air traffic volume has increased significantly over the world, the great mass of traffic management data, named as Big Data, have also accumulated day by day. This factor presents more opportunities and also challenges as well in the study and development of Air Traffic Management (ATM). Usually, Decision Support Systems (DSS) are developed to improve the efficiency of ATM. The main problem for these systems is the data analysis to acquisition sufficient knowledge for the decision. This paper introduces the application of the methods of Data Mining to get the knowledge from air traffic Big Data in management processes. The proposed approach uses a Bayesian network for the data analysis to reduce the costs of flight delay. The process makes possible to adjust the flight plan such as the schedule of arrival at or departure from an airport and also checks the airspace control measurements considering weather conditions. An experimental study is conducted based on the flight scenarios between Los Angeles International Airport (LAX) and Miami International Airport (MIA).

[1]  Kagan Tumer,et al.  Learning Indirect Actions in Complex Domains: Action Suggestions for Air Traffic Control , 2009, Adv. Complex Syst..

[2]  Michael I. Jordan.  Learning in Graphical Models , 1999, NATO ASI Series.

[3]  Cullen Schaffer,et al.  A Conservation Law for Generalization Performance , 1994, ICML.

[4]  Deepak Kulkarni.  Integrated Use of Data Mining and Statistical Analysis Methods to Analyze Air Traffic Delays , 2007 .

[5]  Pat Langley,et al.  Machine learning as an experimental science , 2004, Machine Learning.

[6]  Ian Witten,et al.  Data Mining , 2000 .

[7]  Daniel DeLaurentis,et al.  Air Traffic Demand Forecast at a Commercial Airport using Bayesian Networks , 2011 .

[8]  Kagan Tumer,et al.  Regulating air traffic flow with coupled agents , 2008, AAMAS.

[9]  Judea Pearl,et al.  Evidential Reasoning Using Stochastic Simulation of Causal Models , 1987, Artif. Intell..

[10]  Rakesh Agrawal,et al.  Parallel Mining of Association Rules , 1996, IEEE Trans. Knowl. Data Eng..

[11]  Weigang Li,et al.  Grid Service Agents for Real Time Traffic Synchronization , 2004, IEEE/WIC/ACM International Conference on Web Intelligence (WI'04).

[12]  Peng Cheng,et al.  Data mining for air traffic flow forecasting: a hybrid model of neural network and statistical analysis , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[13]  Alexandre G. de Barros,et al.  Reinforcement learning agents to tactical air traffic flow management , 2012 .

[14]  Le Gruenwald,et al.  A survey of data mining and knowledge discovery software tools , 1999, SKDD.

[15]  Manuel Mendoza,et al.  Bayesian Forecasting Methods for Short Time Series , 2007 .

[16]  A. K. Pujari,et al.  Data Mining Techniques , 2006 .

[17]  Paul Gray,et al.  Special Section: Data Mining , 1999, J. Manag. Inf. Syst..

[18]  Heikki Mannila,et al.  Principles of Data Mining , 2001, Undergraduate Topics in Computer Science.

[19]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[20]  Bernhard Rumpe,et al.  On Demand Data Analysis and Filtering for Inaccurate Flight Trajectories , 2014, ArXiv.

[21]  Evangelos Simoudis,et al.  An Overview of Issues in Developing Industrial Data Mining and Knowledge Discovery Applications , 1996, KDD.

[22]  Lisa Ann Osadciw,et al.  Using Bayesian inference for sensor management of air traffic control systems , 2009, 2009 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making(MCDM).