Prediction of Airline Delays– A Survey

IJCSEC Front Page

Abstract:
Airline delays cause the most economic impact on both airlines and passengers. There are many factors which affect the airline delays such as inclement weather conditions, miscommunications, check-in delays, congestion in air traffic, fueling, security issues, mechanical problems etc. The most common cause of airline delays is due to irregular signal delivery from source or destination and this can be predicted by using data mining algorithms. India’s domestic flight data was extracted and used to train the model. To balance the unstable training data, sampling techniques such as SMOTE is applied. The k-Nearest-Neighbors is applied to build the models which can predict the flight delays and also the nearest location for landing of the aircraft safely.

Keywords: improved KNN Algorithm, decision tree, Naïve-Bayes, Decision Trees, Airline delay Prediction System.

References:

  1. Sun Choi, Young Jin Kim, Simon Briceno and Dimitri Mavris, 2016. "Prediction of Weather-induced Airline Delays Based on Machine Learning Algorithms"IEEE, PP.1-6.
  2. Justin G. Fuller, Loyd Hook, Nathan Hutchins, K. Niki Maleki, Mark A. Skoog,2016."Toward Run-Time Assurance in General Aviation and Unmanned Aircraft Vehicle Autopilots".
  3. Martin Gilje Jaatun, Rainer Koelle “Cyber Security Incident Management in the Aviation Domain” IEEE - 11th International Conference on Availability, Reliability and Security, 2016, pp.510-515.
  4. S Meenakshi Sundaram, Dr. S Senthamarai Kannan, Dr. S Appavu alias Balamurugan “Ensemble Feature Selector for Aviation Accident Analysis and Prevention” Asian Journal of Research in Social Sciences and Humanities, 2016, pp. 81-92.
  5. Maria Solntseva-Chaley “New data mining technique for multidimensional aircraft trajectories analysis” ITM Web of Conferences, 2016, pp.1-7.
  6. Richard M. Keller, “Ontologies for Aviation Data Management” Airspace Operations and Safety Program, 2015, pp.1-8.
  7. Xinmin Tang, Junwei Gu, Zhiyuan Shen, “A Flight Profile Clustering Method Combining TWED with K-means Algorithm for 4d Trajectory Prediction” 978-1-4799-8952-2/15©2015 IEEE, pp.1-9.
  8. Bryan Matthews,Santanu Das,Kanishka Bhaduri, Kamalika Das, Rodney MartinNikunj Oza, Ashok N. Srivastavaand John Stutz,2015. "Discovering Anomalous Aviation Safety Events usingScalable Data Mining Algorithms"American Institute of Aeronautics and Astronautics, pp.1-12.
  9. David A. Pagels "Aviation Data Mining"University of Minnesota, Morris Morris, Minnesota, 2013, pp-1-7.
  10. Nicolas Maille."On the use of data-mining algorithms to improve FOQA tools for Airlines" 978-1-4673-1813-6/13©2013 IEEE, pp1-8.
  11. Yue Song, Peng Cheng, Chundi Mu. ”An Improved Trajectory Prediction Algorithm based on Trajectory Data Mining for Air Traffic Management”978-1-4673-2237-9/12 ©2012 IEEE,pp.1-6.
  12. Douglas J. Equils.”Methodologies for Improving Flight Project Information Capture, Storage and Dissemination” 978-1-4244-7351-9/11 ©2011 IEEE,pp.1-7.
  13. Yang Hui."Research on Similarity Mining for Flight Data", Second International Workshop on Education Technology and Computer Science, 978-0-7695-3987-4/10 © 2010 IEEE, pp.1-4.
  14. Saybani Mahmoud Reza, Adel Lahsasna, Teh Ying Wah.”Applied Data Mining Approach in Ubiquitous World of Air Transportation”, Fourth International Conference on Computer Sciences and Convergence Information Technology,978-0-7695-3896-9/09 © 2009 IEEE, pp.1-5.
  15. Mingqiang Chen,"The Research of Flight Trajectory Based on Association Rule”Air Navigation Section, School of Flight Technology, Civil Aviation Flight University of China,978-1-4244-7255-0/11©2011 IEEE, pp.1-4.