Applying data mining techniques to detect abnormal flight characteristics

H. Emre Aslaner; Cagri Unal; Cem Iyigun

doi:10.1117/12.2224061

12 May 2016 Applying data mining techniques to detect abnormal flight characteristics

H. Emre Aslaner, Cagri Unal, Cem Iyigun

Proceedings Volume 9850, Machine Intelligence and Bio-inspired Computation: Theory and Applications X; 985009 (2016) https://doi.org/10.1117/12.2224061
Event: SPIE Defense + Security, 2016, Baltimore, MD, United States

Abstract

This paper targets to highlight flight safety issues by applying data mining techniques to recorded flight data and proactively detecting abnormalities in certain flight phases. For this purpose, a result oriented method is offered which facilitates the process of post flight data analysis. In the first part of the study, a common time period of flight is defined and critical flight parameters are selected to be analyzed. Then the similarities of the flight parameters in time series basis are calculated for each flight by using Dynamic Time Warping (DTW) method. In the second part, hierarchical clustering technique is applied to the aggregate data matrix which is comprised of all the flights to be studied in terms of similarities among chosen parameters. Consequently, proximity levels among flight phases are determined. In the final part, an algorithm is constructed to distinguish outliers from clusters and classify them as suspicious flights.

Citation Download Citation

H. Emre Aslaner, Cagri Unal, and Cem Iyigun "Applying data mining techniques to detect abnormal flight characteristics", Proc. SPIE 9850, Machine Intelligence and Bio-inspired Computation: Theory and Applications X, 985009 (12 May 2016); https://doi.org/10.1117/12.2224061

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available