12 May 2016 Applying data mining techniques to detect abnormal flight characteristics
Author Affiliations +
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.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
H. Emre Aslaner, H. Emre Aslaner, Cagri Unal, Cagri Unal, Cem Iyigun, 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); doi: 10.1117/12.2224061; https://doi.org/10.1117/12.2224061
PROCEEDINGS
18 PAGES


SHARE
Back to Top