Title :
Detection of Precursors to Aviation Safety Incidents Due to Human Factors
Author :
Melnyk, Igor ; Yadav, Parmatma ; Steinbach, Michael ; Srivastava, Jaideep ; Kumar, Vipin ; Banerjee, Adrish
Author_Institution :
Dept. of Comput. Sci. & Eng., Univ. of Minnesota, Minneapolis, MN, USA
Abstract :
In this paper, we study the problem of anomaly detection with application to aviation systems. We proposed a framework for detecting precursors to aviation safety incidents due to human factors based on Hidden Semi-Markov Models (HSMM). We investigate HSMMs due to their inherent ability to model durations in addition to model latent state transitions based on the observed pilots actions. Empirical evaluation on synthetic data and flight simulator data show that HSMMs perform favorably compared to many other existing anomaly detection algorithms.
Keywords :
aerospace computing; air safety; air traffic; hidden Markov models; human factors; traffic engineering computing; HSMM; anomaly detection problem; aviation safety incidents; aviation systems; duration model; flight simulator data; hidden semi Markov models; human factors; latent state transition model; next generation air transportation system; precursor detection; synthetic data; Aircraft; Atmospheric modeling; Data models; Detection algorithms; Hidden Markov models; Joints; Training; anomaly detection; aviation safety; data mining; hidden markov model;
Conference_Titel :
Data Mining Workshops (ICDMW), 2013 IEEE 13th International Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4799-3143-9
DOI :
10.1109/ICDMW.2013.55
