Detection of precursors to aviation safety incidents due to human factors

Igor Melnyk; Pranjul Yadav; Michael Steinbach; Jaideep Srivastava; Vipin Kumar; Arindam Banerjee

doi:10.1109/ICDMW.2013.55

Detection of precursors to aviation safety incidents due to human factors

Igor Melnyk, Pranjul Yadav, Michael Steinbach, Jaideep Srivastava, Vipin Kumar, Arindam Banerjee

Computer Science and Engineering

Research output: Contribution to conference › Paper › peer-review

19 Scopus citations

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.

Original language	English (US)
Pages	407-412
Number of pages	6
DOIs	https://doi.org/10.1109/ICDMW.2013.55
State	Published - 2013
Event	2013 13th IEEE International Conference on Data Mining Workshops, ICDMW 2013 - Dallas, TX, United States Duration: Dec 7 2013 → Dec 10 2013

Other

Other	2013 13th IEEE International Conference on Data Mining Workshops, ICDMW 2013
Country/Territory	United States
City	Dallas, TX
Period	12/7/13 → 12/10/13

Keywords

Anomaly detection
Aviation safety
Data mining
Hidden markov model

Publisher link

10.1109/ICDMW.2013.55

Find It

Find It at U of M Libraries

Cite this

@conference{96da1fa93ec54fff8af5a35c553c4332,

title = "Detection of precursors to aviation safety incidents due to human factors",

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 = "Anomaly detection, Aviation safety, Data mining, Hidden markov model",

author = "Igor Melnyk and Pranjul Yadav and Michael Steinbach and Jaideep Srivastava and Vipin Kumar and Arindam Banerjee",

year = "2013",

doi = "10.1109/ICDMW.2013.55",

language = "English (US)",

pages = "407--412",

note = "2013 13th IEEE International Conference on Data Mining Workshops, ICDMW 2013 ; Conference date: 07-12-2013 Through 10-12-2013",

}

TY - CONF

T1 - Detection of precursors to aviation safety incidents due to human factors

AU - Melnyk, Igor

AU - Yadav, Pranjul

AU - Steinbach, Michael

AU - Srivastava, Jaideep

AU - Kumar, Vipin

AU - Banerjee, Arindam

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

KW - Anomaly detection

KW - Aviation safety

KW - Data mining

KW - Hidden markov model

UR - http://www.scopus.com/inward/record.url?scp=84898034295&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898034295&partnerID=8YFLogxK

U2 - 10.1109/ICDMW.2013.55

DO - 10.1109/ICDMW.2013.55

M3 - Paper

AN - SCOPUS:84898034295

SP - 407

EP - 412

T2 - 2013 13th IEEE International Conference on Data Mining Workshops, ICDMW 2013

Y2 - 7 December 2013 through 10 December 2013

ER -

Detection of precursors to aviation safety incidents due to human factors

Abstract

Other

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this