575.pdf (457.55 kB)
Download file

An efficient algorithm for anomaly detection in a flight system using dynamic Bayesian networks

Download (457.55 kB)
conference contribution
posted on 13.01.2022, 15:22 by Mohamad SaadaMohamad Saada, Qinggang MengQinggang Meng
Despite the fact that Dynamic Bayesian Network models have become a popular modelling platform to many researchers in recent years, not many have ventured into the realms of data anomaly and its implications on DBN models. An abnormal change in the value of a hidden state of a DBN will cause a ripple-like effect on all descendent states in current and consecutive slices. Such a change could affect the outcomes expected of such models. In this paper we propose a method that will detect anomalous data of past states using a trained network and data of the current network slice. We will build a model of pilot actions during a flight, this model is trained using simulator data of similar flights. Then our algorithm is implemented to detect pilot errors in the past given only current actions and instruments data.

History

School

  • Science

Department

  • Computer Science

Published in

Neural Information Processing

Issue

Part III

Pages

620 - 628

Source

19th International Conference on Neural Information Processing (ICONIP 2012)

Publisher

Springer

Version

AM (Accepted Manuscript)

Rights holder

© Springer

Publisher statement

This version of the contribution has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-642-34487-9_75. Use of this Accepted Version is subject to the publisher's Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms

Publication date

2012-12-31

Copyright date

2012

ISBN

9783642344862; 9783642344879

ISSN

0302-9743

eISSN

1611-3349

Book series

Lecture Notes in Computer Science; vol 7665

Language

en

Editor(s)

Tingwen Huang; Zhigang Zeng; Chuandong Li; Chi-Sing Leung

Location

Doha, Qatar

Event dates

12th-15th November 2012

Depositor

Mr Mohamad Saada. Deposit date: 13 January 2022