Home > Research > Publications & Outputs > Incremental anomaly identification in flight da...

Research

Associated organisational units

Links

Text available via DOI:

Keywords

View graph of relations

Incremental anomaly identification in flight data analysis by adapted one-class SVM method

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Incremental anomaly identification in flight data analysis by adapted one-class SVM method. / Kolev, Denis; Suvorov, Mikhail; Morozov, Evgeniy et al.
Artificial neural networks: methods and applications in bio-/neuroinformatics. ed. / Petia Koprinkova-Hristova; Valeri Mladenov; Nikola K. Kasabov. Springer, 2015. p. 373-391 (Springer Series in Bio-/Neuroinformatics; Vol. 4).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Kolev, D, Suvorov, M, Morozov, E, Markarian, G & Angelov, P 2015, Incremental anomaly identification in flight data analysis by adapted one-class SVM method. in P Koprinkova-Hristova, V Mladenov & NK Kasabov (eds), Artificial neural networks: methods and applications in bio-/neuroinformatics. Springer Series in Bio-/Neuroinformatics, vol. 4, Springer, pp. 373-391. https://doi.org/10.1007/978-3-319-09903-3_18

APA

Kolev, D., Suvorov, M., Morozov, E., Markarian, G., & Angelov, P. (2015). Incremental anomaly identification in flight data analysis by adapted one-class SVM method. In P. Koprinkova-Hristova, V. Mladenov, & N. K. Kasabov (Eds.), Artificial neural networks: methods and applications in bio-/neuroinformatics (pp. 373-391). (Springer Series in Bio-/Neuroinformatics; Vol. 4). Springer. https://doi.org/10.1007/978-3-319-09903-3_18

Vancouver

Kolev D, Suvorov M, Morozov E, Markarian G, Angelov P. Incremental anomaly identification in flight data analysis by adapted one-class SVM method. In Koprinkova-Hristova P, Mladenov V, Kasabov NK, editors, Artificial neural networks: methods and applications in bio-/neuroinformatics. Springer. 2015. p. 373-391. (Springer Series in Bio-/Neuroinformatics). doi: 10.1007/978-3-319-09903-3_18

Author

Kolev, Denis ; Suvorov, Mikhail ; Morozov, Evgeniy et al. / Incremental anomaly identification in flight data analysis by adapted one-class SVM method. Artificial neural networks: methods and applications in bio-/neuroinformatics. editor / Petia Koprinkova-Hristova ; Valeri Mladenov ; Nikola K. Kasabov. Springer, 2015. pp. 373-391 (Springer Series in Bio-/Neuroinformatics).

Bibtex

@inproceedings{5a1c1066b7ad49218dc8111343f85efc,
title = "Incremental anomaly identification in flight data analysis by adapted one-class SVM method",
abstract = "In our work we used the capability of one-class support vector machine (SVM) method to develop a novel one-class classification approach. Algorithm is designed and tested, aimed for fault detection in complex technological systems, such as aircraft. The main objective of this project was to create an algorithm responsible for collecting and analyzing the data since the launch of an aircraft engine. Data can be transferred from a variety of sensors that are responsible for the speed, oil temperature and etc. In order to provide high generalization level and sufficient learning data sets an incremental algorithm is considered. The proposed method analyzes both “positive”/“normal” and “negative”/ “abnormal” examples. However, overall model structure is based on one-class classification paradigm. Modified SVM-base outlier detection method is verified in comparison with several classifiers, including the traditional one-class SVM. This algorithm has been tested on real flight data from the Western European and Russia. The test results are presented in the final part of the article. ",
keywords = "Flight Data Analysis, one-class SVM, Fault Detection and Identification",
author = "Denis Kolev and Mikhail Suvorov and Evgeniy Morozov and Garik Markarian and Plamen Angelov",
year = "2015",
doi = "10.1007/978-3-319-09903-3_18",
language = "English",
isbn = "9783319099026",
series = "Springer Series in Bio-/Neuroinformatics",
publisher = "Springer",
pages = "373--391",
editor = "Petia Koprinkova-Hristova and Valeri Mladenov and Kasabov, {Nikola K.}",
booktitle = "Artificial neural networks",

}

RIS

TY - GEN

T1 - Incremental anomaly identification in flight data analysis by adapted one-class SVM method

AU - Kolev, Denis

AU - Suvorov, Mikhail

AU - Morozov, Evgeniy

AU - Markarian, Garik

AU - Angelov, Plamen

PY - 2015

Y1 - 2015

N2 - In our work we used the capability of one-class support vector machine (SVM) method to develop a novel one-class classification approach. Algorithm is designed and tested, aimed for fault detection in complex technological systems, such as aircraft. The main objective of this project was to create an algorithm responsible for collecting and analyzing the data since the launch of an aircraft engine. Data can be transferred from a variety of sensors that are responsible for the speed, oil temperature and etc. In order to provide high generalization level and sufficient learning data sets an incremental algorithm is considered. The proposed method analyzes both “positive”/“normal” and “negative”/ “abnormal” examples. However, overall model structure is based on one-class classification paradigm. Modified SVM-base outlier detection method is verified in comparison with several classifiers, including the traditional one-class SVM. This algorithm has been tested on real flight data from the Western European and Russia. The test results are presented in the final part of the article.

AB - In our work we used the capability of one-class support vector machine (SVM) method to develop a novel one-class classification approach. Algorithm is designed and tested, aimed for fault detection in complex technological systems, such as aircraft. The main objective of this project was to create an algorithm responsible for collecting and analyzing the data since the launch of an aircraft engine. Data can be transferred from a variety of sensors that are responsible for the speed, oil temperature and etc. In order to provide high generalization level and sufficient learning data sets an incremental algorithm is considered. The proposed method analyzes both “positive”/“normal” and “negative”/ “abnormal” examples. However, overall model structure is based on one-class classification paradigm. Modified SVM-base outlier detection method is verified in comparison with several classifiers, including the traditional one-class SVM. This algorithm has been tested on real flight data from the Western European and Russia. The test results are presented in the final part of the article.

KW - Flight Data Analysis

KW - one-class SVM

KW - Fault Detection and Identification

U2 - 10.1007/978-3-319-09903-3_18

DO - 10.1007/978-3-319-09903-3_18

M3 - Conference contribution/Paper

SN - 9783319099026

T3 - Springer Series in Bio-/Neuroinformatics

SP - 373

EP - 391

BT - Artificial neural networks

A2 - Koprinkova-Hristova, Petia

A2 - Mladenov, Valeri

A2 - Kasabov, Nikola K.

PB - Springer

ER -