DETECTING ANOMALOUS SENSOR DATA IN WAYSIDE DIAGNOSTICS USING ENHANCED LBP-KURTOGRAMS
This paper examines three different methods in comparison for discovering abnormal sensor data retrieved by acoustic and mono-axial accelerometer sensors that are employed in the environment of different train sets and passes to achieve a cost friendly wayside diagnosis in Prague metros. Proposed m...
Main Authors: | , |
---|---|
Format: | Article |
Language: | ces |
Published: |
University of Pardubice
2017-12-01
|
Series: | Perner’s Contacts |
Subjects: | |
Online Access: | https://pernerscontacts.upce.cz/index.php/perner/article/view/474 |
_version_ | 1811250451241238528 |
---|---|
author | Onur Kilinc Jakub Vágner |
author_facet | Onur Kilinc Jakub Vágner |
author_sort | Onur Kilinc |
collection | DOAJ |
description |
This paper examines three different methods in comparison for discovering abnormal sensor data retrieved by acoustic and mono-axial accelerometer sensors that are employed in the environment of different train sets and passes to achieve a cost friendly wayside diagnosis in Prague metros. Proposed methodology, Local Binary Patterns (LBP) on resized Kurtogram images is superior to compared methods up to 75.8% Fisher Linear Discriminant Analysis (FLDA) for anomaly detection in the sensor data. Results may count to be promising even if combined acoustic and vibration sensor data related Kurtograms are used for individual train sets. Proposed method is considered to be the first step in order to achieve an efficient diagnosis framework in wayside vehicle diagnosis.
|
first_indexed | 2024-04-12T16:04:52Z |
format | Article |
id | doaj.art-fafe882fcde7410881f04565f6385c17 |
institution | Directory Open Access Journal |
issn | 1801-674X |
language | ces |
last_indexed | 2024-04-12T16:04:52Z |
publishDate | 2017-12-01 |
publisher | University of Pardubice |
record_format | Article |
series | Perner’s Contacts |
spelling | doaj.art-fafe882fcde7410881f04565f6385c172022-12-22T03:26:06ZcesUniversity of PardubicePerner’s Contacts1801-674X2017-12-01124DETECTING ANOMALOUS SENSOR DATA IN WAYSIDE DIAGNOSTICS USING ENHANCED LBP-KURTOGRAMSOnur KilincJakub Vágner This paper examines three different methods in comparison for discovering abnormal sensor data retrieved by acoustic and mono-axial accelerometer sensors that are employed in the environment of different train sets and passes to achieve a cost friendly wayside diagnosis in Prague metros. Proposed methodology, Local Binary Patterns (LBP) on resized Kurtogram images is superior to compared methods up to 75.8% Fisher Linear Discriminant Analysis (FLDA) for anomaly detection in the sensor data. Results may count to be promising even if combined acoustic and vibration sensor data related Kurtograms are used for individual train sets. Proposed method is considered to be the first step in order to achieve an efficient diagnosis framework in wayside vehicle diagnosis. https://pernerscontacts.upce.cz/index.php/perner/article/view/474Wayside diagnosislocal binary patternswavelet packet energydetecting abnormal data |
spellingShingle | Onur Kilinc Jakub Vágner DETECTING ANOMALOUS SENSOR DATA IN WAYSIDE DIAGNOSTICS USING ENHANCED LBP-KURTOGRAMS Perner’s Contacts Wayside diagnosis local binary patterns wavelet packet energy detecting abnormal data |
title | DETECTING ANOMALOUS SENSOR DATA IN WAYSIDE DIAGNOSTICS USING ENHANCED LBP-KURTOGRAMS |
title_full | DETECTING ANOMALOUS SENSOR DATA IN WAYSIDE DIAGNOSTICS USING ENHANCED LBP-KURTOGRAMS |
title_fullStr | DETECTING ANOMALOUS SENSOR DATA IN WAYSIDE DIAGNOSTICS USING ENHANCED LBP-KURTOGRAMS |
title_full_unstemmed | DETECTING ANOMALOUS SENSOR DATA IN WAYSIDE DIAGNOSTICS USING ENHANCED LBP-KURTOGRAMS |
title_short | DETECTING ANOMALOUS SENSOR DATA IN WAYSIDE DIAGNOSTICS USING ENHANCED LBP-KURTOGRAMS |
title_sort | detecting anomalous sensor data in wayside diagnostics using enhanced lbp kurtograms |
topic | Wayside diagnosis local binary patterns wavelet packet energy detecting abnormal data |
url | https://pernerscontacts.upce.cz/index.php/perner/article/view/474 |
work_keys_str_mv | AT onurkilinc detectinganomaloussensordatainwaysidediagnosticsusingenhancedlbpkurtograms AT jakubvagner detectinganomaloussensordatainwaysidediagnosticsusingenhancedlbpkurtograms |