Bayesian learning of models for estimating uncertainty in alert systems: application to air traffic conflict avoidance

2.50
Hdl Handle:
http://hdl.handle.net/10547/622537
Title:
Bayesian learning of models for estimating uncertainty in alert systems: application to air traffic conflict avoidance
Authors:
Schetinin, Vitaly ( 0000-0003-1826-0153 ) ; Jakaite, Livija; Krzanowski, Wojtek
Abstract:
Alert systems detect critical events which can happen in the short term. Uncertainties in data and in the models used for detection cause alert errors. In the case of air traffic control systems such as Short-Term Conflict Alert (STCA), uncertainty increases errors in alerts of separation loss. Statistical methods that are based on analytical assumptions can provide biased estimates of uncertainties. More accurate analysis can be achieved by using Bayesian Model Averaging, which provides estimates of the posterior probability distribution of a prediction. We propose a new approach to estimate the prediction uncertainty, which is based on observations that the uncertainty can be quantified by variance of predicted outcomes. In our approach, predictions for which variances of posterior probabilities are above a given threshold are assigned to be uncertain. To verify our approach we calculate a probability of alert based on the extrapolation of closest point of approach. Using Heathrow airport flight data we found that alerts are often generated under different conditions, variations in which lead to alert detection errors. Achieving 82.1% accuracy of modelling the STCA system, which is a necessary condition for evaluating the uncertainty in prediction, we found that the proposed method is capable of reducing the uncertain component. Comparison with a bootstrap aggregation method has demonstrated a significant reduction of uncertainty in predictions. Realistic estimates of uncertainties will open up new approaches to improving the performance of alert systems.
Affiliation:
University of Bedfordshire; University of Exeter
Citation:
Schetinin V, Jakaite L, Krzanowski W (2018) 'Bayesian learning of models for estimating uncertainty in alert systems: application to air traffic conflict avoidance', Integrated Computer-Aided Engineering, 25 (3), pp.229-245.
Publisher:
IOS Press
Journal:
Integrated Computer-Aided Engineering
Issue Date:
9-Feb-2018
URI:
http://hdl.handle.net/10547/622537
DOI:
10.3233/ICA-180567
Additional Links:
https://content.iospress.com/articles/integrated-computer-aided-engineering/ica567
Type:
Article
Language:
en
ISSN:
1069-2509
Sponsors:
This research was largely supported by the UK Engineering and Physical Sciences Research Council (EPSRC) grant GR/R24357/01 “Critical Systems and Data-Driven Technology”.
Appears in Collections:
Computing

Full metadata record

DC FieldValue Language
dc.contributor.authorSchetinin, Vitalyen
dc.contributor.authorJakaite, Livijaen
dc.contributor.authorKrzanowski, Wojteken
dc.date.accessioned2018-03-12T10:33:28Z-
dc.date.available2018-03-12T10:33:28Z-
dc.date.issued2018-02-09-
dc.identifier.citationSchetinin V, Jakaite L, Krzanowski W (2018) 'Bayesian learning of models for estimating uncertainty in alert systems: application to air traffic conflict avoidance', Integrated Computer-Aided Engineering, 25 (3), pp.229-245.en
dc.identifier.issn1069-2509-
dc.identifier.doi10.3233/ICA-180567-
dc.identifier.urihttp://hdl.handle.net/10547/622537-
dc.description.abstractAlert systems detect critical events which can happen in the short term. Uncertainties in data and in the models used for detection cause alert errors. In the case of air traffic control systems such as Short-Term Conflict Alert (STCA), uncertainty increases errors in alerts of separation loss. Statistical methods that are based on analytical assumptions can provide biased estimates of uncertainties. More accurate analysis can be achieved by using Bayesian Model Averaging, which provides estimates of the posterior probability distribution of a prediction. We propose a new approach to estimate the prediction uncertainty, which is based on observations that the uncertainty can be quantified by variance of predicted outcomes. In our approach, predictions for which variances of posterior probabilities are above a given threshold are assigned to be uncertain. To verify our approach we calculate a probability of alert based on the extrapolation of closest point of approach. Using Heathrow airport flight data we found that alerts are often generated under different conditions, variations in which lead to alert detection errors. Achieving 82.1% accuracy of modelling the STCA system, which is a necessary condition for evaluating the uncertainty in prediction, we found that the proposed method is capable of reducing the uncertain component. Comparison with a bootstrap aggregation method has demonstrated a significant reduction of uncertainty in predictions. Realistic estimates of uncertainties will open up new approaches to improving the performance of alert systems.en
dc.description.sponsorshipThis research was largely supported by the UK Engineering and Physical Sciences Research Council (EPSRC) grant GR/R24357/01 “Critical Systems and Data-Driven Technology”.en
dc.language.isoenen
dc.publisherIOS Pressen
dc.relation.urlhttps://content.iospress.com/articles/integrated-computer-aided-engineering/ica567en
dc.rightsGreen - can archive pre-print and post-print or publisher's version/PDF-
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectalert systemsen
dc.subjectuncertaintyen
dc.subjectair traffic controlen
dc.subjectBayesian model averagingen
dc.subjectMonte Carlo methodsen
dc.subjectG150 Mathematical Modellingen
dc.titleBayesian learning of models for estimating uncertainty in alert systems: application to air traffic conflict avoidanceen
dc.typeArticleen
dc.contributor.departmentUniversity of Bedfordshireen
dc.contributor.departmentUniversity of Exeteren
dc.identifier.journalIntegrated Computer-Aided Engineeringen
dc.date.updated2018-03-12T10:27:04Z-
This item is licensed under a Creative Commons License
Creative Commons
All Items in UOBREP are protected by copyright, with all rights reserved, unless otherwise indicated.