Uncertainty quantification methods for neural networks pattern recognition

Tolo, Silvia and Santhosh, T. V. and Vinod, Gopika and Oparaji, Uchenna and Patelli, Edoardo; (2018) Uncertainty quantification methods for neural networks pattern recognition. In: 2017 IEEE Symposium Series on Computational Intelligence. Institute of Electrical and Electronics Engineers Inc., USA. ISBN 9781538627259 (https://doi.org/10.1109/SSCI.2017.8285163)

[thumbnail of Tolo-etal-SSCI2017-Uncertainty-quantification-methods-for-neural-networks-pattern-recognition]
Preview
 Text. Filename: Tolo_etal_SSCI2017_Uncertainty_quantification_methods_for_neural_networks_pattern_recognition.pdf
Accepted Author Manuscript
Download (531kB)| Preview

Abstract

On-line monitoring techniques have attracted increasing attention as a promising strategy for improving safety, maintaining availability and reducing the cost of operation and maintenance. In particular, pattern recognition tools such as artificial neural networks are today largely adopted for sensor validation, plant component monitoring, system control, and fault-diagnostics based on the data acquired during operation. However, classic artificial neural networks do not provide an error context for the model response, whose robustness remains thus difficult to estimate. Indeed, experimental data generally exhibit a time/space-varying behaviour and are hence characterized by an intrinsic level of uncertainty that unavoidably affects the performance of the tools adopted and undermines the accuracy of the analysis. For this reason, the propagation of the uncertainty and the quantification of the so called margins of uncertainty in output are crucial in making risk-informed decision. The current study presents a comparison between two different approaches for the quantification of uncertainty in artificial neural networks. The first technique presented is based on the error estimation by a series association scheme, the second approach couples Bayesian model selection technique and model averaging into a unified framework. The efficiency of these two approaches are analysed in terms of their computational cost and predictive performance, through their application to a nuclear power plant fault diagnosis system.

  • Item type:Book Section
    ID code:72134
    Dates:
    Date
    Event
    8 February 2018
    Published
    4 September 2017
    Accepted
    Notes:© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
    Subjects:Technology > Electrical engineering. Electronics Nuclear engineering
    Department:Faculty of Engineering > Civil and Environmental Engineering
    Depositing user: Pure Administrator
    Date deposited:23 Apr 2020 09:43
    Last modified:08 Apr 2024 14:00
    Related URLs:
    URI:https://strathprints.strath.ac.uk/id/eprint/72134
CORE (COnnecting REpositories)