The University of Southampton
University of Southampton Institutional Repository

Subjective machines: probabilistic risk assessment based on deep learning of soft information

Subjective machines: probabilistic risk assessment based on deep learning of soft information
Subjective machines: probabilistic risk assessment based on deep learning of soft information
For several years machine learning methods have been proposed for risk classification. Whilst machine learning methods have also been used for failure diagnosis and condition monitoring, to the best of our knowledge, these methods have not been used for probabilistic risk assessment. Probabilistic risk assessment is a subjective process. The problem of how well machine learning methods can emulate expert judgements is challenging. Expert judgements are based on mental shortcuts, heuristics, which are susceptible to biases. This paper presents a process for developing natural language-based probabilistic risk assessment models, applying deep learning algorithms to emulate experts’ quantified risk estimates. This allows the risk analyst to obtain an apriori risk assessment when there is limited information in the form of text and numeric data. Universal Sentence Embedding (USE) with Gradient Boosting Regression (GBR) trees trained over limited structured data presented the most promising results. When we apply these models' outputs to generate survival distributions for autonomous systems’ likelihood of loss with distance, we observe that for open water and ice shelf operating environments, the differences between the survival distributions generated by the machine learning algorithm and those generated by the experts are not statistically significant.
0272-4332
Brito, Mario
82e798e7-e032-4841-992e-81c6f13a9e6c
Stevenson, Matthew, Paul
c11bc02f-acf9-4e13-a703-8ed273bcd4e8
Cristian, Bravo
d2e3a1d8-74fa-4300-ad91-26856eca161c
Brito, Mario
82e798e7-e032-4841-992e-81c6f13a9e6c
Stevenson, Matthew, Paul
c11bc02f-acf9-4e13-a703-8ed273bcd4e8
Cristian, Bravo
d2e3a1d8-74fa-4300-ad91-26856eca161c

Brito, Mario, Stevenson, Matthew, Paul and Cristian, Bravo (2022) Subjective machines: probabilistic risk assessment based on deep learning of soft information. Risk Analysis. (doi:10.1111/risa.13930).

Record type: Article

Abstract

For several years machine learning methods have been proposed for risk classification. Whilst machine learning methods have also been used for failure diagnosis and condition monitoring, to the best of our knowledge, these methods have not been used for probabilistic risk assessment. Probabilistic risk assessment is a subjective process. The problem of how well machine learning methods can emulate expert judgements is challenging. Expert judgements are based on mental shortcuts, heuristics, which are susceptible to biases. This paper presents a process for developing natural language-based probabilistic risk assessment models, applying deep learning algorithms to emulate experts’ quantified risk estimates. This allows the risk analyst to obtain an apriori risk assessment when there is limited information in the form of text and numeric data. Universal Sentence Embedding (USE) with Gradient Boosting Regression (GBR) trees trained over limited structured data presented the most promising results. When we apply these models' outputs to generate survival distributions for autonomous systems’ likelihood of loss with distance, we observe that for open water and ice shelf operating environments, the differences between the survival distributions generated by the machine learning algorithm and those generated by the experts are not statistically significant.

Text
Manuscript Subjective machines - Accepted Manuscript
Restricted to Repository staff only until 18 March 2024.
Request a copy
Text
Risk Analysis - 2022 - Brito - Subjective machines Probabilistic risk assessment based on deep learning of soft - Version of Record
Available under License Creative Commons Attribution.
Download (1MB)

More information

Accepted/In Press date: 18 March 2022
Published date: 21 April 2022

Identifiers

Local EPrints ID: 455545
URI: http://eprints.soton.ac.uk/id/eprint/455545
ISSN: 0272-4332
PURE UUID: 2d083087-51f8-42c1-b858-10f0664218f4
ORCID for Mario Brito: ORCID iD orcid.org/0000-0002-1779-4535

Catalogue record

Date deposited: 24 Mar 2022 17:46
Last modified: 19 Jul 2022 01:46

Export record

Altmetrics

Contributors

Author: Mario Brito ORCID iD
Author: Matthew, Paul Stevenson
Author: Bravo Cristian

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×