SEJan 30, 2021

Using Bayesian Modelling to Predict Software Incidents

arXiv:2102.00293v1
AI Analysis

This addresses the challenge of software reliability in embedded systems for safety-critical applications, but it appears incremental as it builds on existing Bayesian methods.

The paper tackles the problem of predicting software incidents in safety-critical systems, particularly in SOTIF environments, by proposing Bayesian Belief Networks and reports early results from their research.

Traditionally, fault- or event-tree analyses or FMEAs have been used to estimate the probability of a safety-critical device creating a dangerous condition. However, these analysis techniques are less effective for systems primarily reliant on software, and are perhaps least effective in Safety of the Intended Functionality (SOTIF) environments, where the failure or dangerous situation occurs even though all components behaved as designed. This paper describes an approach we are considering at BlackBerry QNX: using Bayesian Belief Networks to predict defects in embedded software, and reports on early results from our research.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes