Online Verification through Model Checking of Medical Critical Intelligent Systems - Université Paris 1 Panthéon-Sorbonne Access content directly
Conference Papers Year : 2020

Online Verification through Model Checking of Medical Critical Intelligent Systems

Abstract

Software systems based on Artificial Intelligence (AI) and Machine Learning (ML) are being widely adopted in various scenarios, from online shopping to medical applications. When developing these systems, one needs to take into account that they should be verifiable to make sure that they are in accordance with their requirements. In this work we propose a framework to perform online verification of ML models, through the use of model checking. In order to validate the proposal, we apply it to the medical domain to help qualify medical risk. The results reveal that we can efficiently use the framework to determine if a patient is close to the decision boundary. This is particularly relevant since these patients are the ones that might be misclassified. As such, our framework can be used to help medical teams make better informed decisions.
Fichier principal
Vignette du fichier
_DSML_2020__Verification_through_model_checking.pdf (277.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03967999 , version 1 (21-03-2023)

Identifiers

Cite

Joao Martins, Raul Barbosa, Nuno Lourenco, Jacques Robin, Henrique Madeira. Online Verification through Model Checking of Medical Critical Intelligent Systems. 2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), Jun 2020, Valencia, Spain. pp.32-37, ⟨10.1109/DSN-W50199.2020.00015⟩. ⟨hal-03967999⟩

Collections

UNIV-PARIS1 CRI
6 View
25 Download

Altmetric

Share

Gmail Facebook X LinkedIn More