Szczegóły publikacji
Opis bibliograficzny
AI-based design of decision support systems for industrial risk management / Andrzej M. J. SKULIMOWSKI, Paweł ŁYDEK // W: PP-RAI'2022 [Dokument elektroniczny] : proceedings of the 3rd Polish conference on Artificial intelligence : April 25–27, 2022, Gdynia, Poland. — Wersja do Windows. — Dane tekstowe. — Gdynia : Gdynia Maritime University, 2022. — e-ISBN: 978-83-7421-401-8. — S. 138–142. — Wymagania systemowe: Adobe Reader. — Tryb dostępu: https://wydawnictwo.umg.edu.pl/pp-rai2022/pdfs/ProceedingsPP-... [2022-04-27]. — Bibliogr. s. 142, Abstr. — A. M. J. Skulimowski, P. Łydek – dod. afiliacja: International Centre for Decision Sciences and Forecasting, Progress & Business Foundation, Kraków
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
ID BaDAP | 139999 |
---|---|
Data dodania do BaDAP | 2022-04-28 |
Rok publikacji | 2022 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Wydawca | Uniwersytet Morski w Gdyni |
Abstract
This paper presents a new approach to design intelligent decision support system for industrial risk management. The need for this class of systems has been driven by complex resilience building and action planning problems that occur in large industrial plants. The proposed software architecture of the decision support system (DSS) is AI-based and applies Bayesian, causal and anticipatory networks, as well as multicriteria analysis, expert information fusion and knowledge processing techniques. The use of AI-tools follows the AI-alignment paradigm, where AI evolution is followed to discover most suitable techniques to solve safety-related problems. We propose a general scheme of DSS for risk management that includes threats, sensors, information processing, and decision models. The DSS and risk management module are coupled within a semi-supervised machine learning procedure, where the results of prior decisions serve to learn risk mitigation action parameters and managerial preferences.