Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2024 8th International Conference on System Reliability and Safety, ICSRS 2024 |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 463-472 |
| Seitenumfang | 10 |
| ISBN (elektronisch) | 9798350354508 |
| ISBN (Print) | 979-8-3503-5451-5 |
| Publikationsstatus | Veröffentlicht - 20 Nov. 2024 |
| Veranstaltung | 8th International Conference on System Reliability and Safety, ICSRS 2024 - Sicily, Italien Dauer: 20 Nov. 2024 → 22 Nov. 2024 |
Abstract
Risk assessment is essential for identifying vulnerabilities, preventing disruptions, and enhancing decision-making processes. Traditional reliability evaluation techniques, such as Fault-Tree analysis, have been extensively used but have limitations in handling continuous random variables and uncertainties. Bayesian Networks, with their ability to integrate multidisciplinary analyzes through a graph structures based on conditional dependencies, offer a robust alternative. However, traditional Bayesian Networks are inadequate for modeling small probability values and uncertainties. Enhanced Bayesian Networks address these limitations by incorporating Structural Reliability Methods, allowing the usage of continuous random variables with arbitrary distributions and interdependencies. This makes enhanced Bayesian Networks a powerful framework for a more comprehensive and reliable risk analysis across diverse scenarios. The EnhancedBayesianNetworks.jl library, implemented in Julia, leverages Julia's high-performance computing capabilities to efficiently perform advanced Monte Carlo simulations and evaluate enhanced Bayesian Networks Conditional Probability Tables.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Hardware und Architektur
- Ingenieurwesen (insg.)
- Elektrotechnik und Elektronik
- Ingenieurwesen (insg.)
- Maschinenbau
- Ingenieurwesen (insg.)
- Sicherheit, Risiko, Zuverlässigkeit und Qualität
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2024 8th International Conference on System Reliability and Safety, ICSRS 2024. Institute of Electrical and Electronics Engineers Inc., 2024. S. 463-472.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Enhanced Bayesian Networks .jl
T2 - 8th International Conference on System Reliability and Safety, ICSRS 2024
AU - Perin, Andrea
AU - Broggi, Matteo
AU - Beer, Michael
N1 - Publisher Copyright: © 2024 IEEE.
PY - 2024/11/20
Y1 - 2024/11/20
N2 - Risk assessment is essential for identifying vulnerabilities, preventing disruptions, and enhancing decision-making processes. Traditional reliability evaluation techniques, such as Fault-Tree analysis, have been extensively used but have limitations in handling continuous random variables and uncertainties. Bayesian Networks, with their ability to integrate multidisciplinary analyzes through a graph structures based on conditional dependencies, offer a robust alternative. However, traditional Bayesian Networks are inadequate for modeling small probability values and uncertainties. Enhanced Bayesian Networks address these limitations by incorporating Structural Reliability Methods, allowing the usage of continuous random variables with arbitrary distributions and interdependencies. This makes enhanced Bayesian Networks a powerful framework for a more comprehensive and reliable risk analysis across diverse scenarios. The EnhancedBayesianNetworks.jl library, implemented in Julia, leverages Julia's high-performance computing capabilities to efficiently perform advanced Monte Carlo simulations and evaluate enhanced Bayesian Networks Conditional Probability Tables.
AB - Risk assessment is essential for identifying vulnerabilities, preventing disruptions, and enhancing decision-making processes. Traditional reliability evaluation techniques, such as Fault-Tree analysis, have been extensively used but have limitations in handling continuous random variables and uncertainties. Bayesian Networks, with their ability to integrate multidisciplinary analyzes through a graph structures based on conditional dependencies, offer a robust alternative. However, traditional Bayesian Networks are inadequate for modeling small probability values and uncertainties. Enhanced Bayesian Networks address these limitations by incorporating Structural Reliability Methods, allowing the usage of continuous random variables with arbitrary distributions and interdependencies. This makes enhanced Bayesian Networks a powerful framework for a more comprehensive and reliable risk analysis across diverse scenarios. The EnhancedBayesianNetworks.jl library, implemented in Julia, leverages Julia's high-performance computing capabilities to efficiently perform advanced Monte Carlo simulations and evaluate enhanced Bayesian Networks Conditional Probability Tables.
KW - Bayesian Network
KW - Enhanced Bayesian Network
KW - Reliability
KW - Scenarios
KW - Structural Reliability Problem
UR - http://www.scopus.com/inward/record.url?scp=105003212065&partnerID=8YFLogxK
U2 - 10.1109/ICSRS63046.2024.10927415
DO - 10.1109/ICSRS63046.2024.10927415
M3 - Conference contribution
AN - SCOPUS:105003212065
SN - 979-8-3503-5451-5
SP - 463
EP - 472
BT - 2024 8th International Conference on System Reliability and Safety, ICSRS 2024
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 20 November 2024 through 22 November 2024
ER -