An expert system based on a Bayesian network for fire safety analysis in nuclear area

Chojnacki, E.; Plumecocq, W.; Audouin, L.

doi:10.1016/j.firesaf.2019.02.007

Cited by 19 publications

(12 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In data rich contexts, CPT parameters can be evaluated by computing the appropriate frequencies from data. An example is provided by Chojnacki et al (2019) for fire safety analysis where more than 1 million of numerical simulation results are used. This method corresponds to the maximum likelihood estimation (MLE), which is described below.…”

Section: A Pure Data-driven Approachmentioning

confidence: 99%

Uncertainties in conditional probability tables of discrete Bayesian Belief Networks: A comprehensive review

Rohmer

2020

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Discrete Bayesian Belief Network (BBN) has become a popular method for the analysis of complex systems in various domains of application. One of its pillar is the specification of the parameters of the probabilistic dependence model (i.e. the cause-effect relation) represented via a Conditional Probability Table (CPT). Depending on the available data (observations, prior knowledge, expert-based information, etc.), CPTs can be populated in different manners, i.e. different assumptions can be made and different methods are available, which might lead to uncertain BBN-based results. Through an extensive review study of the past ten years, we aim at addressing three questions related to the CPT uncertainties. First, we show how to constrain these uncertainties either using elicitation of expert inputs, or using a combination of scarce data and expert-derived information. Second, we show how to integrate these uncertainties in the BBN-based analysis through propagation procedures either using probabilities or imprecise probabilities within the setting of credal or evidential networks. Finally, we show how to test the robustness of the BBN-based results to these uncertainties via sensitivity analysis specifically dedicated to BBNs. A special care was paid to describe the best practices for the implementation of the reviewed methods and the remaining gaps.

show abstract

Section: A Pure Data-driven Approachmentioning

confidence: 99%

Uncertainties in conditional probability tables of discrete Bayesian Belief Networks: A comprehensive review

Rohmer

2020

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Sistem Pakar (Expert System) adalah program berbasis pengetahuan yang menyediakan solusi-solusi dengan kualitas pakar untuk masalah -masalah dalam suatu wilayah yang spesifik [10]. Sistem pakar merupakan program komputer yang meniru proses pemikiran dan pengetahuan pakar dalam menyelesaikan suatu masalah tertentu.…”

Section: Pendahuluanunclassified

Sistem Pakar Diagnosis Penyakit Gastritis Menggunakan Metode Certainty Factor Berbasis Android

Windarto

Isnanto²,

Setiawan³

2020

View full text Add to dashboard Cite

<p>With the increasingly of the modern era, more and more diseases that arise due to human lifestyle and bacterial transmission. One of them is gastritis which occurs because of inflammation that occurs in the lining of the stomach which makes frequent pain in the stomach. From these problems, it is necessary to make an expert system application of gastritis disease which aims to provide information to the public to know the early symptoms of gastritis from an early age. The process of diagnose using the certainty factor method The methods in this study are data retrieval, system design, system making and system testing.From this research, it produces an expert system application that can diagnose the type of disease with the first test case 98.848%, the second test case 99.8464% and the third test case with the results of 99.99115264% correct and in accordance with expert knowledge. System testing is done by using black-box testing that shows the function of each unit of application 100% successful.</p>

show abstract

“…The systems can be applied in estimations, for example, for estimating fuzzy linear regression model parameters (Icen & Gunay, 2019) or in probabilistic risk assessment (Yazdi et al, 2019). Also, expert systems can be implemented in quite distinct fields of research from investment management, for example, for fire safety (Chojnacki et al, 2019).…”

Section: Literature Reviewmentioning

confidence: 99%

Stochastic Informative Expert System for Investment

Rutkauskas

Stasytytė

2020

Journal of Business Economics and Management

View full text Add to dashboard Cite

The stochastic nature of investment process implies that it should be treated not unambiguously. Instead of concentrating only on possible return, it is worth analysing three parameters when we discuss the future investment results. These parameters are return possibility, reliability of this possibility, and the riskiness. The stochastic informative expert system for investment allows to analyse the behaviour of financial markets, forecasting the dynamics of stock prices and, along with that, rationally allocating investment resources. The proposed system is based on the adequate portfolio model, previously developed by the authors. Considering the real-time characteristics of financial markets, the system can be useful for individual investors, as well as for institutional investors, such as investment funds. Also, the authors propose the original risk tolerance determination methodology, which divides investors into three categories according their risk tolerance. The system can be applicable not only to capital markets, but also to other business or macroeconomic processes. As an example, a portfolio of the interaction of macroeconomic indicators with USA, UK, and Lithuanian data is developed. Such results could be useful for economists and governments in order to attain the higher value added in a particular country.

show abstract

An expert system based on a Bayesian network for fire safety analysis in nuclear area

Cited by 19 publications

References 2 publications

Uncertainties in conditional probability tables of discrete Bayesian Belief Networks: A comprehensive review

Uncertainties in conditional probability tables of discrete Bayesian Belief Networks: A comprehensive review

Sistem Pakar Diagnosis Penyakit Gastritis Menggunakan Metode Certainty Factor Berbasis Android

Stochastic Informative Expert System for Investment

Contact Info

Product

Resources

About