Predictive abnormal events analysis using continuous Bayesian network

Guozheng Song; Faisal Khan; Ming Yang; Hangzhou Wang

doi:10.1115/1.4035438

Predictive abnormal events analysis using continuous Bayesian network

Guozheng Song, Faisal Khan^*, Ming Yang, Hangzhou Wang

^*Corresponding author for this work

Research output: Contribution to journal › Article › Scientific › peer-review

7 Citations (Scopus)

Abstract

The reliable prediction and diagnosis of abnormal events provide much needed guidance for risk management. The traditional Bayesian network (traditional BN) has been used to dynamically predict and diagnose abnormal events. However, its inherent limitation caused by discrete categorization of random variables degrades the assessment reliability. This paper applied a continuous Bayesian network (CBN)-based model to reduce the above-mentioned limitation. To compute complex posterior distributions of CBN, the Markov chain Monte Carlo method (MCMC) was used. A case study was conducted to demonstrate the application of CBN, based on which a comparative analysis of the traditional BN and CBN was presented. This work highlights that the use of CBN can overcome the drawbacks of traditional BN to make dynamic prediction and diagnosis analysis more reliable.

Original language	English
Article number	041004
Journal	ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering
Volume	3
Issue number	4
DOIs	https://doi.org/10.1115/1.4035438
Publication status	Published - Dec 2017
Externally published	Yes

Keywords

Abnormal events
Continuous Bayesian network
Dynamic analysis
Markov chain Monte Carlo method
Uncertainty

Access to Document

10.1115/1.4035438

Cite this

@article{d644fa9a760f4d26a47d247d84a99a08,

title = "Predictive abnormal events analysis using continuous Bayesian network",

abstract = "The reliable prediction and diagnosis of abnormal events provide much needed guidance for risk management. The traditional Bayesian network (traditional BN) has been used to dynamically predict and diagnose abnormal events. However, its inherent limitation caused by discrete categorization of random variables degrades the assessment reliability. This paper applied a continuous Bayesian network (CBN)-based model to reduce the above-mentioned limitation. To compute complex posterior distributions of CBN, the Markov chain Monte Carlo method (MCMC) was used. A case study was conducted to demonstrate the application of CBN, based on which a comparative analysis of the traditional BN and CBN was presented. This work highlights that the use of CBN can overcome the drawbacks of traditional BN to make dynamic prediction and diagnosis analysis more reliable.",

keywords = "Abnormal events, Continuous Bayesian network, Dynamic analysis, Markov chain Monte Carlo method, Uncertainty",

author = "Guozheng Song and Faisal Khan and Ming Yang and Hangzhou Wang",

year = "2017",

month = dec,

doi = "10.1115/1.4035438",

language = "English",

volume = "3",

journal = "ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering",

issn = "2332-9017",

publisher = "The American Society of Mechanical Engineers (ASME)",

number = "4",

}

TY - JOUR

T1 - Predictive abnormal events analysis using continuous Bayesian network

AU - Song, Guozheng

AU - Khan, Faisal

AU - Yang, Ming

AU - Wang, Hangzhou

PY - 2017/12

Y1 - 2017/12

N2 - The reliable prediction and diagnosis of abnormal events provide much needed guidance for risk management. The traditional Bayesian network (traditional BN) has been used to dynamically predict and diagnose abnormal events. However, its inherent limitation caused by discrete categorization of random variables degrades the assessment reliability. This paper applied a continuous Bayesian network (CBN)-based model to reduce the above-mentioned limitation. To compute complex posterior distributions of CBN, the Markov chain Monte Carlo method (MCMC) was used. A case study was conducted to demonstrate the application of CBN, based on which a comparative analysis of the traditional BN and CBN was presented. This work highlights that the use of CBN can overcome the drawbacks of traditional BN to make dynamic prediction and diagnosis analysis more reliable.

AB - The reliable prediction and diagnosis of abnormal events provide much needed guidance for risk management. The traditional Bayesian network (traditional BN) has been used to dynamically predict and diagnose abnormal events. However, its inherent limitation caused by discrete categorization of random variables degrades the assessment reliability. This paper applied a continuous Bayesian network (CBN)-based model to reduce the above-mentioned limitation. To compute complex posterior distributions of CBN, the Markov chain Monte Carlo method (MCMC) was used. A case study was conducted to demonstrate the application of CBN, based on which a comparative analysis of the traditional BN and CBN was presented. This work highlights that the use of CBN can overcome the drawbacks of traditional BN to make dynamic prediction and diagnosis analysis more reliable.

KW - Abnormal events

KW - Continuous Bayesian network

KW - Dynamic analysis

KW - Markov chain Monte Carlo method

KW - Uncertainty

UR - http://www.scopus.com/inward/record.url?scp=85047053120&partnerID=8YFLogxK

U2 - 10.1115/1.4035438

DO - 10.1115/1.4035438

M3 - Article

AN - SCOPUS:85047053120

SN - 2332-9017

VL - 3

JO - ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering

JF - ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering

IS - 4

M1 - 041004

ER -

Predictive abnormal events analysis using continuous Bayesian network

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this