A novel bayesian entropy network for probabilistic damage detection and classification

Yuhao Wang, Yongming Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper introduced a novel Bayesian Entropy Network (BEN) classifier that can achieve fast learning by the ability to handle extra types of knowledge (e.g., not in the form of direct point observations). Such a classifier is based on the simple Bayes theorem and maximum entropy principle. The additional information such as mean, variance or range data about a certain feature can be coded together with the classical direct point observations. These knowledges were given in the form of constraints using the maximum relative entropy principle. The classifier is compared with a simple Naïve Bayes network. By encoding extra information into the network, the classifier behaves better when the training data size is small. In a simple example given in the presented work, the proposed BEN classifier can achieve fast learning comparing to the Naïve Bayes classifier. The proposed method is applied and demonstrated for composite structure damage detection and classification problem using numerical experiments (ongoing). The proposed method is shown to have advantages where there is not enough training data but empirical knowledge of certain feature is available. Some future work is listed in the conclusion part.

Original languageEnglish (US)
Title of host publicationAIAA Non-Deterministic Approaches
PublisherAmerican Institute of Aeronautics and Astronautics Inc, AIAA
Edition209969
ISBN (Print)9781624105296
StatePublished - Jan 1 2018
EventAIAA Non-Deterministic Approaches Conference, 2018 - Kissimmee, United States
Duration: Jan 8 2018Jan 12 2018

Other

OtherAIAA Non-Deterministic Approaches Conference, 2018
CountryUnited States
CityKissimmee
Period1/8/181/12/18

Fingerprint

Damage detection
Classifiers
Entropy
Composite structures
Experiments

ASJC Scopus subject areas

  • Building and Construction
  • Civil and Structural Engineering
  • Architecture
  • Mechanics of Materials

Cite this

Wang, Y., & Liu, Y. (2018). A novel bayesian entropy network for probabilistic damage detection and classification. In AIAA Non-Deterministic Approaches (209969 ed.). American Institute of Aeronautics and Astronautics Inc, AIAA.

A novel bayesian entropy network for probabilistic damage detection and classification. / Wang, Yuhao; Liu, Yongming.

AIAA Non-Deterministic Approaches. 209969. ed. American Institute of Aeronautics and Astronautics Inc, AIAA, 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, Y & Liu, Y 2018, A novel bayesian entropy network for probabilistic damage detection and classification. in AIAA Non-Deterministic Approaches. 209969 edn, American Institute of Aeronautics and Astronautics Inc, AIAA, AIAA Non-Deterministic Approaches Conference, 2018, Kissimmee, United States, 1/8/18.
Wang Y, Liu Y. A novel bayesian entropy network for probabilistic damage detection and classification. In AIAA Non-Deterministic Approaches. 209969 ed. American Institute of Aeronautics and Astronautics Inc, AIAA. 2018
Wang, Yuhao ; Liu, Yongming. / A novel bayesian entropy network for probabilistic damage detection and classification. AIAA Non-Deterministic Approaches. 209969. ed. American Institute of Aeronautics and Astronautics Inc, AIAA, 2018.
@inproceedings{ecc2312b68ce4ecdb0cb1483ca9439fc,
title = "A novel bayesian entropy network for probabilistic damage detection and classification",
abstract = "This paper introduced a novel Bayesian Entropy Network (BEN) classifier that can achieve fast learning by the ability to handle extra types of knowledge (e.g., not in the form of direct point observations). Such a classifier is based on the simple Bayes theorem and maximum entropy principle. The additional information such as mean, variance or range data about a certain feature can be coded together with the classical direct point observations. These knowledges were given in the form of constraints using the maximum relative entropy principle. The classifier is compared with a simple Na{\"i}ve Bayes network. By encoding extra information into the network, the classifier behaves better when the training data size is small. In a simple example given in the presented work, the proposed BEN classifier can achieve fast learning comparing to the Na{\"i}ve Bayes classifier. The proposed method is applied and demonstrated for composite structure damage detection and classification problem using numerical experiments (ongoing). The proposed method is shown to have advantages where there is not enough training data but empirical knowledge of certain feature is available. Some future work is listed in the conclusion part.",
author = "Yuhao Wang and Yongming Liu",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
isbn = "9781624105296",
booktitle = "AIAA Non-Deterministic Approaches",
publisher = "American Institute of Aeronautics and Astronautics Inc, AIAA",
edition = "209969",

}

TY - GEN

T1 - A novel bayesian entropy network for probabilistic damage detection and classification

AU - Wang, Yuhao

AU - Liu, Yongming

PY - 2018/1/1

Y1 - 2018/1/1

N2 - This paper introduced a novel Bayesian Entropy Network (BEN) classifier that can achieve fast learning by the ability to handle extra types of knowledge (e.g., not in the form of direct point observations). Such a classifier is based on the simple Bayes theorem and maximum entropy principle. The additional information such as mean, variance or range data about a certain feature can be coded together with the classical direct point observations. These knowledges were given in the form of constraints using the maximum relative entropy principle. The classifier is compared with a simple Naïve Bayes network. By encoding extra information into the network, the classifier behaves better when the training data size is small. In a simple example given in the presented work, the proposed BEN classifier can achieve fast learning comparing to the Naïve Bayes classifier. The proposed method is applied and demonstrated for composite structure damage detection and classification problem using numerical experiments (ongoing). The proposed method is shown to have advantages where there is not enough training data but empirical knowledge of certain feature is available. Some future work is listed in the conclusion part.

AB - This paper introduced a novel Bayesian Entropy Network (BEN) classifier that can achieve fast learning by the ability to handle extra types of knowledge (e.g., not in the form of direct point observations). Such a classifier is based on the simple Bayes theorem and maximum entropy principle. The additional information such as mean, variance or range data about a certain feature can be coded together with the classical direct point observations. These knowledges were given in the form of constraints using the maximum relative entropy principle. The classifier is compared with a simple Naïve Bayes network. By encoding extra information into the network, the classifier behaves better when the training data size is small. In a simple example given in the presented work, the proposed BEN classifier can achieve fast learning comparing to the Naïve Bayes classifier. The proposed method is applied and demonstrated for composite structure damage detection and classification problem using numerical experiments (ongoing). The proposed method is shown to have advantages where there is not enough training data but empirical knowledge of certain feature is available. Some future work is listed in the conclusion part.

UR - http://www.scopus.com/inward/record.url?scp=85044327129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044327129&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781624105296

BT - AIAA Non-Deterministic Approaches

PB - American Institute of Aeronautics and Astronautics Inc, AIAA

ER -