Matilda: A visual tool for modeling with Bayesian networks

被引：4

作者：

Boneh, T.

Nicholson, A. E. ^{[1
]}

Sonenberg, E. A.

机构：

[1] Monash Univ, Fac Informat Technol, Clayton, Vic 3800, Australia

[2] Univ Melbourne, Dept Informat Syst, Melbourne, Vic 3010, Australia

来源：

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS | 2006年 / 21卷 / 11期

关键词：

D O I：

10.1002/int.20175

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A Bayesian Network (BN) consists of a qualitative part representing the structural assumptions of the domain and a quantitative part, the parameters. To date, knowledge engineering support has focused on parameter elicitation, with little support for designing the graphical structure. Poor design choices in BN construction can impact the network's performance, network maintenance, and the explanatory power of the output. We present a tool to help domain experts examine BN structure independently of the parameters. Our qualitative evaluation of the tool shows that it can help in identifying possible structural modeling errors and, hence, improve the quality of BN models. (c) 2006 Wiley Periodicals, Inc.

引用

页码：1127 / 1150

页数：24

共 21 条

[1]

Acid S, 1996, UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, P3

[2]

Andreassen S., 1989, Computer-aided electromyography and expert systems, P255

[3]

BONEH T, 2003, THESIS U MELBOURNE M

[4]

*CUERG, 2002, ERG GUID US INT DES

[5] Building probabilistic networks: "Where do the numbers come from?" - Guest editors' introduction [J].

Druzdzel, MJ ;

van der Gaag, LC .

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2000, 12 (04) :481-486

[6]

Geiger D., 1989, P 5 WORKSH UNC ART I, P118

[7]

Helsper EM, 2002, FRONT ARTIF INTEL AP, V77, P680

[8]

Henrion M., 1989, UNCERTAINTY ARTIFICI, V3, P161

[9]

Korb K., 2004, COM SCI DAT

[10]

LAGNADO DA, 2002, LEARNING CAUSAL STRU

← 1 2 3 →