Iterative, Probabilistic Classification Using Uncertain Information

M. B. Clausing; Thomas Sudkamp

doi:10.1109/NAECON.1991.165903

Iterative, Probabilistic Classification Using Uncertain Information

M. B. Clausing, Thomas Sudkamp

Wright State University

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

Abstract

The authors have constructed an iterative, probabilistic reasoning architecture for classification problems. A number of assumptions of conditional independence have been employed in this architecture to derive two iterative updating methods, S and D. A Bayesian network was constructed and the results compared with the iterative methods. Method S and the network are both insensitive to the order of evidence, but do not produce the same results. Further investigation of the nature of these differences is warranted. It is suggested that additional information carried in the network may allow uncertain evidence to be used more effectively than in the iterative methods.

Original language	American English
Journal	Proceedings of the IEEE 1991 National Aerospace and Electronics Conference NAECON 1991
DOIs	https://doi.org/10.1109/NAECON.1991.165903
State	Published - May 1 1991

Keywords

Bayesian methods
Calculus
Character generation
Computer architecture
Computer networks
Computer science
Iterative methods
Joining processes
Knowledge based systems
Probabilistic logic

Disciplines

Computer Sciences
Engineering
Mathematics
Physical Sciences and Mathematics

Access to Document

10.1109/NAECON.1991.165903License: Unspecified

http://dx.doi.org/10.1109/NAECON.1991.165903

Cite this

@article{8729b9ba005f4e328ac5e58dac5a902c,

title = "Iterative, Probabilistic Classification Using Uncertain Information",

abstract = " The authors have constructed an iterative, probabilistic reasoning architecture for classification problems. A number of assumptions of conditional independence have been employed in this architecture to derive two iterative updating methods, S and D. A Bayesian network was constructed and the results compared with the iterative methods. Method S and the network are both insensitive to the order of evidence, but do not produce the same results. Further investigation of the nature of these differences is warranted. It is suggested that additional information carried in the network may allow uncertain evidence to be used more effectively than in the iterative methods.",

keywords = "Bayesian methods, Calculus, Character generation, Computer architecture, Computer networks, Computer science, Iterative methods, Joining processes, Knowledge based systems, Probabilistic logic",

author = "Clausing, {M. B.} and Thomas Sudkamp",

year = "1991",

month = may,

day = "1",

doi = "10.1109/NAECON.1991.165903",

language = "American English",

journal = "Proceedings of the IEEE 1991 National Aerospace and Electronics Conference NAECON 1991",

}

TY - JOUR

T1 - Iterative, Probabilistic Classification Using Uncertain Information

AU - Clausing, M. B.

AU - Sudkamp, Thomas

PY - 1991/5/1

Y1 - 1991/5/1

N2 - The authors have constructed an iterative, probabilistic reasoning architecture for classification problems. A number of assumptions of conditional independence have been employed in this architecture to derive two iterative updating methods, S and D. A Bayesian network was constructed and the results compared with the iterative methods. Method S and the network are both insensitive to the order of evidence, but do not produce the same results. Further investigation of the nature of these differences is warranted. It is suggested that additional information carried in the network may allow uncertain evidence to be used more effectively than in the iterative methods.

AB - The authors have constructed an iterative, probabilistic reasoning architecture for classification problems. A number of assumptions of conditional independence have been employed in this architecture to derive two iterative updating methods, S and D. A Bayesian network was constructed and the results compared with the iterative methods. Method S and the network are both insensitive to the order of evidence, but do not produce the same results. Further investigation of the nature of these differences is warranted. It is suggested that additional information carried in the network may allow uncertain evidence to be used more effectively than in the iterative methods.

KW - Bayesian methods

KW - Calculus

KW - Character generation

KW - Computer architecture

KW - Computer networks

KW - Computer science

KW - Iterative methods

KW - Joining processes

KW - Knowledge based systems

KW - Probabilistic logic

UR - https://corescholar.libraries.wright.edu/cse/458

UR - http://dx.doi.org/10.1109/NAECON.1991.165903

U2 - 10.1109/NAECON.1991.165903

DO - 10.1109/NAECON.1991.165903

M3 - Article

JO - Proceedings of the IEEE 1991 National Aerospace and Electronics Conference NAECON 1991

JF - Proceedings of the IEEE 1991 National Aerospace and Electronics Conference NAECON 1991

ER -

Iterative, Probabilistic Classification Using Uncertain Information

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Cite this