Automated fuzzy-clustering for Doctus expert system

Zoltán Baracskai, Viktor Dörfler

Research output: Contribution to conferencePaper

Abstract

Our Knowledge-Based Expert System Shell 'Doctus'1 is capable of deduction also called rule-based reasoning and of induction, which is the symbolic version of reasoning by cases2 . If connected to databases or data warehouses the inductive reasoning of Doctus is also used for data mining. To handle numerical domains Doctus uses statistical clustering algorithm. We define the problem in three steps: how to perform a clustering, which is neither rigid nor sensitive to noise, benefiting from the properties of the application domain, reducing the complexity as much as possible, and supplying the decision maker with useful information enabling the possibility of interaction? In this paper we present the conception of Automated FuzzyClustering using triangular and trapezoidal Fuzzy-sets, which provides overlapping Fuzzy-set covering of the domain.

Conference

ConferenceInternational Conference on Computational Cybernetics
Abbreviated titleICCC 2003
CountryHungary
CitySiófok
Period29/08/0331/08/03
Internet address

Fingerprint

Fuzzy clustering
Expert system
Fuzzy sets
Conception
Knowledge-based
Interaction
Deduction
Data warehouse
Data base
Shell
Rule-based
Clustering
Data mining
Decision maker
Overlapping
Induction
Clustering algorithm

Keywords

  • Doctus
  • fuzzy logic
  • expert system
  • decision support systems

Cite this

Baracskai, Z., & Dörfler, V. (2003). Automated fuzzy-clustering for Doctus expert system. Paper presented at International Conference on Computational Cybernetics , Siófok, Hungary.
Baracskai, Zoltán ; Dörfler, Viktor. / Automated fuzzy-clustering for Doctus expert system. Paper presented at International Conference on Computational Cybernetics , Siófok, Hungary.6 p.
@conference{579614856a9447c2bfd6f87a396a04a0,
title = "Automated fuzzy-clustering for Doctus expert system",
abstract = "Our Knowledge-Based Expert System Shell 'Doctus'1 is capable of deduction also called rule-based reasoning and of induction, which is the symbolic version of reasoning by cases2 . If connected to databases or data warehouses the inductive reasoning of Doctus is also used for data mining. To handle numerical domains Doctus uses statistical clustering algorithm. We define the problem in three steps: how to perform a clustering, which is neither rigid nor sensitive to noise, benefiting from the properties of the application domain, reducing the complexity as much as possible, and supplying the decision maker with useful information enabling the possibility of interaction? In this paper we present the conception of Automated FuzzyClustering using triangular and trapezoidal Fuzzy-sets, which provides overlapping Fuzzy-set covering of the domain.",
keywords = "Doctus, fuzzy logic, expert system, decision support systems",
author = "Zolt{\'a}n Baracskai and Viktor D{\"o}rfler",
year = "2003",
month = "8",
day = "29",
language = "English",
note = "International Conference on Computational Cybernetics , ICCC 2003 ; Conference date: 29-08-2003 Through 31-08-2003",
url = "http://bgk.uni-obuda.hu/iccc03/index_c.html",

}

Baracskai, Z & Dörfler, V 2003, 'Automated fuzzy-clustering for Doctus expert system' Paper presented at International Conference on Computational Cybernetics , Siófok, Hungary, 29/08/03 - 31/08/03, .

Automated fuzzy-clustering for Doctus expert system. / Baracskai, Zoltán; Dörfler, Viktor.

2003. Paper presented at International Conference on Computational Cybernetics , Siófok, Hungary.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Automated fuzzy-clustering for Doctus expert system

AU - Baracskai, Zoltán

AU - Dörfler, Viktor

PY - 2003/8/29

Y1 - 2003/8/29

N2 - Our Knowledge-Based Expert System Shell 'Doctus'1 is capable of deduction also called rule-based reasoning and of induction, which is the symbolic version of reasoning by cases2 . If connected to databases or data warehouses the inductive reasoning of Doctus is also used for data mining. To handle numerical domains Doctus uses statistical clustering algorithm. We define the problem in three steps: how to perform a clustering, which is neither rigid nor sensitive to noise, benefiting from the properties of the application domain, reducing the complexity as much as possible, and supplying the decision maker with useful information enabling the possibility of interaction? In this paper we present the conception of Automated FuzzyClustering using triangular and trapezoidal Fuzzy-sets, which provides overlapping Fuzzy-set covering of the domain.

AB - Our Knowledge-Based Expert System Shell 'Doctus'1 is capable of deduction also called rule-based reasoning and of induction, which is the symbolic version of reasoning by cases2 . If connected to databases or data warehouses the inductive reasoning of Doctus is also used for data mining. To handle numerical domains Doctus uses statistical clustering algorithm. We define the problem in three steps: how to perform a clustering, which is neither rigid nor sensitive to noise, benefiting from the properties of the application domain, reducing the complexity as much as possible, and supplying the decision maker with useful information enabling the possibility of interaction? In this paper we present the conception of Automated FuzzyClustering using triangular and trapezoidal Fuzzy-sets, which provides overlapping Fuzzy-set covering of the domain.

KW - Doctus

KW - fuzzy logic

KW - expert system

KW - decision support systems

UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.2484

M3 - Paper

ER -

Baracskai Z, Dörfler V. Automated fuzzy-clustering for Doctus expert system. 2003. Paper presented at International Conference on Computational Cybernetics , Siófok, Hungary.