kbExplorator vs. rule-based knowledge bases

Agnieszka Nowak-Brzezińska

Abstract


The aim of the study was to describe the functionality of the kbExplorator system which allows to create and use of rule-based knowledge bases with an inference algorithms. Three available tools: Jess, Drools and PC-Shell were characterized and compared to the kbExplorator co-created by the author. Apart from formal definition, an example of the knowledge base with rules partition was shown, and application process implemented for such a knowledge base was discussed.

Keywords


rule-based knowledge base; inference process; rules partition; similarity of rules; expert systems

Full Text:

PDF (Polski)

References


Friedman-Hill E.: Jess in Action: Rule Based Systems in Java. Manning Publications.

http://docs.jboss.org/drools/release/5.2.0.Final/drools-expert-docs/html/ch01.html

https://krzysztof-michalik.com/my-ai-systems/pc-shell-hybrid-expert-system/

Forgy C.: A network match routine for production systems. Working Paper, 1974.

Nowak-Brzezińska A.: Optymalizacja systemów wspomagania decyzji. Studia Informatica, Vol. 32, No. 2A(96), Gliwice 2011, s. 403÷416.

Nowak-Brzezińska A., Simiński R.: ,New inference algorithms based on rules partition. CS&P 2014, Informatik-Berichte, Vol. 245, Humboldt-University, Chemnitz, Germany 2014.

Nowak-Brzezińska A., Simiński R.: Knowledge mining approach for optimization of inference processes in rule knowledge bases. Lecture Notes in Computer Science, Vol. 7567, Springer, Berlin, Heidelberg 2012, s. 534÷537.

Simiński R.: Extraction of Rules Dependencies for Optimization of Backward Inference Algorithm. Communications in Computer and Information Science, Vol. 424, Springer, 2014, s. 191÷200




DOI: http://dx.doi.org/10.21936/si2015_v36.n1.722