Search Results

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
A new similarity measure in formal concept analysis for case-based reasoning
(2012-01-01)
Tadrat, Jirapond
;
Boonjing, Veera
;
Pattaraintakorn, Puntip
In this work, we aim at developing a better knowledge base by using formal concept analysis (FCA) and propose its new similarity measure based on vector model for case-based reasoning (CBR). The features of our proposed approaches are illustrated using a part of CBR system for both classification and problem-solving. Concept lattice knowledge base provides more accuracy classification for hierarchical data structure when comparing with non-hierarchical data structure. Dependency induced from our concept lattice knowledge base can help to suggest informative solutions for problem-solving CBR. In addition, our similarity measure improves the accuracy of classification CBR significantly when we perform experiments on the UCI data sets with cross validation. © 2011 Elsevier Ltd. All rights reserved.
Some of the metrics are blocked by your
consent settings
A new case-based classifier system using rough formal concept analysis
(2008-12-29)
Pattaraintakorn, Puntip
;
Boonjing, Veera
;
Tadrat, Jirapond
Rough set theory and formal concept analysis were invented by Pawlak and Wide in the 1980s and have been applied successfully in several domains. In this paper, we propose a new case-based classifier system based on an integrated rough set theory and formal concept analysis technique. We focus on the construction of a better knowledge base to produce the classification rules. Our system employs rough set theory to discover reduced cases. We then formulate a knowledge base with hierarchical structure by using formal concept analysis. The result is a concept lattice knowledge base embedded in our case-based classifier. We can generate classification rules from implications and subconcept-superconcept relations inside the obtained concept lattice. An illustrative example and a case study are provided to demonstrate the feasibility and applicability of our system. The advantages of our system are thus a better knowledge base for new problem classification and the flexibility to learn new rules. © 2008 IEEE.
Some of the metrics are blocked by your
consent settings
Building classification rules for case-based classifier using fuzzy sets and formal concept analysis
(2008-12-01)
Tadrat, Jirapond
;
Boonjing, Veera
;
Pattaraintakorn, Puntip
The focus of this paper is a construction of better knowledge base in case-based classifier system. Our knowledge base structure is based on concept lattice where rules are built from its subconcept-superconcept relation. Since the lattice can only be constructed from inputs with binary attributes, descriptive and numeric attributes must be transformed to binary attributes. In this paper, we propose the transformation of numeric attributes to descriptive attributes using fuzzy set theory. We experiment on benchmark data sets, Car and Iris, to determine the performance in term of number of rules used and classification precision. The results show that trend of accuracy is proportional to the size of learning inputs. The number of rules used is relatively small compared with size of training data. Our case-based classifier produces very promising results in practice and can classify the new problem more accurate than traditional classifiers. Copyright 2008 ACM.
Some of the metrics are blocked by your
consent settings
An experiment study on text transformation for compression using stoplists and frequent words
(2008-05-27)
Tadrat, Jirapond
;
Boonjing, Veera
The paper presents a new text transform algorithm suitable for embedding in compression algorithms. The strategy the new algorithm employed to increase performance of text compression is to replace words with predefined codes. Instead of using a huge dictionary containing exhaustive words as in previous works, the new algorithm uses a list of stoplists and/or frequent words. The research devised different encoding schemes for such a list. It then made experiments of using these schemes with different compression algorithms on standard texts. The result shows that each scheme gives increasing compression when using with specific compression algorithms. © 2008 IEEE.
Some of the metrics are blocked by your
consent settings
A hybrid case based reasoning system using fuzzy-rough sets and formal concept analysis
(2007-12-01)
Tadrat, Jirapond
;
Boonjing, Veera
;
Pattaraintakorn, Puntip
In this paper, we propose a new hybrid case based reasoning system based on rough set theory, formal concept analysis and fuzzy sets. This system applies rough set theory to assure minimally sufficient cases in its case base. It uses formal concept analysis to reveal knowledge of attribute dependencies in terms of concept lattices. Numeric attributes are transformed to be suitable for formal concept analysis using fuzzy sets. © 2007 IEEE.
Some of the metrics are blocked by your
consent settings
A framework for using rough sets and formal concept analysis in case based reasoning
(2007-12-01)
Tadrat, Jirapond
;
Boonjing, Veera
;
Pattaraintakorn, Puntip
A significant open problem of case based reasoning system is a construction of better knowledge base. We propose a new framework for constructing alternative knowledge base in case based reasoning system based on rough sets and formal concept analysis. Our framework first applies rough set theory for discovering reduced cases required in a case based reasoning system. We then achieve further hierarchical structure of knowledge base using formal concept analysis. The result is the concept lattice knowledge base embedded to our proposed case based reasoning system. A part of case based reasoning system is developed with an example throughout. We also discuss how our proposed framework can be beneficial for a case based reasoning system. © 2007 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results