An incremental concept formation approach for learning from databases

Godin, Robert; Missaoui, Rokia

doi:10.1016/0304-3975(94)90195-3

Cited by 114 publications

(49 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given an entire relation R, as in Figure 1, there exist algorithms to construct its closed set lattice L; however we, and others 15,16 , find it preferable to construct L incrementally, one row or observation, at a time. This is certainly similar to real data acquisition.…”

Section: "Learning" New Rulesmentioning

confidence: 99%

“…Thus we know that x > 10 and y < 9 constitute the generator of i ∧ m, which together imply that y ≥ 5. Inspection of Figure 10 shows that this describes the elements i, j, and m. The node (16,8,12) = l ∧ m ∧ o covers only the single node (15,8,12). If ¬(x ≤ 15), then because (16,8,12) is closed we must have y ≥ 8 and y ≤ 12), or more compactly, (x > 15) → (8 ≤ y ≤ 12).…”

Section: Finding Implications With Numeric Predicatesmentioning

confidence: 99%

See 1 more Smart Citation

Establishing Logical Rules from Empirical Data

Contet

Gechter

Gruer

et al. 2007

19th IEEE International Conference on Tools With Artificial Intelligence(ICTAI 2007)

View full text Add to dashboard Cite

We review a method of generating logical rules, or axioms, from empirical data. This method, using closed set properties of formal concept analysis, has been previously described and tested on rather large sets of deterministic data. In spite of the fact that formal concept techniques have been used to prune frequent set data mining results, frequency and/or statistical significance are totally irrelevant to this method. It is strictly logical and deterministic.The contribution of this paper is a completely new extension of this method to create implications involving numeric inequalities. That is, numerical inequalities such as "age > 39" can be treated as logical predicates that have been extracted from the data itself and not postulated apriori.

show abstract

Section: "Learning" New Rulesmentioning

confidence: 99%

Section: Finding Implications With Numeric Predicatesmentioning

confidence: 99%

Establishing Logical Rules from Empirical Data

Contet

Gechter

Gruer

et al. 2007

19th IEEE International Conference on Tools With Artificial Intelligence(ICTAI 2007)

View full text Add to dashboard Cite

show abstract

“…Several types of dependencies have been investigated, ranging from classical functional dependencies (Schlimmer 1993;Mannila and Räihä 1994) to several types of attribute-oriented rules (Piatetsky-Shapiro 1991;Agrawal and Srikant 1994;Godin andMissaoui 1994, Ziarko andShan 1996), and a number of systems for their extraction have been presented. While differing in many respects, most of this work has two main common features.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper we deal with the problem of finding a minimal cover for a class of data dependencies called implication rules, useful for discovering hidden patterns in data (Godin andMissaoui 1994, Ziarko andShan 1996). An implication rule Q→R is roughly a statement of the form "for all objects in the database, if an object has Q then it has also R".…”

Section: Introductionmentioning

confidence: 99%

“…Section 4 deals with the complexity of inferring implication rules and analyses the complexity of the algorithm for finding maximally general rules. Section 5 contains an experimental comparison between the approach described in this paper and that based on lattice conceptual clustering, which was first proposed by Godin and Missaoui (1994) and has been later improved by Carpineto and Romano (submitted). Section 6 concludes the paper with a summary and some directions for future work.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Inferring minimal rule covers from relations

Carpineto

Romano

1997

Lecture Notes in Computer Science

View full text Add to dashboard Cite

An implication rule Q→R is roughly a statement of the form "for all objects in the database, if an object has Q then it has also R". We introduce a definition of minimal cover for the set of implication rules that hold in a relation, by analogy with earlier work on functional dependencies, and present an approach to computing it. The core of the proposed approach is an algorithm for inferring a reduced cover containing only maximally general rules, i.e., such that no attribute-value pair on any left side is redundant. We study the computational complexity of the proposed approach and present an experimental comparison with another method that confirms its validity, especially when the number of attributes in the database is limited.

show abstract

Design of class hierarchies based on concept, (Galois) lattices

Godin

Mili

Mineau

et al. 1998

Theory Pract. Obj. Syst.

Self Cite

View full text Add to dashboard Cite

Building and maintaining the class hierarchy has been recognized as an important but one of the most difficult activities of object-oriented design. Concept (or Galois) lattices and related structures are presented as a framework for dealing with the design and maintenance of class hierarchies. Because the design of class hierarchies is inherently an iterative and incremental process, we designed incremental algorithms that update existing Galois lattices as the result of adding, removing, or modifying class specifications. A prototype tool incorporating this and other algorithms has been developed as part of the IGLOO project, which is a large objectoriented software engineering joint research project involving academic and industrial partners. The tool can generate either the concept lattice or several variant structures incrementally by incorporating new classes one by one. The resulting hierarchies can be interactively explored and refined using a graphical browser. In addition, several metrics are computed to help evaluating the quality of the hierarchies. Experiments are presented to better assess the applicability of the approach.

show abstract

An incremental concept formation approach for learning from databases

Cited by 114 publications

References 8 publications

Establishing Logical Rules from Empirical Data

Establishing Logical Rules from Empirical Data

Inferring minimal rule covers from relations

Design of class hierarchies based on concept, (Galois) lattices

Contact Info

Product

Resources

About