Abstract | ||
---|---|---|
This paper presents a novel approach for knowledge discovery from sequential data. Instead of mining the examples in their sequential form, we suppose they have been processed by a machine learning algorithm that has generalized them into a deterministic finite automaton (DFA). Thus, we present a theoretical framework to extract decision rules from this DFA. Our method relies on statistical inference theory and contrary to usual support-based frequent pattern mining techniques it does not depend on such a global threshold, but rather allows us to determine an adaptive relevance threshold. Various experiments show the advantage of mining DFA instead of mining sequences. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/ICTAI.2004.86 | ICTAI |
Keywords | Field | DocType |
data mining,decision theory,deterministic automata,finite automata,inference mechanisms,learning (artificial intelligence),pattern matching,very large databases,decision rule mining,deterministic finite automata,knowledge discovery,machine learning algorithm,pattern mining,sequential data mining,statistical inference theory,very large database | Data mining,Computer science,Theoretical computer science,Artificial intelligence,Decision theory,Statistical inference,Decision rule,Deterministic finite automaton,Finite-state machine,DFA minimization,Knowledge extraction,Pattern matching,Machine learning | Conference |
ISSN | ISBN | Citations |
1082-3409 | 0-7695-2236-X | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Francois Jacquenet | 1 | 7 | 1.16 |
Marc Sebban | 2 | 906 | 61.18 |
Georges Valetudie | 3 | 0 | 0.68 |