P
Philippe Lenca
Researcher at Institut Mines-Télécom
Publications - 113
Citations - 1405
Philippe Lenca is an academic researcher from Institut Mines-Télécom. The author has contributed to research in topics: Association rule learning & Decision tree. The author has an hindex of 17, co-authored 110 publications receiving 1281 citations. Previous affiliations of Philippe Lenca include Centre national de la recherche scientifique & École nationale supérieure des télécommunications de Bretagne.
Papers
More filters
Journal ArticleDOI
On selecting interestingness measures for association rules: User oriented description and multiple criteria decision aid
TL;DR: This article proposes a new direction to select the best rules: a two-step solution to the problem of the recommendation of one or more user-adapted interestingness measures, based on meaningful classical properties.
Book ChapterDOI
Association Rule Interestingness Measures: Experimental and Theoretical Studies
TL;DR: A formal and an experimental study of 20 measures of association rule interestingness measures and the properties are used in a multi-criteria decision analysis in order to select amongst the available measures the one or those that best take into account the user’s needs.
Book ChapterDOI
A clustering of interestingness measures
TL;DR: In this article, the authors present an experimental study of the behaviour of 20 interestingness measures on 10 datasets and compare them to a previous analysis of formal and meaningful properties of the measures, by means of two clusterings.
Book ChapterDOI
Mining Top-K Periodic-Frequent Pattern from Transactional Databases without Support Threshold
Komate Amphawan,Komate Amphawan,Komate Amphawan,Philippe Lenca,Philippe Lenca,Athasit Surarerks +5 more
TL;DR: This paper introduces the problem of mining the top-k periodic frequent patterns i.e. the periodic patterns with the k highest support, and proposes an efficient single-pass algorithm, called MTKPP (Mining Top-K Periodic-frequent Patterns), which is efficient.
Book ChapterDOI
Classifying Very-High-Dimensional Data with Random Forests of Oblique Decision Trees
TL;DR: This work investigates a new approach for supervised classification with a huge number of numerical attributes and proposes a random oblique decision trees method that has significant better performance on very-high-dimensional datasets with slightly better results on lower dimensional datasets.