Matches in SemOpenAlex for { <https://semopenalex.org/work/W82425933> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W82425933 abstract "The classification performance of an associative classifier is strongly dependent on the statistic measure or metric that is used to quantify the strength of the association between features and classes (i.e., confidence, correlation etc.). Previous studies have shown that classifiers produced by different metrics may provide conflicting predictions, and that the best metric to use is data-dependent and rarely known while designing the classifier. This uncertainty concerning the optimal match between metrics and problems is a dilemma, and prevents associative classifiers to achieve their maximal performance. This dilemma is the focus of this paper. A possible solution to this dilemma is to learn the competence, expertise, or assertiveness of metrics. The basic idea is that each metric has a specific sub-domain for which it is most competent (i.e., it consistently produces more accurate classifiers than the ones produced by other metrics). Particularly, we investigate stacking-based metalearning methods, which use the training data to find the domain of competence of each metric. The meta-classifier describes the domains of competence (or areas of expertise) of each metric, enabling a more sensible use of these metrics so that competence-conscious classifiers can be produced (i.e., a metric is only used to produce classifiers for test instances that belong to its domain of competence). We conducted a systematic evaluation, using different datasets and evaluation measures, of classifiers produced by different metrics. The result is that, while no metric is always superior than all others, the selection of appropriate metrics according to their competence/expertise (i.e., competence-conscious associative classifiers) seems very effective, showing gains that range from 7% to 26% when compared to the baselines (SVMs and an existing ensemble method). This research was sponsored by UOL (www.uol.com.br) through its UOL Bolsa Pesquisa program (grant number 20080131200100), and partially supported by CNPq, Capes, Finep, Fapemig, and by the projects 5SVQ (CNPq grant number 551013/2005-2), INCTWeb (CNPq grant number 573871/2008-6), and InfoWeb (CNPq grant number 550874/2007-0)." @default.
- W82425933 created "2016-06-24" @default.
- W82425933 creator A5015728115 @default.
- W82425933 creator A5019559411 @default.
- W82425933 creator A5046370637 @default.
- W82425933 creator A5086714399 @default.
- W82425933 date "2009-04-30" @default.
- W82425933 modified "2023-09-23" @default.
- W82425933 title "The Metric Dilemma: Competence-Conscious Associative Classification" @default.
- W82425933 cites W1540371141 @default.
- W82425933 cites W1585743408 @default.
- W82425933 cites W1974054882 @default.
- W82425933 cites W2031173026 @default.
- W82425933 cites W2035720976 @default.
- W82425933 cites W2066277072 @default.
- W82425933 cites W2085419825 @default.
- W82425933 cites W2106571168 @default.
- W82425933 cites W2119254562 @default.
- W82425933 cites W2135849125 @default.
- W82425933 cites W2160535740 @default.
- W82425933 cites W2166559705 @default.
- W82425933 cites W2912573428 @default.
- W82425933 cites W2912744730 @default.
- W82425933 cites W2912934387 @default.
- W82425933 doi "https://doi.org/10.1137/1.9781611972795.79" @default.
- W82425933 hasPublicationYear "2009" @default.
- W82425933 type Work @default.
- W82425933 sameAs 82425933 @default.
- W82425933 citedByCount "1" @default.
- W82425933 crossrefType "proceedings-article" @default.
- W82425933 hasAuthorship W82425933A5015728115 @default.
- W82425933 hasAuthorship W82425933A5019559411 @default.
- W82425933 hasAuthorship W82425933A5046370637 @default.
- W82425933 hasAuthorship W82425933A5086714399 @default.
- W82425933 hasBestOaLocation W824259332 @default.
- W82425933 hasConcept C100521375 @default.
- W82425933 hasConcept C105795698 @default.
- W82425933 hasConcept C119857082 @default.
- W82425933 hasConcept C153180895 @default.
- W82425933 hasConcept C154945302 @default.
- W82425933 hasConcept C15744967 @default.
- W82425933 hasConcept C2524010 @default.
- W82425933 hasConcept C2778496695 @default.
- W82425933 hasConcept C33923547 @default.
- W82425933 hasConcept C41008148 @default.
- W82425933 hasConcept C77805123 @default.
- W82425933 hasConcept C89128539 @default.
- W82425933 hasConcept C95623464 @default.
- W82425933 hasConceptScore W82425933C100521375 @default.
- W82425933 hasConceptScore W82425933C105795698 @default.
- W82425933 hasConceptScore W82425933C119857082 @default.
- W82425933 hasConceptScore W82425933C153180895 @default.
- W82425933 hasConceptScore W82425933C154945302 @default.
- W82425933 hasConceptScore W82425933C15744967 @default.
- W82425933 hasConceptScore W82425933C2524010 @default.
- W82425933 hasConceptScore W82425933C2778496695 @default.
- W82425933 hasConceptScore W82425933C33923547 @default.
- W82425933 hasConceptScore W82425933C41008148 @default.
- W82425933 hasConceptScore W82425933C77805123 @default.
- W82425933 hasConceptScore W82425933C89128539 @default.
- W82425933 hasConceptScore W82425933C95623464 @default.
- W82425933 hasLocation W824259331 @default.
- W82425933 hasLocation W824259332 @default.
- W82425933 hasOpenAccess W82425933 @default.
- W82425933 hasPrimaryLocation W824259331 @default.
- W82425933 hasRelatedWork W2031173026 @default.
- W82425933 hasRelatedWork W2109205796 @default.
- W82425933 hasRelatedWork W2134566648 @default.
- W82425933 hasRelatedWork W2148209062 @default.
- W82425933 hasRelatedWork W2285012423 @default.
- W82425933 hasRelatedWork W2344869223 @default.
- W82425933 hasRelatedWork W2395138913 @default.
- W82425933 hasRelatedWork W2553022200 @default.
- W82425933 hasRelatedWork W2599331200 @default.
- W82425933 hasRelatedWork W2922342112 @default.
- W82425933 hasRelatedWork W2926244135 @default.
- W82425933 hasRelatedWork W2944740470 @default.
- W82425933 hasRelatedWork W2962807656 @default.
- W82425933 hasRelatedWork W3014461195 @default.
- W82425933 hasRelatedWork W3015864665 @default.
- W82425933 hasRelatedWork W3020900419 @default.
- W82425933 hasRelatedWork W3022710845 @default.
- W82425933 hasRelatedWork W3132751580 @default.
- W82425933 hasRelatedWork W3137020683 @default.
- W82425933 hasRelatedWork W3179820658 @default.
- W82425933 isParatext "false" @default.
- W82425933 isRetracted "false" @default.
- W82425933 magId "82425933" @default.
- W82425933 workType "article" @default.