New Methods for Feature Ranking

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F10%3A00166078" target="_blank" >RIV/68407700:21230/10:00166078 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21240/10:00166078

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

New Methods for Feature Ranking

Popis výsledku v původním jazyce

Most of Feature Ranking and Feature Selection approaches can be used for categorial data only. Some of them rely on statistical measures of the data, some are tailored to a specific data mining algorithm (wrapper approach). In this paper we present new methods for feature ranking and selection obtained as a combination of the above mentioned approaches. The data mining algorithm (GAME) is designed for numerical data, but it can be applied to categorial data as well. It incorporates feature selection mechanisms and new methods, proposed in this paper, derive feature ranking from final data mining model. The rank of each feature selected by model is computed by processing correlations of outputs between neighboring model?s neurons in different ways. We used four different methods based on fuzzy logic, certainty factors and simple calculus. The performance of these four feature ranking methods was tested on artificial data sets, on well known Ionosphere data set and on well known Housing

Název v anglickém jazyce

New Methods for Feature Ranking

Popis výsledku anglicky

Most of Feature Ranking and Feature Selection approaches can be used for categorial data only. Some of them rely on statistical measures of the data, some are tailored to a specific data mining algorithm (wrapper approach). In this paper we present new methods for feature ranking and selection obtained as a combination of the above mentioned approaches. The data mining algorithm (GAME) is designed for numerical data, but it can be applied to categorial data as well. It incorporates feature selection mechanisms and new methods, proposed in this paper, derive feature ranking from final data mining model. The rank of each feature selected by model is computed by processing correlations of outputs between neighboring model?s neurons in different ways. We used four different methods based on fuzzy logic, certainty factors and simple calculus. The performance of these four feature ranking methods was tested on artificial data sets, on well known Ionosphere data set and on well known Housing

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)<br>V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Rok uplatnění

2010

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Workshop 2010

ISBN

978-80-01-04513-8

ISSN

—

e-ISSN

—

Počet stran výsledku

2

Strana od-do

—

Název nakladatele

České vysoké učení technické v Praze

Místo vydání

Praha

Místo konání akce

Praha

Datum konání akce

22. 2. 2010

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—