Performing Feature Selection Before Removing Outliers To Increase Classfier's Accuracy

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F18%3A00106777" target="_blank" >RIV/00216224:14330/18:00106777 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Performing Feature Selection Before Removing Outliers To Increase Classfier's Accuracy

Original language description

This work addresses the problem of feature selection for boosting the performance of outlier detectors in the context of supervised classification. Different feature selection and outlier detection methods are applied to four datasets used in the experiment and a comparative analysis between combinations of these methods is reported. We present combinations producing the best accuracy of a classifier and show the optimal number of outliers to be removed.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10200 - Computer and information sciences

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2018

Confidentiality

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

Article name in the collection

DATA A ZNALOSTI & WIKT 2018, sborník konference

ISBN

9788021456792

ISSN

—

e-ISSN

—

Number of pages

6

Pages from-to

77-82

Publisher name

VUT Brno

Place of publication

Brno

Event location

Brno

Event date

Jan 1, 2018

Type of event by nationality

EUR - Evropská akce

UT code for WoS article

—