An Evolutionary Pentagon Support Vector Finder Method

Seyed Muhammad Hossein Mousavi, Vincent Charles, Tatiana Gherman

Research output: Contribution to JournalArticle

Abstract

In dealing with big data, we need effective algorithms; effectiveness that depends, among others, on the ability to remove outliers from the data set, especially when dealing with classification problems. To this aim, support vector finder algorithms have been created to save just the most important data in the data pool. Nevertheless, existing classification algorithms, such as Fuzzy C-Means (FCM), suffer from the drawback of setting the initial cluster centers imprecisely. In this paper, we avoid existing shortcomings and aim to find and remove unnecessary data in order to speed up the final classification task without losing vital samples and without harming final accuracy; in this sense, we present a unique approach for finding support vectors, named evolutionary pentagon support vector (PSV) finder method. The originality of the current research lies in using geometrical computations and evolutionary algorithms to make a more effective system, which has the advantage of higher accuracy in some data sets. The proposed method is subsequently tested with seven benchmark data sets and the results are compared to those obtained from performing classification on the original data (classification before and after PSV) under the same conditions. The testing returned promising results.
Original languageEnglish
Number of pages26
JournalExpert Systems with Applications
Publication statusAccepted/In press - 5 Feb 2020

Fingerprint

Evolutionary algorithms
Testing
Big data

Keywords

  • Big Data
  • Data mining
  • Support vector
  • Artificial Bee Colony (ABC)
  • Evolutionary clustering
  • Fuzzy C means (FCM)
  • Pentagon Support Vector finder (PSV)

Cite this

@article{bdd271e2f9e84fe887c956ba01ed973c,
title = "An Evolutionary Pentagon Support Vector Finder Method",
abstract = "In dealing with big data, we need effective algorithms; effectiveness that depends, among others, on the ability to remove outliers from the data set, especially when dealing with classification problems. To this aim, support vector finder algorithms have been created to save just the most important data in the data pool. Nevertheless, existing classification algorithms, such as Fuzzy C-Means (FCM), suffer from the drawback of setting the initial cluster centers imprecisely. In this paper, we avoid existing shortcomings and aim to find and remove unnecessary data in order to speed up the final classification task without losing vital samples and without harming final accuracy; in this sense, we present a unique approach for finding support vectors, named evolutionary pentagon support vector (PSV) finder method. The originality of the current research lies in using geometrical computations and evolutionary algorithms to make a more effective system, which has the advantage of higher accuracy in some data sets. The proposed method is subsequently tested with seven benchmark data sets and the results are compared to those obtained from performing classification on the original data (classification before and after PSV) under the same conditions. The testing returned promising results.",
keywords = "Big Data, Data mining, Support vector, Artificial Bee Colony (ABC), Evolutionary clustering, Fuzzy C means (FCM), Pentagon Support Vector finder (PSV)",
author = "Mousavi, {Seyed Muhammad Hossein} and Vincent Charles and Tatiana Gherman",
year = "2020",
month = "2",
day = "5",
language = "English",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier",

}

An Evolutionary Pentagon Support Vector Finder Method. / Mousavi, Seyed Muhammad Hossein; Charles, Vincent; Gherman, Tatiana.

In: Expert Systems with Applications, 05.02.2020.

Research output: Contribution to JournalArticle

TY - JOUR

T1 - An Evolutionary Pentagon Support Vector Finder Method

AU - Mousavi, Seyed Muhammad Hossein

AU - Charles, Vincent

AU - Gherman, Tatiana

PY - 2020/2/5

Y1 - 2020/2/5

N2 - In dealing with big data, we need effective algorithms; effectiveness that depends, among others, on the ability to remove outliers from the data set, especially when dealing with classification problems. To this aim, support vector finder algorithms have been created to save just the most important data in the data pool. Nevertheless, existing classification algorithms, such as Fuzzy C-Means (FCM), suffer from the drawback of setting the initial cluster centers imprecisely. In this paper, we avoid existing shortcomings and aim to find and remove unnecessary data in order to speed up the final classification task without losing vital samples and without harming final accuracy; in this sense, we present a unique approach for finding support vectors, named evolutionary pentagon support vector (PSV) finder method. The originality of the current research lies in using geometrical computations and evolutionary algorithms to make a more effective system, which has the advantage of higher accuracy in some data sets. The proposed method is subsequently tested with seven benchmark data sets and the results are compared to those obtained from performing classification on the original data (classification before and after PSV) under the same conditions. The testing returned promising results.

AB - In dealing with big data, we need effective algorithms; effectiveness that depends, among others, on the ability to remove outliers from the data set, especially when dealing with classification problems. To this aim, support vector finder algorithms have been created to save just the most important data in the data pool. Nevertheless, existing classification algorithms, such as Fuzzy C-Means (FCM), suffer from the drawback of setting the initial cluster centers imprecisely. In this paper, we avoid existing shortcomings and aim to find and remove unnecessary data in order to speed up the final classification task without losing vital samples and without harming final accuracy; in this sense, we present a unique approach for finding support vectors, named evolutionary pentagon support vector (PSV) finder method. The originality of the current research lies in using geometrical computations and evolutionary algorithms to make a more effective system, which has the advantage of higher accuracy in some data sets. The proposed method is subsequently tested with seven benchmark data sets and the results are compared to those obtained from performing classification on the original data (classification before and after PSV) under the same conditions. The testing returned promising results.

KW - Big Data

KW - Data mining

KW - Support vector

KW - Artificial Bee Colony (ABC)

KW - Evolutionary clustering

KW - Fuzzy C means (FCM)

KW - Pentagon Support Vector finder (PSV)

M3 - Article

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -