main.tex

\documentclass[sigconf]{acmart}


\usepackage{booktabs}    % For formal tables
\usepackage{mathtools}
\usepackage{multirow}
\usepackage{subcaption}
\usepackage{tabularx}


% For subcaption
\captionsetup[subfigure]{labelformat=simple}
\renewcommand{\thesubfigure}{(\alph{subfigure})}


% Copyright
%\setcopyright{none}
%\setcopyright{acmcopyright}
%\setcopyright{acmlicensed}
\setcopyright{rightsretained}
%\setcopyright{usgov}
%\setcopyright{usgovmixed}
%\setcopyright{cagov}
%\setcopyright{cagovmixed}


% DOI
\acmDOI{10.1145/3377929.3398153}


% ISBN
\acmISBN{978-1-4503-7127-8/20/07}


% Conference
\acmConference[GECCO '20 Companion]{Genetic and Evolutionary Computation Conference Companion}{July 8--12, 2020}{Cancún, Mexico}
\acmYear{2020}
\copyrightyear{2020}
%\acmArticle{4}
\acmPrice{15.00}


% These commands are optional
\acmBooktitle{Genetic and Evolutionary Computation Conference Companion (GECCO '20 Companion), July 8--12, 2020, Cancún, Mexico}
%\editor{Jennifer B. Sartor}
%\editor{Theo D'Hondt}
%\editor{Wolfgang De Meuter}


\begin{document}

\title{A Genetic Algorithm to Optimize SMOTE and GAN Ratios in Class Imbalanced Datasets}


%% Authors
\author{Hwi-Yeon Cho}
\orcid{0000-0002-4604-2578}
\affiliation{%
    \institution{Department of Computer Science, Kwangwoon University}
    \city{Seoul}
    \country{Republic of Korea}
}
\email{hwyn.cho@gmail.com}

\author{Yong-Hyuk Kim}
\orcid{0000-0002-0492-0889}
\affiliation{%
    \institution{Department of Computer Science, Kwangwoon University}
    \city{Seoul}
    \state{Republic of Korea}
}
\email{yhdfly@kw.ac.kr}

% The default list of authors is too long for headers.
\renewcommand{\shortauthors}{H.-Y. Cho et al.}


\begin{abstract}
Class imbalance is one of the problem easily encountered in the fields of data analysis and machine learning.
When there is an imbalance in learning dataset, machine learning models become biased and learn inaccurate classifiers.
To resolve such data imbalance problems, a strategy that increases the volume of data of minority classes is often used by applying the synthetic minority oversampling technique (SMOTE).
Furthermore, the use of generative adversarial networks (GANs) for data oversampling has recently become more common.
This research used a genetic algorithm to search and optimize the combinations of oversampling ratios based on the SMOTE and GAN techniques.
The case in which the proposed method was used was compared with the cases in which a single technique was used to train either the imbalanced data or oversampled data.
From the results, it was established that the classifier that learned the oversampled data with the optimized ratio using the proposed method was superior in classification performance.
\end{abstract}


%
% The code below should be generated by the tool at http://dl.acm.org/ccs.cfm
% Please copy and paste the code instead of the example below.
%
\begin{CCSXML}
<ccs2012>
    <concept>
        <concept_id>10010147.10010257.10010293.10011809.10011812</concept_id>
        <concept_desc>Computing methodologies~Genetic algorithms</concept_desc>
        <concept_significance>500</concept_significance>
    </concept>

    <concept>
       <concept_id>10010147.10010257.10010293</concept_id>
       <concept_desc>Computing methodologies~Machine learning approaches</concept_desc>
       <concept_significance>300</concept_significance>
    </concept>
</ccs2012>
\end{CCSXML}

\ccsdesc[500]{Computing methodologies~Genetic algorithms}
\ccsdesc[300]{Computing methodologies~Machine learning approaches}


\keywords{genetic algorithm, machine learning}


\maketitle


\input{body}


\begin{acks}
This research was a part of the project titled `Marine Oil Spill Risk Assessment and Development of Response Support System through Big Data Analysis', funded by the Korea Coast Guard.
\end{acks}


\bibliographystyle{ACM-Reference-Format}
% \bibliographystyle{ieeetr}
\bibliography{bibliography}


\end{document}