A Novel Variant Autoencoder for Class Imbalance

Q4 Engineering
Chen Xinyuan, Zhao Yihang, Feng Ao, Shi Xiaoshi, Tang Zuoliang
{"title":"A Novel Variant Autoencoder for Class Imbalance","authors":"Chen Xinyuan, Zhao Yihang, Feng Ao, Shi Xiaoshi, Tang Zuoliang","doi":"10.25103/jestr.165.23","DOIUrl":null,"url":null,"abstract":"Deep learning requires a large amount of data, and enhanced processing of the data is particularly important. This study aims to investigate the enhancement of the dataset from the perspective of the underlying data distribution and solve the problem of unbalanced data samples. In this study, a novel approach called the single-sample sampling variant autoencoder (S3VAE) was proposed to generate data which were then compared. Experimental results demonstrate that, under the same data discard rate, the data generated by the S3VAE architecture exhibit a test accuracy closer to that of the original data, which proves the ability of the S3VAE architecture to generate results closer to the original data. Furthermore, the reconstruction abilities of C-VAE and S3VAE were compared using two public datasets and conducted five different discard rate experiments. As observed, the test accuracy of S3VAE is higher than that of C-VAE in all cases. With an increase in the data discard rate, the advantage of S3VAE becomes more pronounced. When the data discard rate is 97.5%, the test accuracy of S3VAE is 2.7% higher than that of C-VAE. These results confirm that the method has a significant positive effect on data enhancement and can be effectively used in practical scenarios. Moreover, this method can be extended to most advanced variant autoencoders.","PeriodicalId":15707,"journal":{"name":"Journal of Engineering Science and Technology Review","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Engineering Science and Technology Review","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.25103/jestr.165.23","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Engineering","Score":null,"Total":0}
引用次数: 0

Abstract

Deep learning requires a large amount of data, and enhanced processing of the data is particularly important. This study aims to investigate the enhancement of the dataset from the perspective of the underlying data distribution and solve the problem of unbalanced data samples. In this study, a novel approach called the single-sample sampling variant autoencoder (S3VAE) was proposed to generate data which were then compared. Experimental results demonstrate that, under the same data discard rate, the data generated by the S3VAE architecture exhibit a test accuracy closer to that of the original data, which proves the ability of the S3VAE architecture to generate results closer to the original data. Furthermore, the reconstruction abilities of C-VAE and S3VAE were compared using two public datasets and conducted five different discard rate experiments. As observed, the test accuracy of S3VAE is higher than that of C-VAE in all cases. With an increase in the data discard rate, the advantage of S3VAE becomes more pronounced. When the data discard rate is 97.5%, the test accuracy of S3VAE is 2.7% higher than that of C-VAE. These results confirm that the method has a significant positive effect on data enhancement and can be effectively used in practical scenarios. Moreover, this method can be extended to most advanced variant autoencoders.
一种新型的类不平衡自编码器
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
1.00
自引率
0.00%
发文量
66
审稿时长
24 weeks
期刊介绍: The Journal of Engineering Science and Technology Review (JESTR) is a peer reviewed international journal publishing high quality articles dediicated to all aspects of engineering. The Journal considers only manuscripts that have not been published (or submitted simultaneously), at any language, elsewhere. Contributions are in English. The Journal is published by the Eastern Macedonia and Thrace Institute of Technology (EMaTTech), located in Kavala, Greece. All articles published in JESTR are licensed under a CC BY-NC license. Copyright is by the publisher and the authors.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信