Automated Corn Seed Fusarium Disease Classification System Using Hybrid Feature Space and Conventional Machine Learning Techniques

Samreen Naeem, Aqib Ali, Jamal Abdul Nasir, Arooj Fatima, Farrukh Jamal, M. Ahmed, Muhammad Rizwan, Sania Anam, Muhammad Zubair
{"title":"Automated Corn Seed Fusarium Disease Classification System Using Hybrid Feature Space and Conventional Machine Learning Techniques","authors":"Samreen Naeem, Aqib Ali, Jamal Abdul Nasir, Arooj Fatima, Farrukh Jamal, M. Ahmed, Muhammad Rizwan, Sania Anam, Muhammad Zubair","doi":"10.53560/ppasa(58-2)692","DOIUrl":null,"url":null,"abstract":"The purpose of this learning is to detect the Corn Seed Fusarium Disease using Hybrid Feature Space and Conventional machine learning (ML) approaches. A novel machine learning approach is employed for the classification of a total of six types of corn seed are collected which contain Infected Fusarium (moniliforme, graminearum, gibberella, verticillioides, kernel) as well as healthy corn seed, based on a multi-feature dataset, which is the grouping of geometric, texture and histogram features extracted from digital images. For each corn seed image, a total of twenty-five multi-features have been developed on every area of interest (AOI), sizes (50 × 50), (100 × 100), (150 × 150), and (200 × 200). A total of seven optimized features were selected by using a machine learning-based algorithm named “Correlation-based Feature Selection”. For experimentation, “Random forest”, “BayesNet” and “LogitBoost” have been employed using an optimized multi-feature user-supplied dataset divided with 70% training and 30 % testing. A comparative analysis of three ML classifiers RF, BN, and LB have been used and a considerably very high classification ratio of 96.67 %, 97.22 %, and 97.78 % have been achieved respectively when the AOI size (200×200) have been deployed to the classifiers.","PeriodicalId":36961,"journal":{"name":"Proceedings of the Pakistan Academy of Sciences: Part A","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2021-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Pakistan Academy of Sciences: Part A","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.53560/ppasa(58-2)692","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Physics and Astronomy","Score":null,"Total":0}
引用次数: 0

Abstract

The purpose of this learning is to detect the Corn Seed Fusarium Disease using Hybrid Feature Space and Conventional machine learning (ML) approaches. A novel machine learning approach is employed for the classification of a total of six types of corn seed are collected which contain Infected Fusarium (moniliforme, graminearum, gibberella, verticillioides, kernel) as well as healthy corn seed, based on a multi-feature dataset, which is the grouping of geometric, texture and histogram features extracted from digital images. For each corn seed image, a total of twenty-five multi-features have been developed on every area of interest (AOI), sizes (50 × 50), (100 × 100), (150 × 150), and (200 × 200). A total of seven optimized features were selected by using a machine learning-based algorithm named “Correlation-based Feature Selection”. For experimentation, “Random forest”, “BayesNet” and “LogitBoost” have been employed using an optimized multi-feature user-supplied dataset divided with 70% training and 30 % testing. A comparative analysis of three ML classifiers RF, BN, and LB have been used and a considerably very high classification ratio of 96.67 %, 97.22 %, and 97.78 % have been achieved respectively when the AOI size (200×200) have been deployed to the classifiers.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于混合特征空间和传统机器学习技术的玉米种子枯萎病自动分类系统
本学习的目的是利用混合特征空间和传统机器学习(ML)方法检测玉米种子枯萎病。采用一种新的机器学习方法,基于从数字图像中提取的几何、纹理和直方图特征分组的多特征数据集,对收集到的含有感染镰刀菌(moniliforme, graminearum, gibberella, verticillioides, kernel)和健康玉米种子的六种玉米种子进行分类。对于每张玉米种子图像,在每个感兴趣区域(AOI)、大小(50 × 50)、(100 × 100)、(150 × 150)和(200 × 200)上共开发了25个多特征。采用基于机器学习的“相关性特征选择”算法,共选择了7个优化特征。在实验中,“随机森林”、“BayesNet”和“LogitBoost”使用了一个优化的多特征用户提供的数据集,其中70%的训练和30%的测试。对三种ML分类器RF、BN和LB进行了比较分析,当AOI大小(200×200)部署到分类器时,分类率分别达到了96.67%、97.22%和97.78%。
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 去求助
来源期刊
Proceedings of the Pakistan Academy of Sciences: Part A
Proceedings of the Pakistan Academy of Sciences: Part A Computer Science-Computer Science (all)
CiteScore
0.70
自引率
0.00%
发文量
15
期刊最新文献
Practical Analysis of Tap Water Dissolved Solids Efficient Reduction Acoustical Analysis of Insertion Losses of Ceiling Materials Blockchain in Healthcare: A Comprehensive Survey of Implementations and a Secure Model Proposal Design and Development of Neutronics and Thermal Hydraulics Modeling Code for ACP1000 Nuclear Reactor Dynamics in LabVIEW Quantum Computer Architecture: A Quantum Circuit-Based Approach Towards Quantum Neural Network
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1