基于专家级图像的高度多样化植物昆虫科Miridae非常相似物种识别的机器学习(半翅目:异翅目)

IF 4.7 1区 农林科学 Q1 ENTOMOLOGY
Alexander Popkov, Fedor Konstantinov, Vladimir Neimorovets, Alexey Solodovnikov
{"title":"基于专家级图像的高度多样化植物昆虫科Miridae非常相似物种识别的机器学习(半翅目:异翅目)","authors":"Alexander Popkov,&nbsp;Fedor Konstantinov,&nbsp;Vladimir Neimorovets,&nbsp;Alexey Solodovnikov","doi":"10.1111/syen.12543","DOIUrl":null,"url":null,"abstract":"<p>Deep learning algorithms and particularly convolutional neural networks are very successful in pattern recognition from images and are increasingly employed in biology. The development of automated systems for rapid and reliable species identification is vital for insect systematics and may revolutionize this field soon. In this study, we demonstrate the ability of a convolutional neural network to identify species based on habitus photographs with expert-level accuracy in a taxonomically challenging group where a human-based identification would require notorious genitalia dissections. Using the economically important and polymorphic plant bug genus <i>Adelphocoris Reuter</i> (Heteroptera: Miridae) as a model group, we explore the variability in the performance of 11 convolutional neural models most commonly used for image classification, test the role of class-imbalance on the model performance assessment and visualize areas of interest using three interpretation algorithms. Classification performance in our experiments with collection-based habitus photographs is high enough to identify very similar species from a large group with an expert-level accuracy. The accuracy is getting lower only in the experiments with an additional dataset of <i>Adelphocoris</i> and other live plant bugs photographs taken from the Web. Our article demonstrates the importance of comprehensive institutional insect collections for bringing deep learning algorithms into service for systematic entomology using affordable equipment and methods.</p>","PeriodicalId":22126,"journal":{"name":"Systematic Entomology","volume":null,"pages":null},"PeriodicalIF":4.7000,"publicationDate":"2022-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Machine learning for expert-level image-based identification of very similar species in the hyperdiverse plant bug family Miridae (Hemiptera: Heteroptera)\",\"authors\":\"Alexander Popkov,&nbsp;Fedor Konstantinov,&nbsp;Vladimir Neimorovets,&nbsp;Alexey Solodovnikov\",\"doi\":\"10.1111/syen.12543\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Deep learning algorithms and particularly convolutional neural networks are very successful in pattern recognition from images and are increasingly employed in biology. The development of automated systems for rapid and reliable species identification is vital for insect systematics and may revolutionize this field soon. In this study, we demonstrate the ability of a convolutional neural network to identify species based on habitus photographs with expert-level accuracy in a taxonomically challenging group where a human-based identification would require notorious genitalia dissections. Using the economically important and polymorphic plant bug genus <i>Adelphocoris Reuter</i> (Heteroptera: Miridae) as a model group, we explore the variability in the performance of 11 convolutional neural models most commonly used for image classification, test the role of class-imbalance on the model performance assessment and visualize areas of interest using three interpretation algorithms. Classification performance in our experiments with collection-based habitus photographs is high enough to identify very similar species from a large group with an expert-level accuracy. The accuracy is getting lower only in the experiments with an additional dataset of <i>Adelphocoris</i> and other live plant bugs photographs taken from the Web. Our article demonstrates the importance of comprehensive institutional insect collections for bringing deep learning algorithms into service for systematic entomology using affordable equipment and methods.</p>\",\"PeriodicalId\":22126,\"journal\":{\"name\":\"Systematic Entomology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.7000,\"publicationDate\":\"2022-03-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Systematic Entomology\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/syen.12543\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENTOMOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Systematic Entomology","FirstCategoryId":"97","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/syen.12543","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENTOMOLOGY","Score":null,"Total":0}
引用次数: 5

摘要

深度学习算法,特别是卷积神经网络在图像模式识别方面非常成功,并且越来越多地应用于生物学。开发快速可靠的物种识别自动化系统对昆虫分类学至关重要,并可能在不久的将来彻底改变这一领域。在这项研究中,我们展示了卷积神经网络在一个具有分类学挑战性的群体中以专家水平的准确性识别基于习性照片的物种的能力,其中基于人类的识别将需要臭名昭着的生殖器解剖。以具有重要经济意义和多态性的植物蝽属(Adelphocoris Reuter,异翅目:Miridae)为模型组,研究了11种最常用于图像分类的卷积神经模型性能的可变性,测试了类不平衡对模型性能评估的作用,并使用三种解释算法可视化感兴趣的区域。在我们的实验中,基于收集的习性照片的分类性能足够高,可以以专家级的精度从一个大的群体中识别出非常相似的物种。只有在使用额外的Adelphocoris数据集和其他从网上拍摄的活的植物昆虫照片进行实验时,准确性才会降低。我们的文章展示了全面的机构昆虫收集对于使用负担得起的设备和方法将深度学习算法应用于系统昆虫学的重要性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Machine learning for expert-level image-based identification of very similar species in the hyperdiverse plant bug family Miridae (Hemiptera: Heteroptera)

Machine learning for expert-level image-based identification of very similar species in the hyperdiverse plant bug family Miridae (Hemiptera: Heteroptera)

Deep learning algorithms and particularly convolutional neural networks are very successful in pattern recognition from images and are increasingly employed in biology. The development of automated systems for rapid and reliable species identification is vital for insect systematics and may revolutionize this field soon. In this study, we demonstrate the ability of a convolutional neural network to identify species based on habitus photographs with expert-level accuracy in a taxonomically challenging group where a human-based identification would require notorious genitalia dissections. Using the economically important and polymorphic plant bug genus Adelphocoris Reuter (Heteroptera: Miridae) as a model group, we explore the variability in the performance of 11 convolutional neural models most commonly used for image classification, test the role of class-imbalance on the model performance assessment and visualize areas of interest using three interpretation algorithms. Classification performance in our experiments with collection-based habitus photographs is high enough to identify very similar species from a large group with an expert-level accuracy. The accuracy is getting lower only in the experiments with an additional dataset of Adelphocoris and other live plant bugs photographs taken from the Web. Our article demonstrates the importance of comprehensive institutional insect collections for bringing deep learning algorithms into service for systematic entomology using affordable equipment and methods.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Systematic Entomology
Systematic Entomology 生物-进化生物学
CiteScore
10.50
自引率
8.30%
发文量
49
审稿时长
>12 weeks
期刊介绍: Systematic Entomology publishes original papers on insect systematics, phylogenetics and integrative taxonomy, with a preference for general interest papers of broad biological, evolutionary or zoogeographical relevance.
×
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