机器学习分析翅膀脉纹模式可以准确识别麻蝇科、栉蝇科和蝇科蝇类。

IF 1.6 3区 农林科学 Q2 ENTOMOLOGY
Min Hao Ling, Tania Ivorra, Chong Chin Heo, April Hari Wardhana, Martin Jonathan Richard Hall, Siew Hwa Tan, Zulqarnain Mohamed, Tsung Fei Khang
{"title":"机器学习分析翅膀脉纹模式可以准确识别麻蝇科、栉蝇科和蝇科蝇类。","authors":"Min Hao Ling,&nbsp;Tania Ivorra,&nbsp;Chong Chin Heo,&nbsp;April Hari Wardhana,&nbsp;Martin Jonathan Richard Hall,&nbsp;Siew Hwa Tan,&nbsp;Zulqarnain Mohamed,&nbsp;Tsung Fei Khang","doi":"10.1111/mve.12682","DOIUrl":null,"url":null,"abstract":"<p>In medical, veterinary and forensic entomology, the ease and affordability of image data acquisition have resulted in whole-image analysis becoming an invaluable approach for species identification. Krawtchouk moment invariants are a classical mathematical transformation that can extract local features from an image, thus allowing subtle species-specific biological variations to be accentuated for subsequent analyses. We extracted Krawtchouk moment invariant features from binarised wing images of 759 male fly specimens from the Calliphoridae, Sarcophagidae and Muscidae families (13 species and a species variant). Subsequently, we trained the Generalized, Unbiased, Interaction Detection and Estimation random forests classifier using linear discriminants derived from these features and inferred the species identity of specimens from the test samples. Fivefold cross-validation results show a 98.56 ± 0.38% (standard error) mean identification accuracy at the family level and a 91.04 ± 1.33% mean identification accuracy at the species level. The mean <i>F</i>1-score of 0.89 ± 0.02 reflects good balance of precision and recall properties of the model. The present study consolidates findings from previous small pilot studies of the usefulness of wing venation patterns for inferring species identities. Thus, the stage is set for the development of a mature data analytic ecosystem for routine computer image-based identification of fly species that are of medical, veterinary and forensic importance.</p>","PeriodicalId":18350,"journal":{"name":"Medical and Veterinary Entomology","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2023-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning analysis of wing venation patterns accurately identifies Sarcophagidae, Calliphoridae and Muscidae fly species\",\"authors\":\"Min Hao Ling,&nbsp;Tania Ivorra,&nbsp;Chong Chin Heo,&nbsp;April Hari Wardhana,&nbsp;Martin Jonathan Richard Hall,&nbsp;Siew Hwa Tan,&nbsp;Zulqarnain Mohamed,&nbsp;Tsung Fei Khang\",\"doi\":\"10.1111/mve.12682\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>In medical, veterinary and forensic entomology, the ease and affordability of image data acquisition have resulted in whole-image analysis becoming an invaluable approach for species identification. Krawtchouk moment invariants are a classical mathematical transformation that can extract local features from an image, thus allowing subtle species-specific biological variations to be accentuated for subsequent analyses. We extracted Krawtchouk moment invariant features from binarised wing images of 759 male fly specimens from the Calliphoridae, Sarcophagidae and Muscidae families (13 species and a species variant). Subsequently, we trained the Generalized, Unbiased, Interaction Detection and Estimation random forests classifier using linear discriminants derived from these features and inferred the species identity of specimens from the test samples. Fivefold cross-validation results show a 98.56 ± 0.38% (standard error) mean identification accuracy at the family level and a 91.04 ± 1.33% mean identification accuracy at the species level. The mean <i>F</i>1-score of 0.89 ± 0.02 reflects good balance of precision and recall properties of the model. The present study consolidates findings from previous small pilot studies of the usefulness of wing venation patterns for inferring species identities. Thus, the stage is set for the development of a mature data analytic ecosystem for routine computer image-based identification of fly species that are of medical, veterinary and forensic importance.</p>\",\"PeriodicalId\":18350,\"journal\":{\"name\":\"Medical and Veterinary Entomology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2023-07-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Medical and Veterinary Entomology\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1111/mve.12682\",\"RegionNum\":3,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENTOMOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical and Veterinary Entomology","FirstCategoryId":"97","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/mve.12682","RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENTOMOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

在医学、兽医和法医昆虫学中,图像数据采集的方便性和可负担性使全图像分析成为物种识别的宝贵方法。Krawtchouk不变矩是一种经典的数学变换,它可以从图像中提取局部特征,从而使细微的物种特异性生物变化能够被强调,以便进行后续分析。我们从来自丽蝇科、沙蝇科和蝇科的759个雄蝇标本(13个物种和一个物种变体)的二值化翅膀图像中提取了Krawtchouk矩不变特征。随后,我们使用从这些特征导出的线性判别法训练了广义、无偏、交互检测和估计随机森林分类器,并从测试样本中推断出样本的物种身份。五倍交叉验证结果显示98.56 ± 0.38%(标准误差)家庭水平的平均识别准确率和91.04 ± 物种水平的平均识别准确率为1.33%。F1平均得分为0.89 ± 0.02反映了模型的精度和召回特性之间的良好平衡。本研究综合了先前小型试点研究的结果,即翼脉模式对推断物种身份的有用性。因此,为开发一个成熟的数据分析生态系统奠定了基础,该生态系统用于具有医学、兽医和法医学重要性的苍蝇物种的常规计算机图像识别。
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 analysis of wing venation patterns accurately identifies Sarcophagidae, Calliphoridae and Muscidae fly species

Machine learning analysis of wing venation patterns accurately identifies Sarcophagidae, Calliphoridae and Muscidae fly species

In medical, veterinary and forensic entomology, the ease and affordability of image data acquisition have resulted in whole-image analysis becoming an invaluable approach for species identification. Krawtchouk moment invariants are a classical mathematical transformation that can extract local features from an image, thus allowing subtle species-specific biological variations to be accentuated for subsequent analyses. We extracted Krawtchouk moment invariant features from binarised wing images of 759 male fly specimens from the Calliphoridae, Sarcophagidae and Muscidae families (13 species and a species variant). Subsequently, we trained the Generalized, Unbiased, Interaction Detection and Estimation random forests classifier using linear discriminants derived from these features and inferred the species identity of specimens from the test samples. Fivefold cross-validation results show a 98.56 ± 0.38% (standard error) mean identification accuracy at the family level and a 91.04 ± 1.33% mean identification accuracy at the species level. The mean F1-score of 0.89 ± 0.02 reflects good balance of precision and recall properties of the model. The present study consolidates findings from previous small pilot studies of the usefulness of wing venation patterns for inferring species identities. Thus, the stage is set for the development of a mature data analytic ecosystem for routine computer image-based identification of fly species that are of medical, veterinary and forensic importance.

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
Medical and Veterinary Entomology
Medical and Veterinary Entomology 农林科学-昆虫学
CiteScore
3.70
自引率
5.30%
发文量
65
审稿时长
12-24 weeks
期刊介绍: Medical and Veterinary Entomology is the leading periodical in its field. The Journal covers the biology and control of insects, ticks, mites and other arthropods of medical and veterinary importance. The main strengths of the Journal lie in the fields of: -epidemiology and transmission of vector-borne pathogens changes in vector distribution that have impact on the pathogen transmission- arthropod behaviour and ecology- novel, field evaluated, approaches to biological and chemical control methods- host arthropod interactions. Please note that we do not consider submissions in forensic entomology.
×
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