Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection.

Mosquito species identification using convolutional neural networks with a multitiered ensemble model for novel species detection.
复制标题

DOI:
10.1038/s41598-021-92891-9
复制
发表时间:
2021-07-01
期刊:
影响因子:
4.6
通讯作者:
Acharya S
Acharya S
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Goodwin A;Padmanabhan S;Hira S;Glancey M;Slinowsky M;Immidisetti R;Scavo L;Brey J;Sai Sudhakar BMM;Ford T;Heier C;Linton YM;Pecor DB;Caicedo-Quiroga L;Acharya S

文献摘要

参考文献

被引文献

相似文献

由于描述了超过3500种蚊子,准确识别与疾病传播有关的少数物种对于减轻蚊媒疾病至关重要。然而,这一任务受到有限的全球分类学专业知识和常见捕获方法一致的标本损坏的阻碍。卷积神经网络(CNN)是有前途的有限的物种集,但图像数据库的要求限制了实际的实施。使用来自67种蚊子的2696个标本的图像数据库,我们解决了实际的开集问题与新物种的检测算法。对16个已知物种的闭集分类,独立获得了97.04 ± 0.87%的准确率,当与新奇检测级联时,获得了89.07 ± 5.58%的准确率。39个物种的闭集分类产生86.07 ± 1.81%的宏观F1分数。这证明了一种准确,可扩展和实用的计算机视觉解决方案,可以识别野生捕获的蚊子,用于生物监测和有针对性的病媒控制计划,而不需要为每个新的目标区域开发广泛的图像数据库。
With over 3500 mosquito species described, accurate species identification of the few implicated in disease transmission is critical to mosquito borne disease mitigation. Yet this task is hindered by limited global taxonomic expertise and specimen damage consistent across common capture methods. Convolutional neural networks (CNNs) are promising with limited sets of species, but image database requirements restrict practical implementation. Using an image database of 2696 specimens from 67 mosquito species, we address the practical open-set problem with a detection algorithm for novel species. Closed-set classification of 16 known species achieved 97.04 ± 0.87% accuracy independently, and 89.07 ± 5.58% when cascaded with novelty detection. Closed-set classification of 39 species produces a macro F1-score of 86.07 ± 1.81%. This demonstrates an accurate, scalable, and practical computer vision solution to identify wild-caught mosquitoes for implementation in biosurveillance and targeted vector control programs, without the need for extensive image database development for each new target region.
非洲瞬间蚊子(双翅目:Culicidae)对疟疾控制程序的形态鉴定的重要性。
DOI: 10.1186/s12936-018-2189-5
发表时间: 2018-01-22
期刊: Malaria journal
影响因子: 3
作者:
Erlank E;Koekemoer LL;Coetzee M
通讯作者: Coetzee M
DOI: 10.4269/ajtmh.2003.69.200
发表时间: 2003-08-01
影响因子: 3.3
作者:
Cohuet, A;Simard, F;Fontenille, D
通讯作者: Fontenille, D
DOI: 10.1016/j.envres.2016.07.026
发表时间: 2016-11-01
影响因子: 8.3
作者:
Ebi, Kristie L.;Nealon, Joshua
通讯作者: Nealon, Joshua
使用卷积神经网络划定人类疟疾载体物种之间的隐性形态变化。
DOI: 10.1371/journal.pntd.0008904
发表时间: 2020-12
影响因子: 3.8
作者:
Couret J;Moreira DC;Bernier D;Loberti AM;Dotson EM;Alvarez M
通讯作者: Alvarez M
DOI: 10.4269/ajtmh.2002.66.804
发表时间: 2002-06-01
影响因子: 3.3
作者:
Koekemoer, LL;Kamau, L;Coetzee, M
通讯作者: Coetzee, M