Search research articles

Search research articles

相关实验视频

Updated: Sep 9, 2025

Flying Insect Detection and Classification with Inexpensive Sensors

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

在飞行中检测登革热:利用机器学习分析蚊子的飞行模式以检测感染

Nouman Javed¹, Adam J López-Denman², Prasad N Paradkar²

¹Institute for Intelligent Systems Research and Innovation, Deakin University, Geelong, Victoria, 3216, Australia.

Advanced biology

|August 28, 2025

概括

此摘要是机器生成的。

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Chromosome-scale genome of Culicoides brevitarsis provides a resource for comparative and vector biology studies.

Parasites & vectors·2026

Same author

Automated Detection of Digital Alcohol Marketing Using SCANNER: An Integrated Deep-Learning Approach.

Drug and alcohol review·2025

Same author

PLVNet: EEG-based trust classification using Phase Locking Value connectivity and deep neural networks.

Computers in biology and medicine·2025

Same author

Contemporary digital marketing techniques used in unhealthy food campaigns targeting young people.

Appetite·2025

Same author

Characterisation of the virome of <i>Culicoides brevitarsis</i> Kieffer (Diptera: Ceratopogonidae)<i>,</i> a vector of bluetongue virus in Australia.

The Journal of general virology·2025

Same author

Complete mitochondrial genomes of <i>Culicoides brevitarsis</i> and <i>Culicoides imicola</i> biting midge vectors of Bluetongue Virus.

Mitochondrial DNA. Part B, Resources·2025

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

机器学习使用3D飞行模式准确检测感染登革热的蚊子, 提供比传统疾病监测和疫情预测方法更快的替代方案.

科学领域:

媒介性疾病监测
计算生物学
机器学习应用

背景情况:

蚊子传播的疾病对全球健康构成重大威胁.
目前的监测方法 (陷,PCR,ELISA) 是缓慢且资源密集的.
需要对蚊子感染状况进行自动化和快速评估.

研究的目的:

根据飞行模式开发和评估用于检测登革热感染的蚊子的机器学习模型.
为了比较各种分类算法的性能.
评估飞行数据特征对预测准确性的影响.

主要方法:

使用卷积神经网络 (CNN) 和立方脊线插入用于3D飞行轨迹跟踪.
使用多种机器学习模型对受感染的蚊子进行分类:CNN,XGBoost,AdaBoost,随机森林,决策树,天真贝叶斯,物流回归,MLP和CNN+XGBoost混合.
使用5倍交叉验证来评估模型的性能.

主要成果:

XGBoost获得了最高的平均精度 (81.43%),而Random Forest获得了最佳的平均F1评分 (82.80%).
在特定的验证折叠中观察到异常性能,AdaBoost达到95. 85%的准确性,Random Forest达到97. 77%的回忆.

关键词:

三维飞行模式疾病爆发机器学习算法蚊子传播的疾病载体监测

更多相关视频

A Multi-detection Assay for Malaria Transmitting Mosquitoes

A Multi-detection Assay for Malaria Transmitting Mosquitoes

Published on: February 28, 2015

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus

Published on: May 31, 2020

相关实验视频

Last Updated: Sep 9, 2025

Flying Insect Detection and Classification with Inexpensive Sensors

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

A Multi-detection Assay for Malaria Transmitting Mosquitoes

A Multi-detection Assay for Malaria Transmitting Mosquitoes

Published on: February 28, 2015

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus

Published on: May 31, 2020

随着蚊子飞行时间的延长,模型的准确性得到了提高.

结论:

对3D蚊子飞行模式的机器学习分析提供了一种快速有效的感染状况评估方法.
这种方法支持实时的病媒监测,并提高了疾病爆发的早期发现.
飞行模式分析为传统的劳动密集型监控技术提供了一个有前途的替代方案.