人工智能培训

搜索

人工智能论文:深度学习启用了多波长空间相干显微镜,用于分类标记数据有限的疟疾感染阶段(Deep learning enabled multi-wavelengt

[复制链接]
xc133280 发表于 2019-3-15 12:17:21 | 显示全部楼层 |阅读模式
xc133280 2019-3-15 12:17:21 469 0 显示全部楼层
人工智能论文:深度学习启用了多波长空间相干显微镜,用于分类标记数据有限的疟疾感染阶段(Deep learning enabled multi-wavelength spatial coherence microscope for  the classification of malaria-infected stages with limited labelled data size)疟疾是一种威胁生命的蚊子传播的血液病,因此早期检测对健康至关重要。传统的检测方法是对Giemsa染色的血涂片进行显微镜检查,这需要训练有素的技术人员。不同阶段的疟疾的自动分类仍然是一项具有挑战性的任务,特别是在检测早期滋养体和晚期滋养体或裂殖体阶段具有有限标记数据的敏感性差。该研究旨在通过使用预先训练的卷积神经网络(CNN)作为分类器和多波长来增加样本量,开发一种快速,稳健且全自动化的系统,用于分类具有有限数据大小的疟疾的不同阶段。我们还将我们的定制CNN与其他着名的CNN进行比较,并表明我们的网络具有相当的性能和更少的计算时间。我们相信我们提出的方法可以应用于其他有限的标记生物数据集。
Malaria is a life-threatening mosquito-borne blood disease, hence earlydetection is very crucial for health.The conventional method for the detectionis a microscopic examination of Giemsa-stained blood smears, which needs ahighly trained skilled technician.Automated classifications of differentstages of malaria still a challenging task, especially having poor sensitivityin detecting the early trophozoite and late trophozoite or schizont stage withlimited labelled datasize.The study aims to develop a fast, robust and fullyautomated system for the classification of different stages of malaria withlimited data size by using the pre-trained convolutional neural networks (CNNs)as a classifier and multi-wavelength to increase the sample size.We alsocompare our customized CNN with other well-known CNNs and shows that ournetwork have a comparable performance with less computational time.We believethat our proposed method can be applied to other limited labelled biologicaldatasets.人工智能论文:深度学习启用了多波长空间相干显微镜,用于分类标记数据有限的疟疾感染阶段(Deep learning enabled multi-wavelength spatial coherence microscope for  the classification of malaria-infected stages with limited labelled data size) xd2Q89sdsyq14904.jpg
URL地址:https://arxiv.org/abs/1903.06056     ----pdf下载地址:https://arxiv.org/pdf/1903.06056    ----人工智能论文:深度学习启用了多波长空间相干显微镜,用于分类标记数据有限的疟疾感染阶段(Deep learning enabled multi-wavelength spatial coherence microscope for  the classification of malaria-infected stages with limited labelled data size)
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则 返回列表 发新帖

xc133280当前离线
新手上路

查看:469 | 回复:0

快速回复 返回顶部 返回列表