摘要
针对空间站等空间密闭舱室中微生物的有效监测等问题,选取空间密闭舱室的4种典型真菌,在空间舱常用铝合金板材料表面进行接种腐蚀实验,得到了真菌滋生图像。通过图像增强、特征筛选等方法对图像进行预处理得到数据集,比较了支持向量机(SVM)和随机森林2种分类模型的识别效果。结果表明:SVM模型对铝合金板材料表面真菌滋生图像的种类识别效果要优于随机森林模型,且对真菌种类识别和真菌生物量等级分类识别的准确率均达到97%以上。
To effectively monitor the microorganisms in airtight cabins such as space station,four typical fungi in space airtight cabins were selected to inoculate corrosion experiments on the surface of commonly used aluminum alloy plates in space cabins,and fungal growth images were obtained.The data set was obtained by preprocessing the image through image enhancement and feature selection methods.The recognition performances of the Support Vector Machine(SVM)and random forest were compared.The results showed that the SVM model was better than the random forest model in identifying fungal growth images on the surface of aluminum alloy plates,and the accuracy of fungal species identification and fungal biomass classification and identification were both over 97%.
作者
陆月盈
付玉明
刘红
LU Yueying;FU Yuming;LIU Hong(School of Biological Science and Medical Engineering,Beihang University,Beijing 100191,China;Beijing Advanced Innovation Center for Biomedical Engineering,School of Biological Science and Medical Engineering,Beihang University,Beijing 100191,China;International Joint Research Center of Aerospace Biotechnology&Medical Engineering,Beihang University,Beijing 100191,China)
出处
《载人航天》
CSCD
北大核心
2021年第2期190-197,共8页
Manned Spaceflight
基金
载人航天领域预先研究项目(020301)。
关键词
空间舱室
真菌
图像分析
支持向量机
随机森林模型
space cabin
fungi
image analysis
support vector machine
random forest model
