目的:为提高精子形态学分类的准确性,提出一种基于卷积神经网络的精子分类模型。方法:使用EfficientNetB0作为基础模型,通过数据预处理增强、迁移学习以及余弦衰减进行微调,构建FT-EfficientNet模型。在精子公开数据集SCIAN-Morpho和HuS...目的:为提高精子形态学分类的准确性,提出一种基于卷积神经网络的精子分类模型。方法:使用EfficientNetB0作为基础模型,通过数据预处理增强、迁移学习以及余弦衰减进行微调,构建FT-EfficientNet模型。在精子公开数据集SCIAN-Morpho和HuSHeM上进行分类实验,利用5折交叉验证对数据集进行分割与验证,并与级联式的支持向量机(cascade ensemble of support vector machines,CE-SVM)模型、基于块的自适应字典学习(adaptive patchbased dictionary learning,APDL)模型、微调可视几何组(fine tuning of visual geometry group,FT-VGG)模型、人类精子头部形态分类(morphological classification of human sperm heads,MC-HSH)模型、迁移学习(transfer learning,TL)模型的分类结果进行对比。在SCIAN-Morpho数据集中进行消融实验,验证不同微调方法对模型的影响。结果:FT-EfficientNet模型在SCIAN-Morpho验证集上的准确率、精确度及F_(1)分数分别为64.1%、63.8%和64.8%,优于CE-SVM、APDL、FT-VGG、MC-HSH模型,召回率为65.2%,略低于MC-HSH模型(68.0%)。FT-EfficientNet模型在HuSHeM验证集上的准确率、精确度、F_(1)分数、召回率分别为95.4%、95.8%、95.4%和96.0%,略低于TL模型,但优于CE-SVM、APDL、FT-VGG、MC-HSH模型。消融实验结果表明,FT-EfficientNet模型应用的微调方法所得结果最优。结论:基于卷积神经网络的精子分类模型能够完成精子形态学分类,提升分类的准确度及性能。展开更多
国内以海阳核电为代表的第三代核电首次采用了高密度聚乙烯高完整容器。文章介绍了美国Barnwell和Clive处置场HDPE-HIC的处置经验以及国内低放处置场的处置现状,结合我国处置标准要求分析了HDPE-HIC处置要求,并介绍了国内针对HDPE-HIC...国内以海阳核电为代表的第三代核电首次采用了高密度聚乙烯高完整容器。文章介绍了美国Barnwell和Clive处置场HDPE-HIC的处置经验以及国内低放处置场的处置现状,结合我国处置标准要求分析了HDPE-HIC处置要求,并介绍了国内针对HDPE-HIC处置的堆码方案研究,以期为妥善处置HDPE-HIC提供参考。In China, the third-generation nuclear power plant represented by Haiyang Nuclear Power Plant used high-density polyethylene high integrity container for the first time. This paper introduces the disposal experience of HDPE-HIC in Barnwell and Clive disposal sites in the United States as well as the present disposal situation of low radioactive disposal sites in China. Combining with the requirements of China’s disposal standards, the disposal requirements of HDPE-HIC are analyzed, and the stacking scheme research for HDPE-HIC disposal in China is introduced, in order to provide a reference for the proper disposal of HDPE-HIC.展开更多
文摘目的:为提高精子形态学分类的准确性,提出一种基于卷积神经网络的精子分类模型。方法:使用EfficientNetB0作为基础模型,通过数据预处理增强、迁移学习以及余弦衰减进行微调,构建FT-EfficientNet模型。在精子公开数据集SCIAN-Morpho和HuSHeM上进行分类实验,利用5折交叉验证对数据集进行分割与验证,并与级联式的支持向量机(cascade ensemble of support vector machines,CE-SVM)模型、基于块的自适应字典学习(adaptive patchbased dictionary learning,APDL)模型、微调可视几何组(fine tuning of visual geometry group,FT-VGG)模型、人类精子头部形态分类(morphological classification of human sperm heads,MC-HSH)模型、迁移学习(transfer learning,TL)模型的分类结果进行对比。在SCIAN-Morpho数据集中进行消融实验,验证不同微调方法对模型的影响。结果:FT-EfficientNet模型在SCIAN-Morpho验证集上的准确率、精确度及F_(1)分数分别为64.1%、63.8%和64.8%,优于CE-SVM、APDL、FT-VGG、MC-HSH模型,召回率为65.2%,略低于MC-HSH模型(68.0%)。FT-EfficientNet模型在HuSHeM验证集上的准确率、精确度、F_(1)分数、召回率分别为95.4%、95.8%、95.4%和96.0%,略低于TL模型,但优于CE-SVM、APDL、FT-VGG、MC-HSH模型。消融实验结果表明,FT-EfficientNet模型应用的微调方法所得结果最优。结论:基于卷积神经网络的精子分类模型能够完成精子形态学分类,提升分类的准确度及性能。
文摘国内以海阳核电为代表的第三代核电首次采用了高密度聚乙烯高完整容器。文章介绍了美国Barnwell和Clive处置场HDPE-HIC的处置经验以及国内低放处置场的处置现状,结合我国处置标准要求分析了HDPE-HIC处置要求,并介绍了国内针对HDPE-HIC处置的堆码方案研究,以期为妥善处置HDPE-HIC提供参考。In China, the third-generation nuclear power plant represented by Haiyang Nuclear Power Plant used high-density polyethylene high integrity container for the first time. This paper introduces the disposal experience of HDPE-HIC in Barnwell and Clive disposal sites in the United States as well as the present disposal situation of low radioactive disposal sites in China. Combining with the requirements of China’s disposal standards, the disposal requirements of HDPE-HIC are analyzed, and the stacking scheme research for HDPE-HIC disposal in China is introduced, in order to provide a reference for the proper disposal of HDPE-HIC.
