基于近红外光谱的家蚕种茧雌雄鉴别模型在多设备和多品种间的迁移  

Transfer of Sex Identification Model for Silkworm Cocoons Based on Near-infrared Spectrum Among Multiple Devices and Varieties

作　　者：陈楚汉 钟苏苑[2] 钟杨生[3] 王先燕[2] 代芬 CHEN Chuhan;ZHONG Suyuan;ZHONG Yangsheng;WANG Xianyan;DAI Fen(College of Electronic Engineering,South China Agricultural University,Guangzhou 510642,China;Guangdong Sericulture Technology Promotion Center,Guangzhou 510640,China;College of Animal Science,South China Agricultural University,Guangzhou 510642,China)

机构地区：[1]华南农业大学电子工程学院,广东广州510642 [2]广东省蚕业技术推广中心,广东广州510640 [3]华南农业大学动物科学学院,广东广州510642

出　　处：《广东农业科学》2021年第2期129-137,共9页Guangdong Agricultural Sciences

基　　金：国家自然科学基金(61675003);广东省自然科学基金(2018A030310153);广州市科技计划项目(201707010346)。

摘　　要：【目的】在家蚕种茧雌雄鉴别设备推广应用中,为了减少新品种、新设备需要重新建模的难度和时间,进行了基于近红外光谱的家蚕种茧雌雄鉴别模型在多设备和多品种间的迁移研究。【方法】首先使用2种型号光谱仪(NirQuest512光谱仪和SW2540光谱仪)采集4个品种蚕茧(9芙、7湘、7夏和932)的近红外漫透射光谱数据;然后用源域数据集训练的卷积神经网络作为源域模型,并对其中的中间层输出进行可视化分析;针对不同的种茧品种和不同的采集设备对源域模型进行微调,构建了迁移后的模型;最后将迁移后的模型预测准确率与卷积神经网络(Convolutional neural networks,CNN)、支持向量机(Support vector machine,SVM)和随机森林(Random forests,RF)算法进行对比。【结果】采用源域1700个9芙样本(NirQuest512光谱仪)构建的CNN源域模型,具有很好的雌雄分辨能力,分辨准确率达到99%以上。以源域CNN模型中间层输出作为输入构建的SVM和RF模型,雌雄分辨准确率分别为92%和90%以上,通过可视化分析表明卷积层能很好地提取雌雄特征。对于目标域中样本数量较少的100个7湘(NirQuest512光谱仪)、77个7夏和112个932的样本(SW2540光谱仪),训练集比例为70%时,通过微调源域CNN模型后得到的目标域CNN模型的准确率分别为96.90%、99.67%、97.29%,效果最优;独立的SVM模型准确率分别为92.49%、94.25%、93.65%,效果次之;独立RF模型的准确率分别为80.93%、80.17%、81.47%,效果稍差;独立CNN模型的准确率分别只有58.87%、56.33%、72.17%,效果最差。通过多次不同训练集数量的建模比较,同样显示在数据量较少的情况下,迁移学习后CNN模型最优,传统机器学习方法次之,深度CNN模型最差。【结论】不同光谱仪或者不同品种的情况下深度迁移学习模型的可迁移性,为使用多种光谱仪和采集多种品种蚕茧时快速建立一个蚕茧雌雄分类模型提供了理论�【Objective】In the promotion and application of sex identification equipment of silkworm cocoons,in order to reduce the difficulty and time of new varieties and new equipment to be re-modeled,the transfer of a sex identification model for silkworm cocoons based on near-infrared spectrum among multiple devices and varieties was studied.【Method】Firstly,two kinds of spectrometers(NirQuest512 spectrometer and SW2540 spectrometer)were used to collect the near-infrared diffuse transmission spectrum data of four silkworm varieties(9fu,7xiang,7xia and 932),then the convolutional neural networks trained by source domain dataset were used as the source domain model,and the outputs of the middle layer were analyzed visually.Furthly,the source domain model was tuned finely according to different silkworm varieties and different collection devices,and the transferred model was constructed.Finally,the model prediction accuracy after transfer learning was compared with the algorithm of Convolutional Neural Networks(CNN),Support Vector Machine(SVM)and Random Forests(RF).【Result】The results show that the CNN source domain model constructed with 1700 samples of 9fu(NirQuest512 spectrometer)has good sex resolution ability,and the accuracy of sex resolution is over 99%.The SVM and RF models were constructed with the outputs of middle layer of CNN source domain model as inputs,and the accuracy of sex discrimination is over 92%and 90%,respectively.Visual analysis shows that the convolutional layer can well extract the sex characteristics.For the target domain with less sample size of 1007xiang(NirQuest512 spectrometer),777xia and 112932(SW2540 spectrometer),when the proportion of the training set is 70%,by fine-tuning the source domain CNN model,the accuracy of the obtained target domain CNN model is 96.90%,99.67%and 97.29%respectively,with the optimal effect;the accuracy of the independent SVM model is 92.49%,94.25%and 93.65%respectively,with the effect slightly lower than that of CNN;the accuracy of the independent RF mod

关 键 词：卷积神经网络 迁移学习 家蚕种茧 近红外光谱 雌雄检测 

分 类 号：S881[农业科学—特种经济动物饲养]