基于拉曼光谱和深度学习的家蚕卵微粒子病无损检测  

Non-Destructive Detection of Silkworm Pebrine Disease at Egg Stage Based on Raman Spectroscopy and Deep Learning

作　　者：代芬 邢鸿昕 王先燕[3] 冯敏 胡豆豆 孙京臣[2] 赵懿琨 王叶元[2] Dai Fen;Xing Hongxin;Wang Xianyan;Feng Min;Hu Doudou;Sun Jingchen;Zhao Yikun;Wang Yeyuan(College of Electronic Engineering(College of Artificial Intelligence),South China Agricultural University,Guangzhou 510642,China;College of Animal Science,South China Agricultural University,Guangzhou 510642,China;Guangdong Sericultural Technology Promotion Center,Guangzhou 510640,China)

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

出　　处：《蚕业科学》2023年第6期560-567,共8页ACTA SERICOLOGICA SINICA

基　　金：国家自然科学基金项目(61675003);广东省自然科学基金项目(2018A030310153);广州市科技计划资助项目(201707010346);广东省蚕桑产业技术体系项目(2023KJ124)。

摘　　要：为研究家蚕微粒子病检测方法,基于密集连接块提出用R-DenseNet模型对家蚕微粒子病拉曼光谱进行无损检测。以患家蚕微粒子病原原母种卵为实验样本,构建家蚕微粒子病拉曼光谱数据集。R-DenseNet与其他5种分类模型的对比结果表明,不使用额外预处理的R-DenseNet的检测准确率达到97.32%,优于使用预处理的传统分类模型;对于处理60 dB强度噪声的光谱数据,R-DenseNet能达到93.66%的检测精度,在同等性能中,其模型训练的参数量较对比模型减少50%以上,表现出更好的鲁棒性和计算效率。文中提出的R-DenseNet网络结构能够对家蚕卵微粒子病拉曼光谱实现快速、准确且无损的检测,为家蚕微粒子病检测提供了一种新途径。In order to study the detection method of silkworm pebrine disease, we proposed R-DenseNet based on dense connected blocks for non-destructive detection of silkworm pebrine disease in Raman spectra. R-DenseNet was compared with five other classification models, and the results showed that the detection accuracy of R-DenseNet without additional preprocessing reached 97.32%, which was better than the traditional classification models with preprocessing. R-DenseNet achieve 93.66% for spectral data processing 60 dB intensity noise, and its model training parametric number reduced by more than 50% compared with the comparison model in the same performance, showing better robustness and computational efficiency. The proposed R-DenseNet network structure can achieve fast, accurate and non-destructive detection of silkworm egg pebrine disease Raman spectra, providing a new way for silkworm pebrine disease detection.

关 键 词：拉曼光谱 家蚕微粒子病 无损检测 深度学习 

分 类 号：S884.21[农业科学—特种经济动物饲养]