基于近红外光谱与深度学习的紫菜水分无损检测  

Non-destructive Detection of Water Content in Porphyra Based on Near-infrared Spectroscopy and Deep Learning

作　　者：张雯雯[1] 胡亚东 孙文珂 潘明轩 沈照鹏[3] 周兴虎 钱津 王鹏[3] ZHANG Wenwen;HU Yadong;SUN Wenke;PAN Mingxuan;SHEN Zhaopeng;ZHOU Xinghu;QIAN Jin;WANG Peng(Haide College,Ocean University of China,Qingdao 266104,China;Jiangsu Coast Development Group Co.,Ltd.,Jiangsu Jinniu Industry&Trade Co.,Ltd.,Jiangsu Inovation Center of Marine Resources,Nanjing 210019,China;College of Food Science and Engineering,Ocean University of China,Qingdao 266104,China)

机构地区：[1]中国海洋大学海德学院,山东青岛266104 [2]江苏省沿海开发集团有限公司,江苏省沿海开发投资有限公司,江苏海洋生物资源创新中心,江苏南京210019 [3]中国海洋大学食品科学与工程学院,山东青岛266104

出　　处：《食品工业科技》2024年第21期190-197,共8页Science and Technology of Food Industry

基　　金：江苏省沿海开发集团有限公司江苏海洋生物资源创新中心自主立项项目(2023YHTZZZ01)。

摘　　要：为探索近红外光谱结合深度学习网络对紫菜水分定量检测的可行性,本研究检测并收集了479组干条斑紫菜的光谱数据和水分含量数据,分别使用四种方法对其中的光谱数据进行了预处理,并在全波段下建立了四种传统定量水分预测模型和一种卷积神经网络(Convolution Neural Networks,CNN)深度学习水分预测模型。对比五种模型预测结果后发现,在S-G平滑结合二阶导数的预处理方法下所建立的CNN模型预测效果最佳,其预测均方根误差(Root-Mean-Square Error of Prediction,RMSEP)值为0.456,预测集决定系数(Coefficient of Determination of Prediction,R_(p)^(2))值为0.990,优化后,该模型的RMSEP值降至0.342,R_(p)^(2)值可以达到0.994(>0.8),同时,外部验证相对误差(Ratio of Performance to Deviation for Validation,RPD)值达6.155(>3),证明了模型实际应用于农业和食品工业的可能性。该CNN模型能够快速、准确、无损地预测条斑紫菜的水分含量,提高了紫菜水分检测的效率和准确性,为相关干制水产品的质量控制提供了重要的参考依据。In order to explore the feasibility of combining near-infrared(NIR)spectroscopy and deep learning network for quantitative moisture detection,the dried Porphyra was divided into 479 groups,which detected the NIR spectra and moisture content.Four traditional quantitative moisture prediction models and a convolution neural networks(CNN)deep-learning moisture prediction model were finally established at full spectrum by preprocessing and analyzing the experimental data.After comparing the prediction results of the five models,it was found that the CNN model established by the preprocessing method of S-G smoothing combined with the second derivative had the best prediction effect.Its root-mean-square error of prediction(RMSEP)value was 0.456 and the coefficient of determination of prediction(R_(p)^(2))value was 0.990.After optimization,the RMSEP value of the model was reduced to 0.342 and the R_(p)^(2) value could reach 0.994(>0.8).At the same time,the ratio of performance to deviation for validation(RPD)was 6.155(>3),which proved the possibility of practical application of the model in agriculture and food industry.The CNN model could predict the moisture content quickly,accurately,and non-destructive,improve the efficiency and accuracy of moisture detection,and provide an important reference for the quality control of related dry aquatic products.

关 键 词：条斑紫菜 水分含量 近红外光谱 深度学习 卷积神经网络 

分 类 号：TS201.1[轻工技术与工程—食品科学]