• EI
  • Scopus
  • 食品科学与工程领域高质量科技期刊分级目录第一方阵T1
  • DOAJ
  • EBSCO
  • 北大核心期刊
  • 中国核心学术期刊RCCSE
  • JST China
  • FSTA
  • 中国精品科技期刊
  • 中国农业核心期刊
  • CA
  • WJCI
  • 中国科技核心期刊CSTPCD
  • 中国生物医学SinoMed
中国精品科技期刊2020
张雯雯,胡亚东,孙文珂,等. 基于近红外光谱与深度学习的紫菜水分无损检测[J]. 食品工业科技,2024,45(21):1−8. doi: 10.13386/j.issn1002-0306.2023100153.
引用本文: 张雯雯,胡亚东,孙文珂,等. 基于近红外光谱与深度学习的紫菜水分无损检测[J]. 食品工业科技,2024,45(21):1−8. doi: 10.13386/j.issn1002-0306.2023100153.
ZHANG Wenwen, HU Yadong, SUN Wenke, et al. Non-destructive Detection of Water Content in Porphyra Based on Near-infrared Spectroscopy and Deep Learning[J]. Science and Technology of Food Industry, 2024, 45(21): 1−8. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2023100153.
Citation: ZHANG Wenwen, HU Yadong, SUN Wenke, et al. Non-destructive Detection of Water Content in Porphyra Based on Near-infrared Spectroscopy and Deep Learning[J]. Science and Technology of Food Industry, 2024, 45(21): 1−8. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2023100153.

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

  • 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,Rp2)值为0.990,优化后,该模型的RMSEP值降至0.342,Rp2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。

     

    Abstract: 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 (Rp2) value was 0.990. After optimization, the RMSEP value of the model was reduced to 0.342 and the Rp2 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.

     

/

返回文章
返回