• 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
谢安国,纪思媛,李月玲,等. 基于遗传算法和深度神经网络的近红外高光谱检测猪肉新鲜度[J]. 食品工业科技,2024,45(17):1−7. doi: 10.13386/j.issn1002-0306.2023120096.
引用本文: 谢安国,纪思媛,李月玲,等. 基于遗传算法和深度神经网络的近红外高光谱检测猪肉新鲜度[J]. 食品工业科技,2024,45(17):1−7. doi: 10.13386/j.issn1002-0306.2023120096.
XIE Anguo, JI Siyuan, LI Yueling, et al. Detection of Pork Freshness using NIR Hyperspectral Imaging Based on Genetic Algorithm and Deep Neural Network[J]. Science and Technology of Food Industry, 2024, 45(17): 1−7. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2023120096.
Citation: XIE Anguo, JI Siyuan, LI Yueling, et al. Detection of Pork Freshness using NIR Hyperspectral Imaging Based on Genetic Algorithm and Deep Neural Network[J]. Science and Technology of Food Industry, 2024, 45(17): 1−7. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2023120096.

基于遗传算法和深度神经网络的近红外高光谱检测猪肉新鲜度

Detection of Pork Freshness using NIR Hyperspectral Imaging Based on Genetic Algorithm and Deep Neural Network

  • 摘要: 为系统评估基于深度学习的智能辅助高光谱成像系统在猪肉新鲜度指标检测中的效果,采集了猪肉在4 ℃冷藏12 d中挥发性盐基氮(volatile basic nitrogen,TVB-N)、菌落总数(total viable count,TVC)以及900~2500 nm近红外光谱数据。基于Python的TensorFlow和Keras平台,对高光谱数据进行处理,建立了深度神经网络的定量检测模型。并利用遗传算法(GA)选择与猪肉新鲜度相关的特征光谱波段。结果表明,遗传算法选取波段对光谱模型的性能有明显提升。当光谱波段数达到35和50时,GA+ANN模型预测精度高于全波段的线性回归模型。TVC为预测指标的预测性能优于TVB-N,TVC测试集最佳Rp2为0.877,RMSEP为0.575;预测TVB-N的最佳Rp2为0.826,RMSEP为1.01。此外,通过研究还发现,遗传算法优选的近红外光谱波段与肉品的O-H,N-H,C=O等分子振动吸收带有较高的吻合度。本研究为处理近红外和高光谱数据提供了新的方法,也为猪肉及其他肉品新鲜度快速无损检测提供了技术参考。

     

    Abstract: To evaluate the effectiveness of a deep learning which is based intelligent assisted hyperspectral imaging system on the detection of pork freshness indicators, volatile basic nitrogen (TVB-N), total viable count (TVC), and 900~2500 nm near-infrared spectral data were collected from pork which were refrigerated at 4 ℃ for 12 days. Based on Python's TensorFlow and Keras platform, hyperspectral data was processed and a quantitative detection model of deep neural network was also established. And the characteristic spectral bands related to pork freshness were selected by genetic algorithm (GA). The results showed that the performance of the spectral model could be improved significantly by selecting the band of genetic algorithm. When the number of spectral bands reached 35 and 50, the prediction accuracy of GA+ANN model was higher than that of full-band linear regression model. The predictive performance of TVC was better than that of TVB-N, and the best Rp2 and RMSEP of TVC were 0.877 and 0.575, respectively. The best Rp2 and RMSEP for TVB-N were 0.826 and 1.01, respectively. In addition, it was also found that the NIR band selected by genetic algorithm had a high coincidence with the molecular vibration absorption bands of meat, such as O-H, N-H, C=O and so on. This study provides a new method which can be used for processing the near-infrared and hyperspectral data, and also provides a technical reference for rapid nondestructive testing of pork and other meat freshness.

     

/

返回文章
返回