Detection for lead pollution level of lettuce leaves based on deep belief network combined with hyperspectral image technology,Journal of Food Safety

当前位置： X-MOL 学术 › J. Food Saf. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Detection for lead pollution level of lettuce leaves based on deep belief network combined with hyperspectral image technology
Journal of Food Safety ( IF 1.9 ) Pub Date : 2020-10-16 , DOI: 10.1111/jfs.12866
Jun Sun ₁ , Yan Cao ₁ , Xin Zhou ₁ , Minmin Wu ₁ , Yidan Sun ₁ , Yinghui Hu ₁

Affiliation

Fast detection for heavy metal in vegetables is one of the most important steps to ensure the food safety. A novel method to identify lead pollution levels of lettuce based on hyperspectral image technology was proposed in this study. Firstly, hyperspectral images of lettuce samples cultivated under four lead stress levels (0 mg/L, 50 mg/L, 100 mg/L and 200 mg/L) were collected using hyperspectral image system. Then, a total of 240 spectra were calculated from region of interest (ROI) in the range of 478–978 nm covering 399 bands. Besides, chemical test showed that the excessive level of lead residues content in lettuce leaves were none, slight, moderate and severe. Moreover, conventional models and deep belief network (DBN) were established to determine the best identification model. The discriminant DBN model reached the highest accuracy with the training set of 100% and test set of 96.67%. Finally, t‐distribution stochastic neighbor embedding (t‐SNE) was successful to visualize the feature values in DBN's last hidden layer. This study indicates that it is viable to detect the lead pollution levels of lettuce leaves based on hyperspectral image technology coupled with DBN discriminant model.

中文翻译：

基于深度信念网络结合高光谱图像技术的生菜叶片铅污染水平检测

快速检测蔬菜中的重金属是确保食品安全的最重要步骤之一。提出了一种基于高光谱图像技术的莴苣铅污染水平识别新方法。首先，使用高光谱图像系统收集在四种铅胁迫水平（0 mg / L，50 mg / L，100 mg / L和200 mg / L）下培养的生菜样品的高光谱图像。然后，从478-978 nm范围内的399个波段的感兴趣区域（ROI）计算出总共240个光谱。此外，化学测试表明，莴苣叶片中的铅残留量过高，无，轻度，中度和重度。此外，建立了常规模型和深度信任网络（DBN）来确定最佳识别模型。判别式DBN模型达到最高的准确性，训练集为100％，测试集为96.67％。最后，t分布随机邻居嵌入（t-SNE）成功地可视化了DBN的最后一个隐藏层中的特征值。这项研究表明，基于高光谱图像技术结合DBN判别模型，检测莴苣叶中的铅污染水平是可行的。

更新日期：2020-10-16

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11