•  
  •  
 

Corresponding Author(s)

王志强（1977—），男，山东理工大学教授，博士。E-mail: wzq@sdut.edu.cn

Abstract

Objective: To realize the rapid traceability detection of Astragalus membranaceus from different origins. Methods: This study proposed a rapid detection method for the origin of Astragalus membranaceus based on the improved MobileNetv3 network based on the combination of electronic tongue and electronic eye. The electronic tongue and electronic eye were used to collect the one-dimensional fingerprint and two-dimensional appearance image information of different samples of Astragalus membranaceus. The Gramian Angular Field (GAF) was used to convert the one-dimensional electronic tongue signal into two-dimensional image information, retain the time series related features in the electronic tongue signal, and then fused them with the image information collected by the electronic eye. Finally, the MobileNetv3 model improved based on Pyramid Split Attention (PSA) was adopted to realize the classification and recognition of Astragalus samples from different habitats. Results: The experimental results showed that the method in this paper had higher recognition accuracy than using electronic tongue or electronic eye alone. The accuracy, precision, rrecall and F1-score of the test set were 98.8%, 98.8%, 98.8% and 0.99, respectively. The classification accuracy of the improved MobileNetv3 network was 8% higher than that of the original model, and the parameter quantity was only about 1/5 of the original parameter quantity. Conclusion: The improved MobileNetv3 network can effectively reduce the calculation of parameters and improve the recognition accuracy of Astragalus membranaceus from different origins.

Publication Date

10-20-2023

First Page

37

Last Page

47

DOI

10.13652/j.spjx.1003.5788.2022.81009

References

[1] 明荔莉, 范稚莉, 王海燕, 等. 元素分析—同位素质谱法测定黄芪中碳、氮同位素比值及其在产地溯源中的应用[J]. 化工时刊, 2021, 35（5）: 18-21. MING L L, FAN Z L, WANG H Y, et al. Element analysis-isotope ratio mass spectrometer for determination of carbon and nitrogen isotope in astragali radix and its application in geographical origin traceability[J]. Chemical Industry Times, 2021, 35（5）: 18-21.
[2] 张艳贺, 张雷鸣, 刘秀波, 等. 不同产地黄芪的性状和显微鉴别[J]. 中药材, 2013, 36（10）: 1 602-1 604. ZHANG Y H, ZHANG L M, LIU X B, et al. Characters and microscopic identification ofastragalus from different habitats[J]. Journal of Chinese Medicinal Materials, 2013, 36（10）: 1 602-1 604.
[3] HU L, YIN C, MA S, et al. Comparison and application of fluorescence EEMs and DRIFTS combined with chemometrics for tracing the geographical origin of radix astragali[J]. Spectrochim Acta A Mol Biomol Spectrosc, 2018, 205: 207-213.
[4] 高继勇, 王首程, 于雪莹, 等. 基于电子舌与GAN-CDAE-ELM模型的咖啡产地快速溯源检测[J]. 电子测量技术, 2021, 44（21）: 36-43. GAO J Y, WANG S C, YU X Y, et al. Rapid origin tracesbility delection of coffee based on electronic tongue and GAN-CDAE-ELM model[J]. Electronic Measurement Technology, 2021, 44（21）: 36-43.
[5] 吴仕敏, 余勤艳, 朱佳依, 等. 基于电子舌和代谢组学分析揉捻频率对工夫红茶品质的影响[J/OL]. 食品科学. （2022-06-29） [2023-01-31]. http://kns-cnki-net.vpn.sdut.edu.cn:8118/kcms/detail/11.2206.TS.20220628.1538.032.html. WU S M, YU Q Y, ZHU J Y, et al. Analysis on the effect of rolling frequency on the Gongou black tea quality based on electronic tongue and metabonomics[J/OL]. Food Science. （2022-06-29） [2023-01-31]. http://kns-cnki-net.vpn.sdut.edu.cn:8118/kcms/detail/11.2206.TS.20220628.1538.032.html.
[6] 程铁辕, 夏于林, 张莹. 基于机器学习和电子舌技术的白酒掺假鉴别[J]. 食品工业, 2021, 42（5）: 288-291. CHENG T Y, XIA Y L, ZHANG Y. Identification of adulteration of Chinese liquor based on machine learning and electronic tongue technology[J]. Food Industry, 2021, 42（5）: 288-291.
[7] 陈晓旭, 刘聪, 王丽霞, 等. 基于电子眼技术和化学指纹图谱的陈皮与蒸陈皮质量差异分析[J]. 中国实验方剂学杂志, 2023, 29（10）: 202-208. CHEN X X, LIU C, WANG L X, et al. Quality difference analysis of raw and steamed products of citri reticulatae pericarpium based on electronic eye technique and chemical fingerprint[J]. Chinese Journal of Experimental Traditional Medical Formulae, 2023, 29（10）: 202-208.
[8] 康明, 陶宁萍, 俞骏, 等. 不同干燥方式无花果干质构及挥发性成分比较[J]. 食品与发酵工业, 2020, 46（4）: 204-210. KANG M, TAO N P, YU J, et al. Comparison of texture quality and volatile components of dried figs by different drying methods[J]. Food and Fermentation Industries, 2020, 46（4）: 204-210.
[9] ORLANDI G, CALVINI R, PIGANI L, et al. Electronic eye for the prediction of parameters related to grape ripening[J]. Talanta, 2018, 186: 381-388.
[10] 段金芳, 肖洋, 刘影, 等. 一测多评法与电子眼和电子舌技术相结合优化山茱萸蒸制时间[J]. 中草药, 2017, 48（6）: 1 108-1 116. DUAN J F, XIAO Y, LIU Y, et al. Optimization of steaming time ofcornus officinalis by QAMS combined with electronic-eye and electronic-tongue techniques[J]. Chinese Traditional and Herbal Drugs, 2017, 48（6）: 1 108-1 116.
[11] 陈佳瑜, 袁海波, 沈帅, 等. 基于智能感官多源信息融合技术的滇红工夫茶汤综合感官品质评价[J]. 食品科学, 2022, 43（16）: 294-301. CHEN J Y, YUAN H B, SHEN S, et al. Comprehensive sensory quality evaluation ofdianhong congou tea infusions based on intelligent sensory multi-source information fusion technology[J]. Food Science, 2022, 43（16）: 294-301.
[12] ZHANG S F, ZHU D H, CHEN X J. Analysis of E-tongue data for tea classification based on semi-supervised learning of generative adversarial network[J]. Chinese Journal of Analytical Chemistry, 2022, 50（2）: 77-85.
[13] 杨正伟, 张鑫, 李庆盛, 等. 基于电子舌及一维深度CNN-ELM模型的普洱茶贮藏年限快速检测[J]. 食品与机械, 2020, 36（8）: 45-52. YANG Z W, ZHANG X, LI Q S, et al. A fast detection Pu-erh tea storage based on thevoltammertric electronic tongue and one-dimension CNN-ELM[J]. Food & Machinery, 2020, 36（8）: 45-52.
[14] 张海超, 张闯. 融合注意力的轻量级行为识别网络研究[J]. 电子测量与仪器学报, 2022, 36（5）: 173-179. ZHANG H C, ZHANG C. Research on lightweight action recognition network integrating attention[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36（5）: 173-179.
[15] LI J, WANG Q. Intra-group and inter-group electrocardiograph coding image fusion and classification based on multi-scale group convolution feature fusion network[J]. Biomedical Signal Processing and Control, 2022, 72: 103374.
[16] 姚立, 孙见君, 马晨波. 基于格拉姆角场和CNN-RNN的滚动轴承故障诊断方法[J]. 轴承, 2022（2）: 61-67. YAO L, SUN J J, MA C B. Fault diagnosis method for rolling bearing based on gramian angular fields and CNN-RNN[J]. Bearing, 2022（2）: 61-67.
[17] 王云艳, 罗帅, 王子健. 基于改进MobileNetV3的遥感目标检测[J]. 陕西科技大学学报, 2022, 40（3）: 164-171. WANG Y Y, LUO S, WANG Z J. Remote sensing target detection based on improved MobileNetV3[J]. Journal of Shaanxi University of Science & Technology, 2022, 40（3）: 164-171.
[18] HE C, LI X, LIU Y, et al. Combining multicolor fluorescence imaging with multispectral reflectance imaging for rapid citrus Huanglongbing detection based on lightweight convolutional neural network using a handheld device[J]. Computers and Electronics in Agriculture, 2022, 194: 106808.
[19] LI X, SHEN X, ZHOU Y, et al. Classification of breast cancer histopathological images using interleaved DenseNet with SENet （IDSNet） [J]. PLoS One, 2020, 15（5）: e0232127.
[20] ZHANG H, ZU K, LU J, et al. EPSANet: An efficient pyramid squeeze attention block on convolutional neural network[J]. Computer Vision and Pattern Recognition, 2021, DOI: 10.48550/arXiv.2015.14447.
[21] 李媛媛, 王艳丽, 姚静, 等. 基于电子舌的白及及其近似饮片的快速辨识研究[J]. 世界科学技术: 中医药现代化, 2021, 23（5）: 1 532-1 539. LI Y Y, WANG Y L, YAO J, et al. Research on the rapid identification of rhizoma bletillae and its approximate decoction pieces based on electronic tongue[J]. World Science and Technology: Modernization of Traditional Chinese Medicine, 2021, 23（5）: 1 532-1 539.
[22] 刘瑞新, 郝小佳, 张慧杰, 等. 基于电子眼技术的中药川贝母真伪及规格的快速辨识研究[J]. 中国中药杂志, 2020, 45（14）: 3 441-3 451. LIU R X, HAO X J, ZHANG H J, et al. A rapid identification of the authenticity and specifications of Chinese medicine fritillariae cirrhosae bulhus based on E-eye technology[J]. China Journal of Chinese Materia Medica, 2020, 45（14）: 3 441-3 451.
[23] YANG Z, MIAO N, ZHANG X, et al. Employment of an electronic tongue combined with deep learning and transfer learning for discriminating the storage time of Pu-erh tea[J]. Food Control, 2021, 121（3）: 107608.
[24] HOWARD A G, ZHU M, CHEN B, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications[J/OL]. arXiv. （2017-04-17） [2023-01-31]. https://arxiv.org/abs/1704.04861.
[25] SANDLER M, HOWARD A, ZHU M, et al. MobileNetV2: Inverted residuals and linear bottlenecks[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 4 510-4 520.
[26] 孙丰刚, 王云露, 兰鹏, 等. 基于改进YOLOv5s和迁移学习的苹果果实病害识别方法[J]. 农业工程学报, 2022, 38（11）: 171-179. SUN F G, WANG Y L, LAN P, et al. Apple fruit disease identification method based on improved YOLOv5s and transfer learning[J]. Journal of Agricultural Engineering, 2022, 38（11）: 171-179.
[27] 张利军, 段礼祥, 万夫, 等. 往复压缩机故障的残差网络诊断方法[J]. 电子测量与仪器学报, 2021, 35（5）: 38-46. ZHANG L J, DUAN L X, WAN F, et al. Residual network diagnosis method for reciprocating compressor fault[J]. Journal of Electronic Measurement and Instrumentation, 2021, 35（5）: 38-46.
[28] 王首程, 于雪莹, 高继勇, 等. 基于电子舌和电子鼻结合DenseNet-ELM的陈醋年限检测[J]. 食品与机械, 2022, 38（4）: 72-80, 133. WANG S C, YU X Y, GAO J Y, et al. Age detection of mature vinegar based on electronic tongueandelectronic nose combined with DenseNet-ELM[J]. Food & Machinery, 2022, 38（4）: 72-80, 133.

Download

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.