Application of Convolutional Neural Network-Based Feature Extraction and Data Fusion for Geographical Origin Identification of Radix Astragali by Visible/Short-Wave Near-Infrared and Near Infrared Hyperspectral Imaging

Radix Astragali is a prized traditional Chinese functional food that is used for both medicine and food purposes, with various benefits such as immunomodulation, anti-tumor, and anti-oxidation. The geographical origin of Radix Astragali has a significant impact on its quality attributes. Determining the geographical origins of Radix Astragali is essential for quality evaluation. Hyperspectral imaging covering the visible/short-wave near-infrared range (Vis-NIR, 380–1030 nm) and near-infrared range (NIR, 874–1734 nm) were applied to identify Radix Astragali from five different geographical origins. Principal component analysis (PCA) was utilized to form score images to achieve preliminary qualitative identification. PCA and convolutional neural network (CNN) were used for feature extraction. Measurement-level fusion and feature-level fusion were performed on the original spectra at different spectral ranges and the corresponding features. Support vector machine (SVM), logistic regression (LR), and CNN models based on full wavelengths, extracted features, and fusion datasets were established with excellent results; all the models obtained an accuracy of over 98% for different datasets. The results illustrate that hyperspectral imaging combined with CNN and fusion strategy could be an effective method for origin identification of Radix Astragali.

[1]  Shuping Zhao,et al.  Joint deep convolutional feature representation for hyperspectral palmprint recognition , 2019, Inf. Sci..

[2]  Xuchu Yu,et al.  A dense convolutional neural network for hyperspectral image classification , 2018, Remote Sensing Letters.

[3]  Yong He,et al.  Rapid Screen of the Color and Water Content of Fresh-Cut Potato Tuber Slices Using Hyperspectral Imaging Coupled with Multivariate Analysis , 2020, Foods.

[4]  Zhenhao Li,et al.  A Hyperspectral Imaging Approach for Classifying Geographical Origins of Rhizoma Atractylodis Macrocephalae Using the Fusion of Spectrum-Image in VNIR and SWIR Ranges (VNIR-SWIR-FuSI) , 2019, Sensors.

[5]  Chu Zhang,et al.  Sensitive Wavelengths Selection in Identification of Ophiopogon japonicus Based on Near-Infrared Hyperspectral Imaging Technology , 2017, International journal of analytical chemistry.

[6]  Zhongqiu Liu,et al.  A Systematic Review of Phytochemistry, Pharmacology and Pharmacokinetics on Astragali Radix: Implications for Astragali Radix as a Personalized Medicine , 2019, International journal of molecular sciences.

[7]  Yidan Bao,et al.  Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties , 2019, Molecules.

[9]  Chu Zhang,et al.  Variety identification of oat seeds using hyperspectral imaging: investigating the representation ability of deep convolutional neural network , 2019, RSC advances.

[10]  Chu Zhang,et al.  Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network , 2018 .

[11]  Mohamed Farah,et al.  Hyperspectral imagery classification based on semi-supervised 3-D deep neural network and adaptive band selection , 2019, Expert Syst. Appl..

[12]  Yong He,et al.  Theory and application of near infrared reflectance spectroscopy in determination of food quality , 2007 .

[13]  Emanuele Frontoni,et al.  Deep Learning for Soil and Crop Segmentation from Remotely Sensed Data , 2019, Remote. Sens..

[14]  Qiang Zhang,et al.  [Chemical composition and pharmacological activities of astragali radix]. , 2012, Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica.

[15]  Y. Woo,et al.  Discrimination of herbal medicines according to geographical origin with near infrared reflectance spectroscopy and pattern recognition techniques. , 1999, Journal of pharmaceutical and biomedical analysis.

[16]  C. Huck,et al.  A Review of Mid-Infrared and Near-Infrared Imaging: Principles, Concepts and Applications in Plant Tissue Analysis , 2017, Molecules.

[17]  Qi Li,et al.  Hyperspectral Imagery Classification Using Sparse Representations of Convolutional Neural Network Features , 2016, Remote. Sens..

[18]  Jerry Workman,et al.  Practical guide to interpretive near-infrared spectroscopy , 2007 .

[19]  Chu Zhang,et al.  Determination and Visualization of Peimine and Peiminine Content in Fritillaria thunbergii Bulbi Treated by Sulfur Fumigation Using Hyperspectral Imaging with Chemometrics , 2017, Molecules.

[20]  Fa-ming Wu,et al.  [A review of pharmacological study on Astragalus membranaceus (Fisch.) Bge]. , 2004, Zhong yao cai = Zhongyaocai = Journal of Chinese medicinal materials.

[21]  Chu Zhang,et al.  Identification of Maize Kernel Vigor under Different Accelerated Aging Times Using Hyperspectral Imaging , 2018, Molecules.

[22]  Xiao Xiang Zhu,et al.  Learning to Pay Attention on Spectral Domain: A Spectral Attention Module-Based Convolutional Network for Hyperspectral Image Classification , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Zhi‐Feng Zhang,et al.  Discovery of chemical markers for identifying species, growth mode and production area of Astragali Radix by using ultra-high-performance liquid chromatography coupled to triple quadrupole mass spectrometry. , 2019, Phytomedicine : international journal of phytotherapy and phytopharmacology.

[24]  Da‐Wen Sun,et al.  Kinetic modeling of microwave extraction of polysaccharides from Astragalus membranaceus , 2019, Journal of Food Processing and Preservation.

[25]  Qian Du,et al.  Learning Sensor-Specific Spatial-Spectral Features of Hyperspectral Images via Convolutional Neural Networks , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[26]  S. Sinclair,et al.  Chinese herbs: a clinical review of Astragalus, Ligusticum, and Schizandrae. , 1998, Alternative medicine review : a journal of clinical therapeutic.

[27]  Prabukumar Manoharan,et al.  Hyperspectral image classification using CNN with spectral and spatial features integration , 2020, Infrared Physics & Technology.

[28]  Erich-Christian Oerke,et al.  Sensory assessment of Cercospora beticola sporulation for phenotyping the partial disease resistance of sugar beet genotypes , 2019, Plant Methods.

[29]  Juan He,et al.  Nondestructive Determination and Visualization of Quality Attributes in Fresh and Dry Chrysanthemum morifolium Using Near-Infrared Hyperspectral Imaging , 2019, Applied Sciences.

[30]  Bor-Chen Kuo,et al.  A Kernel-Based Feature Selection Method for SVM With RBF Kernel for Hyperspectral Image Classification , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[31]  Yong He,et al.  Discrimination of CRISPR/Cas9-induced mutants of rice seeds using near-infrared hyperspectral imaging , 2017, Scientific Reports.

[32]  Yan Li,et al.  Discriminating geographic origin of sesame oils and determining lignans by near-infrared spectroscopy combined with chemometric methods , 2019 .

[33]  Yong He,et al.  Information fusion of emerging non-destructive analytical techniques for food quality authentication: A survey , 2020 .

[34]  Chu Zhang,et al.  Detection of Subtle Bruises on Winter Jujube Using Hyperspectral Imaging With Pixel-Wise Deep Learning Method , 2019, IEEE Access.

[35]  R. Salzer.  Practical Guide to Interpretive Near‐Infrared Spectroscopy. By Jerry Workman, Jr. and Lois Weyer. , 2008 .

[36]  Liu Yun,et al.  Identification of Tea Based on CARS-SWR Variable Optimization of Visible / Near Infrared Spectrum. , 2020, Journal of the science of food and agriculture.

[37]  Wei Wenlong,et al.  Discrimination of producing areas of Astragalus membranaceus using electronic nose and UHPLC-PDA combined with chemometrics , 2017 .

[38]  Koushik Nagasubramanian,et al.  Plant disease identification using explainable 3D deep learning on hyperspectral images , 2019, Plant Methods.