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)

Hyperspectral data processing technique has gained increasing interests in the field of chemical and biomedical analysis. However, appropriate approaches to fusing features of hyperspectral data-cube are still lacking. In this paper, a new data fusion approach was proposed and applied to discriminate Rhizoma Atractylodis Macrocephalae (RAM) slices from different geographical origins using hyperspectral imaging. Spectral and image features were extracted from hyperspectral data in visible and near-infrared (VNIR, 435–1042 nm) and short-wave infrared (SWIR, 898–1751 nm) ranges, respectively. Effective wavelengths were extracted from pre-processed spectral data by successive projection algorithm (SPA). Meanwhile, gray-level co-occurrence matrix (GLCM) and gray-level run-length matrix (GLRLM) were employed to extract textural variables. The fusion of spectrum-image in VNIR and SWIR ranges (VNIR-SWIR-FuSI) was implemented to integrate those features on three fusion dimensions, i.e., VNIR and SWIR fusion, spectrum and image fusion, and all data fusion. Based on data fusion, partial least squares-discriminant analysis (PLS-DA) and support vector machine (SVM) were utilized to establish calibration models. The results demonstrated that VNIR-SWIR-FuSI could achieve the best accuracies on both full bands (97.3%) and SPA bands (93.2%). In particular, VNIR-SWIR-FuSI on SPA bands achieved a classification accuracy of 93.2% with only 23 bands, which was significantly better than those based on spectra (80.9%) or images (79.7%). Thus it is more rapid and possible for industry applications. The current study demonstrated that hyperspectral imaging technique with data fusion holds the potential for rapid and nondestructive sorting of traditional Chinese medicines (TCMs).

[1]  Mary M. Galloway,et al.  Texture analysis using gray level run lengths , 1974 .

[2]  Zhongyu Wang,et al.  Improving the Classification Accuracy for Near-Infrared Spectroscopy of Chinese Salvia miltiorrhiza Using Local Variable Selection , 2018, Journal of analytical methods in chemistry.

[3]  Jing He,et al.  [Study on the fingerprint of processed Rhizoma Atractylodis Macrocephalae by HPLC]. , 2009, Zhong yao cai = Zhongyaocai = Journal of Chinese medicinal materials.

[4]  Frans van den Berg,et al.  Review of the most common pre-processing techniques for near-infrared spectra , 2009 .

[5]  Silvia Serranti,et al.  Classification of oat and groat kernels using NIR hyperspectral imaging. , 2013, Talanta.

[6]  Xiong Cai,et al.  Atractylodes macrocephala Koidz stimulates intestinal epithelial cell migration through a polyamine dependent mechanism. , 2015, Journal of ethnopharmacology.

[7]  Joseph Maria Kumar Irudayaraj,et al.  Classification of simple and complex sugar adulterants in honey by mid-infrared spectroscopy , 2002 .

[8]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[9]  P. Baranowski,et al.  Supervised classification of bruised apples with respect to the time after bruising on the basis of hyperspectral imaging data , 2013 .

[10]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[11]  M. C. U. Araújo,et al.  The successive projections algorithm for variable selection in spectroscopic multicomponent analysis , 2001 .

[12]  Hiroshi Okamoto,et al.  Distinguishing overripe berries of Japanese blue honeysuckle using hyperspectral imaging analysis , 2014 .

[13]  Hong-Ju He,et al.  Non-Destructive and rapid evaluation of staple foods quality by using spectroscopic techniques: A review , 2016, Critical reviews in food science and nutrition.

[14]  Li Yutao,et al.  Enhancement of the immune responses to vaccination against foot-and-mouth disease in mice by oral administration of an extract made from Rhizoma Atractylodis Macrocephalae (RAM). , 2009, Vaccine.

[15]  Nicola Caporaso,et al.  Protein content prediction in single wheat kernels using hyperspectral imaging , 2018, Food chemistry.

[16]  Qiang Liu,et al.  Classification and Discrimination of Different Fungal Diseases of Three Infection Levels on Peaches Using Hyperspectral Reflectance Imaging Analysis , 2018, Sensors.

[17]  Zhang Jianmin,et al.  Fingerprints establishment of Rhizoma Atractylodis Macrocephalae by high performance liquid chromatography and analysis of plant resource , 2010 .

[18]  Qing-song Shao,et al.  Fast determination of two atractylenolides in Rhizoma Atractylodis Macrocephalae by Fourier transform near-infrared spectroscopy with partial least squares. , 2014, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[19]  Ge Jian-hua,et al.  Study on Quality of Atractylodes macrocephala Koidz.I ——Determination of 2 Atractylenolides by HPLC , 2001 .

[20]  Robert S. Rand,et al.  Spatially smooth partitioning of hyperspectral imagery using spectral/spatial measures of disparity , 2003, IEEE Trans. Geosci. Remote. Sens..

[21]  Cai Qian.  HPLC determination of atractylenolide I and atractylenolide III in 50 batches crude drugs and slices of Atractylodes macrocephala Koidz.from different sources , 2012 .

[22]  S. Tankeu,et al.  Hyperspectral Imaging and Support Vector Machine: A Powerful Combination to Differentiate Black Cohosh (Actaea racemosa) from Other Cohosh Species , 2017, Planta Medica.

[23]  Fengle Zhu,et al.  Application of hyperspectral imaging technology to discriminate different geographical origins of Jatropha curcas L. seeds , 2013 .

[24]  Peng Li,et al.  Discrimination of Multi-Origin Chinese Herbal Medicines Using Gas Chromatography-Mass Spectrometry-Based Fatty Acid Profiling , 2013, Molecules.

[25]  Robert King,et al.  Textural features corresponding to textural properties , 1989, IEEE Trans. Syst. Man Cybern..

[26]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[27]  Yuan-Zhong Wang,et al.  Comprehensive Quality Assessment Based Specific Chemical Profiles for Geographic and Tissue Variation in Gentiana rigescens Using HPLC and FTIR Method Combined with Principal Component Analysis , 2017, Front. Chem..

[28]  Fang Cheng,et al.  Spectral and Image Integrated Analysis of Hyperspectral Data for Waxy Corn Seed Variety Classification , 2015, Sensors.

[29]  Zhenjie Xiong,et al.  Use of Hyperspectral Imaging to Discriminate the Variety and Quality of Rice , 2015, Food Analytical Methods.

[30]  Da-Wen Sun,et al.  Application of Hyperspectral Imaging to Discriminate the Variety of Maize Seeds , 2015, Food Analytical Methods.

[31]  C. Metz.  Basic principles of ROC analysis. , 1978, Seminars in nuclear medicine.

[32]  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.

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

[34]  Shyr‐Yi Lin,et al.  Pro-oxidant and cytotoxic activities of atractylenolide I in human promyeloleukemic HL-60 cells. , 2006, Food and chemical toxicology : an international journal published for the British Industrial Biological Research Association.

[35]  Lei Zheng,et al.  Non-destructive determination and visualisation of insoluble and soluble dietary fibre contents in fresh-cut celeries during storage periods using hyperspectral imaging technique. , 2017, Food chemistry.

[36]  Lei Zhang,et al.  Band-Subset-Based Clustering and Fusion for Hyperspectral Imagery Classification , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[37]  Wei Liu,et al.  Fingerprint Analysis of Daturae Flos Using Rapid Resolution Liquid Chromatography-Electrospray Ionization Mass Spectrometry Combined with Stoichiometry , 2015 .

[38]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[39]  Sun Xudong,et al.  Application of visible and near infrared spectroscopy to identification of navel orange varieties using SIMCA and PLS-DA methods , 2010 .

[40]  Xin Peng,et al.  A novel method for geographical origin identification of Tetrastigma hemsleyanum (Sanyeqing) by near-infrared spectroscopy , 2018 .

[41]  Da-Wen Sun,et al.  Principles and Applications of Hyperspectral Imaging in Quality Evaluation of Agro-Food Products: A Review , 2012, Critical reviews in food science and nutrition.

[42]  Lang-Chong He,et al.  Screening for the anti-inflammatory activity of fractions and compounds from Atractylodes macrocephala koidz. , 2007, Journal of ethnopharmacology.

[43]  Qinhua Chen,et al.  Identification of volatile compounds of Atractylode lancea rhizoma using supercritical fluid extraction and GC-MS. , 2009, Journal of separation science.

[44]  Chu Zhang,et al.  Application of near-infrared hyperspectral imaging to discriminate different geographical origins of Chinese wolfberries , 2017, PloS one.

[45]  Mohan S. Kankanhalli,et al.  Multimodal fusion for multimedia analysis: a survey , 2010, Multimedia Systems.

[46]  Ş. Ţălu,et al.  Mathematical methods used in monofractal and multifractal analysis for the processing of biological and medical data and images. , 2012 .