Hyperspectral Imaging-Based Multiple Predicting Models for Functional Component Contents in Brassica juncea

Partial least squares regression (PLSR) prediction models were developed using hyperspectral imaging for noninvasive detection of the five most representative functional components in Brassica juncea leaves: chlorophyll, carotenoid, phenolic, glucosinolate, and anthocyanin contents. The region of interest for functional component analysis was chosen by polygon selection and the extracted average spectra were used for model development. For pre-processing, 10 combinations of Savitzky–Golay filter (S. G. filter), standard normal variate (SNV), multiplicative scatter correction (MSC), 1st-order derivative (1st-Der), 2nd-order derivative (2nd-Der), and normalization were applied. Root mean square errors of calibration (RMSEP) was used to assess the performance accuracy of the constructed prediction models. The prediction model for total anthocyanins exhibited the highest prediction level (RV2 = 0.8273; RMSEP = 2.4277). Pre-processing combination of SNV and 1st-Der with spectral data resulted in high-performance prediction models for total chlorophyll, carotenoid, and glucosinolate contents. Pre-processing combination of S. G. filter and SNV gave the highest prediction rate for total phenolics. SNV inclusion in the pre-processing conditions was essential for developing high-performance accurate prediction models for functional components. By enabling visualization of the distribution of functional components on the hyperspectral images, PLSR prediction models will prove valuable in determining the harvest time.

[1]  S. Park,et al.  Measurement of Environmentally Influenced Variations in Anthocyanin Accumulations in Brassica rapa subsp. Chinensis (Bok Choy) Using Hyperspectral Imaging , 2021, Frontiers in Plant Science.

[2]  L. Mondello,et al.  Chemical Characterization of Three Accessions of Brassica juncea L. Extracts from Different Plant Tissues , 2020, Molecules.

[3]  Jeong-Eun Lee,et al.  Antioxidant Activity, Whitening and Anti-wrinkle Effects of Leaf and Seed Extracts of Brassica juncea L. Czern. , 2020 .

[4]  Yong He,et al.  Detection of Sulfite Dioxide Residue on the Surface of Fresh-Cut Potato Slices Using Near-Infrared Hyperspectral Imaging System and Portable Near-Infrared Spectrometer , 2020, Molecules.

[5]  F. Deng,et al.  Phytochemistry and biological activity of mustard (Brassica juncea): a review , 2020, CyTA - Journal of Food.

[6]  Maulana Ihsan,et al.  Flavonoid Distribution Mapping System of Velvet Apple Leaf Based on Hyperspectral Imaging , 2019, 2019 International Conference on Advanced Computer Science and information Systems (ICACSIS).

[7]  L. Mounien,et al.  Anti-Obesity Effect of Carotenoids: Direct Impact on Adipose Tissue and Adipose Tissue-Driven Indirect Effects , 2019, Nutrients.

[8]  H. Nawaz,et al.  Phytochemical Composition and Antioxidant Potential of Brassica , 2018, Brassica Germplasm - Characterization, Breeding and Utilization.

[9]  Bingquan Chu,et al.  Determination of Total Polysaccharides and Total Flavonoids in Chrysanthemum morifolium Using Near-Infrared Hyperspectral Imaging and Multivariate Analysis , 2018, Molecules.

[10]  M. S. Fowler,et al.  Hyperspectral imaging for non-destructive prediction of fermentation index, polyphenol content and antioxidant activity in single cocoa beans , 2018, Food chemistry.

[11]  A. Gosselin,et al.  Characterization of industrial broccoli discards (Brassica oleracea var. italica) for their glucosinolate, polyphenol and flavonoid contents using UPLC MS/MS and spectrophotometric methods. , 2018, Food chemistry.

[12]  Mareike Jezek,et al.  Anthocyanin Management in Fruits by Fertilization. , 2018, Journal of agricultural and food chemistry.

[13]  Anguo Xie,et al.  Potential of Hyperspectral Imaging for Rapid Prediction of Anthocyanin Content of Purple-Fleshed Sweet Potato Slices During Drying Process , 2017, Food Analytical Methods.

[14]  B. Gurung,et al.  A simple spectrophotometric method for estimating total glucosinolates in mustard de-oiled cake , 2017 .

[15]  Xiaoli Li,et al.  Hyperspectral Imaging for Determining Pigment Contents in Cucumber Leaves in Response to Angular Leaf Spot Disease , 2016, Scientific Reports.

[16]  C. Igathinathane,et al.  Nondestructive determination of cocoa bean quality using FT-NIR spectroscopy , 2016, Comput. Electron. Agric..

[17]  Ssang-Goo Cho,et al.  Molecular Mechanisms of the Anti-Obesity and Anti-Diabetic Properties of Flavonoids , 2016, International journal of molecular sciences.

[18]  Yul-Ho Kim,et al.  Growing Environment Influence the Anthocyanin Content in Purple- and Red-Fleshed Potatoes During Tuber Development , 2015 .

[19]  Xingyi Huang,et al.  Estimating cocoa bean parameters by FT-NIRS and chemometrics analysis. , 2015, Food chemistry.

[20]  Yi-Chao Yang,et al.  Rapid detection of anthocyanin content in lychee pericarp during storage using hyperspectral imaging coupled with model fusion , 2015 .

[21]  Jun-Hu Cheng,et al.  Rapid Quantification Analysis and Visualization of Escherichia coli Loads in Grass Carp Fish Flesh by Hyperspectral Imaging Method , 2015, Food and Bioprocess Technology.

[22]  Colm P. O'Donnell,et al.  Preliminary study on the use of near infrared hyperspectral imaging for quantitation and localisation of total glucosinolates in freeze-dried broccoli , 2014 .

[23]  M. Diaby,et al.  Chemical Composition, Nutritional Properties and Antioxidant Activity of Monkey Apple (Anisophyllea laurina R. Br. ex Sabine) , 2014 .

[24]  F. Toribio,et al.  Characterization of the Glucosinolates and Isothiocyanates in Mustard (Brassica juncea L.) Extracts and Determination of Its Myrosinase Activity and Antioxidant Capacity , 2014 .

[25]  M. Kim,et al.  Development of a non-destructive on-line pungency measurement system for red-pepper powder , 2013 .

[26]  Mi-hye Kim Antioxidant and Antibacterial Activity of Extracts from Brassica juncea czerniak et coss., Celosia cristata L., and Beta vulgaris L. , 2012 .

[27]  Vikas Kumar,et al.  Therapeutic potentials of Brassica juncea : an overview , 2011 .

[28]  M. E. Cartea,et al.  Phenolic Compounds in Brassica Vegetables , 2010, Molecules.

[29]  M. Okulicz Multidirectional Time-Dependent Effect of Sinigrin and Allyl Isothiocyanate on Metabolic Parameters in Rats , 2010, Plant foods for human nutrition.

[30]  Yuesheng Zhang Allyl isothiocyanate as a cancer chemopreventive phytochemical. , 2010, Molecular nutrition & food research.

[31]  Reshmi Pushpan,et al.  Mustard and its uses in Ayurveda , 2009 .

[32]  R. Holley,et al.  Enzymatic inhibition by allyl isothiocyanate and factors affecting its antimicrobial action against Escherichia coli O157:H7. , 2009, International journal of food microbiology.

[33]  J. Weller,et al.  Manipulation of the Blue Light Photoreceptor Cryptochrome 2 in Tomato Affects Vegetative Development, Flowering Time, and Fruit Antioxidant Content1 , 2005, Plant Physiology.

[34]  H. Lichtenthaler,et al.  Chlorophylls and Carotenoids: Measurement and Characterization by UV‐VIS Spectroscopy , 2001 .

[35]  Ahmad,et al.  Cryptochrome 1 controls tomato development in response to blue light. , 1999, The Plant journal : for cell and molecular biology.

[36]  Albert Olioso,et al.  Chlorophyll fluorescence as a tool for management of plant resources , 1994 .