Comparison of variable selection algorithms on vis-NIR hyperspectral imaging spectra for quantitative monitoring and visualization of bacterial foodborne pathogens in fresh pork muscles

Abstract This research aims to verify the feasibility of developing an improved and efficient reduced spectrum model for quantitative tracking of foodborne pathogens. Rapid monitoring of bacteria foodborne pathogen (Escherichia coli O157 and Staphylococcus aureus) contamination of fresh longissimus pork muscles was implemented by employing visible near-infrared (Vis-NIR) hyperspectral imaging spectra and partial least squares regression algorithm (PLSR). Six (6) wavelength variables selection algorithms were applied to the full spectral information to determine the wavelength variables of the collected HSI spectra that provides essential and relevant information about the concentration of bacterial foodborne pathogen. Commonly used algorithms based on model population analysis (MPA) (2), Intelligent Optimization Algorithms (2), and Hybrid variable selection methods (HVSM) (2) were utilised to select characteristic wavelengths. Compared to other strategies, variable combination population analysis with genetic algorithm (VCPA – GA), and variable combination population analysis with iteratively retaining informative variables (VCPA – IRIV) considerably bettered the predictive efficiency of the model, suggesting that the updated VCPA step is a very efficient way to remove unrelated variables. Vcpa-based hybrid strategy is an effective and reliable approach for variable selection of visible near-infrared (vis-NIR) spectra. Visualising bacterial foodborne pathogen distribution map on the pork samples provided a more insightful and detailed evaluation of the bacterial contamination at each pixel, offering a novel approach for evaluating bacterial contamination of agricultural products.

[1]  Xingyi Huang,et al.  Vis-NIR hyperspectral imaging for the classification of bacterial foodborne pathogens based on pixel-wise analysis and a novel CARS-PSO-SVM model , 2020 .

[2]  Z. Wen,et al.  A reliable multiclass classification model for identifying the subtypes of parotid neoplasms constructed with variable combination population analysis and partial least squares regression based on Raman spectra , 2017 .

[3]  Xingyi Huang,et al.  Combination of spectra and image information of hyperspectral imaging data for fast prediction of lipid oxidation attributes in pork meat , 2019, Journal of Food Process Engineering.

[4]  M. Misra,et al.  Developments in Micro- and Nanotechnology for Foodborne Pathogen Detection. , 2018, Foodborne pathogens and disease.

[5]  Weijun Chen,et al.  Three-step hybrid strategy towards efficiently selecting variables in multivariate calibration of near-infrared spectra. , 2020, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[6]  Dong-Sheng Cao,et al.  A strategy that iteratively retains informative variables for selecting optimal variable subset in multivariate calibration. , 2014, Analytica chimica acta.

[7]  R. Rambo,et al.  Self-Assembly, Antimicrobial Activity, and Membrane Interactions of Arginine-Capped Peptide Bola-Amphiphiles , 2019, ACS applied bio materials.

[8]  Bruce R. Kowalski,et al.  Partial least-squares path modelling with latent variables , 1979 .

[9]  M. Holmes,et al.  Noise-free microbial colony counting method based on hyperspectral features of agar plates. , 2019, Food chemistry.

[10]  Hui Jiang,et al.  Quantitative analysis of yeast fermentation process using Raman spectroscopy: Comparison of CARS and VCPA for variable selection. , 2019, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[11]  A. Jarmusch,et al.  Rapid discrimination of bacteria by paper spray mass spectrometry. , 2014, Analytical chemistry.

[12]  Xingyi Huang,et al.  Application of Hyperspectral Imaging as a Nondestructive Technique for Foodborne Pathogen Detection and Characterization. , 2019, Foodborne pathogens and disease.

[13]  Dong-Sheng Cao,et al.  An overview of variable selection methods in multivariate analysis of near-infrared spectra , 2019, TrAC Trends in Analytical Chemistry.

[14]  Xingyi Huang,et al.  Evaluation of lipid oxidation and volatile compounds of traditional dry‐cured pork belly: The hyperspectral imaging and multi‐gas‐sensory approaches , 2019, Journal of Food Process Engineering.

[15]  Pengcheng Nie,et al.  Hybrid variable selection in visible and near-infrared spectral analysis for non-invasive quality determination of grape juice. , 2010, Analytica chimica acta.

[16]  Xingyi Huang,et al.  Multi-sensor integration approach based on hyperspectral imaging and electronic nose for quantitation of fat and peroxide value of pork meat , 2020, Analytical and Bioanalytical Chemistry.

[17]  Yi-Zeng Liang,et al.  Model population analysis in chemometrics , 2015 .

[18]  I. Johnstone,et al.  Statistical challenges of high-dimensional data , 2009, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[19]  Hui Jiang,et al.  Comparison of algorithms for wavelength variables selection from near-infrared (NIR) spectra for quantitative monitoring of yeast (Saccharomyces cerevisiae) cultivations. , 2019, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[20]  Yankun Peng,et al.  A method for nondestructive prediction of pork meat quality and safety attributes by hyperspectral imaging technique , 2014 .

[21]  Anthony J. Durkin,et al.  Review of short-wave infrared spectroscopy and imaging methods for biological tissue characterization , 2015, Journal of biomedical optics.

[22]  Jiewen Zhao,et al.  In vivo noninvasive detection of chlorophyll distribution in cucumber (Cucumis sativus) leaves by indices based on hyperspectral imaging. , 2011, Analytica chimica acta.

[23]  Quansheng Chen,et al.  Rapid and Nondestructive Quantification of Trimethylamine by FT-NIR Coupled with Chemometric Techniques , 2019, Food Analytical Methods.

[24]  T. Mocan,et al.  Development of nanoparticle-based optical sensors for pathogenic bacterial detection , 2017, Journal of Nanobiotechnology.

[25]  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.

[26]  S. Lanteri,et al.  The potential of spectral and hyperspectral-imaging techniques for bacterial detection in food: A case study on lactic acid bacteria. , 2016, Talanta.

[27]  Mohammad-Ali Shahbazi,et al.  Microfluidic devices for sample preparation and rapid detection of foodborne pathogens. , 2018, Biotechnology advances.

[28]  Santosh Lohumi,et al.  Application of hyperspectral imaging for characterization of intramuscular fat distribution in beef , 2016 .

[29]  Changyeun Mo,et al.  Selection of Optimal Hyperspectral Wavebands for Detection of Discolored, Diseased Rice Seeds , 2019 .

[30]  Jun Sun,et al.  Visualizing distribution of moisture content in tea leaves using optimization algorithms and NIR hyperspectral imaging , 2019, Comput. Electron. Agric..

[31]  Shuxiang Fan,et al.  Rapid prediction and visualization of moisture content in single cucumber (Cucumis sativus L.) seed using hyperspectral imaging technology , 2019, Infrared Physics & Technology.

[32]  Min Zhang,et al.  Optimal Wavelength Selection for Hyperspectral Imaging Evaluation on Vegetable Soybean Moisture Content during Drying , 2019 .

[33]  Dong-Sheng Cao,et al.  A hybrid variable selection strategy based on continuous shrinkage of variable space in multivariate calibration. , 2019, Analytica chimica acta.

[34]  Xingyi Huang,et al.  Investigation into crystal size effect on sodium chloride uptake and water activity of pork meat using hyperspectral imaging , 2019, Journal of Food Processing and Preservation.