基于Fisher判别分析可分性信息融合的马铃薯VC含量高光谱检测方法

摘要/Abstract

摘要： 为了提高马铃薯维生素C（VC）含量检测结果的准确性和可靠性，提出了一种基于Fisher判别分析（Fisher Discriminant Analysis，FDA）可分性数据融合的检测模型输入变量构造方法。首先，利用高光谱成像技术采集了200个马铃薯的高光谱信息，通过对比6种预处理方法和原始数据的建模结果，确定了多元散射校正为光谱数据的预处理方法。其次，采用竞争性自适应重加权算法（competitive adaptive reweighted sampling，CARS）、连续投影算法（successive projections algorithm，SPA）及CARS-SPA组合算法等3种方法提取相应的特征波长，通过对比分析最终确定了34个有效特征波长。然后，将有效特征波长进行FDA可分性数据融合，根据融合的新变量对样本间差异性判别能力的大小进行筛选，确定构造检测模型的输入变量。最后，分别对FDA融合前后筛选的变量建立偏最小二乘模型和反向传播神经网络（Back Propagation Neural Network，BPNN）模型，并对检测结果进行对比分析。结果表明，将CARS算法提取的34个特征波长进行FDA融合，采用前3个融合变量作为构造检测模型的输入变量时，其所建BPNN模型的相关系数由0.9726提高到了0.9990，均方根误差也由0.7723降低到了0.1727，不仅极大地降低了数据分析维度，而且还提高了检测结果的准确性。因此，基于FDA可分性数据融合构造检测模型输入变量以提高马铃薯VC含量检测结果的准确性是适宜的。

关键词: 高光谱成像, Fisher判别分析, 马铃薯, VC含量检测, 模型

Abstract: In order to improve the accuracy and reliability of the prediction results of potato VC content, a method for constructing input variables of detection model based on Fisher discriminant analysis (FDA) separable data fusion was proposed. Firstly, hyperspectral information of 200 potato samples was collected by hyperspectral imaging technology; and by comparing the modeling results the spectral data before and after the preprocessing by six methods, the multiplicative scatter correction was determined as the optimal preprocessing method. Secondly, competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA) and CARS-SPA combination algorithm were used to extract the corresponding feature wavelengths, and 34 effective feature wavelengths were finally determined through comparative analysis. Thirdly, the effective feature wavelengths were fused by FDA to achieve the separability of the data, and the fused new variables was screened according to the discrimination capacity for different samples, so as to determine the input variables of the detection model to be constructed. Finally, the partial least squares model and BP neural network model were established for the variables screened before and after FDA fusion, respectively, and the detection results were compared and analyzed. The results show that the correlation coefficient of the BPNN model is increased from 0.9726 to 0.9990, and the root mean square error is also reduced from 0.7723 to 0.1727 when the first three fused variables of 34 feature wavelengths extracted by CARS algorithm after FDA fusion are used as the input variables for the detection model, which not only reduces data analysis dimension, but also improves its detection ability. Therefore, it is suitable and effective to construct input variables of detection model based on FDA separable data fusion to improve the accuracy of potato VC content detection results.

Key words: Hyperspectral imaging, Fisher discriminant analysis, Potato, VC content detection, Model

中图分类号:

TS205.9

郭林鸽殷勇于慧春袁云霞. 基于Fisher判别分析可分性信息融合的马铃薯VC含量高光谱检测方法[J]. 食品科学, 2024, 45(7): 0-0.

参考文献

[1]周童童, 梁单, 刘伟等.不同中薯系列马铃薯淀粉组成与理化性质的差异分析[J].核农学报, 2022, 36(04):766-776
[2]张欣昕, 张福金, 刘广华等.基于矿质元素和稳定同位素的马铃薯产地溯源技术[J].食品科学, 2020, 41(18):296-302
[3]SUN X, JIN X, FU N, et al.Effects of different pretreatment methods on the drying characteristics and quality of potatoes[J].Food Science & Nutrition, 2020, 8(11):5767-5775
[4]GB 5009.86-2016，食品安全国家标准　食品中抗坏血酸的测定[S].
[5]黄金萍, 吴继红, 廖小军等.果蔬汁饮料中花色苷与相互作用研究进展[J].食品科学, 2022, 43(21):358-371
[6]BAI X, FENG X, TAO M, et al.Evaluation of rice bacterial blight severity from lab to field with hyperspectral imaging technique[J].Frontiers in Plant Science, 2022, 13:4192-
[7]HUANG Y, WANG D, LIU Y, et al.Measurement of early disease blueberries based on visnir hyperspectral imaging system[J].Sensors, 2020, 20(20):5783-
[8]ZHANG X, WANG Y, ZHOU Z, et al.Detection Method for Tomato Leaf Mildew Based on Hyperspectral Fusion Terahertz Technology[J].Foods, 2023, 12(3):535-
[9]SHAO Y, LIU Y, XUAN G, et al.Detection and analysis of sweet potato defects based on hyperspectral imaging technology[J].Infrared Physics & Technology, 2022, 127:104403-
[10]PHAM Q T, LIOU N S.The development of on-line surface defect detection system for jujubes based on hyperspectral images[J].Computers and Electronics in Agriculture, 2022, 194:106743-
[11]XU P, SUN W, XU K, et al.Identification of Defective Maize Seeds Using Hyperspectral Imaging Combined with Deep Learning[J].Foods, 2022, 12(1):144-
[12]KUCHA C T，LIU L，NGADI M，et al.Assessment of intramuscular fat quality in pork using hyperspectral imaging[J].Food Engineering Reviews, 2021, 13:274-289
[13]TANG X，RAO L，XIE L，et al.Quantification and visualization of meat quality traits in pork using hyperspectral imaging[J].Meat Science, 2023, 196:109052-
[14]JIANG H, RU Y, CHEN Q, et al.Near-infrared hyperspectral imaging for detection and visualization of offal adulteration in ground pork[J].Spectrochimica Acta Part A：Molecular and Biomolecular Spectroscopy, 2021, 249:119307-
[15]ZHANG Y, ZHENG M, ZHU R, et al.Adulteration discrimination and analysis of fresh and frozen-thawed minced adulterated mutton using hyperspectral images combined with recurrence plot and convolutional neural network[J].Meat Science, 2022, 192:108900-
[16]杨佳, 刘强, 赵楠等.基于高光谱成像的干燥胡萝卜片水分及类胡萝卜素含量无损检测和可视化分析[J].食品科学, 2020, 41(12):285-291
[17]CUI H, CHENG Z, LI P, et al.Prediction of sweet corn seed germination based on hyperspectral image technology and multivariate data regression[J].Sensors, 2020, 20(17):4744-
[18]XIAO Q, BAI X, HE Y.Rapid screen of the color and water content of fresh-cut potato tuber slices using hyperspectral imaging coupled with multivariate analysis[J].Foods, 2020, 9(1):94-
[19]WANG F, WANG C, SONG S, et al.Study on starch content detection and visualization of potato based on hyperspectral imaging[J].Food Science & Nutrition, 2021, 9(8):4420-4430
[20]CHEN H, QIAO H, FENG Q, et al.Rapid detection of pomelo fruit quality using near-infrared hyperspectral imaging combined with chemometric methods[J].Frontiers in bioengineering and biotechnology, 2021, 8:616943-
[21]XUE S, YIN Y.An exploration of robust model construction for monitoring banana quality during storage based on hyperspectral information[J].Journal of Food Measurement and Characterization, 2022, 16(6):4526-4539
[22]MA L, ZHANG Y, ZHANG Y, et al.Rapid Nondestructive Detection of Chlorophyll Content in Muskmelon Leaves under Different Light Quality Treatments[J].Agronomy, 2022, 12(12):3223-
[23]ZHANG J, TIAN H, WANG D, et al.A novel spectral index for estimation of relative chlorophyll content of sugar beet[J].Computers and Electronics in Agriculture, 2021, 184:106088-
[24]任志尚，彭慧慧，贺壮壮等.基于高光谱成像技术的面条中马铃薯全粉含量检测[J].农业机械学报, 2020, 51(S2):466-470
[25]刘昊灵, 张仲雄, 陈昂等.融合光谱形态特征的苹果霉心病检测方法[J].农业工程学报, 2023, 39(01):162-170
[26]GUO W, LI X, XIE T.Method and system for nondestructive detection of freshness in Penaeus vannamei based on hyperspectral technology[J].Aquaculture, 2021, 538:736512-
[27]YAN X, QIAO X, YANG S, et al.Hyperspectral response and monitoring study of soil moisture content based on the optimized spectral index[J].Soil Science Society of America Journal, 2023, 87(2):216-230
[28]ZHOU Y, CHEN J, MA J, et al.Early warning and diagnostic visualization of Sclerotinia infected tomato based on hyperspectral imaging[J].Scientific Reports, 2022, 12(1):21140-
[29]YUAN R, LIU G, HE J, et al.Classification of Lingwu long jujube internal bruise over time based on visible near-infrared hyperspectral imaging combined with partial least squares-discriminant analysis[J]. [J].Computers and Electronics in Agriculture, 2021, 182:106043-
[30]CHEN Z, WANG Q, ZHANG H, et al.Hyperspectral imaging (HSI) technology for the non-destructive freshness assessment of pearl gentian grouper under different storage conditions[J].Sensors, 2021, 21(2):583-
[31]ZHANG F, SHI L, LI L, et al.Nondestructive detection for adulteration of panax notoginseng powder based on hyperspectral imaging combined with arithmetic optimization algorithm-support vector regression[J].Journal of Food Process Engineering, 2022, 45(9):e14096-
[32]AHMAD H, SUN J, NIRERE A, et al.Classification of tea varieties based on fluorescence hyperspectral image technology and ABC-SVM algorithm[J].Journal of Food Processing and Preservation, 2021, 45(3):e15241-
[33]MAO Y, LI H, WANG Y, et al.Prediction of Tea Polyphenols,Free Amino Acids and Caffeine Content in Tea Leaves during Wilting and Fermentation Using Hyperspectral Imaging[J].Foods, 2022, 11(16):2537-
[34]ZHANG W, PAN L, LU L.Prediction of TVB-N content in beef with packaging films using visible-near infrared hyperspectral imaging[J].Food Control, 2023, 147:109562-
[35]FENG S, CAO Y, XU T, et al.Rice leaf blast classification method based on fused features and one-dimensional deep convolutional neural network[J].Remote Sensing, 2021, 13(16):3207-
[36]SHAO Y, LIU Y, XUAN G, et al.Detection and analysis of sweet potato defects based on hyperspectral imaging technology[J]. Infrared Physics & Technology, 2022, 127:104403-
[37]JIANG S, HE H, MA H, et al.Quick assessment of chicken spoilage based on hyperspectral NIR spectra combined with partial least squares regression[J].International Journal of Agricultural and Biological Engineering, 2021, 14(1):243-250
[38]KONG D, SUN D, QIU R, et al.Rapid and nondestructive detection of marine fishmeal adulteration by hyperspectral imaging and machine learning[J]. [J].Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2022, 273:120990-
[39]JIANG H, YANG Y, SHI M.Chemometrics in tandem with hyperspectral imaging for detecting authentication of raw and cooked mutton rolls[J].Foods, 2021, 10(9):2127-
[40]FENG Z H, WANG L Y, YANG Z Q, et al.Hyperspectral monitoring of powdery mildew disease severity in wheat based on machine learning[J]. [J].Frontiers in Plant Science, 2022, 13:828454-
[41]XU M, SUN J, ZHOU X, et al.Research on nondestructive identification of grape varieties based on EEMD-DWT and hyperspectral image[J].Journal of Food Science, 2021, 86(5):2011-2023
[42]SUDU B, RONG G, GUGA S, et al.Retrieving SPAD Values of Summer Maize Using UAV Hyperspectral Data Based on Multiple Machine Learning Algorithm[J].Remote Sensing, 2022, 14(21):5407-
[43]GAO S, XU J.Hyperspectral image information fusion-based detection of soluble solids content in red globe grapes[J].Computers and Electronics in Agriculture, 2022, 196:106822-
[44]许童羽，金忠煜，郭忠辉等.基于--算法的水稻叶片氮磷含量协同反演方法[J].农业工程学报, 2022, 38(10):148-155
[45]FENG S, CAO Y, XU T, et al.Rice leaf blast classification method based on fused features and one-dimensional deep convolutional neural network[J].Remote Sensing, 2021, 13(16):3207-
[46]YU S, FAN J, LU X, et al.Hyperspectral Technique Combined with Deep Learning Algorithm for Prediction of Phenotyping Traits in Lettuce[J]. [J].Frontiers in Plant Science, 2022, 13:927832-
[47]陈玮，徐占军，郭琦.煤炭矿区耕地土壤有机质无人机高光谱遥感估测[J].农业工程学报, 2022, 38(8):98-106
[48]李国旭，耿静，许选虹，等.基于 - 多光谱和关键环境变量的土壤镉含量反演[J].农业工程学报, 2022, 38(12):224-232
[49]马仪, 黄组桂, 贾江栋等.基于无人机-卫星遥感升尺度的土壤水分监测模型研究[J].农业机械学报, 2023, 54(06):307-318