基于SVM的近红外黑木耳多糖含量分类

doi:10.16180/j.cnki.issn1007-7820.2019.08.004

摘要/Abstract

摘要：

黑木耳作为一种胶质食用菌,富含多种营养物质,其中多糖是其中所占比重最大、含量最高的功能性成分之一。针对黑木耳多糖的分类,区别于传统的化学方法检测操作复杂、检测速度慢的问题,文中利用红外光谱技术,对东北黑木耳样本进行多糖成分进行无损检测,并利用支持向量机(SVM)的算法进行建模仿真。通过选定核函数的最优惩罚系数C=100、正则化系数V=10 ^-1,测得黑木耳多糖分类模型的识别结果的精确率为85.7%,召回率为87.3%,F1-score为0.864,达到了预期目标。试验证明,相比较于常规的黑木耳多糖检测方法来说,根据支持向量机算法建立的高精度黑木耳近红外光谱多糖分类模型是可行的。

关键词: 计算机仿真, 支持向量机, 近红外光谱技术, 黑木耳, 多糖含量, 分类模型

Abstract:

As a kind of colloidal edible fungus, auricularia auricular was rich in a variety of nutrients, among which polysaccharide was one of the most important functional ingredients. According to the classification of polysaccharides from Auricularia auricula, it was different from the traditional chemical detection method, and the detection speed was slow. In this paper, infrared spectrometry was used to carry out nondestructive detection of polysaccharides in northeast auricularia auricular samples, and the algorithm is modeled by SVM simulation. The accuracy of the recognition result of the auricularia auricular polysaccharide classification model was 85.7% and the recall rate was 87.3% , F1-score was 0.864, which achieved the expected goal. The experiment proved that compared with the conventional black fungus polysaccharide detection method, the high-precision auricularia auricular near-infrared spectrum polysaccharide classification model established by the support vector machine algorithm is feasible.

Key words: computer simulation, support vector machine, near infrared spectroscopy, auricularia auricular, polysaccharide content, classification model

中图分类号:

TP391.9

孙丽萍,张希萌,何睿,李佳琪. 基于SVM的近红外黑木耳多糖含量分类[J]. 电子科技, 2019, 32(8): 16-21.

SUN Liping,ZHANG Ximeng,HE Rui,LI Jiaqi. Near-infrared Scanning Polysaccharide Content Classification of Auricularia Auricular Based on SVM[J]. Electronic Science and Technology, 2019, 32(8): 16-21.

图/表 9

图1

图2

图3

表1

图4

图5

表2

表3

表4

参考文献 27

[1]	卞春, 王振宇 , John Shi. 黑木耳多糖生物功能的研究进展[J]. 食品工业科技, 2015,36(16):390-400.
	Bian Chun, Wang Zhenyu, John Shi . Research progress of auricularia auricular polysaccharide(AAP)biological functions[J]. Science and Technology of Food Industry, 2015,36(16):390-400.
[2]	李凡姝, 张焕丽, 马慧等. 黑木耳多糖提取的工艺研究[J]. 农产品加工, 2016(18):13-16,20.
	Li Fanshu, Zhang Lihuan, Ma Hui , et al. Study of auricularia auricula polysaccharide extraction technology[J]. Farm Products Processing, 2016(18):13-16,20.
[3]	Oliver M D L, Günther K Bonn, Bernd M Rode , et al. Reproducible quantification of ethanol in gasoline via a customized mobile near-infrared spectrometer[J]. Analytica Chimica Acta, 2014,826(1):61-68.
[4]	Yao Linxing, Zhou Wen, Wang Tong , et al. Quantification of egg yolk contamination in egg white using UV/Vis spectroscopy:Prediction model development and analysis[J]. Food Control, 2014,43(43):88-97.
[5]	Liu Muhua, Yao Linxing, Wang Tong , et al. Rapiddetermination of egg yolk contamination in egg white by VIS spectroscopy[J]. Journal of Food Engineering, 2014,124(3):117-121
[6]	王凡, 李永玉, 彭彦昆 , 等. 便携式番茄多品质参数可见/近红外检测装置研发[J]. 农业工程学报, 2017,33(19):295-300.
	Wang Fan, Li Yongyu, Peng Yankun , et al. Development of portable device for simultaneous detection on multi-quality attributes of tomato by visible and near-infrared[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017,33(19):295-300.
[7]	褚小立, 陆婉珍 . 近五年我国近红外光谱分析技术研究与应用进展[J]. 光谱学与光谱分析, 2014,34(10):2595-2605.
	Chu Xiaoli, Chen Wanzhen . Research and application progress of near infrared spectroscopy analytical technology in china in the past five years[J]. Spectroscopy and Spectral Analysis, 2014,34(10):2595-2605.
[8]	Amit Kumar Gorai, Francis Tuluri, Paul B Tchounwou . Development of PLS-path model for understanding the role of precursors on ground level ozone concentration in Gulfport,Mississippi,USA[J]. Atmospheric Pollution Research, 2015,6(3):389-397.
[9]	Lin Jinshan . Performance comparisons between MFDFA and EMD using neural network and support vector machine[C]. MA,USA:Proceedings of 2017 2^nd International Conference on Applied Mechanics and Mechatronics Engineering(AMME 2017), 2017.
[10]	赛金辰 . 基于Spark的SVM算法优化及其应用[D]. 北京:北京邮电大学, 2017.
	Sai Jinchen . Optimization and application of SVM algorithm based on spark[D]. Beijing:Beijing University of Posts and Telecommunications, 2017.
[11]	赵芳, 马玉磊 . 自训练半监督加权球结构支持向量机多分类方法[J]. 重庆邮电大学学报:自然科学版, 2014,26(3):404-408,415.
	Zhao Fang, Ma Yulei . Multi-class classification based on self-training semi-supervised weighted sphere structured support[J]. Journal of Chongqing University of Posts and Telecommunications:Natural Science Edition, 2014,26(3):404-408,415.
[12]	赵杰文, 呼怀平, 邹小波 . 支持向量机在苹果分类的近红外光谱模型中的应用[J]. 农业工程学报, 2007,23(4):149-152
	Zhao Jiewen, Hu Huaiping, Zou Xiaobo . Application of support vector machine to apple classification with near-infrared spectroscopy[J]. Transactions of the CSAE, 2007,23(4):149-152
[13]	Scholkpf B, Smola A J . Learning with kernels:support vector machines,regularization,optimizition,and beyond[J]. Journal of the American Statistical Association, 2003,98(462):329-338.
[14]	Herbrich R. Learning kernel classifiers,theory and algorithms[M]. Cambridge: Massachusettes Institute of Technology Press, 2002.
[15]	张强, 刘成海, 孙井坤 , 等. 基于支持向量机的稻谷黄曲霉毒素B_1近红外无损检测[J]. 东北农业大学学报, 2015,46(5):84-88.
	Zhang Qiang, Liu Chenghai, Sun Jingkun , et al. Near- infrared spectroscopy nondestructive determination of aflatoxin B1 in paddy rice based on support vector machine regression[J]. Journal of Northeast Agricultural University, 2015,46(5):84-88.
[16]	陈艳秋, 鹿道富, 王歧 , 等. 袋料栽培黑木耳与段木栽培黑木耳的品质分析[J]. 食用菌学报, 2001,8(1):48-50.
	Chen Yanqiu, Lu Daofu, Wang Qi , et al. Analysis of the nutritional contents of auricularia auricula cultivated with sawdust medium and log[J] Acta Edulis Fungi, 2001,8(1):48-50.
[17]	张晶晶 . 六地区黑木耳产品的综合评价及其多糖特性的研究[D]. 武汉:华中农业大学, 2013.
	Zhang Jingjing . The study on six auricularia auricula commodity comprehensive evaluation and their polysaccharides characteristics[D]. Wuhan:Huazhong Agricultural University, 2013.
[18]	陈雪凤, 韦仕岩, 吴圣进 , 等. 不同黑木耳菌株的营养成分分析比较[J]. 食用菌, 2016,38(2):72-73.
	Chen Xuefeng, Wei Shiyan, Wu Shengjin , et al. Comparison of nutritional components of different auricularia auricula strains[J]. Edible Fungus, 2016,38(2):72-73.
[19]	吕明亮 . 黑木耳袋料栽培品种筛选及栽培技术研究[D]. 杭州:浙江农林大学, 2010.
	Lv Mingliang . Study on the auricularia auricula strain selection and cultivation technic with substrate material[D]. Hangzhou:Zhejiang Agriculture and Forestry University, 2010.
[20]	尼珍, 胡昌勤, 冯芳近 . 红外光谱分析中光谱预处理方法的作用及其发展[J]. 药物分析杂志, 2008,28(5):825-826.
	Ni Zhen, Hu Changqin, Feng Fangjin . Progress and efect of spectral data pretreatment in nir analytical technique[J]. Chinese Journal of Pharmaceutical Analysis, 2008,28(5):825-826.
[21]	金凤石 . 玉木耳多糖提取工艺优化及玉木耳抗疲劳乳饮料的研制[D]. 长春:吉林农业大学, 2016.
	Jin Fengshi . Process optimization on the extraction of white auricularia polysaccharide and preparation of anti-fatigue beverage of white auricularia[D]. Changchun: Jilin Agricultural University, 2016.
[22]	刘小丽 . 红外光谱在药物分析中的应用研究[D]. 西安:西北大学, 2013.
	Liu Xiaoli . Application of infrared spectroscopy in pharmaceutical analysis[D]. Xi’an:Northwest University, 2013.
[23]	仇逊超, 曹军 . 近红外光谱波段优化在东北松子蛋白质定量检测中的应用[J]. 现代食品科技, 2016,32(11):303-309.
	Qiu Xunchao, Cao Jun . Application of band optimization of near-infrared spectra for quantitative detection of proteins in northeastern pine nuts[J]. Modern Food Science and Technology, 2016,32(11):303-309.
[24]	郭国丽 . 黑木耳根多糖提取及黑木耳多糖啤酒的研制[D]. 大连:大连海洋大学, 2016.
	Guo Guoli . Extraction of polysaccharide from auricularia auricula root and preparation of AAP beer[D]. Dalian:Dalian Ocean University, 2016.
[25]	刘晓亮, 丁世飞, 朱红 , 等. SVM用于文本分类的适用性[J]. 计算机工程与科学, 2010,32(6):106-108. doi: 10.3969/j.issn.1007130X.2010.
	Liu Xiaoliang, Ding Shifei, Zhu Hong , et al. Appropriateness in applying SVMs to text classification[J]. Computer Engineering and Science, 2010,32(6):106-108. doi: 10.3969/j.issn.1007130X.2010.
[26]	柳长源 . 相关向量机多分类算法的研究与应用[D]. 哈尔滨:哈尔滨工程大学, 2013.
	Liu Changyuan . Research and application on the multi-classification of relevance vector machine algorithm[D]. Harbin:Harbin Engineering University, 2013.
[27]	王瑞平, 方云录, 何洪辉 . 稳健最小二乘单类支持向量机及其稀疏化方法[J]. 计算机工程与设计, 2018,39(6):1745-1749.
	Wang Ruiping, Fang Yunlu, He Honghui . Robust least squares one support vector machine and its sparse approximation[J]. Computer Engineering and Design, 2018,39(6):1745-1749.

	A₁	A₂	A₃	A₄
建模集样本量	15.1 g	14.5 g	15.1 g	14.5 g
验证集样本量	9.7 g	10.3 g	9.8 g	10.4 g

样本编号	APS溶出量/%
A₁	4.124
A₂	4.371
A₃	4.526
A₄	4.763

惩罚系数C	正则化系数V	准确率/%
10^-5	10^-6	0.654
10^-4	10^-5	0.534
10^-3	10^-4	0.662
10^-2	10^-3	0.757
10^-1	10^-2	0.895
100	10^-1	0.937
10	100	0.579