[1]张津源,张德贤,张苗.基于连续投影算法的小麦蛋白质含量近红外光谱预测分析[J].江苏农业学报,2019,(04):960-964.[doi:doi:10.3969/j.issn.1000-4440.2019.04.030]
　ZHANG Jin yuan,ZHANG De xian,ZHANG Miao.Prediction and analysis of wheat protein content by nearinfrared spectroscopy based on successive projections algorithm[J].,2019,(04):960-964.[doi:doi:10.3969/j.issn.1000-4440.2019.04.030]
点击复制

基于连续投影算法的小麦蛋白质含量近红外光谱预测分析()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年04期
页码:
960-964
栏目:
加工贮藏·质量安全
出版日期:
2019-08-31

文章信息/Info

Title:
Prediction and analysis of wheat protein content by nearinfrared spectroscopy based on successive projections algorithm
作者:
张津源; 张德贤; 张苗
（河南工业大学信息科学与工程学院，河南郑州450001）
Author(s):
ZHANG Jinyuan; ZHANG Dexian; ZHANG Miao
(College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China)
关键词:
小麦; 蛋白质含量; 近红外光谱; 检测模型; 特征波段点
Keywords:
wheat; protein content; near infrared spectroscopy; detection model; characteristic band points
分类号:
S126
DOI:
doi:10.3969/j.issn.1000-4440.2019.04.030
文献标志码:
A
摘要:
为了快速无损检测分析小麦蛋白质含量，构建近红外光谱最优小麦蛋白质定量检测分析模型。利用一阶SG平滑算法+SNV算法对光谱进行预处理。使用连续投影算法（Successive projections algorithm, SPA）提取光谱中的特征波段点，使全谱图的141个波段点降低到17个特征波段点。在选择的17个特征波段点基础上分别建立偏最小二乘回归（Partial least regression, PLSR）模型、支持向量机（Support vector machine, SVM）模型、多元线性回归（Multiple linear squares regression, MLR）模型和主成分回归（Principal component regression, PCR）模型。在构建的4种小麦蛋白质含量预测模型中，MLR预测分析模型的验证集均方根误差（RMSEV）和校正集均方根误差（RMSEC）最小，验证集相关系数（rv）和校正集相关系数（rc）最大，其rv=0968，rc=0976，RMSEV=0300，RMSEC=0275。因此，相比于其他3种检测模型，建立的MLR小麦蛋白质含量检测模型最优，稳定性和精确性最高。
Abstract:
In order to detect the wheat protein content quickly and nondestructively, an optimal quantitative analysis model of wheat protein content was constructed. The first derivative SG smoothing algorithm and the standard normal variable (SNV) were used to preprocess the spectrum. The successive projections algorithm (SPA) was used to extract the characteristic band points in the spectrum, so that 141 band points of the full spectrum were reduced to 17 characteristic band points. Partial least square regression(PLSR) model, support vector machine(SVM) model, multiple linear regression(MLR) model and principal component regression(PCR) model were established on the basis of 17 selected characteristic band points. In the four wheat protein content prediction models, the MLR model had the smallest rootmeansquare error of the validation set (RMSEV), the smallest rootmeansquare error of the calibration set (RMSEC), the largest correlation coefficient of the validation set (rv) and the largest correlation coefficient of calibration set(rc). The correlation coefficients of validation set and calibration set were 0968 and 0976. The root mean square error of validation set and calibration set were 0300 and 0275. Compared with the other three detection models, the MLR detection model is the best, and the stability and accuracy are the highest.

参考文献/References:

[1]吕程序，蒋训鹏，张银桥,等. 基于变量选择的小麦粗蛋白质含量的近红外光谱检测[J].农业机械学报，2016,47(S1):266-270.
[2]张松，冯美臣，杨武德,等.基于近红外光谱的冬小麦籽粒蛋白质质含量检测[J].生态学杂志，2018,37(4):1276-1281.
[3]宋雨宸，宦克为，韩雪艳,等.基于蒙特卡洛变量组合集群分析法的小麦蛋白质质近红外光谱变量选择[J].长春理工大学学报，2017,40(5):29-34.
[4]毛晓东，孙来军，戴长军,等.基于近红外光谱的小麦品质分类研究[J].中国农学通报，2013,29(36):386-390.
[5]钱海波，孙来军，王乐凯,等.基于连续投影算法的小麦湿面筋近红外校正模型优化[J].中国农学通报，2011,27(18):51-56.
[6]吴静珠，董文菲，董晶晶,等.基于Si_cPLS的小麦种子发芽率近红外模型优化研究[J].光谱学与光谱分析，2017,37(4)：1114-1117.
[7]王赋腾，孙晓荣,刘翠玲,等. 光谱预处理对便携式近红外光谱仪快速检测小麦粉灰分含量的影响[J].食品工业科技，2017(10)：58-61,66.
［8]张平平,张瑜,唐果,等. 近红外光谱技术检测小麦谷蛋白大聚体含量［J].江苏农业学报,2017,33(6):1207-1211.
[9]惠广艳，孙来军，王佳楠,等.可见近红外光谱的小麦硬度预测模型预处理方法研究[J].光谱学与光谱分析，2016,36(7):2111-2116.
[10]王冬，李安，靳欣欣,等.基于2原理的近红外光谱仪对辐射花生的快速鉴别比较[J].食品科学，2016,37(8):212-215.
[11]吴迪，吴洪喜，蔡景波,等.基于无信息变量消除和连续投影算法的可见近红外光谱技术白蚁种分类方法研究[J].红外与毫米波学报，2009,28(6):423-427.
[12]CHENG Z, ZHANG L Q, LIU H Y, et al. Successive projections algorithm and its application to selecting the wheat nearinfrared spectral variables[J]. Spectroscopy and Spectral Analysis, 2010,30(4): 949-952.
[13]孙旭东，郝勇，蔡丽君,等.基于抽取和连续投影算法的可见近红外光谱变量筛选[J]. 光谱学与光谱分析，2011,31(9):2399-2402.
[14]任东，瞿芳芳，陆安祥,等.近红外光谱分析技术与应用[M].北京:科学出版社，2017:31-42.
[15]展晓日，朱向荣，史新元,等.SPXY样本划分及蒙特卡洛交叉结合近红外光谱永远橘叶中橙皮苷的含量测定[J].光谱学与光谱分析，2009,29(4):964-968.

相似文献/References:

[1]伍 宏,朱昌华,夏 凯,等.叶面喷施激动素对小麦品种济麦22品质的影响[J].江苏农业学报,2016,(02):299.[doi:10.3969/j.issn.1000-4440.2016.02.010]
　WU Hong,ZHU Chang-hua,XIA Kai,et al.Effect of foliar application of kinetin on quality of Triticum aestivum L. Jimai 22[J].,2016,(04):299.[doi:10.3969/j.issn.1000-4440.2016.02.010]
[2]蒋正宁,别同德,赵仁惠,等.受条锈菌诱导的小麦丝氨酸苏氨酸激酶基因TaS/TK的克隆与表达[J].江苏农业学报,2016,(05):980.[doi:10.3969/j.issn.1000-4440.2016.05.004]
　JIANG Zheng-ning,BIE Tong-de,ZHAO Ren-hui,et al.Cloning and expression analysis of a Serine/Threonine protein kinase gene TaS/TK in wheat in response to stripe rust fungal infection[J].,2016,(04):980.[doi:10.3969/j.issn.1000-4440.2016.05.004]
[3]丁彬彬,张旭,吴磊,等.小麦3B 短臂染色体抗赤霉病主效 QTL 区域候选基因的表达[J].江苏农业学报,2017,(01):6.[doi:10.3969/j.issn.1000-4440.2017.01.002 ]
　DING Bin-bin,ZHANG Xu,WU Lei,et al.Expression of candidate genes on the region of a major QTL for the resistance to Fusarium head blight on the short arm of chromosome 3B in wheat[J].,2017,(04):6.[doi:10.3969/j.issn.1000-4440.2017.01.002 ]
[4]周淼平,姚金保,张鹏,等.小麦幼苗纹枯病抗性评价新方法[J].江苏农业学报,2017,(01):61.[doi:10.3969/j.issn.1000-4440.2017.01.010 ]
　ZHOU Miao-ping,YAO Jin-bao,ZHANG Peng,et al.New method for the resistance evaluation of wheat sharp eyespot in seedling[J].,2017,(04):61.[doi:10.3969/j.issn.1000-4440.2017.01.010 ]
[5]吴磊,姜朋,张瑜,等.苏麦3号小麦穗部病毒诱导的基因沉默（VIGS）体系的建立及验证[J].江苏农业学报,2017,(02):248.[doi:doi:10.3969/j.issn.1000-4440.2017.02.002]
　WU Lei,JIANG Peng,ZHANG Yu,et al.Construction and validation of virus-induced gene silencing(VIGS) system in spike of wheat variety Sumai 3[J].,2017,(04):248.[doi:doi:10.3969/j.issn.1000-4440.2017.02.002]
[6]邵继锋,陈荣府,董晓英,等.利用分根技术研究小麦铝磷交互作用[J].江苏农业学报,2016,(01):78.[doi:10.3969/j.issn.1000-4440.2016.01.012 ]
　SHAO Ji-feng,CHEN Rong-fu,DONG Xiao-ying,et al.Aluminum-phosphorus interaction in wheat grown in a split-root device[J].,2016,(04):78.[doi:10.3969/j.issn.1000-4440.2016.01.012 ]
[7]叶景秀.小麦籽粒蛋白质双向电泳体系的优化[J].江苏农业学报,2015,(05):957.[doi:doi:10.3969/j.issn.1000-4440.2015.05.002]
　YE Jing-xiu.Optimization of two-dimensional electrophresis system for grain protein in spring wheat[J].,2015,(04):957.[doi:doi:10.3969/j.issn.1000-4440.2015.05.002]
[8]郑舒文,徐其隆,邹华文.脱落酸对涝渍胁迫下小麦产量的影响[J].江苏农业学报,2015,(05):967.[doi:doi:10.3969/j.issn.1000-4440.2015.05.004]
　ZHENG Shu-wen,XU Qi-long,ZOU Hua-wen.Yield of waterlogged wheat in response to ABA application[J].,2015,(04):967.[doi:doi:10.3969/j.issn.1000-4440.2015.05.004]
[9]张玉萍,马占鸿.不同施氮量下小麦遥感估产模型构建[J].江苏农业学报,2015,(06):1325.[doi:doi:10.3969/j.issn.1000-4440.2015.06.020]
　ZHANG Yu-ping,MA Zhan-hong.Yield estimation model of wheat based on remote sensing data under different nitrogen supply conditions[J].,2015,(04):1325.[doi:doi:10.3969/j.issn.1000-4440.2015.06.020]
[10]张卓亚,王晓琳,许晓明,等.腐植酸对小麦扬花期水分利用效率及灌浆进程的影响[J].江苏农业学报,2015,(04):725.[doi:10.3969/j.issn.1000-4440.2015.04.003]
　ZHANG Zhuo-ya,WANG Xiao-ling,XU Xiao-ming,et al.Effect of humic acid on water use efficiency and grouting process of wheat at flowering[J].,2015,(04):725.[doi:10.3969/j.issn.1000-4440.2015.04.003]
[11]杨丹,姚金保,杨学明,等.北方麦区小麦品种高分子量谷蛋白亚基组成及其与品质性状的关系[J].江苏农业学报,2015,(02):241.[doi:10.3969/j.issn.1000-4440.2015.02.003]
　YANG Dan,YAO Jin-bao,YANG Xue-ming,et al.High molecular weight gluten subunit(HMW-GS) composition of wheat cultivars in northern region and its relationship with quality traits[J].,2015,(04):241.[doi:10.3969/j.issn.1000-4440.2015.02.003]

备注/Memo

备注/Memo:
收稿日期：2018-07-04 基金项目：国家科技支撑计划项目（2013BAD17B04）；河南省科技厅自然科学项目（172106000013）；粮食信息处理与控制教育部重点实验室开放基金课题（KFJJ2016102） 作者简介：张津源（1992-），男，河南周口人，硕士研究生，主要研究方向为模式识别与智能信息处理。 (E-mail)15303816835@163.com 通讯作者：张德贤，(E-mail)zdx@haut.edu.cn
更新日期/Last Update: 2019-08-31