首页 > 论文 > 中国激光 > 42卷 > 11期(pp:1115003--1)

基于光声光谱结合LS-SVR 的稻种活力快速无损检测方法研究

Study on Rapid and Non-Destructive Detection of Rice Seed Vigor Based on Photoacoustic Spectroscopy Combined with LS-SVR

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

传统活力检测方法存在操作复杂、耗时长、可重复性差、对种子造成损伤且不可逆等不足,基于此,提出一种基于光声光谱结合最小二乘支持向量机回归(LS-SVR)的稻种活力快速、无损检测方法。在温度为45 ℃、相对湿度为90%的条件下,对南粳46(粳稻)和内5 优8015(杂交稻)进行高温高湿人工老化处理,依次老化0,24,48,72,96 h,获得不同活力的稻种;采集2类稻种光声光谱数据,总计100份,其中校正集样本60个,预测集样本40个;采用小波包对原始光谱数据进行预处理,通过协方差分析和主成分分析(PCA)对光谱进行降维;分别通过偏最小二乘回归(PLSR)、反向传播神经网络(BPNN)和LS-SVR 建立稻种活力预测模型。其中,采用协方差分析结合LS-SVR 建立的模型性能最优,该模型不仅适用于单一稻种,而且适用于不同种类稻种活力的预测。研究表明,采用光声光谱技术结合LS-SVR 对稻种活力进行测定是可行的,且所建模型在稻种活力预测方面具有较好的预测精度,为便携式水稻活力光声光谱仪的研制提供了理论依据。

Abstract

Considering that the traditional method for vigor test is complex, time- consuming, with poor reproducibility, irreversible, and likely to cause damage to the seed, a rapid and non-destructive testing method of rice seed vigor based on photoacoustic spectroscopy technology and least squares support vector regression (LSSVR) is proposed. Under the condition of temperature of 45 ℃ and relative humidity of 90%, Nanjing46 (japonica rice) and Nei5you 8015 (hybrid rice) rice seeds are artificially aged for 0, 24, 48, 72, 96 h to get rice seeds with different vigor. Spectral data of 100 samples for the two types of rice seeds are collected and divided into a calibration set (60 samples) and a prediction set (40 samples). Wavelet packet analysis is used in spectral preprocessing. Dimensionality reduction of the spectrum data is realized by covariance analysis and principal component analysis (PCA). Prediction models of rice seed vigor are established respectively by partial least squares regression (PLSR), back propagation neural network (BPNN) and LS-SVR. The results show that the optimal model is constructed by covariance analysis and LS-SVR, and the model is not only suitable for single rice species, but also for different types of rice seed in vigor forecast. The experiment shows that it is feasible that rice seed vigor is detected rapidly and non-destructively by photoacoustic spectroscopy technology and LS-SVR. The model has better prediction accuracy in vigor detection, and provides a theoretical basis for the development of portable rice seed vigor spectrometers.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:S511;S339.3+1;TH744.1

DOI:10.3788/cjl201542.1115003

所属栏目:光谱学

基金项目:国家自然科学基金青年基金(61401215)、中央高校基本科研业务经费(KYZ201427)、江苏省自然科学基金青年基金(BK20130696)、远程测控技术江苏省重点实验室开放基金(YCCK201501)

收稿日期:2015-06-01

修改稿日期:2015-07-14

网络出版日期:--

作者单位    点击查看

李欢欢:南京农业大学工学院江苏省现代设施农业技术与装备工程实验室, 江苏 南京 210031
卢伟:南京农业大学工学院江苏省现代设施农业技术与装备工程实验室, 江苏 南京 210031远程测控技术江苏省重点实验室, 江苏 南京 210096
杜昌文:中国科学院南京土壤研究所土壤与农业可持续发展国家重点实验室, 江苏 南京 210008
马菲:中国科学院南京土壤研究所土壤与农业可持续发展国家重点实验室, 江苏 南京 210008
罗慧:南京农业大学工学院江苏省现代设施农业技术与装备工程实验室, 江苏 南京 210031

联系人作者:李欢欢(hhlnjau@126.com)

备注:李欢欢(1994—),男,本科生,主要从事农产品无损检测技术方面的研究。

【1】Xin Liangjie, Li Xiubin. Changes of multiple cropping in double cropping rice area of southern China and its policy implications[J]. Journal of Natural Resources, 2009, 24(1): 58-65.
辛良杰, 李秀彬. 近年来我国南方双季稻区复种的变化及其政策启示[J]. 自然资源学报, 2009, 24(1): 58-65.

【2】Yu Zheng, Fang Fang, Peng Zuodeng, et al.. New technologies for detecting seed vigor[J]. Seed, 2012, 31(8): 52-55.
于征, 方芳, 彭祚登, 等. 基于新兴技术的种子活力检测方法研究[J]. 种子, 2012, 31(8): 52-55.

【3】Sun Qun, Wang Qing, Xue Weiqing, et al.. Advances in nondestructive detection of seed quality[J]. Journal of China Agricultural University, 2012, 17(3): 1-6.
孙群, 王庆, 薛卫青, 等. 无损检测技术在种子质量检验上的应用进展[J]. 中国农业大学学报, 2012, 17(3): 1-6.

【4】Han Liangliang, Mao Peisheng, Wang Xinguo, et al.. Study on vigour test of oat seeds with near infrared reflectance spectroscopy[J]. Journal of Infrared Millimeter Waves, 2008, 27(2): 86-90.
韩亮亮, 毛培胜, 王新国, 等. 近红外光谱技术在燕麦种子活力测定中的应用研究[J]. 红外与毫米波学报, 2008, 27(2): 86-90.

【5】Pourreza A, Pourreza H, Abbaspour-Fard M H, et al.. Identification of nine Iranian wheat seed varieties by textural analysis with image processing[J]. Computers and Electronics in Agriculture, 2012, 83(4): 102-108.

【6】Xu Sai, Zhou Zhiyan, Luo Xiwen. Classification and recognition of hybrid and inbred rough rice based on bionic electronic nose[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(9): 133-139.
徐赛, 周志艳, 罗锡文. 常规稻与杂交稻谷的仿生电子鼻分类识别[J]. 农业工程学报, 2014, 30(9): 133-139.

【7】Kranner I, Kastberger G, Hartbauer M, et al.. Noninvasive diagnosis of seed viability using infrared thermography[J]. Proceedings of the National Academy of Sciences, 2010, 107(8): 3912-3917.

【8】Zheng Dezhong, Zhao Nan. Design and experimental analysis of new photoacoustic cell[J]. Chinese J Lasers, 2014, 41(4): 0415002.
郑德忠, 赵南. 新型光声腔的设计及实验分析[J]. 中国激光, 2014, 41(4): 0415002.

【9】Du C, Ma Z, Zhou J, et al.. Application of mid-infrared photoacoustic spectroscopy in monitoring carbonate content in soils[J]. Sensors & Actuators B Chemical, 2013, 188(11): 1167-1175.

【10】National Standardization Technical Committee. GB/T3543.4-1995 Rules for agricultural seed testing - Germination test[S]. Beijing: China Standard Press, 1995.
国家标准化技术委员会. GB/T3543.4-1995农作物种子检验发规程——发芽试验[S]. 北京: 中国标准出版社, 1995.

【11】Xu Huibin, Wei Yidong, Lian Ling, et al.. Comparative analysis of artificial aging and natural aging with rice seeds[J]. Molecular Plant Breeding, 2013, 11(5): 552-556.
许惠滨, 魏毅东, 连玲, 等. 水稻种子人工老化与自然老化的分析比较[J]. 分子植物育种, 2013, 11(5): 552-556.

【12】Wickerhauser M V. INRIA lectures on wavelet packet algorithms[J]. Lecture Notes Inria, 1991: 31-99.

【13】Gao Ling, Li Xiaoping, Ren Shouxin. Simultaneous resolution of overlapped spectra of three kinds of organic compounds using a wavelet packet transform-based generalized regression neural network[J]. Spectroscopy and Spectral Analysis, 2008, 28(10): 2392-2395.
高玲, 李小平, 任守信. 小波包变换广义回归神经网络同时分辨三种有机化合物的重叠光谱[J]. 光谱学与光谱分析, 2008, 28 (10): 2392-2395.

【14】Yang H, Irudayaraj J. Characterization of semisolid fats and edible oils by Fourier transform infrared photoacoustic spectroscopy[J]. Journal of the American Oil Chemists′ Society, 2000, 77(3): 291-295.

【15】Bernstein M P, Cruikshank D P, Sandford S A. Near-infrared laboratory spectra of solid H2O/CO2 and CH3OH/CO2 ice mixtures[J]. Icarus, 2005, 179(2): 527-534.

【16】Barth A. Infrared spectroscopy of proteins[J]. Biochimica et Biophysica Acta (BBA)-Bioenergetics, 2007, 1767(9): 1073-1101.

【17】Ren Jing, Liu Gang, Zhao Xingxiang, et al.. Study of rhizome crops by Fourier transform infrared spectroscopy combined with wavelet analysis[J]. Chinese Agricultural Science Bulletin, 2015, 31(3): 149-154.
任静, 刘刚, 赵兴祥, 等. FTIR 结合小波变换分析鉴别8种根茎类作物[J]. 中国农学通报, 2015, 31(3): 149-154.

【18】Lu Yuzhen, Du Luowen, Yu Changbing, et al.. Determination of nitrogen and oil contents in rapeseeds using infrared photoacoustic spectroscopy combined with iPLS and siPLS[J]. Chinese Journal of Analysis Laboratory, 2013, 32(9): 78-82.
陆宇振, 杜罗文, 余常兵, 等. 红外光声光谱技术结合区间, 组合区间偏最小二乘测定油菜籽含氮量和含油量[J]. 分析试验室, 2013, 32(9): 78-82.

【19】Zeng Yin, Lu Yuzhen, Du Changwen, et al.. Applying infrared photoacoustics spectroscopy and support vector machine model to quantify soil organic matter content[J]. Acta Pedologica Sinica, 2014, 51(6): 1262-1269.
曾胤, 陆宇振, 杜昌文, 等. 应用红外光声光谱技术及支持向量机模型测定土壤有机质含量[J]. 土壤学报, 2014, 51(6): 1262- 1269.

【20】Su H J, Sheng Y H. Hyperspectral feature recognition based on kernel PCA and relational perspective map[J]. Chinese Optics Letters, 2010, 8(8): 811-814.

【21】Weng Shizhuang, Zheng Shouguo, Li Pan, et al.. Quantitative analysis of fenitrothion based on surface-enhanced Raman spectroscopy [J]. Chinese J Lasers, 2013, 40(8): 0815001.
翁士状, 郑守国, 李盼, 等. 基于表面增强拉曼光谱的杀螟硫磷定量分析[J]. 中国激光, 2013, 40(8): 0815001.

【22】Shokri S, Sadeghi M T, Marvast M A, et al.. Integrating principal component analysis and vector quantization with support vector regression for sulfur content prediction in HDS process[J]. Chemical Industry and Chemical Engineering Quarterly, 2015, 21(3): 379-390.

【23】Zhang W J, Liu R, Zhang W, et al.. Net analyte signal with floating reference theory in non-invasive blood glucose sensing by near-infrared spectroscopy[J]. Chinese Optics Letters, 2012, 10(8): 083002.

【24】Xu Zhaomei, Zhou Jianzhong, Huang Shu, et al.. Quality of prediction of laser milling based on optimized back propagation networks by genetic algorithms[J]. Chinese J Lasers, 2013, 40(6): 0603004.
许兆美, 周建忠, 黄舒, 等. 基于遗传算法优化反向传播神经网络的激光铣削层质量预测[J]. 中国激光, 2013, 40(6): 0603004.

【25】Van Gestel T, De Brabanter J, De Moor B, et al.. Least Squares Support Vector Machines[M]. Singapore: World Scientific, 2002.

【26】Keerthi S S, Lin C J. Asymptotic behaviors of support vector machines with Gaussian kernel[J]. Neural Computation, 2003, 15(7): 1667- 1689.

【27】Yang Yaping, Jiang Xiaocheng, Chen Liangbi, et al.. Study on physiological mechanism in aging of rice seeds[J]. Journal of Hunan Agricultural University (Natural Sciences), 2008, 34(3): 265-269.
杨亚平, 姜孝成, 陈良碧, 等. 水稻种子老化的生理机制[J]. 湖南农业大学学报: 自然科学版, 2008, 34(3): 265-269.

【28】Zhu Shiyang. Studies on Priming Technology, Its Mechanism of F1 Seed and Genetic Analysis on Anti-Aging in Rice (Oryza sativa L) [D]. Nanjing: Nanjing Agricultural University, 2008: 42-49.
朱世杨. 水稻F_1 种子引发技术及其机理和抗老化遗传的研究[D]. 南京: 南京农业大学, 2008: 42-49.

【29】Chen Zicong, Gao Zhihui, Cao Zhi, et al.. Research on CO2 gas concentration test system based on mid-infrared LED[J]. Laser & Infrared, 2012, 42(11): 1255-1258.
陈子聪, 高致慧, 曹志, 等. 基于中红外LED 的CO2气体浓度检测系统研究[J]. 激光与红外, 2012, 42(11): 1255-1258.

引用该论文

Li Huanhuan,Lu Wei,Du Changwen,Ma Fei,Luo Hui. Study on Rapid and Non-Destructive Detection of Rice Seed Vigor Based on Photoacoustic Spectroscopy Combined with LS-SVR[J]. Chinese Journal of Lasers, 2015, 42(11): 1115003

李欢欢,卢伟,杜昌文,马菲,罗慧. 基于光声光谱结合LS-SVR 的稻种活力快速无损检测方法研究[J]. 中国激光, 2015, 42(11): 1115003

被引情况

【1】王书涛,张彩霞,王志芳,张 强,马晓晴,郑亚南. 最小二乘支持向量机在对羟基苯甲酸甲酯钠荧光检测中的应用. 激光与光电子学进展, 2017, 54(7): 73001--1

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF