光学学报, 2009, 29 (10): 2800, 网络出版: 2009-10-19   

遗传算法在鱼粉中肉骨粉近红外光谱检测中的应用

Genetic Algorithm Used for Predicting Meat and Bone Meal Content in Fishmeal by Near Infrared Spectroscopy
湛小梅 1,2,*韩鲁佳 1,2刘贤 1,2杨增玲 1,2
作者单位
1 中国农业大学 工学院,北京 100083
2 动物营养学国家重点实验室,北京 100083
摘要
为了研究近红外光谱模型的优化方法,提高模型的精度,利用遗传算法对64个掺加了肉骨粉的鱼粉样品近红外光谱进行变量筛选,采用偏最小二乘法回归建模,并用21个样品进行外部验证。遗传算法共选取310个波长变量,相对于全谱的1556个变量减少了80%,与全谱范围的偏最小二乘法相比,交互验证相关系数(RCV)从0.80提高到0.90,交互验证均方根误差从5.22%降低到3.62%,预测相关系数(RV)从0.91提高到0.96,预测均方根误差从3.85%降低到2.95%,模型的稳健性和预测精度都显著提高。试验结果表明遗传算法可以改善近红外光谱法预测鱼粉中肉骨粉含量的效果。
Abstract
For the purpose of optimizing near infrared spectroscopy model,and improving the prediction result,Genetic Algorithm (GA) was used to select wavelength variables of near infrared spectroscopy for fishmeal adulterated with meat and bone meal. 310 wavelengths are selted in genetic algorithm. By contrast with all wavelengths based partial least squares(PLS),GA based PLS reduced 80% of the wavelengths,and gained much better cross validation and prediction results. Related coefficient of cross-validation RCV was improved from 0.80 to 0.90,while the value of root mean square error of cross- validation (RMSECV) was reduced from 5.22% to 3.62%. The related coefficient of prediction RV was improved from 0.91 to 0.96,while the value of root mean square error of prediction (RMSEP) was reduced from 3.85% to 2.95%. GA improved the robustness and predictability of the model. It’s indicated that GA was an effective method for variable selection and could improve the prediction result of the meat and bone meal content in fishmeal by near infrared spectroscopy.
参考文献

[1] 吴迪,黄凌霞,何勇 等. 作物和杂草叶片的可见近红外反射光谱特性[J]. 光学学报,2008,28(8):1618-1622

    Wu Di,Huang Lingxia,He Yong et al.. Visible-near infrared reflection spectroscopy for crop-weed discrimination [J]. Acta Optica Sinica,2008,28(8):1618-1622

[2] 刘飞,何勇,王莉. 黄酒糖度预测的可见近红外光谱方法研究[J]. 光学学报,2007,27(11):2054-2058

    Liu Fei,He Yong,Wang Li. Methods for the prediction of sugar content of rice wine using visible-near infrared spectroscopy [J]. Acta Optica Sinica,2007,27(11):2054-2058

[3] Cen Haiyan,He Yong. Theory and application of near infrared reflectance spectroscopy in determination of food quality [J]. Trends Food Sci. Tech.,2007,18(2):72-83

[4] Roggo Y,Pascal C,Lene M et al.. A review of near infrared spectroscopy and chemometrics in pharmaceutical technologies [J]. J. Pharm. Biomed. Anal.,2007,44(3):683-700

[5] 陆婉珍,袁洪福,徐广通 等. 现代近红外光谱分析技术[M]. 北京:中国石化出版社,2007

    Lu Wanzhen,Yuan Hongfu,Xu Guangtong et al.. Modern Near Infrared Spectroscopy Analytical Technology [M]. Beijing:Chinese Petrochemical Industry Press,2007

[6] 陈孝敬,吴迪,虞佳佳 等. 一种用于可见近红外光谱特征波长选择的新方法[J]. 光学学报,2008,28(11):2153-2158

    Chen Xiaojing,Wu Di,Yu Jiajia et al.. A new choice method of characteristic wavelength of visible/near infrared spectroscopy [J]. Acta Optica Sinica,2008,28(11):2153-2158

[7] Nurns D A,Ciurczak E W. Handbook of Near infrared Analysis [M]. New York:Marcel Dekker,2001

[8] 褚小立,袁洪福,陆婉珍. 近红外分析中光谱预处理及波长选择方法进展与应用[J]. 化学进展,2004,16(4):528-542

    Chu Xiaoli,Yuan Hongfu,Lu Wanzhen. Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique [J]. Progress In Chemistry,2004,16(4):528-542

[9] 褚小立,袁洪福,王艳斌 等. 遗传算法用于偏最小二乘方法建模中的变量筛选[J]. 分析化学,2001,29(4):437-442

    Chu Xiaoli,Yuan Hongfu,Wang Yanbin et al.. Variable selection for partial least squares modeling by genetic algorithms [J]. Chinese Journal of Analytieal Chemistry,2001,29(4):437-442

[10] Leardi R,Seasholtz M B,Pell R J. Variable selection for multivariate calibration using a genetic algorithm:prediction of additive concentrations in polymer films from Fourier transform-infrared spectral data [J]. Anal. Chim. Acta.,2002,461(2):189-200

[11] Ghasemi J,Niazi A,Leardi R. Genetic-algorithm-based wavelength selection in multicomponent spectrophotometric determination by PLS:application on copper and zinc mixture [J]. Talanta,2003,59(2):311-317

[12] 邹小波,赵杰文. 用遗传算法快速提取近红外光谱特征区域和特征波长[J]. 光学学报,2007,27(7):1316-1321

    Zou Xiaobo,Zhao Jiewen. Methods of characteristic wavelength region and wavelength selection based on genetic algorithm [J]. Acta Optica Sinica,2007,27(7):1316-1321

[13] 李艳肖,邹小波,董英. 用遗传区间偏最小二乘法建立苹果糖度近红外光谱模型[J]. 光谱学与光谱分析,2007,27(1):2001-2004

    Li Yanxiao,Zou Xiaobo,Dong Ying. Near infrared determination of sugar content in apples based on GA-iPLS [J]. Spectroscopy and Spectral Analysis,2007,27(1):2001-2004

[14] Ying Yibin,Liu Yande. Nondestructive measurement of internal quality in pear using genetic algorithms and FT-NIR spectroscopy [J]. J. Food Eng.,2008,84(2):206-213

[15] 刘辉军,吕进,林敏. 基于遗传算法的波长选择方法在绿茶近红外光谱分析模型中的应用[J]. 分析测试学报,2007,26(5):679-681

    Liu Huijun,Lü Jin,Lin Min. Application of characteristic wavelength selection method in NIR model of green tea based on genetic algorithms [J]. J. Instrumental Anal.,2007,26(5):679-681

[16] 曾立波,贺志平. 遗传算法在近红外光谱分析波长及预处理方法同步选择中的应用[J]. 分析仪器,2006,3:23-26

    Zeng Libo,He Zhiping. Study on the application of genetic algorithm for synchronous selection of wavelength and spectral data pretreatment method in near-infrared spectrometric analysis [J]. Analytical Instrumentation,2006,3:23-26

[17] 祝诗平,王一鸣,张小超 等. 基于遗传算法的近红外光谱谱区选择方法[J]. 农业机械学报,2004,35(5):152-156

    Zhu Shiping,Wang Yiming,Zhang Xiaochao et al.. Region selection method of near infrared spectrum based on genetic algorithm [J]. Transactions of The Chinese Society of Agricultural Machinery,2004,35(5):152-156

[18] 牛智有. 鱼粉、精料补充料及其中肉骨粉含量的近红外漫反射光谱分析[D]. 北京:中国农业大学,2005

    Niu Zhiyou. The NIRS Analysis of Fish Meal,Concentrate Supplement and MBM Content Inside [D]. Beijing:China Agricultural University,2005

[19] 李民赞. 光谱分析技术及其应用[M]. 北京:科学出版社,2006

    Li Minzan. Spectral analysis technology and application [M]. Beijing:Science Press,2006

[20] Chen Quansheng,Zhao Jiewen,Chaitep Sumpun et al.. Simultaneous analysis of main catechins contents in green tea (Camellia sinensis (L.)) by Fourier transform near infrared reflectance (FT-NIR) spectroscopy [J]. Food Chemistry,2009,113(4):1272-1277

湛小梅, 韩鲁佳, 刘贤, 杨增玲. 遗传算法在鱼粉中肉骨粉近红外光谱检测中的应用[J]. 光学学报, 2009, 29(10): 2800. Zhan Xiaomei, Han Lujia, Liu Xian, Yang Zengling. Genetic Algorithm Used for Predicting Meat and Bone Meal Content in Fishmeal by Near Infrared Spectroscopy[J]. Acta Optica Sinica, 2009, 29(10): 2800.

本文已被 1 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!