摘要
针对几种天然产物,研究如何将几种模式识别技术,即偏最小二乘、模糊模式识别、人工神经网络、支持向量机及灰度关联分析与红外光谱分析有机地结合以实现定量和定性分析,旨在找到一种更为有效的红外光谱的建模方法,为天然产物的红外光谱分析提供新思路和新技巧。
1.以天然产物人参、淫羊藿和烟草为研究对象,提出将模糊模式识别技术应用于红外光谱的定性分析中,解决了其分析过程中光谱变量的降维、贴近度和择近原则以及分析步骤等关键性问题。
2.针对天然产物烟草和黄连,研究了偏最小二乘法(PLS)用于近红外光谱的单组分及多组分的定量分析,并确定了光谱的预处理方案及泛化能力的评价指标。
3.以天然产物人参、淫羊藿、烟草、黄连为例,研究人工神经网络应用于中红外光谱的产地鉴别分析及近红外光谱的定性和定量分析时的关键参数设置和相关问题的解决方案,并对建立的模型进行了有效评价。
4.研究支持向量机技术(SVM)用于近红外光谱定量分析时有关核参数和核函数的选择方法,同时提出结合小波变换技术,利用支持向量机对烟草及黄连近红外光谱的单组分、多组分的定量分析进行了仿真实验,并将不同模式识别技术建立的模型进行细致的对比研究。
5.提出将灰色关联分析法用于近红外光谱的谱区优化选取,通过计算某一谱区的峰面积与特定组分的灰色关联度,并将灰色关联度较大的谱区作为特征谱区参与建模,使其建模时间大大缩短,预测精度有较大的提高。
In recent years, the infrared spectroscopy analysis, as result of its many advantages, that is quick analysis speed, no pollution, not to need special pretreatment, not to use virulent and the harmful reagent, nodestructive, simple operation, the lower analysis cost, green environmental protection and so on, has made the breakthrough progress in quality analysis of some natural products, especially in the traditional Chinese medicine field. The spectrum area of infrared spectroscopy mainly shows the frequency multiplication absorption of stretching vibration in O-H, N-H and C-H key, which is special suitable for quantitative analysis of functional groups in natural products. But the vibration base frequency of the overwhelming majority organic compound appears in the middle infrared spectroscopy, which is more suitable for qualitative analysis of functional groups and structure of natural products.
Multiple linear regression(MLR), the principal components analysis (PCA) and partial least squares regression (PLSR) are the traditional chemometric methods in the infrared spectral analysis. However the massive reports indicated that the non-linear relations often present between the target and the spectrum data, so these linear regression technologies certainly cannot obtain the very good predicted accuracy. But pattern recognition technology, because it has the ability of distinguishing the specimen which the specific object imitates through the computer technology, simultaneously has the very good generation, therefore can be used in the choice and extract of spectral characteristics, the classification and prediction of object, simultaneously the quantitative analysis and prediction of specific component through self-learning and regression technology.
However, the traditional pattern recognition methods use one pattern characteristic to apply in all sample classes, and does not differentiate to them. When each characteristic is input match module, it carries on directly match and classification. Therefore, when the pattern is not match with symbol, it is very difficult to judge problems part, and the revision algorithms and parameters adjustment own certain blindness.Then people's experience function is unable to be displayed, it would enhance the recognition rate only through the massive samples learning and unceasing adjusting parameters. Regarding to infrared spectrum, because the complexity and the massive spectrum peak overlap of its spectrum data cause analysis difficulty, its difficulty of pattern recognition is very obvious.If only traditional pattern recognition methods are used, the effective classification may be made with difficuly. What is lucky, after L.A.Zadeh proposed the fuzzy set thought, the fuzzy mathematics method had been introduced in the pattern recognition (i.e. fuzzy pattern recognition). When the recognition system is designed by use of fuzzy technology, it can more widespreadly and thoroughly simulate the thinking process of human brain, then the computer intelligence, the usability and reliability of system can be enhanced.
In such cases, the artificial neural network (ANN) has been used with relative success in the spectral analysis because it may willfully approach to the nonlinear function. But ANN suffers critical drawbacks that it easily falls into over-fitting. Simultaneously the ANN model excessively relies on the train sample data, and under the majority situation, the sample data is extremely limited (namely so-called small sample), the prediction ability of ANN model will be weakly. Next, because the spectrum data of samples is usually high-dimensional, it is necessary that the characteristics of the primitive spectrum data must be withdrawn using dimensionality reduction technology for reducing the computation quantity. Otherwise the training time of ANN model would greatly increase, the convergence speed would become very slow, and it couldn’t even converge. Recently, as a new pattern recognition method, support vector machine (SVM) has a good theoretical foundation in statistical learning theory. It has been widely applied in the fields of pattern recognition, the time-series analysis as well as the function approximation and so on. Instead of the traditional statistical theory, SVM mainly aims at the small samples, namely the optimal solution is based on the limited sample information, but not on the information that the number of samples tends to infinity. Moreover, SVM models can avoid over-fitting problem, has the superior generalization ability and prediction accuracy.
The research point of this paper lies in: in view of some natural products, it was carried out that the infrared spectroscopy analysis was organically combined with several kinds of pattern recognition technology, namely partial least squares, fuzzy pattern recognition, artificial neural networks, support vector machine and grey correlation analysis, to realize qualitative and quantitative analysis for the purpose of seeking one kind of more effective modeling method of infrared spectroscopy and providing the infrared spectroscopy analysis of natural products with new ideas and skill.
Take the natural products, that is ginseng, Epimedium Brevicornum and tobacco, as the objects of study, the fuzzy pattern recognition technology to apply in qualitative analysis of infrared spectroscopy was first proposed. simultaneously, the crucial questions, namely dimension reduction of spectrum variables, closeness degree, principle of choosing the nearest as well as analysis steps and so on, had also solved during the process of analysis. The simulation result indicated that the habitat distinction models can basically correctly distinguish 42 Epimedium Brevicornum samples, 40 ginseng samples, and 120 tobacco samples, which is satisfying. Moreover it can avoid the separation and drawing of natural products with traditional spectroscopy analysis, thus offer the effectively and reliable basis for the quality controls and modernized management of natural products.
In view of the natural products, namely tobacco and concocted Coptis, the least squares method was studied to realize quantitative analysis of single component and the multi-components together near-infrared spectroscopy, and the pretreatment plan of spectrum data and evaluating index of generalization had been also determined. The simulation experiment indicated that when the partial least squares method was used in the spectral analysis of natural products, it could meet the practical application needs to a certain extent, but the optimization time was excessively long, it was not to suit the small samples and the generation ability was relatively weak, thus its practical application value was reduced to some extent.
Take the natural products, that is ginseng, Epimedium Brevicornum, tobacco and concocted Coptis as the examples, the research of artificial neural networks applied in habitat distinction analysis of middle infrared spectrum and qualitative analysis of near-infrared spectrum had been completed, and the key parameters, the solution of related question and effective appraisal to the models had been also carried on. The simulation results indicated that habitat distinction models, regardless of near-infrared spectroscopy or the middle infrared spectroscopy, their distinction accuracy rates achieve above 92%. Simultaneously, the prediction of quantitative analysis models was quite accurate, each evaluating index of models was ideal. At the same time, it was also found that when the artificial neural networks was appllied in the infrared spectroscopy analysis, really, its generation had certain limitation, and it was easily to fall into local optimal problem.Moreover, when the quantity of samples used in modeling was relatively less, the predictive ability of models were obviously weaken.
The wavelet transform technique combined the support vector technology were first proposed to realize the qualitative and quantitative analysis work of middle infrared and near-infrared spectroscopy. Simultaneously, the related nuclear parameters and the method of nuclear function choice were discussed and analyzed, which was simulated in single component, the multi-component quantitative analysis of near-infrared spectroscopy of tobacco and concocted Coptis samples, and habitat distinction analysis of infrared spectroscopy of ginsengs and Epimedium Brevicornum samples. Finally, the models by use of different pattern recognition methods were carefully compared. The contrast result indicated that qualitative and quantitative analysis models based on support vector machines, regardless of the near-infrared spectroscopy or the middle infrared spectroscopy, manifest some advantages, namely the good reliability, the robustness, the best distinction accuracy rate, the highest prediction precision, the strongest generation, the shortest modeling time, the fewer manual controlling factors, the most suitable for the small sample, not easy to fall into local optimal problem and so on.Therefore, the support vector machine owns the high practical application value and the broad application prospect in the infrared spectroscopy analysis field.
The grey correlation analysis method was first used in the optimization selection of spectrum regions of near-infrared spectroscopy. Through calculating the peak area of some spectrum region and correlation degree of the specific component, the spectrum regions of maximum correlation degree were took as the optimal spectrum region and participated to establish models. The simulation results showed that the modeling time was greatly reduced and the predicting precision was significantly increased. Therefore, this research owns the high application value.
引文
[1]边肇祺,张学工.模式识别(第二版)[M].北京:清华大学出版社, 1999, 1-3
[2] J. P. Marques de Sá著,吴逸飞译.模式识别-原理、方法及应用(原书名:Pattern Recognition Concepts、Methods and Applications)[M].北京:清华大学出版社, 2002, 1-7
[3]苏剑波,徐波.应用模式识别技术导论[M].上海:上海交通大学出版社, 2001, 3-10
[4]钟珞,潘昊,封筠,何平.模式识别[M].武汉:武汉大学出版社, 2006, 1-12
[5]肖健华.智能模式识别方法[M].广州:华南理工大学出版社, 2006, 1-20
[6] http: //baike. baidu. com/view/40692. htm
[7]郑新章,高琳,周雅宁.近5年国内外烟草科技论文统计分析与研究热点[J].中国烟草学报, 2008, 14(3): 63-64
[8]李小福,殷全玉.同时蒸馏萃取和减压蒸馏萃取方法提取烟叶香气成分的比较[J].中国科技论文在线, 2008, 3(9): 672-676
[9]王海燕,崔春,赵谋明,沈光林,饶国华.烟草多酚提取工艺优化及成分定性分析[J].华南理工大学学报(自然科学版), 2008, 36(3): 64-68
[10]黄翼飞,沈光林,温东奇,施文庄,李峰,李敏健,张优茂.液相色谱-电喷雾离子阱串联质谱分析烟草水提取物中的尼古丁[J].分析化学, 2007, 35(2): 293-296
[11]陈章玉.固相苹取和固相微苹取在烟草重要化学成分分析中的应用研究[D].中国科学技术大学博士学位论文, 2007
[12]龚伟,刘惠民,石杰,谢复炜. LC-MS-MS分析烟草中氨基甲酸酯农药残留[J].烟草科技, 2008, 8: 44-46
[13]李福娟,蔡文生,邵学广.反相高效液相色谱法分离测定烟草中的多酚类化合物[J].色谱, 2008, 25(4): 565-568
[14]孙凯健,王美琳,沈轶,刘百战.溶剂助蒸馏法在烟草香气成分分析中的应用[J].中国烟草科学, 2007, 28(2): 23-26
[15]邓云,陈志燕,曾德芬.近红外快速定量分析烟草化学成分模型的建立[J].广西烟草, 2008, 2: 56-59
[16]李艳坤,邵学广,蔡文生.基于多模型共识的偏最小二乘法用于近红外光谱定量分析[J].高等学校化学学报, 2007, 28(2): 246-249
[17]王芳,陈达,邵学广.小波变换和偏最小二乘法在烟草常规成分预测中的应用[J].烟草科技, 2004, 3: 31-34
[18] Pilar B. Garc′?a-Allende , Olga M. Conde, Ana M. Cubillas, C′esar J′auregui , Jos′e M. L′opez-Higuera. New raw material discrimination system based on a spatial optical spectroscopy technique[J]. Sensors and Actuators A , 2007, 135(2): 605-612
[19]何智慧,练文柳,吴名剑,唐丽云,陈亚.声光可调-近红外光谱技术分析烟草主要化学成分[J].分析化学, 2006, 34(5): 702-704
[20] Yongni Shao, Yong He, Yanyan Wang. A new approach to discriminate varieties of tobacco usingvis/near infrared spectra[J]. Eur Food Res Technol, 2007, 224(5): 591-596
[21] Shao Y. N., Hu X. Y., He Y., Wang Y. Y.. Discrimination of varieties of tobacco using Vis/Near infrared spectra by wavelet transform and BP model[J]. Dynamics of Continuous Discrete and Impulsive System-series B-Applications & Algorithm, 2006, 13E: 2120-2124
[22]农训学.滋补壮阳良品—淫羊藿[J].养生月刊, 2008, 11: 1-3
[23]徐艳琴,李作洲,张学军,陈建军,周建峰,王瑛.三种药用淫羊藿的地理分布与资源调查[J].武汉植物学研究, 2008, 26(1): 91-98
[24]谭淋,袁明,汤加勇,丁春邦,杨瑞武,廖进秋.柔毛淫羊藿生长势及花期的研究[J],时珍国医国药, 2008, 19(9): 2264-2265
[25]姜宁,刘晓鹏.淫羊藿中淫羊藿苷的快速提取与测定研究[J].中华中医药杂志, 2008, 23(1): 64-66
[26]陈彦,赵艳红,贾晓斌,丁安伟. RP-HPLC法同时测定不同品种淫羊藿药材中5种主要黄酮类成分的含量[J].中国药房, 2008, 19(6): 431-433
[27] Nurul M. Islam, Hye Hyun Yoo, Min Woo Lee, Mi-sook. Simultaneous Quantitation of Five Flavonoid Glycosides in Herba Epimedii by High-performance Liquid Chromatography–Tandem Mass Spectrometry[J]. Phytochemical Analysis, 2008, 19(1): 71-77
[28]裴利宽,郭宝林,孙素琴,黄文华.淫羊藿药材一些混淆物种的FTIR鉴别研究[J].光谱学与光谱分析, 2008, 28(1): 64-66
[29] Li-Kuan Pei, Su-Qin Sun, Bao-Lin Guo, Wen-Hua Huang, Pei-Gen Xiao. Fast quality control of Herba Epimedii by using Fourier transform infrared Spectroscopy[J]. Spectrochimica Acta Part A , 2008, 70(2): 258-264
[30] http: //baike. baidu. com/view/21017. htm
[31]邓雅婷.黄连-吴茱英药对主要成分的溶出变化和药动学研究[D].沈阳药科大学硕士学位论文, 2008
[32]韩晶.黄连(RhizaomaCoptidis)的指纹图谱研究[D].西南大学硕士学位论文, 2008
[33]吴剑峰,李海燕,杨安平.高效液相色谱法分析黄连炮制品中盐酸小檗碱的含量变化[J].中成药, 1999, 21(8): 408-409
[34]康兰芳,姜莲,吕春霞.黄连须药材的定性与定量分析[J].今日药学, 2008, 18(1): 37-40
[35]孙健,马吉胜,金瑾,王怀生,温庆辉,张宏桂,周秋丽.黄连解毒汤各成分的HPLC-UV /MS定性与定量测定方法研究[J].药学学报, 2006, 41(4): 380-384
[36]马莲,杨秀伟.盐酸黄连碱和小檗红碱在人源Caco-2细胞单层模型中的吸收研究[J].中国中药杂志, 2007, 32(23): 2523-2527
[37]王本详.人参的研究[M].天津:天津科学技术出版社, 1985, 34-40
[38]刘飞,贺浪冲.人参质量控制的定性和定量方法研究[J].药物分析杂志, 2002, 22(3): 173-175
[39]刘训红,王玉玺.中药材光谱鉴别[M].上海:第二军医大学出版社, 2001, 112-116
[40]鱼红闪,陈琪,金凤.不同种类人参及其各部分中皂甙组成和比例的研究[J].食品与发酵工业, 2002, 28(2): 24-27
[41]刘高峰,张丽梅.薄层扫描法测定肝速宁胶囊人参皂甙Rg1的含量[J].中国中药杂志, 1996, 21(9): 542-544
[42]于超,刁长发,夏文娟,周碧珍.反相高效液相色谱法测定人参及其制剂中人参皂苷Rg1含量[J].药物分析杂志, 2000, 20: 263-265
[43]喻春皓,魏峰,何志敏.酶法修饰人参茎叶总皂苷及其HPLC图谱研究[J].中草药, 2007, 38(1): 46-49
[44] Ping Hu, Guo-An Luo, Qing Wang, Zhong-Zhen Zhao, Wan Wang, and Zhi-Hong Jiang. The Retention Behavior of Ginsenosides in HPLC and Its Application to Quality Assessment of Radix Ginseng[J]. Arch Pharm Res , 2008, 31(10): 1265-1273
[45] G. Kernaghan , R. D. Reeleder , S. M. T. Hoke. Quantification of Pythium populations in ginseng soils by culture dependent and real-time PCR methods[J]. Applied Soil Ecology, 2008, 40(3): 447-455
[46]杨伟峰,赵维良.胶束电动毛细管色谱法测定西洋参中人参皂苷Rb1、Re的含量[J].中国中药杂志, 2003, 28(12): 1135-1137
[47] Yan Yao, Wan-Ying Wu, Shu-Hong Guan, Bao-Hong Jiang, Min Yang, Xiao-Hui Chen, Kai-Shun Bi, Xuan Liua, De-An Guo. Proteomic analysis of differential protein expression in rat platelets treated with notoginsengnosides [J]. Phytomedicine, 2008, 15(10): 800-807
[48]张云峰,柯开富.人参皂苷及其单体的神经药理学研究进展[J].中国交通医学杂志, 2005, 19(5): 502-504
[49]芦永军,曲艳玲,曹志强,宋敏.人参总糖的近红外光谱定量分析[J].光谱学与光谱分析, 2006, 26(8): 1457-1459
[50]陈瑞战,张守勤,王长征.正交试验优化超高压提取人参中人参皂苷的工艺研究[J].中草药, 2005, 36(3): 365-368
[51]陈红杰. FTIR光谱无损分析法在丹参产地鉴别中的应用[J].科技资讯, 2008, 17: 3
[52]王静.红外光谱数据库系统的研究[D].华东师范大学硕士学位论文, 2008
[53]谢晶曦.红外光谱在有机化学和药物化学中的应用[M].北京:科学出版社, 2002, 38-50
[54]吴瑾光.近代傅里叶变换红外光谱技术及应用[M].北京:科学技术文献出版社, 1994, 24-30
[55]姜大成,王永生,翁丽丽.常用中药光谱鉴定[M].北京:化学工业出版社, 2006, 78-86
[56]王晶,胡晋红,肖杰,陆峰,吴玉田.红外指纹图谱与计算机辅助解析技术定性分析中药注射剂[J].中成药, 2005, 27(5): 505-507
[57]陈亚,江滨,曾元儿.红外光谱在中药鉴别中的应用[J].广州中医药大学学报, 2004, 21(03): 1007-1010
[58]苏薇薇,吴忠,全健.中药指纹图谱的构建及计算机解析[J],中药材, 2001, 24(4): 295-298
[59]李燕,吴然然,于佰华,王俊德.红外光谱在中药定性定量分析中的应用[J].光谱学与光谱分析, 2006, 26(10): 1846-1849
[60]史敏.基于红外光谱技术的猕猴桃品质检测研究[D].西北农林科技大学硕士学位论文, 2008
[61]王钊,孙素琴,李小波.红外光谱法无损鉴别升麻的研究[J].光谱学与光谱分析, 2001, 22(3): 311-313
[62]刘刚,董勤,俞帆.天麻的傅立叶变换红外光谱鉴别研究[J].光谱学与光谱分析, 2004, 24(3): 308-310
[63]郭萍,熊平,袁亚莉.乌头的傅立叶变换红外光谱分析[J].光谱学与光谱分析, 2002, 22(4): 603-606
[64] Hua R., Sun S. Q., Zhou Q.. Discrimination of Fritillary according to geographical origin with Fourier transform infrared spectroscopy and two-dimensional correlation IR spectroscopy [J]. Journal of pharmaceutical and biomedical analysis, 2003, 33(2): 199-209
[65] Liu H. X., Sun S. Q., Lv G.. H.. Study on Angelica and its different extracts by Fourier transform infrared spectroscopy and two-dimensional correlation IR spectroscopy[J]. Spectrochimica ACTA part A-molecular and biomolecular spectroscopy, 2006, 64 (3): 321-326
[66] Liu H. X., Sun S. Q., Lv G. H.. Discrimination of extracted lipophilic constituents of Angelica with multi-steps infrared macro-fingerprint method[J]. Vibrational spectroscopy, 2006, 40(2): 202-208
[67] Yu L., Sun S. Q., Fan K. F.. Research on processing medicinal herbs with multi-steps infrared macro-fingerprint method[J]. Spectrochimica ACTA part A-molecular and biomolecular spectroscopy, 2005, 62(1-3): 22-29
[68] Li Y. M., Sun S. Q., Zhou Q.. Identification of American ginseng from different regions using FT-IR and two-dimensional correlation IR spectroscopy[J]. Vibrational spectroscopy, 2004, 36(2): 227-232
[69] http: //www. cnpharm. com/www/news/57/6343. html
[70]徐广通,袁洪福,陆婉珍.现代近红外光谱技术及应用进展[J].光谱学与光谱分析, 2000, 20(2): 132-142
[71]严衍禄,赵龙莲,韩东海等.近红外光谱分析基础与应用[M].北京:中国轻工业出版社, 2005, 31-39
[72]杨南林.基于近红外光谱的中药过程分析方法研究[D].浙江大学博士学位论文, 2008
[73]李惠.傅立叶近红外光谱技术测定传统豆制品品质研究[D].西北农林科技大学硕士学位论文, 2008
[74]王亚敏.基于NIR、MIR光谱和化学计量学的松花粉、大黄质量控制[D].首都师范大学硕士学位论文, 2008
[75]李文良.近红外光谱法用于中药蛇床子的萃取物的快速无损定量分析的研究[D].吉林大学硕士学位论文, 2008
[76] Shenk JS and Westerhaus MO. Monograph. Analysis of agriculture and food products bynear infrared reflectance spectroscopy. Infrasoft International[M], Port Matilda, PA, USA, 1993, 44-51
[77] Starr C. , suttle J. , Morgan A. G. . etal. A comparision of sample preparation and calibrationtechniques for the estimation of nitrogen, oil and glucosinolate content of rapeseed by near infrared spectroscopy[J]. Agric Sci Camb, 1985, 104(2): 317-323
[78] Sato. T.. Application of near infrared spectroscopy for the analysis of fatty acid Composition [J]. Lipis Technology. 1997, 9(2): 46-49
[79] Ciurczak E. W. Use of near infrared spectroscopy in cereal products[J]. Food Testing and Analysis, 1995, 5: 35-39
[80] Meadows F., Barton F. E.. Determination of Rapid Visco Analysis parameters in rice by Near Infrared Spectroscopy[J]. Cereal Chemstr, 2002, 79: 563-566
[81] Gonzá1ez-Martinl, Gonzá1ez-Pérez C, Hernández-MéndezJ. On-1ine on-destruetive determination of Proteins and infiltrated fat in Iberian pork loin by near infrared speetrometry with a remote reflectance fibre optic Probe[J]. Analytica Chimica Acta. 2002, 453(2): 281-288
[82] Lu R., Ariana D. A.. Near-infrared Sensing Technique for Measuring internalQuality of apple fruit[J]. Trans of the AS E, 2002, 18(5): 585-590
[83] Cimander C., Carlsson M. , Mandenius C. Sensorfusionforon-line Monitoring of yoghurt fermentation[J]. Journal of Bioteehnology. 2002, 99(3): 237-248
[84] Bowers, S. V. , R. B. Dodd, and Y. J. Han. Nondestructive testing to determine internal quality of fruit[C]. ASAE Paper, 1988, 88: 65-69
[85] Sehmiloviteh Z., Shmulevieh I., Notea A., etal. Near infrared spectrometry of milk in its heterogeneous state[J]. Computers and Electronies in Agriculture. 2000, 29(3): 195-207
[86]白琪林,陈绍江,严衍禄等.近红外漫反射光谱法测定青贮玉米品质性状的研究[J].中国农业科学, 2006, 39(7): 1346-1351
[87]王秀荣,廖红,严小龙.应用近红外光谱分析法测定大豆种子蛋白质和脂肪含量的研究[J].大豆科学, 2005, 24(3): 199-201
[88]孙永海,万鹏,于春生.基于BP神经网络的大米含水量近红外检测方法[J].中国粮油学报, 2008, 23(6): 193-196
[89]段民孝,邢锦丰,郭景伦.近红外光谱(NIRS)分析技术及其在农业中的应用[J].北京农业科学, 2002, 20(1): 12-14
[90]籍保平.近红外光谱技术在农产品加工中的应用[J].粮油加工与食品机械, 2006, 47(6): 31-33
[91]吕丽娜,张碉,周定文.采用近红外漫反射光谱法分析牛奶成分[J].天津大学学报, 2004, 12(3): 1093-1095
[92]姚鑫淼,张瑞英,李霞辉.近红外透射光谱法(NITS)分析大豆品质的研究[J].大豆科学, 2006, 25(4): 417- 424
[93]蔡鑫茹,刘广新,焦仁海.近红外光谱仪测定玉米子粒淀粉含量的研究[J].吉林农业科学, 2006, 31(6): 10-11
[94]李钧,王宁惠,余青兰.傅立叶变换近红外光谱技术分析完整油菜籽含油量数学模型的建立[J].青海大学学报(自然科学版), 2006, 24(6): 28-30
[95]应义斌,刘燕德,傅霞萍.基于小波变换的水果糖度近红外光谱检测研究[J].光谱学与光谱分析, 2006, 26(1): 63-66
[96]郭晓东,罗海峰.近红外透射光谱法(NIT)分析酸奶中蔗糖含量的研究[J].中国乳业, 2006, 11: 45-48
[97]夏俊芳,李小昱,李培武.基于小波消噪柑橘内部品质近红外光谱的无损检测[J].华中农业大学学报(自然科学版), 2006, 26(1): 120-123
[98] Yong He, Xiaoli Li, Xunfei Deng. Discrimination of varieties of tea using near infrared spectroscopy by principal component analysis and BP model[J]. Journal of Food Engineering, 2007, 79(4): 1238-1242
[99]赵杰文,陈全胜,张海东.近红外光谱分析技术在茶叶鉴别中的应用研究[J].光谱学与光谱分析, 2006, 26(9): 1601-1604
[100]罗一帆,郭振飞,朱振宇.近红外光谱测定茶叶中茶多酚和茶多糖的人工神经网络模型研究[J].光谱学与光谱分析, 2005, 25(8): 1230-1233
[101]刘国林,蔡金娜.李伟.近红外光谱技术在中药蛇床子分类中的应用[J].计算机与应用化学, 2000, 17(2): 109-111
[102]吴拥军,李伟,相秉仁.近红外光谱技术用于白芷类中药的鉴定研究[J].中药材, 2001, 24(l): 26-29
[103]杜德国,孙素琴,周群.芦丁和维生素C的近红外漫反射光谱技术定量分析研究[J].光谱学与光谱分析, 2000, 20(4): 474-476
[104]芦永军,曲艳玲,曹志强,宋敏.人参总糖的近红外光谱定量分析[J].光谱学与光谱分析, 2006, 26(8): 1457-1459
[105]瞿海斌,刘全,程翼宇.近红外漫反射光谱法测定黄连浸膏粉中生物碱含量[J].分析化学, 2004, 32(4): 477-480
[106]钟蕾,朱斌,宓鹤鸣,陆峰,范国荣.近红外漫反射光谱聚类分析用于血竭的鉴别[J].理化检验-化学分册, 2004, 40(1): 9-12
[107]杨玉兰,吴龙奇,王建华.用近红外光谱检测银杏叶中的黄酮含量[J].河南科技大学学报, 2003, 23(2): 5-8
[108]杨南林,程翼宇,瞿海斌.用人工神经网络-近红外光谱法测定冬虫夏草中的甘露醇[J].分析化学, 2003, 31(6): 664-668
[109] Woo YA, Kim H. J. , Cho J. , etal. Discrimination of herbal medicines according togeographical origin with near-infrared reflectance spectroscopy and pattern recognition techniques[J]. J. Pharmaceut Biomed, 1999, 21(2): 407-413
[110] Woo YA, Kim H. J. , Chung H. . Classification of cultivation area of ginseng radix with NIR and Raman spectroscopy[J]. Analyst, 1999, 124: 1223-1726
[111] Woo YA, Cho C. H. , Kim H. J. , etal. Classification of cultivation area of ginseng by near infrared spectroscopy and ICP2AES[J]. Microchem. J. , 2002, 73(3): 299-306
[112] Ming Yang LIU , Yu MENG, Jun Feng LI, Hai Tao ZHANG, Hong Yan WANG. Nondestructive Quantitative Analysis of Cofrel Medicines by Double ANN-NIR Spectroscopy[J]. Chinese Chemical Letters, 2006, 17(9): 1209-1212
[113] U. Depczynski, V. J. Frost, K. Molt, Genetic algorithms applied to the selection of factors in principal component regression[J]. Anal. Chim. Acta, 2000, 420: 217-227.
[114] Stordrange Laila, Libnau Fred Olav, Malthe-Sorenssen Dick et al. , Feasibility study of NIR for surveillance of a pharmaceutical process, including a study of different preprocessing techniques[J]. Chemometrics, 2002, 16: 529-541
[115] Cho C. H. , Woo Y. A. , Kim H. J. , etal. Rapid qualitative and quantitative evaluation of deerantler(Cervus elaphus)using near-infrared reflectance spectroscopy[J]. icrochem J, 2001, 68(2): 189-195
[116] Xiang L., Fan G. Q., Li J. H., etal. The Application of an Artificial neural Network in the Identification of Medicinal Rhubarbs by Near-infrared Spectroscopy[J]. Phytochem. Anal., 2002, 13(5): 272-276
[117] Fuzzati N.. Analysis methods of ginsenosides [J]. Journal of chromatography of chromatography B-analytical technologies in the biomedical and life sciences, 2004, 812 (1-2): 119-133
[118]许禄,邵学广.化学计量学方法[M].北京:科学出版社, 2004, 21-35
[119]韩磊,李兴兵,谭跃进.近红外光谱分析方法研究[J].计算机技术与发展, 2006, 16(5): 85-87
[120] Johan Trygg, Svante Wold, O2-PLS, a two-block (X-Y) latent variable regression (LVR) method with an integral OSC filter[J]. Chemometrics, 2003, 17: 53-64
[121] Tomas Isaksson and Peter. R. Griffiths, Optimal absorbance for transmission or reflection spectra measured under conditions of constant detector noise in the presence of stray radiation [J]. Appl. Spectrosc. , 2002, 56(7): 916-919
[122] Xueguang Shao,Chaoxiong Ma, A general approach to derivative calculation using wavelet transform [J] . Chemom. Intell. Lab. Syst. , 2003, 69: 157-165
[123]李晓丽,胡兴越,何勇.基于主成分和多类判别分析的可见-红外光谱水蜜桃品种鉴别新方法[J].红外与毫米波学报, 2006, 25(6): 417-420
[124]任玉林,邴春亭,逮家辉,郭哗.近红外漫反射光谱的主成分分析[J].光谱学与光谱分析, 1996, 16(6): 31-35
[125]夏柏杨,任芊.近红外光谱分析技术的一些数据处理方法的讨论[J].光谱实验室, 2005, 22(3): 629-631
[126] Myung-Ja YOUN, Hong-Seob SO, Hea-Joong CHO, Hyung-Jin KIM, Yunha KIM, Jeong-Han LEE, Jung Sook SOHN, Yong Kyu KIM, Sang-Young CHUNG, and Raekil PARK. Berberine, a Natural Product, Combined with Cisplatin Enhanced Apoptosis through a Mitochondria/Caspase-Mediated Pathway in HeLa Cells[J]. Biol. Pharm. Bull. , 2008, 31(5): 789-795
[127] Yan Dan, Xiao XiaoHe, Jin Cheng, Dong XiaoPing. Microcalorimetric investigation of the effect of berberine alkaloids from Coptis chinensis Franch on Staphylococcus aureus growth[J]. Science in China Series B: Chemistry, 2008, 51(7): 640-645
[128] Ben Liu, Wenjing Li, Yiling Chang, Wenhong Dong, Li Ni. Extraction of berberine from rhizome of Coptis chinensis Franch using supercritical fluid extraction[J]. Journal of Pharmaceutical and Biomedical Analysis, 2006, 41: 1056-1060
[129] Eun-Kyung Park, Hae In Rhee, Hye-Sook Jung, Seoung Min Ju, Yeon-Ah Lee, Sang-Hoon Lee, Seung-Jae Hong, Hyung-In Yang, Myung-Chul Yoo and Kyoung Soo Kim. Antiinflammatory Effects of a Combined Herbal Preparation (RAH13) of Phellodendron amurense and Coptis chinensis in Animal Models of Inflammation[J]. Phytother. Res. , 2007, 21: 746-750
[130]崔娅,龙杰,王淑华,李萍,李苓.用连续流动分析法测定烟草总氮[J].烟草科技, 2001, 12: 173-176
[131]杜瑞华,周明松.连续流动分析法在烟草分析中的应用[J].中国测试技术, 2007, 33(3): 87-90
[132]周春光,梁艳春.计算智能[M].长春:吉林大学出版社, 1992, 16-18
[133]高隽.人工神经网络原理及其仿真实例[M].北京:机械工业出版社, 2003,6-18
[134]飞思科技产品研发中心.神经网络理论与MATLAB 7实现[M].北京:电子工业出版社, 2005, 315-325
[135] Pascal Chalus, Serge Walter, &Michel Ulmschneider. Combined wavelet transform–artificial neural network use in tablet active content determination by near-infrared spectroscopy[J]. Analytica Chimica Acta, 2007, 591(2): 219-224
[136] YE Zheng-Liang, YU Ke, CHENG Yi-Yu. Near Infrared Chemical Fingerprinting Based on Wavelet Transform[J]. Chemical Journal of Chinese university , 2007, 28(3): 441-444
[137]田高友,袁洪福,刘慧颖,陆婉珍.小波变换用于近红外光谱数据压缩[J].分析测试学报, 2005, 24(1): 17-20
[138]杜文,任建新,张文利,邵学广.小波变换光谱前处理提高近红外分析模型的转移性能[J].中国烟草学报, 2005, 11(5): 9-12
[139]赵琛,瞿海斌,程翼宇.虫草氨基酸的人工神经网络-近红外光谱快速测定方法[J].光谱学与光谱分析, 2004, 24(1): 50-53
[140]刘建学,吴守一,方如明.基于近红外光谱的神经网络预测大米直链淀粉含量[J].农业机械学报, 2001, 21(2): 55-57
[141]何勇,李晓丽,邵咏妮.基于主成分分析和神经网络的近红外光谱苹果品种鉴别方法研究[J].光谱学与光谱分析, 2006, 26(5): 850-853
[142]左平,马驷良,马捷.近红外光谱分析中人工神经网络法的应用[J].吉林大学学报(理学版), 2006, 44(1): 57-60
[143]吴新生,谢益民.主成分-BP算法在近红外光谱法纸浆卡伯值测量中的应用研究[J].分析测试学报, 2005, 24(4): 10-12
[144]崔景泰.小波分析导论[M].西安:西安交通大学出版社, 1995, 3-20
[145]张德丰.小波分析与工程应用[M].北京:国防工业出版社, 2008, 3-24
[146] Nello Cristianini and John Shawe-Taylor著,李国正,王猛,曾华军译.支持向量机导论(原书名:An Introduction to Support Vector Machines and Other Kernel-based Learning Methods)[M].北京:电子工业出版社, 2004, 1-6
[147]李晓宇,张新峰,沈兰荪.支持向量机(SVM)的研究进展[J].测控技术, 2006, 25(5): 8-11
[148]艾娜,吴作伟,任江华.支持向量机与人工神经网络[J].山东理工大学学报(自然科学版), 2005, 19(5): 45-49
[149]刘碧森.支持向量机研究及其应用[D].电子科技大学硕士学位论文, 2003
[150]张鸽,陈书开.基于SVM的手写体阿拉伯数字识别[J].军民两用技术与产品, 2005, 20(9): 41-43
[151]杜树新,吴铁军.模式识别中的支持向量机方法[J].浙江大学学报(工学版), 2003, 37(5): 522-527
[152]梅虎,梁桂兆,周原,李志良.支持向量机用于定量构效关系建模的研究[J].科学通报, 2005, 50(16): 1703-1708
[153] Saeed Masoum, Christophe Malabat, Mehdi Jalali-Heravi, Claude Guillou, Serge Rezzi, Douglas Neil Rutledge. Application of support vector machines to 1H NMR data of fish oils: methodology for the confirmation of wild and farmed salmon and their origins[J]. Anal Bioanal Chem. , 2007, 387: 1499-1510
[154]虞科,程翼宇.一种基于最小二乘支持向量机算法的近红外光谱判别分析方法[J],分析化学, 2006, 36(4): 561-564
[155] T. Coen, W. Saeys, H. Ramon & J. De Baerdemaeker. Optimizing the tuning parameters of least squares support vector machines regression for NIR spectra[J]. J. Chemometrics. , 2006, 20(5): 184-192
[156] Cristianimi N. Shawe-Taylor J. . An introduction to support vector machines and other kernel-based learning methods[M]. Cambridge: Cambridge University Press, 2000, 35-48
[157] Scholkopf B. , Smola A. J. . Learning with kernels: support vector machines, regularization, optimization, and beyond[M]. USA: MIT Press, 2002, 67-75
[158] Vapnik V. N. . The Nature of Statistical Learning Theory[M]. Berlin: Springer, 1995, 23-30
[159] Vapnik V. . The support vector method of function estimation, in J. A. K. Suykens and J. Vandewalle (Eds) Nonlinear Modeling: Advanced Black-Box Techniques[M]. Boston: Kluwer Academic Publishers, 1998, 55-85
[160] T. Coen, W. Saeys, H. Ramon & J. De Baerdemaeker. Optimizing the tuning parameters of least squares support vector machines regression for NIR spectra[J]. J.Chemometrics, 2006, 20(5): 184-192
[161] Tomasz Czekaj, Wen Wu & Beata Walczak. About kernel latent variable approaches and SVM[J]. J. Chemometrics, 2005, 19(5-7): 341-354
[162] ZHAO Jie-wen, CHEN Quan-sheng,HUANG Xing-yi,FANG C. H. . Qualitative identification of tea categories by near infrared spectroscopy and support vector machine[J]. Journal of Pharmaceutical and Biomedical Analysis. 2006, 41(4): 1198-1204
[163] Alessandra Borin, Marco Fl?res Ferr?o, Cesar Mello. Least-squares support vector machines and near infrared spectroscopy for quantification of common adulterants in powdered milk[J]. Analytica Chimica Acta. , 2006, 579(1): 25-32
[164] J. A. Fernández Pierna, V. Baeten, A. Michotte Renier, R. P. Cogdill & P. Dardenne. Combination of support vector machines(SVM) and near-infrared(NIR)imaging spectroscopy for the detection of meat and bone meal(MBM) in compound feeds[J]. Journal of Chemometrics, 2004, 18(7-8): 341-349
[165] Y. Langeron, M. Doussot, D. J. Hewson, &J. Duch?ne. Classifying NIR spectra of textile products with kernel methods[J]. Engineering Applications of Artificial Intelligence, 2007, 20(3): 415-427
[166] Ning Li, Yan Wang, Kexin Xu. Fast discrimination of traditional Chinese medicine according to geographical origins with FTIR spectroscopy and advanced pattern recognition techniques[J]. Optics Express, 2006, 14(17): 7630-7635
[167] Alessandra Borin, Marco Fl?res Ferr?o , Cesar Mello , Lívia Cordi , Luiz C. M. Pataca , Nelson Durán , Ronei J. Poppi. Quantification of Lactobacillus in fermented milkby multivariate image analysis with least-squaressupport-vector machines[J]. Anal Bioanal Chem , 2007, 387(3): 1105-1112
[168] Suykens J. A. K. , L. Lukas L. , Vandewalle J. . Sparse approximation using least squares support vector machines[J]. ISCAS 2000-IEEE International Symposium on Circuits and Systems, 2000,Ⅱ: 757-760
[169] Suykens J. A. K. , Branbanter J. K. , Lukas L. , et al. Weighted least squares support vector machines: robustness and spare approximation[J]. Neurocomputing, 2002, 48(1): 85-105
[170]杜天宝.基于近红外光谱和最小二乘支撑向量回归机测定白酒中乙醇含量[D].吉林大学硕士学位论文, 2006
[171]田盛丰,黄厚宽.回归型支持向量机的简化算法[J].软件学报, 2002, 13(6): 1169-1172
[172]王涛,刘兴年,黄尔.基于SVM方法的小流域泥石流输沙量预测[J].水利水电科技进展,2008, 28(2): 1-4
[173]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): 528-536
[174]祝诗平,王一鸣,张小超.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
[175]唐启义,冯明光.实用统计分析及其DPS数据处理系统[M].北京:科学出版社, 2002, 614-633
[176]邓聚龙.灰色系统基本方法[M].武汉:华中工学院出版社, 1987, 23-33
[177]刘思峰.灰色系统理论及其应用[M].北京:科学出版社, 2004, 12-25
[178]雷鸣涛.基于灰色系统理论的公路运输量预测[J].公路交通科技(应用技术版), 2007, 4: 342-346.
[179]寇铁军,金双华.灰色系统理论在税收预测中的应用研究[J].数量经济技术经济研究, 2001, 18(12): 86-89
[180] Zhen Z. Y., Gu Z., Liu Y. Y.. Anovel fuzzy entropyimage segmentation approach based on greyrelational analysis[C]. Proceedings of 2007 IEEE International Conference on Grey Systems andIntelligent Serv-ices. Nanjing, China, 2007, 11: 1019-1022
[181] Deng J. L.. Transformation in greyinference[J]. The Journal of Grey System, 1997, 9 (4): 299-306
[182] Ma M, Fan YY, Xie SY, et al. Anovel algorithmbasedon grayimage edge detection systemtheory[J] . Journal of Image and Graphics, 2003, 8(10): 1136-1139
[183] Deng Julong. Introduction to grey system theory[J]. Journal of Grey System, l989, 1: l-24
[184] Quinlan J. R. . Induction of decision tree[J]. Machine Learning, 1986, 1: 81-106
[185] Meng Xianlin, Shen Jin, Sun Lixin. Application of grey weighted re-lated degreeto the ambient air quality assessment[J]. Journal of Harbin Institute of Technolog, 2006, 13(4) : 395-397
[186]刘媛媛,刘文波,甄子洋,张弓.灰色关联度和模糊熵相结合的图像分割算法[J].光电子·激光, 2008, 19(9): 1250-1254
[187]董洪乐,曹敏,胡杰民.基于灰色关联的预警系统目标识别[J].指挥控制与仿真, 2007, 29(7): 38-42
[188]胡新华,杨旭升.基于灰色关联分析的爆破效果综合评价[J].辽宁工程技术大学学报(自然科学版), 2008, 27(1): 143-146
[189]孙勇成,周献中,李桂芳,江金龙.基于灰色关联分析的仿真模型验证及其改进[J].系统仿真学报, 2005, 17(3): 522-525
[190]刘新梅,徐润芳,张若勇.邓氏灰色关联分析的应用模型[J].统计与决策, 2008, 10: 23-25
[191]苏博,刘鲁,杨方廷.基于灰色关联分析的神经网络模型[J].系统工程理论与实践, 2008, 28(9): 98-105
[192]杨元,黎放,胡剑.灰色关联分析法在聚类评估中的应用[J].武汉理工大学学报(信息与管理工程版), 2007, 29(4): 94-99