水质总氮光谱检测建模方法研究
|
摘要
水环境富营养化问题是当今世界面临的最主要水污染问题之一，氮的过量是造成水体富营养化的重要原因，水体中总氮浓度的检测是水环境质量研究的重要内容，本文以水体中氮浓度的检测为研究目标，针对自然水环境的特性，在对被测水样进行氧化消解后，建立了结合小波去噪和支持向量回归机的水质检测模型，研究了水质检测方法。
论文的主要工作如下：
1针对国标所规定的氧化消解方法中需要消耗化学氧化试剂，会对环境造成二次污染等缺陷，设计了一套利用臭氧、紫外光、超声波、高压静放电等氧化技术集一体的高级氧化消解装置。
2针对经典软阈值滤波去噪法和空间域滤波去噪法在信号去噪过程中存在的不足，把空域相关小波滤噪法的思想引入软阈值消噪法，提出了一种改进的阈值小波滤噪法；同时又对空域相关小波滤噪法进行了优化，并把两种方法在不同参数下的去噪效果进行对比。
3针对单一模型建模方法的缺陷和水质光谱数据的高维输入特点，提出了通过半监督近邻传播算法、无信息变量消除方法、偏最小二乘投影波段选择和连续投影算法等波段选择方法，对高维光谱数据进行波段选择，建立其检测模型；并在此基础上，利用支持向量机建立水质检测融合模型。
4针对传统的水质连续光谱检测方法存在的模型复杂度高、易引入未知物质干扰光谱信息的缺点，提出一种基于紫外吸收光谱的水质中总氮含量局部线性嵌入-支持向量回归机建模方法。新方法利用局部线性嵌入算法对紫外吸收连续光谱数据作非线性降维，再利用支持向量回归机进行建模。仿真实验结果表明：新的建模方法降低了模型的复杂度，显著提高了模型的预测精度。
5同其它学习算法一样，支持向量回归机的性能依赖于学习机的参数，不同参数的选择对于模型的推广能力有一定的影响。基于这一状况，针对水质预测建模问题，提出了一种基于混合粒子群算法的混合核函数参数优化算法。该算法针对混合核函数的核参数变量过多，难以人工选择确定的困难，利用混合粒子群进行参数优化。仿真实验结果表明，这种方法能显著的提高水质检测模型的精度。
Water eutrophication is one of the main water pollution problem,facing the worldtoday.Since the excess nitrogen is the key reason of eutrophication,detection of the totalnitrogen concentration is important for understanding and study of the water environmentquality. Taking into account the characteristics of the natural water environment,afterproceeding an oxidation process on the water sample,this thesis combines the waveletdenoising and the support vector regression to establish the prediction model for water test.
The main contributions of this thesis are summarized as follows:
1Considering the oxidizing digestion method used in the National Standard requires toconsume chemical oxidation reagents, resulted in secondary pollution on the environment,aset of advanced oxidation method by combination of ozone, ultraviolet,high voltage staticdischarge and other oxidation technologies is proposed in this thesis.
2To avoid the disadvantages of the soft threshold denoising method and the hardthreshold denoising method,the spatial correlation based wavelet denoising method isintroduced into the soft threshold denoising method,and an improved thresholding waveletdenoising method is proposed in this thesis; Furthermore, the proposed method has beencompared with the optimized spatial correlation wavelet method is optimized, and the twomethods are compared in terms of the denoising effect.
3Considering the high dimensional characteristic of the quality spectral data thesemi-supervised affinity propagation algorithm, successive projections algorithm, partial leastsquares algorithm and uninformative variable elimination algorithm are applied for spectralband selection, then each sub-model is established by using the support vector machine. Toimprove the precision of the single modeling method,the sub-models are further combined topredict the water quality.
4Since the traditional water quality detection method based on continuous spectrumanalysis is often complex and can introduce unknown substances to interfere the spectralinformation an ultraviolet absorption spectrum analysis based local linear embedded(LLE)-support vector regression modeling(SVR) method. is proposed to predict the totalnitrogen content in the water. The basic idea is to use the LLE algorithm for nonlineardimensionality reduction of the ultraviolet absorption spectrum data, and then use the SVRmethod for modeling. The experimental results show that: the proposed method is effective toreduce the model complexity,and improves the prediction accuracy.
5The same as other learning algorithms, the performance of the support vectorregression machine depends on its parameters,different parameter can result in differentgeneralization capability.To relieve this situation,the hybrid particle swarm optimizationalgorithm is proposed to optimize the mixed kernel function parameters of the water quality prediction model. The proposed method can automatically select the kernel parametervariables of the mixed kernel function.Furthermore,the experimental results show that,thismethod can significantly improve the prediction accuracy.
论文的主要工作如下：
1针对国标所规定的氧化消解方法中需要消耗化学氧化试剂，会对环境造成二次污染等缺陷，设计了一套利用臭氧、紫外光、超声波、高压静放电等氧化技术集一体的高级氧化消解装置。
2针对经典软阈值滤波去噪法和空间域滤波去噪法在信号去噪过程中存在的不足，把空域相关小波滤噪法的思想引入软阈值消噪法，提出了一种改进的阈值小波滤噪法；同时又对空域相关小波滤噪法进行了优化，并把两种方法在不同参数下的去噪效果进行对比。
3针对单一模型建模方法的缺陷和水质光谱数据的高维输入特点，提出了通过半监督近邻传播算法、无信息变量消除方法、偏最小二乘投影波段选择和连续投影算法等波段选择方法，对高维光谱数据进行波段选择，建立其检测模型；并在此基础上，利用支持向量机建立水质检测融合模型。
4针对传统的水质连续光谱检测方法存在的模型复杂度高、易引入未知物质干扰光谱信息的缺点，提出一种基于紫外吸收光谱的水质中总氮含量局部线性嵌入-支持向量回归机建模方法。新方法利用局部线性嵌入算法对紫外吸收连续光谱数据作非线性降维，再利用支持向量回归机进行建模。仿真实验结果表明：新的建模方法降低了模型的复杂度，显著提高了模型的预测精度。
5同其它学习算法一样，支持向量回归机的性能依赖于学习机的参数，不同参数的选择对于模型的推广能力有一定的影响。基于这一状况，针对水质预测建模问题，提出了一种基于混合粒子群算法的混合核函数参数优化算法。该算法针对混合核函数的核参数变量过多，难以人工选择确定的困难，利用混合粒子群进行参数优化。仿真实验结果表明，这种方法能显著的提高水质检测模型的精度。
Water eutrophication is one of the main water pollution problem,facing the worldtoday.Since the excess nitrogen is the key reason of eutrophication,detection of the totalnitrogen concentration is important for understanding and study of the water environmentquality. Taking into account the characteristics of the natural water environment,afterproceeding an oxidation process on the water sample,this thesis combines the waveletdenoising and the support vector regression to establish the prediction model for water test.
The main contributions of this thesis are summarized as follows:
1Considering the oxidizing digestion method used in the National Standard requires toconsume chemical oxidation reagents, resulted in secondary pollution on the environment,aset of advanced oxidation method by combination of ozone, ultraviolet,high voltage staticdischarge and other oxidation technologies is proposed in this thesis.
2To avoid the disadvantages of the soft threshold denoising method and the hardthreshold denoising method,the spatial correlation based wavelet denoising method isintroduced into the soft threshold denoising method,and an improved thresholding waveletdenoising method is proposed in this thesis; Furthermore, the proposed method has beencompared with the optimized spatial correlation wavelet method is optimized, and the twomethods are compared in terms of the denoising effect.
3Considering the high dimensional characteristic of the quality spectral data thesemi-supervised affinity propagation algorithm, successive projections algorithm, partial leastsquares algorithm and uninformative variable elimination algorithm are applied for spectralband selection, then each sub-model is established by using the support vector machine. Toimprove the precision of the single modeling method,the sub-models are further combined topredict the water quality.
4Since the traditional water quality detection method based on continuous spectrumanalysis is often complex and can introduce unknown substances to interfere the spectralinformation an ultraviolet absorption spectrum analysis based local linear embedded(LLE)-support vector regression modeling(SVR) method. is proposed to predict the totalnitrogen content in the water. The basic idea is to use the LLE algorithm for nonlineardimensionality reduction of the ultraviolet absorption spectrum data, and then use the SVRmethod for modeling. The experimental results show that: the proposed method is effective toreduce the model complexity,and improves the prediction accuracy.
5The same as other learning algorithms, the performance of the support vectorregression machine depends on its parameters,different parameter can result in differentgeneralization capability.To relieve this situation,the hybrid particle swarm optimizationalgorithm is proposed to optimize the mixed kernel function parameters of the water quality prediction model. The proposed method can automatically select the kernel parametervariables of the mixed kernel function.Furthermore,the experimental results show that,thismethod can significantly improve the prediction accuracy.
引文
1.石虹.浅谈全球水资源态势和中国水资源环境问题[J].水土保持研究,2002,9(1):145-150.
2.孔繁翔,高光.大型浅水富营养化湖泊中蓝藻水华形成机理的思考[J].生态学报,2005,25(3):590-594.
3.秦伯强,高光,朱广伟,等.湖泊富营养化及其生态系统响应[J].科学通报,2013,58(10):855-864.
4.胡吉炜,高军省.基于属性识别模型的湖泊富营养化评价[J].水资源与水工程学报,2013,24(4):127-130.
5.周名江,于仁成.有害赤潮的形成机制、危害效应与防治对策[J].自然杂志,2007,29(2):72-76.
6. Sgombert, Jasta, Mrdseaward. Correlation Between the Nitrogen Concentration of Two EpiphyticLichens and the Traffic Density in an Urban Area[J]. Environmental Pollution,2003,12(3):281-290.
7.张岩,李畅游, SHEN Hung Tao,等.乌梁素海湖泊冰生长过程中总氮的迁移规律[J].水科学进展,2013,24(5):729-734.
8.宫宇周.生活污水深度除磷的试验研究[D]:[硕士学位论文].桂林:桂林理工大学环境科学与工程学院,2009.
9.国家环境保护局. HJ/T199─2005水质总氮的测定-气相分子吸收光谱法[S].北京:中国环境出版社,2005.
10.国家环境保护局. GB11894-1989水质总氮的测定-碱性过硫酸钾消解紫外分光光度法[S].北京:中国标准出版社,2002.
11.彭鹏,石慧.碱性过硫酸钾消解紫外分光光度法测定水样中的总氮[J].污染防治技术,2008,21(2):86-88.
12. Ogura N. Ultraviolet absorbing materials in natural water[J]. Nippon Kagaku Zasshi，1965，86(12):1286-1288.
13.吕清.连续流动分析-分光光度法测定水和废水中总氮[J].环境监测管理与技术,2014,26(1):42-45.
14.马仁坤,余震虹,鱼瑛,等. BP神经网络用于总氮测定过程中I~-、Br~-的干扰消除[J].光谱实验室,2011,28(2):517-521.
15.武晓莉.信息融合及集成学习在水质光谱分析中的应用研究[D]:[博士学位论文].浙江大学,2007.
16.廉晶晶,罗泽娇,刘江霞.微波消解-紫外分光光度法测定水中总氮[J].安全与环境工程,2009,16(1):18-21.
17.吴国枝,吴纯德,张捷鑫,等.超声、臭氧、光催化及其组合工艺处理苯酚废水[J].工业用水与废水,2007,38(5):38-41.
18.康颖,吴祖成.水为自由基源的电晕放电引发羟基自由基及氧化甲苯[J].科学通报,2008(12):1475-1478.
19.徐培君,刘红,周志辉,等.硝酸根紫外光降解对硝基苯甲酸的研究[J].环境工程学报,2011,5(1):80-84.
20.杨佩丽,曹云,张前龙,等.快速测定水源水中总磷、总氮方法应用分析[J].河南预防医学杂志,2013,24(4):284-287.
21.李影,杨慧中.一种水质总氮总磷在线自动监测仪的优化设计[J].工业水处理,2013,33(5):77-81.
22. L.Nunez, J.A.Garcia-Hortal, F Torrades. Study of kinetic parameters related to the decocourization andmineralization of reactive dyes from textile dyeing using Fenton and Photo-Fenton Proeess[J]. Dyesand Piglnents,2007,75:647-652.
23. A.Bach, H.Shemer, R.Semiat. Kinetics of Phenol mineralization by Fenton-like oxidation[J].Desalination.2010,4(12):51-56.
24. Garoma T, Gurol MD. Treatment of groundwater contaminated with gasoline components by anozone/UV process[J]. Chemosphere,2008,73:825-831.
25. Arana J, Pena Alono A. Comparative study of MTBE photocatalytic degradation with TIO2andCu-Ti02[J]. Appied Catalysis B:Environmental,2008,78:355-363.
26. Abbasi M, Asl N R. Sonochemical degradation of Basic Blue41dye assisted by nano TiO2andH2O2[J]. Journal of Hazardous Materials,2008,153(3):942-947.
27.陈祯.基于近红外光谱分析的土壤水分信息的提取与处理[D]:[博士学位论文].华中科技大学,2010.
28.叶丛雷,谢品华,秦敏,等.差分吸收光谱技术测量氯气的数据处理方法研究[J].光谱学与光谱分析,2012,32(7):1734-1738.
29. S.G.Mallat, W.L. Hwang. Singularity detection and Processing With wavelets[J]. IEEE Transaction onInformation Theory,1992,38(2):617-643.
30. D.L.Donoho, I.M. Johnstone. Ideal spatial adaptation by wavelet shrinkage[J]. Biometrika,1994,81(3):425-455.
31. Walczak.B, Massart DL. Noise suppression and singal compression using the wavelet packettransform[J]. Chemometr.Inerll.Lab,1997,36:81.
32. Donoho DL. De-noising by soft-thresholding[J]. IEEE T.Inform.Theory,1995,41:613.
33.黄双萍,岳学军,洪添胜,等.基于小波变换与LS-SVR的柑橘叶片磷含量高光谱监测模型[J].广东农业科学,2013,13:37-40.
34.陆宇振,周健民,余常兵,等.应用小波分析进行油菜籽红外光声光谱去噪[J].光谱实验室,2013,30(5):2126-2131.
35.张瑶,郑立华,李民赞,等.基于光谱特征分析的苹果树叶片营养素预测模型构建[J].农业工程学报,2013,29(8):171-178.
36.赵进辉,袁海超,刘木华,等.导数同步荧光光谱-小波-SGA-LSSVR联用快速测定鸭蛋蛋清中新霉素残留含量[J].分析化学,2013,41(4),546-552.
37.郭延波,杨东升,李雪.基于小波去噪的返回散射电离图前沿提取[J].中国电子科学研究院学报,2014,9(1):81-84.
38.张晓楠,曾庆山,万红.基于改进小波去噪和EMD方法的轴承故障诊断[J].测控技术,2014,33(1):23-30.
39. L.Liang, B.Wang,Y.Guo, et al. A support vector machine-based analysis method with Waveletdenoised near-infrared spectroscopy[J]. Vibrational Spectroscopy,2009,49(2):274-277.
40.陈孝敬.小波变换在光谱和多光谱图像的应用与研究[D]:[博士学位论文].厦门大学,2009.
41.白英奎.近红外光谱技术在药品检测中的应用研究[D]:[博士学位论文].吉林大学,2005.
42. Pijnappel W.W.F., Boogaart A.V. SVD-based quantification of magnetic resonance signals[J]. Journalof Magnetic Resonance,1992,97:122-134.
43. Belhumeur P.N., Hespanda J.P., Kriegman D.J. Eigenfaces vs.fisherfaces:recognition using classspecific linear projection[J]. IEEE Trans.on PAMI,1997,711-720.
44. Comon P. Independent components analysis,a new concept Signal Processing[J]. Special Issue onHigher Order Statistics,1994,36(3):287-314.
45. Sammon J.W. A nonlinear mapping for data structure analysis[J]. IEEE Trans.on computers,1969,18(5):401-409.
46. Kohonen T. Self-Organization and Associative Memory[M]. Berlin: Springer-Verlag,1988.
47.薛寺中,谈锐,陈秀宏.基于核的半监督的局部保留投影降维方法[J].计算机应用,2012,32(8):2235-2237，2244.
48.张朝阳,田铮.特征有效提取的自适应核特征子空间方法[J].模式识别与人工智能,2013,26(4):392-401.
49.周丽丽,李凡长.基于范畴的数据降维方法[J].计算机科学,2011,38(9):242-247.
50.吴晓婷,闫德勤.数据降维方法分析与研究[J].计算机应用研究,2009,26(8):2832-2835.
51.毕达天,邱长波,张晗.数据降维技术研究现状及其进展[J].情报理论与实践,2013,36(2):125-128.
52.李庆波,贾召会.一种光谱分析中的降维方法[J].光谱学与光谱分析,2013,33(3):780-784.
53. Xing E, Jordan M, Karp R. Feature selection for high-dimensional genomic microarray data[C].Proceedings of the18th International Conference on Machine Learning.San Francisco:MorganKaufmann,2001,601-608.
54.曾雪强.偏最小二乘降维方法的研究与应用[D]:[硕士学位论文].上海大学.2009.
55. Lei, Ying-Ke, Xu Yang-Ming, et al. Feature extraction using orthogonal discriminant local tangentspace alignment[J]. Pattern Analysis and Applications,2012,15(3):249-259.
56.吴迪,金春华,何勇.基于连续投影算法的光谱主成分组合优化方法研究[J].光谱学与光谱分析,2009,29(10):2734-2737.
57.黄凌霞,吴迪,金航峰,等.基于变量选择的蚕茧茧层量可见-近红外光谱无损检测[J].农业工程学报,2010,26(2):231-236.
58. MacQueen J. Some methods for classification and analysis of multivariate observations [C].Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. Califonia:University of California Press,1967,281-297.
59. Kaufman L, Rousseeuw P J. Finding Groups in Data:an Introduction to Cluster Analysis [M].NewYork: John Wiley and Sons,1990.
60. Frey B J, Dueck D. Clustering by passing messages between data points[J]. Science,2007,315(5):972-976.
61.赵海滨,颜世玉,于清文.采用Fisher线性判别分析进行MEG信号的分类[J].东北大学学报(自然科学版),2013,34(12):1695-1698.
62.吴志媛,钱雪忠.基于PLSI的标签聚类研究[J].计算机应用研究,2013,30(5):1316-1319.
63.黄勇.基于图像优化局部保留投影的人脸表情识别[J].计算机工程与应用,2011,47(27):210-215.
64. Hardoon D.R., Szedmak S.R., Shawetaylor J.R. Canonical correlation analysis:an overview withapplication to learning methods[J]. Neural Computation,2004,16(12):2639-2664.
65. Yang, Guang, Lin, et al. Comparative analysis on feature selection based Bayesian textclassification[C]. Changchun, China:2nd International Conference on Computer Science andNetworkTechnology, ICCSNT2012:1190-1194.
66. DUNCAN C C, BARRY R J, CONNOLLY J F, et al. Event-related potentials in clinical research:Guidelines for eliciting,recording,and quantifying mismatch negativity,P300, and N400[J]. ClinicalNeurophysiology,2009,120(1):1883-1908.
67. Zhan Yu-bin, Yin Jian, ping,Liu Xin-wang, et al. Adaptive neighborhood selection based on locallinearity for manifold learning[J]. Computer Research and Development,2011,48(4):576-583．
68.董小玲,孙旭东.基于小波压缩的马铃薯全粉还原糖近红外光谱检测研究[J].光谱学与光谱分析,2013,33(12):3216-3220.
69. Dai J.J., Lieu L., Rocke D. Dimension reduction for classification with gene expression data[J].Statistical Applications in Genetics and Molecular Biology,2006,5(1): Article6.
70. Lee G., Rodriguez C., Madabhushi A. Investigating the Efficacy of Nonlinear DimensionalityReduction Schemes in Classifying Gene and Protein Expression Studies[J]. IEEE Transactions onComputational Biology and Bioinformatics,2008,5(3):368-384.
71.秦进春,余旭初,张鹏强,等.一种基于核偏最小二乘法的高光谱影像最佳波段选择方法[J].测绘科学技术学报,2013,30(2):172-176.
72.霍星,陈皓.基于双核的协同嵌入式人脸识别系统研究[J].合肥工业大学学报(自然科学版),2012,35(9):1200-1203.
73.梁胜杰,张志华,崔立林.主成分分析法与核主成分分析法在机械噪声数据降维中的应用比较[J].中国机械工程,2011,22(1):80-83.
74.李月娇,刘秉瀚.基于自适应邻域参数的拉普拉斯特征映射[J].福州大学学报(自然科学版),2013,41(2):153-157.
75. Gao Shangbing, Yan Yunyang, Zong Hui. Image segmentation based on salient region[J]. MicroelEctronics and Computer,2011,28(10):21-23,27.
76. HUANG W L, YIN H J. On nonlinear dimensionality reduction for face recognition[J]. Image andVision Computing,2012,30(4):355-366.
77.陈斌辉,白清源.半监督复杂结构数据降维方法[J].计算机工程与应用,2011,7(5):135-138.
78.闫德勤,刘胜蓝,李燕燕.一种基于稀疏嵌入分析的降维方法[J].自动化学报,2011,37(11):1306-1312.
79. C.M.Bachmann, T.L.Ainsworth, R.A. Fusina.Exploiting manifold geometry in hyperspectralimagery[J]. IEEE Trans.Geosci.Remote,2005,43(3):441-454.
80. C.M.Bachmann,T.L.Ainsworth,R.A.Fusina. Improved manifold coordinates representations of large-scale hyperspectral scenes[J].IEEETrans.Geosci.Remote,2006,44(10):2786-2803.
81. Y.Chen, M.M.Crawford, J. Ghosh. Improved nonlinear manifold learning for land cover classificationvia intelligent landmark selection[C]. IEEE International Geoscience and Remote Sensing Symposium,IGARSS. Denver, Colorado, USA.2006:549-552
82. M.M.Crawford, L.Ma, W.Kim. Exploring nonlinear manifold learning for classification ofhyperspectral dat[C]. Chapter11of"Optical Remote Sensing:Advances in Signal Processing andExploitation Techniques". Springer,2010
83. T.Han, D.G.Goodenough. Nonlinear feature extraction of hyperspectral data based on locally linearembedding[C]. IEEE International Geoscience and Remote Sensing Symposium, IGARSS.Seoul,South Korea,2005:1237-1240.
84. Thomas O., Theraulaz F., Domeizel M., et al. UV spectral deconvolution:A valuable tool for wastewater quality determination[J]. Environmental Technology,1993,14:1187-1192.
85. Langergraber G., Fleischmann N., Hostadter F. A multivariate calibration Procedure for UV/VISspectrometric quantification of organic matter and nitrate in Wastewater[J]. Water Science andTechnology,2003,47(2):63-71.
86. Azedine C., Antoine G., Patrick B., et al. Water quality monitoring using a smart Sensing system[J].Measurement,2000,28:219-224.
87. Esealas A., Droguet M., Guadayol J.M., et al. Estimating DOC regime in a wastewater treatmentplant by UV deconvolution[J]. Water Research,2003,37:2627-2635.
88.杜树新,武晓莉,吴铁军.紫外光谱水质分析仪中的支持向量机方法[J].分析化学,2004,32(9):1227-1230.
89.吴冰.相关向量回归元建模关键技术及其应用研究[D]:[博士学位论文].国防科学技术大学,2011.
90. Boser B., Guyon L., Vapnik V. A training algorithm for optima margin classifer[C]. In Fifth annualWorkshop on Computational Learning Theory, Baltimore, MD: ACM Press,1992:144-152.
91. Cortes C., Vapnik V. The soft margin classifier,Technical memorandum11359-931209-18TM, AT&TBell Labs,1997.
92. Vapnik V.. The nature of statistical learning theory[M]. Springer-Verlag, NewYork,1997.
93. M.Anthony, P.Bartlett. Learning in Neural Networks:Theoretical Foundations[M]. CambridgeUniversity Press,1999.
94. J.Shawe-Taylor, N.Cristianini. Margin Distribution and Soft Margin[M]. Advances in Large MarginClassifiers, MIT Press, Cambridge, MA,2000:349-358.
95. Weston J. Extensions to the support vector method[D]. Ph.D thesis,Royal Holloway.University ofLondon,1999.
96. Vapnik V. An overview of statistical learning theory[C]. IEEE1'ran.On Neural Networks,1999,10(5).
97. A.Smola, B.Schlkopf, K.R.Muller. Convex Cost Functions for Support Vector Regression[C]. InL.Niklasson,M.Bodtn,and T.Ziemke,editors,Proceedings of the Eighth International Conference onArtificial Neural Networks,Perspectives in Neural Computing, Berlin, Springer-Verlag.1998.
98.徐红敏,刘亚禄.改进的支持向量回归机及其在水质预测中的应用[J].统计与决策,2006,12:12-13.
99.徐劲力.支持向量机在水质评价中的应用[J].中国农村水利水电,2007,3:7-9.
100.马文涛.支持向量机回归方法在地表水水质评价中的应用[J].数学的实践与认识.2007,37(9):45-50.
101.杨绒,赵满兴,周建斌.过硫酸钾氧化法测定溶液中全氮含量的影响条件研究[J].西北农林科技大学学报(然科学版),2005,33(12):107-110.
102.孟宪春,朱春媛,陈学玲.碱性过硫酸钾法测定总氮常见问题与解决办法[J].环境科学与管理,2010,35(5):126-128.
103.李清.水质氮磷自动检测系统的研究[D]:[硕士学位论文].江南大学,2011.
104.李月兰,谭五丰.高级氧化技术处理工业废水的研究进展[J].广东化工,2010,37(7):70.
105. Shaobin Wang. Acomperative study of Fenton-like reaction kinetics in decolorisation of wastewater[J].Dyes and Pigmenis,2008,76:714-20.
106.任南琪,周显娇,郭婉茜,等.染料废水处理技术研究进展[J].化工学报,2013,64(1):84-94.
107.汪婷. DNT废水处理方法及研究进展[J].轻工科技,2013,175(6):117-118.
108.李金英,杨春维.水处理中的高级氧化技术[J].科技导报,2008,26(16):88-92.
109.郭亮,焦纬洲,刘有智,等.含硝基苯类化合物废水处理技术研究进展[J].化工环保,2013,33(4):299-303.
110.梁伟夏,陆志发,钟彤,等.超声波协同光催化降解酚类废水的研究[J].科学与财富,2012,14(5):137-138.
111.杨淑英,高岩松,张记市,等.电化学-生物共代谢处理硝基苯废水研究［J］.石油炼制与化工,2011,42(3):97-100.
112.程正兴,杨守志,冯晓霞.小波分析的理论、算法、进展和应用[M].国防工业出版社,2007:366-369.
113. D.L.Donoho. De-noising by soft-thresholding[J]. IEEE Transeaction on Information,1995,41(3):613-617.
114.裴萍,卞继承.基于一种新阈值函数在信号去噪中的应用[J].电子测试,2013,7:266-269.
115.洪明坚,温志渝,张小洪.基于稀疏优化的近红外光谱波长选择方法[J].仪器仪表学报,2011,32(5):1114-1118．
116.王文帅,陈刚.基于半监督近邻传播的数据流聚类算法[J].计算机工程与应用,2013,49(8):6-8.
117.武国正.基于支持向量机在湖泊富营养化评价及水质预测中的应用研究[D]:[博士学位论文].内蒙古农业大学,2008.
118. Suykens J, Branbanter J.D, Lukas L, et al. Weighted least squares support vector machines:robustnessand spare approximation[J]. Neurocomputing,2002,48(1):85-105.
119.彭泓.基于数据挖掘与信息融合的瓦斯灾害预测方法研究[D]:[博士学位论文].中国矿业大学,2013.
120. Tang W, Xiong H, zhong S, et al. Enhancing semi-supervised clustering:Afeature Projeetionperspective[C]. In:pavel B,Rich C,Xindong w，eds，Proc.of the13thACM SIGKDD Int’l Conf.onKnowledge Diseovery and Data Mining(KDD2007).San Jose: ACM,2007:707-716.
121.肖宇,于剑.基于近邻传播算法的半监督聚类[J].软件学报,2008,19(11),2308-2813.
122.曹巍,赵英凯,高世伟,等.基于模糊核聚类的多类支持向量机[J].化工学报,2010,61(2):420-424.
123.张仲明,于明光,郭东伟.基于聚类的神经网络规则抽取算法[J].吉林大学学报:信息科学版,2010,28(5):506-512．
124.于明,朱超.利用半监督近邻传播聚类算法实现P2P流量识别[J].哈尔滨工程大学学报,2013,34(5):653-661.
125.郝勇,孙旭东,王豪.基于改进连续投影算法的光谱定量模型优化[J].江苏大学学报(自然科学版),2013,34(1):49-53
126.高洪智,卢启鹏,丁海泉,等.基于连续投影算法的土壤总氮近红外特征波长的选取[J].光谱学与光谱分析,2009,29(11):2951-2954．
127.王爽,黄敏,朱启兵.基于无信息变量和偏最小二乘投影分析的高光谱散射图像最优波段选择[J].光子学报,2011,40(3):428-432.
128.杜博,张乐飞,张良培,等.高光谱图像降维的判别流形学习方法[J].光子学报,2013,42(3):320-325.
129.董超,赵慧洁.基于局部线性嵌入的高光谱影像特征提取算法[J].北京航空航天大学学报,2010,36(8):957-960.
130. V.D Silva, J.B. Tenenbaum.Global versus Loeal Methods in Nonlinear Dimensionality Reduetion[C].Advances in Neural Information Processing Systems(NIPS03),2003,15:705-712.
131.唐炬,魏钢,李伟,等.基于双向二维最大间距准则的局部放电灰度图像特征提取[J].电网技术,2011,35(3):129-134.
132.任剑锋,梁雪,李淑红.基于非线性流形学习和支持向量机的文本分类算法[J].计算机科学,2012,39(1):261-263.
133.陈丹伟,侯楠,孙国梓.一种基于改进流形学习方法的云计算入侵检测模型[J].计算机科学,2010,37(10):59-62.
134. Luo Lei, Li Yuehua, Luan Yinghong. LLE-BASED CLASSIFICATION ALGORITHM FOR MMWRADAR TARGET RECOGNITION [J]. JOURNAL OF ELECTRONICS,2010,27(1):139-144.
135.赵桂林,朱启兵,黄敏.基于高光谱图像技术的苹果粉质LLE-SVM分类[J].光谱学与光谱分析,2010,30(10):2739-2743.
136. T.Zhang, J.Yang, D.Zhao, et al. Linear local tangent space alignment and application to facerecognition[J]. Neurocomputing,2007,70:1547-1553.
137.潘国锋.基于紫外吸收光谱的水质硝酸盐含量LLE-SVR建模[J].仪器仪表学报,2011,32(12):2869-2873.
138.冷亦琴,张莉,杨季文.一种基于局部稀疏线性嵌入的降维方法及其应用[J].南京大学学报（自然科学）,2013,49(4):403-410.
139.刘嘉敏,周晓莉,朱晟君,等.基于LLE及其改进算法的人耳识别[J].光电工程,2012,39(12):132-137.
140. Zhang A.J., Wu Z.L., Li C.H., et al. On Hadamard-type output coding in multiclass learning[J].In:Intelligent Data Engineering and Automated Learning,Lecture Notes in Computer Science,2003,2690:397-404.
141.刘跃辉,郑建东.基于支持向量机原理的复杂地层岩性识别方法[J].国外测井技术,2011(4):22-26.
142. Mercer J. Function of positive and negative type and their connection with the theory of integralequations[J]. Philos.Trans.Roy.Soc.London, A209,1909:415-446.
143. Baesens B, Viaene S, Van Gestel T, et al. An Empirical assessment of Kenrel Type performance forleast squares support vector machine classification[C]. Proceedings of Fourth Intenrational Conferenceon Knowledge-Based Intelligent Engineer system and Allied Technologies,2000,313-316.
144. Smits G F, J ORDAN E M. Improved SVM regression using mixtures of kernels[C]. Proceedings of the2002International Joint Conference on Neural Networks. Hawaii: IEEE,2002:2785-2790.
145.庄严,白振林,许云.基于蚁群算法的支持向量机参数选择方法研究[J].计算机仿真,2011,28(5):216-219.
146.朱凤明,樊明龙.混沌粒子群算法对支持向量机模型参数的优化[J].计算机仿真,2011,27(11):183-186.
147. Ebethart R C, Kennedy J. A new Optimizer using Partiele swarm theory[C]. Proceedings of the SixthInterational SymPosium on Miero Machine and Human Seienee, Nagoya,Japan， IEEE press，Piscataway, NJ,1995,39-43.
148.钱彭飞,章兢,谢燕.一种新的混合粒子群优化算法[J].科技导报,2010,28(22):74-76.
149. Chen D B, Zhao C X. Particle swarm optimization with adaptive population size and its application[J].Applied Soft Computing,2009,9(1):39-48.
150. Kao Y T, Zahara E. A hybrid genetic algorithm and particle swarm optimization for multimodalfunctions[J]. Applied Soft Computing,2008,8(2):849-857.
151. Zhang C S, Ning J X, Lu S,et al. N.A novel hybrid differential evolution and particle swarmoptimization algorithm for unconstrained optimization[J]. Operations Research Letters,2009,37(2):117-122.
152. Wang Y J, Yang Y P. Particle swarm optimization with preference order ranking for multi-objectiveoptimization[J]. Information Sciences,2009,179(12):1944-1959.
2.孔繁翔,高光.大型浅水富营养化湖泊中蓝藻水华形成机理的思考[J].生态学报,2005,25(3):590-594.
3.秦伯强,高光,朱广伟,等.湖泊富营养化及其生态系统响应[J].科学通报,2013,58(10):855-864.
4.胡吉炜,高军省.基于属性识别模型的湖泊富营养化评价[J].水资源与水工程学报,2013,24(4):127-130.
5.周名江,于仁成.有害赤潮的形成机制、危害效应与防治对策[J].自然杂志,2007,29(2):72-76.
6. Sgombert, Jasta, Mrdseaward. Correlation Between the Nitrogen Concentration of Two EpiphyticLichens and the Traffic Density in an Urban Area[J]. Environmental Pollution,2003,12(3):281-290.
7.张岩,李畅游, SHEN Hung Tao,等.乌梁素海湖泊冰生长过程中总氮的迁移规律[J].水科学进展,2013,24(5):729-734.
8.宫宇周.生活污水深度除磷的试验研究[D]:[硕士学位论文].桂林:桂林理工大学环境科学与工程学院,2009.
9.国家环境保护局. HJ/T199─2005水质总氮的测定-气相分子吸收光谱法[S].北京:中国环境出版社,2005.
10.国家环境保护局. GB11894-1989水质总氮的测定-碱性过硫酸钾消解紫外分光光度法[S].北京:中国标准出版社,2002.
11.彭鹏,石慧.碱性过硫酸钾消解紫外分光光度法测定水样中的总氮[J].污染防治技术,2008,21(2):86-88.
12. Ogura N. Ultraviolet absorbing materials in natural water[J]. Nippon Kagaku Zasshi，1965，86(12):1286-1288.
13.吕清.连续流动分析-分光光度法测定水和废水中总氮[J].环境监测管理与技术,2014,26(1):42-45.
14.马仁坤,余震虹,鱼瑛,等. BP神经网络用于总氮测定过程中I~-、Br~-的干扰消除[J].光谱实验室,2011,28(2):517-521.
15.武晓莉.信息融合及集成学习在水质光谱分析中的应用研究[D]:[博士学位论文].浙江大学,2007.
16.廉晶晶,罗泽娇,刘江霞.微波消解-紫外分光光度法测定水中总氮[J].安全与环境工程,2009,16(1):18-21.
17.吴国枝,吴纯德,张捷鑫,等.超声、臭氧、光催化及其组合工艺处理苯酚废水[J].工业用水与废水,2007,38(5):38-41.
18.康颖,吴祖成.水为自由基源的电晕放电引发羟基自由基及氧化甲苯[J].科学通报,2008(12):1475-1478.
19.徐培君,刘红,周志辉,等.硝酸根紫外光降解对硝基苯甲酸的研究[J].环境工程学报,2011,5(1):80-84.
20.杨佩丽,曹云,张前龙,等.快速测定水源水中总磷、总氮方法应用分析[J].河南预防医学杂志,2013,24(4):284-287.
21.李影,杨慧中.一种水质总氮总磷在线自动监测仪的优化设计[J].工业水处理,2013,33(5):77-81.
22. L.Nunez, J.A.Garcia-Hortal, F Torrades. Study of kinetic parameters related to the decocourization andmineralization of reactive dyes from textile dyeing using Fenton and Photo-Fenton Proeess[J]. Dyesand Piglnents,2007,75:647-652.
23. A.Bach, H.Shemer, R.Semiat. Kinetics of Phenol mineralization by Fenton-like oxidation[J].Desalination.2010,4(12):51-56.
24. Garoma T, Gurol MD. Treatment of groundwater contaminated with gasoline components by anozone/UV process[J]. Chemosphere,2008,73:825-831.
25. Arana J, Pena Alono A. Comparative study of MTBE photocatalytic degradation with TIO2andCu-Ti02[J]. Appied Catalysis B:Environmental,2008,78:355-363.
26. Abbasi M, Asl N R. Sonochemical degradation of Basic Blue41dye assisted by nano TiO2andH2O2[J]. Journal of Hazardous Materials,2008,153(3):942-947.
27.陈祯.基于近红外光谱分析的土壤水分信息的提取与处理[D]:[博士学位论文].华中科技大学,2010.
28.叶丛雷,谢品华,秦敏,等.差分吸收光谱技术测量氯气的数据处理方法研究[J].光谱学与光谱分析,2012,32(7):1734-1738.
29. S.G.Mallat, W.L. Hwang. Singularity detection and Processing With wavelets[J]. IEEE Transaction onInformation Theory,1992,38(2):617-643.
30. D.L.Donoho, I.M. Johnstone. Ideal spatial adaptation by wavelet shrinkage[J]. Biometrika,1994,81(3):425-455.
31. Walczak.B, Massart DL. Noise suppression and singal compression using the wavelet packettransform[J]. Chemometr.Inerll.Lab,1997,36:81.
32. Donoho DL. De-noising by soft-thresholding[J]. IEEE T.Inform.Theory,1995,41:613.
33.黄双萍,岳学军,洪添胜,等.基于小波变换与LS-SVR的柑橘叶片磷含量高光谱监测模型[J].广东农业科学,2013,13:37-40.
34.陆宇振,周健民,余常兵,等.应用小波分析进行油菜籽红外光声光谱去噪[J].光谱实验室,2013,30(5):2126-2131.
35.张瑶,郑立华,李民赞,等.基于光谱特征分析的苹果树叶片营养素预测模型构建[J].农业工程学报,2013,29(8):171-178.
36.赵进辉,袁海超,刘木华,等.导数同步荧光光谱-小波-SGA-LSSVR联用快速测定鸭蛋蛋清中新霉素残留含量[J].分析化学,2013,41(4),546-552.
37.郭延波,杨东升,李雪.基于小波去噪的返回散射电离图前沿提取[J].中国电子科学研究院学报,2014,9(1):81-84.
38.张晓楠,曾庆山,万红.基于改进小波去噪和EMD方法的轴承故障诊断[J].测控技术,2014,33(1):23-30.
39. L.Liang, B.Wang,Y.Guo, et al. A support vector machine-based analysis method with Waveletdenoised near-infrared spectroscopy[J]. Vibrational Spectroscopy,2009,49(2):274-277.
40.陈孝敬.小波变换在光谱和多光谱图像的应用与研究[D]:[博士学位论文].厦门大学,2009.
41.白英奎.近红外光谱技术在药品检测中的应用研究[D]:[博士学位论文].吉林大学,2005.
42. Pijnappel W.W.F., Boogaart A.V. SVD-based quantification of magnetic resonance signals[J]. Journalof Magnetic Resonance,1992,97:122-134.
43. Belhumeur P.N., Hespanda J.P., Kriegman D.J. Eigenfaces vs.fisherfaces:recognition using classspecific linear projection[J]. IEEE Trans.on PAMI,1997,711-720.
44. Comon P. Independent components analysis,a new concept Signal Processing[J]. Special Issue onHigher Order Statistics,1994,36(3):287-314.
45. Sammon J.W. A nonlinear mapping for data structure analysis[J]. IEEE Trans.on computers,1969,18(5):401-409.
46. Kohonen T. Self-Organization and Associative Memory[M]. Berlin: Springer-Verlag,1988.
47.薛寺中,谈锐,陈秀宏.基于核的半监督的局部保留投影降维方法[J].计算机应用,2012,32(8):2235-2237，2244.
48.张朝阳,田铮.特征有效提取的自适应核特征子空间方法[J].模式识别与人工智能,2013,26(4):392-401.
49.周丽丽,李凡长.基于范畴的数据降维方法[J].计算机科学,2011,38(9):242-247.
50.吴晓婷,闫德勤.数据降维方法分析与研究[J].计算机应用研究,2009,26(8):2832-2835.
51.毕达天,邱长波,张晗.数据降维技术研究现状及其进展[J].情报理论与实践,2013,36(2):125-128.
52.李庆波,贾召会.一种光谱分析中的降维方法[J].光谱学与光谱分析,2013,33(3):780-784.
53. Xing E, Jordan M, Karp R. Feature selection for high-dimensional genomic microarray data[C].Proceedings of the18th International Conference on Machine Learning.San Francisco:MorganKaufmann,2001,601-608.
54.曾雪强.偏最小二乘降维方法的研究与应用[D]:[硕士学位论文].上海大学.2009.
55. Lei, Ying-Ke, Xu Yang-Ming, et al. Feature extraction using orthogonal discriminant local tangentspace alignment[J]. Pattern Analysis and Applications,2012,15(3):249-259.
56.吴迪,金春华,何勇.基于连续投影算法的光谱主成分组合优化方法研究[J].光谱学与光谱分析,2009,29(10):2734-2737.
57.黄凌霞,吴迪,金航峰,等.基于变量选择的蚕茧茧层量可见-近红外光谱无损检测[J].农业工程学报,2010,26(2):231-236.
58. MacQueen J. Some methods for classification and analysis of multivariate observations [C].Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. Califonia:University of California Press,1967,281-297.
59. Kaufman L, Rousseeuw P J. Finding Groups in Data:an Introduction to Cluster Analysis [M].NewYork: John Wiley and Sons,1990.
60. Frey B J, Dueck D. Clustering by passing messages between data points[J]. Science,2007,315(5):972-976.
61.赵海滨,颜世玉,于清文.采用Fisher线性判别分析进行MEG信号的分类[J].东北大学学报(自然科学版),2013,34(12):1695-1698.
62.吴志媛,钱雪忠.基于PLSI的标签聚类研究[J].计算机应用研究,2013,30(5):1316-1319.
63.黄勇.基于图像优化局部保留投影的人脸表情识别[J].计算机工程与应用,2011,47(27):210-215.
64. Hardoon D.R., Szedmak S.R., Shawetaylor J.R. Canonical correlation analysis:an overview withapplication to learning methods[J]. Neural Computation,2004,16(12):2639-2664.
65. Yang, Guang, Lin, et al. Comparative analysis on feature selection based Bayesian textclassification[C]. Changchun, China:2nd International Conference on Computer Science andNetworkTechnology, ICCSNT2012:1190-1194.
66. DUNCAN C C, BARRY R J, CONNOLLY J F, et al. Event-related potentials in clinical research:Guidelines for eliciting,recording,and quantifying mismatch negativity,P300, and N400[J]. ClinicalNeurophysiology,2009,120(1):1883-1908.
67. Zhan Yu-bin, Yin Jian, ping,Liu Xin-wang, et al. Adaptive neighborhood selection based on locallinearity for manifold learning[J]. Computer Research and Development,2011,48(4):576-583．
68.董小玲,孙旭东.基于小波压缩的马铃薯全粉还原糖近红外光谱检测研究[J].光谱学与光谱分析,2013,33(12):3216-3220.
69. Dai J.J., Lieu L., Rocke D. Dimension reduction for classification with gene expression data[J].Statistical Applications in Genetics and Molecular Biology,2006,5(1): Article6.
70. Lee G., Rodriguez C., Madabhushi A. Investigating the Efficacy of Nonlinear DimensionalityReduction Schemes in Classifying Gene and Protein Expression Studies[J]. IEEE Transactions onComputational Biology and Bioinformatics,2008,5(3):368-384.
71.秦进春,余旭初,张鹏强,等.一种基于核偏最小二乘法的高光谱影像最佳波段选择方法[J].测绘科学技术学报,2013,30(2):172-176.
72.霍星,陈皓.基于双核的协同嵌入式人脸识别系统研究[J].合肥工业大学学报(自然科学版),2012,35(9):1200-1203.
73.梁胜杰,张志华,崔立林.主成分分析法与核主成分分析法在机械噪声数据降维中的应用比较[J].中国机械工程,2011,22(1):80-83.
74.李月娇,刘秉瀚.基于自适应邻域参数的拉普拉斯特征映射[J].福州大学学报(自然科学版),2013,41(2):153-157.
75. Gao Shangbing, Yan Yunyang, Zong Hui. Image segmentation based on salient region[J]. MicroelEctronics and Computer,2011,28(10):21-23,27.
76. HUANG W L, YIN H J. On nonlinear dimensionality reduction for face recognition[J]. Image andVision Computing,2012,30(4):355-366.
77.陈斌辉,白清源.半监督复杂结构数据降维方法[J].计算机工程与应用,2011,7(5):135-138.
78.闫德勤,刘胜蓝,李燕燕.一种基于稀疏嵌入分析的降维方法[J].自动化学报,2011,37(11):1306-1312.
79. C.M.Bachmann, T.L.Ainsworth, R.A. Fusina.Exploiting manifold geometry in hyperspectralimagery[J]. IEEE Trans.Geosci.Remote,2005,43(3):441-454.
80. C.M.Bachmann,T.L.Ainsworth,R.A.Fusina. Improved manifold coordinates representations of large-scale hyperspectral scenes[J].IEEETrans.Geosci.Remote,2006,44(10):2786-2803.
81. Y.Chen, M.M.Crawford, J. Ghosh. Improved nonlinear manifold learning for land cover classificationvia intelligent landmark selection[C]. IEEE International Geoscience and Remote Sensing Symposium,IGARSS. Denver, Colorado, USA.2006:549-552
82. M.M.Crawford, L.Ma, W.Kim. Exploring nonlinear manifold learning for classification ofhyperspectral dat[C]. Chapter11of"Optical Remote Sensing:Advances in Signal Processing andExploitation Techniques". Springer,2010
83. T.Han, D.G.Goodenough. Nonlinear feature extraction of hyperspectral data based on locally linearembedding[C]. IEEE International Geoscience and Remote Sensing Symposium, IGARSS.Seoul,South Korea,2005:1237-1240.
84. Thomas O., Theraulaz F., Domeizel M., et al. UV spectral deconvolution:A valuable tool for wastewater quality determination[J]. Environmental Technology,1993,14:1187-1192.
85. Langergraber G., Fleischmann N., Hostadter F. A multivariate calibration Procedure for UV/VISspectrometric quantification of organic matter and nitrate in Wastewater[J]. Water Science andTechnology,2003,47(2):63-71.
86. Azedine C., Antoine G., Patrick B., et al. Water quality monitoring using a smart Sensing system[J].Measurement,2000,28:219-224.
87. Esealas A., Droguet M., Guadayol J.M., et al. Estimating DOC regime in a wastewater treatmentplant by UV deconvolution[J]. Water Research,2003,37:2627-2635.
88.杜树新,武晓莉,吴铁军.紫外光谱水质分析仪中的支持向量机方法[J].分析化学,2004,32(9):1227-1230.
89.吴冰.相关向量回归元建模关键技术及其应用研究[D]:[博士学位论文].国防科学技术大学,2011.
90. Boser B., Guyon L., Vapnik V. A training algorithm for optima margin classifer[C]. In Fifth annualWorkshop on Computational Learning Theory, Baltimore, MD: ACM Press,1992:144-152.
91. Cortes C., Vapnik V. The soft margin classifier,Technical memorandum11359-931209-18TM, AT&TBell Labs,1997.
92. Vapnik V.. The nature of statistical learning theory[M]. Springer-Verlag, NewYork,1997.
93. M.Anthony, P.Bartlett. Learning in Neural Networks:Theoretical Foundations[M]. CambridgeUniversity Press,1999.
94. J.Shawe-Taylor, N.Cristianini. Margin Distribution and Soft Margin[M]. Advances in Large MarginClassifiers, MIT Press, Cambridge, MA,2000:349-358.
95. Weston J. Extensions to the support vector method[D]. Ph.D thesis,Royal Holloway.University ofLondon,1999.
96. Vapnik V. An overview of statistical learning theory[C]. IEEE1'ran.On Neural Networks,1999,10(5).
97. A.Smola, B.Schlkopf, K.R.Muller. Convex Cost Functions for Support Vector Regression[C]. InL.Niklasson,M.Bodtn,and T.Ziemke,editors,Proceedings of the Eighth International Conference onArtificial Neural Networks,Perspectives in Neural Computing, Berlin, Springer-Verlag.1998.
98.徐红敏,刘亚禄.改进的支持向量回归机及其在水质预测中的应用[J].统计与决策,2006,12:12-13.
99.徐劲力.支持向量机在水质评价中的应用[J].中国农村水利水电,2007,3:7-9.
100.马文涛.支持向量机回归方法在地表水水质评价中的应用[J].数学的实践与认识.2007,37(9):45-50.
101.杨绒,赵满兴,周建斌.过硫酸钾氧化法测定溶液中全氮含量的影响条件研究[J].西北农林科技大学学报(然科学版),2005,33(12):107-110.
102.孟宪春,朱春媛,陈学玲.碱性过硫酸钾法测定总氮常见问题与解决办法[J].环境科学与管理,2010,35(5):126-128.
103.李清.水质氮磷自动检测系统的研究[D]:[硕士学位论文].江南大学,2011.
104.李月兰,谭五丰.高级氧化技术处理工业废水的研究进展[J].广东化工,2010,37(7):70.
105. Shaobin Wang. Acomperative study of Fenton-like reaction kinetics in decolorisation of wastewater[J].Dyes and Pigmenis,2008,76:714-20.
106.任南琪,周显娇,郭婉茜,等.染料废水处理技术研究进展[J].化工学报,2013,64(1):84-94.
107.汪婷. DNT废水处理方法及研究进展[J].轻工科技,2013,175(6):117-118.
108.李金英,杨春维.水处理中的高级氧化技术[J].科技导报,2008,26(16):88-92.
109.郭亮,焦纬洲,刘有智,等.含硝基苯类化合物废水处理技术研究进展[J].化工环保,2013,33(4):299-303.
110.梁伟夏,陆志发,钟彤,等.超声波协同光催化降解酚类废水的研究[J].科学与财富,2012,14(5):137-138.
111.杨淑英,高岩松,张记市,等.电化学-生物共代谢处理硝基苯废水研究［J］.石油炼制与化工,2011,42(3):97-100.
112.程正兴,杨守志,冯晓霞.小波分析的理论、算法、进展和应用[M].国防工业出版社,2007:366-369.
113. D.L.Donoho. De-noising by soft-thresholding[J]. IEEE Transeaction on Information,1995,41(3):613-617.
114.裴萍,卞继承.基于一种新阈值函数在信号去噪中的应用[J].电子测试,2013,7:266-269.
115.洪明坚,温志渝,张小洪.基于稀疏优化的近红外光谱波长选择方法[J].仪器仪表学报,2011,32(5):1114-1118．
116.王文帅,陈刚.基于半监督近邻传播的数据流聚类算法[J].计算机工程与应用,2013,49(8):6-8.
117.武国正.基于支持向量机在湖泊富营养化评价及水质预测中的应用研究[D]:[博士学位论文].内蒙古农业大学,2008.
118. Suykens J, Branbanter J.D, Lukas L, et al. Weighted least squares support vector machines:robustnessand spare approximation[J]. Neurocomputing,2002,48(1):85-105.
119.彭泓.基于数据挖掘与信息融合的瓦斯灾害预测方法研究[D]:[博士学位论文].中国矿业大学,2013.
120. Tang W, Xiong H, zhong S, et al. Enhancing semi-supervised clustering:Afeature Projeetionperspective[C]. In:pavel B,Rich C,Xindong w，eds，Proc.of the13thACM SIGKDD Int’l Conf.onKnowledge Diseovery and Data Mining(KDD2007).San Jose: ACM,2007:707-716.
121.肖宇,于剑.基于近邻传播算法的半监督聚类[J].软件学报,2008,19(11),2308-2813.
122.曹巍,赵英凯,高世伟,等.基于模糊核聚类的多类支持向量机[J].化工学报,2010,61(2):420-424.
123.张仲明,于明光,郭东伟.基于聚类的神经网络规则抽取算法[J].吉林大学学报:信息科学版,2010,28(5):506-512．
124.于明,朱超.利用半监督近邻传播聚类算法实现P2P流量识别[J].哈尔滨工程大学学报,2013,34(5):653-661.
125.郝勇,孙旭东,王豪.基于改进连续投影算法的光谱定量模型优化[J].江苏大学学报(自然科学版),2013,34(1):49-53
126.高洪智,卢启鹏,丁海泉,等.基于连续投影算法的土壤总氮近红外特征波长的选取[J].光谱学与光谱分析,2009,29(11):2951-2954．
127.王爽,黄敏,朱启兵.基于无信息变量和偏最小二乘投影分析的高光谱散射图像最优波段选择[J].光子学报,2011,40(3):428-432.
128.杜博,张乐飞,张良培,等.高光谱图像降维的判别流形学习方法[J].光子学报,2013,42(3):320-325.
129.董超,赵慧洁.基于局部线性嵌入的高光谱影像特征提取算法[J].北京航空航天大学学报,2010,36(8):957-960.
130. V.D Silva, J.B. Tenenbaum.Global versus Loeal Methods in Nonlinear Dimensionality Reduetion[C].Advances in Neural Information Processing Systems(NIPS03),2003,15:705-712.
131.唐炬,魏钢,李伟,等.基于双向二维最大间距准则的局部放电灰度图像特征提取[J].电网技术,2011,35(3):129-134.
132.任剑锋,梁雪,李淑红.基于非线性流形学习和支持向量机的文本分类算法[J].计算机科学,2012,39(1):261-263.
133.陈丹伟,侯楠,孙国梓.一种基于改进流形学习方法的云计算入侵检测模型[J].计算机科学,2010,37(10):59-62.
134. Luo Lei, Li Yuehua, Luan Yinghong. LLE-BASED CLASSIFICATION ALGORITHM FOR MMWRADAR TARGET RECOGNITION [J]. JOURNAL OF ELECTRONICS,2010,27(1):139-144.
135.赵桂林,朱启兵,黄敏.基于高光谱图像技术的苹果粉质LLE-SVM分类[J].光谱学与光谱分析,2010,30(10):2739-2743.
136. T.Zhang, J.Yang, D.Zhao, et al. Linear local tangent space alignment and application to facerecognition[J]. Neurocomputing,2007,70:1547-1553.
137.潘国锋.基于紫外吸收光谱的水质硝酸盐含量LLE-SVR建模[J].仪器仪表学报,2011,32(12):2869-2873.
138.冷亦琴,张莉,杨季文.一种基于局部稀疏线性嵌入的降维方法及其应用[J].南京大学学报（自然科学）,2013,49(4):403-410.
139.刘嘉敏,周晓莉,朱晟君,等.基于LLE及其改进算法的人耳识别[J].光电工程,2012,39(12):132-137.
140. Zhang A.J., Wu Z.L., Li C.H., et al. On Hadamard-type output coding in multiclass learning[J].In:Intelligent Data Engineering and Automated Learning,Lecture Notes in Computer Science,2003,2690:397-404.
141.刘跃辉,郑建东.基于支持向量机原理的复杂地层岩性识别方法[J].国外测井技术,2011(4):22-26.
142. Mercer J. Function of positive and negative type and their connection with the theory of integralequations[J]. Philos.Trans.Roy.Soc.London, A209,1909:415-446.
143. Baesens B, Viaene S, Van Gestel T, et al. An Empirical assessment of Kenrel Type performance forleast squares support vector machine classification[C]. Proceedings of Fourth Intenrational Conferenceon Knowledge-Based Intelligent Engineer system and Allied Technologies,2000,313-316.
144. Smits G F, J ORDAN E M. Improved SVM regression using mixtures of kernels[C]. Proceedings of the2002International Joint Conference on Neural Networks. Hawaii: IEEE,2002:2785-2790.
145.庄严,白振林,许云.基于蚁群算法的支持向量机参数选择方法研究[J].计算机仿真,2011,28(5):216-219.
146.朱凤明,樊明龙.混沌粒子群算法对支持向量机模型参数的优化[J].计算机仿真,2011,27(11):183-186.
147. Ebethart R C, Kennedy J. A new Optimizer using Partiele swarm theory[C]. Proceedings of the SixthInterational SymPosium on Miero Machine and Human Seienee, Nagoya,Japan， IEEE press，Piscataway, NJ,1995,39-43.
148.钱彭飞,章兢,谢燕.一种新的混合粒子群优化算法[J].科技导报,2010,28(22):74-76.
149. Chen D B, Zhao C X. Particle swarm optimization with adaptive population size and its application[J].Applied Soft Computing,2009,9(1):39-48.
150. Kao Y T, Zahara E. A hybrid genetic algorithm and particle swarm optimization for multimodalfunctions[J]. Applied Soft Computing,2008,8(2):849-857.
151. Zhang C S, Ning J X, Lu S,et al. N.A novel hybrid differential evolution and particle swarmoptimization algorithm for unconstrained optimization[J]. Operations Research Letters,2009,37(2):117-122.
152. Wang Y J, Yang Y P. Particle swarm optimization with preference order ranking for multi-objectiveoptimization[J]. Information Sciences,2009,179(12):1944-1959.