首页 > 论文 > 大气与环境光学学报 > 13卷 > 6期(pp:436-446)

主成分分析联合Fisher判别在紫外-可见光谱法水质检测中的应用

Application of Principal Component Analysis Combined Fisher Discrimination in Water Quality Detection by UV-Vis Spectroscopy

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

摘要

水质类型的判别是实现光谱法水质参数准确检测的重要前提。针对直接光谱法水质检测系统采集的光谱数据信息冗余较大的问题, 利用主成分分析消除信息指标间的相关性,实现光谱数据的降维和特征信息提取。采集某化工厂和某溪水水样的紫外-可见光谱数据, 利用主成分分析联合Fisher判别的方法建立判别模型,以12组水样光谱数据作为训练样本,6组作为测试样本,对模型的判别能力进行 论证和检验,并与传统的Fisher判别模型进行对比实验。实验结果表明,利用主成分分析联合Fisher判别模型可以有效消除信息冗 余带来的影响,相比传统的Fisher判别模型具有分类精度高、回代误判率为零、计算时间短等优点,计算时间由传统Fisher判别 方法的0.6733 s减少到0.6012 s。该方法为直接光谱法水质类型判别工程实用化提供了一种高效手段。

Abstract

The identification of water quality is an important prerequisite for accurate spectroscopic detection of water quality parameters. Aiming at the problem of large redundancy of spectral data collected by direct spectrum water quality detection system, the principal component analysis is used to eliminate the correlation of information indexes, and the spectral data is reduced and the feature information is extracted. The UV-Vis spectra of water from a chemical plant and a stream were collected. The discriminant model was established by using the method of principal component analysis and Fisher discriminant. First, 12 sets of water samples were used as training samples and 6 groups as test samples. Then, the discriminant ability of the model was demonstrated and tested, and compared with the traditional Fisher discriminant model. Finally, The experimental results show that the joint Fisher discriminant model can effectively eliminate the influence of information redundancy. Compared with the traditional Fisher discriminant model, it has the advantages of high classification precision, zero return error rate and short calculation time. The calculation time is reduced from 0.6733 s to 0.6012 s. This method provides an efficient means for practical application of direct spectrum method to determine the water quality.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:X832

DOI:10.3969/j.issn.1673-6141.2018.06.004

基金项目:Supported by Chongqing Municipal Education Commission Science and Technology Research Project (重庆市教委科学技术研究项目, KJ1709201)

收稿日期:2017-05-15

修改稿日期:2017-06-30

网络出版日期:--

作者单位    点击查看

赵明富:重庆理工大学现代光电检测技术与仪器重点实验室,重庆 400054重庆理工大学光纤传感与光电检测重庆市重点实验室,重庆 400054
唐平:重庆理工大学现代光电检测技术与仪器重点实验室,重庆 400054重庆理工大学光纤传感与光电检测重庆市重点实验室,重庆 400054
汤斌:重庆理工大学现代光电检测技术与仪器重点实验室,重庆 400054重庆理工大学光纤传感与光电检测重庆市重点实验室,重庆 400054
徐杨非:重庆理工大学现代光电检测技术与仪器重点实验室,重庆 400054重庆理工大学光纤传感与光电检测重庆市重点实验室,重庆 400054
邓思兴:重庆理工大学现代光电检测技术与仪器重点实验室,重庆 400054重庆理工大学光纤传感与光电检测重庆市重点实验室,重庆 400054

联系人作者:赵明富(1469273789@qq.com)

备注:赵明富 (1964-),男,重庆人,博士,教授,研究生导师,主要从事信息获取与处理、光纤生物化学传感技术、智能信息处理方面的研究。

【1】Wei Kanglin, Wen Zhiyu, Wu Xin,et al. Study on water quality monitoring technology based on UV-Vis spectroscopy[J]. Spectroscopy and Spectral Analysis, 2013, 33(4): 1074-1077(in Chinese).
魏康林, 温志渝, 武 新, 等. 基于紫外-可见光谱分析的水质监测技术研究进展[J]. 光谱学与光谱分析, 2013, 33(4): 1074-1077.

【2】Xu Yuge, Liu Li, Cao Tao,et al. A classification method based on KNN and RVM KNN RVM Classifier[J]. Journal of Chemical Industry, 2015, 6(11): 4540-4545(in Chinese).
许玉格, 刘 莉, 曹 涛,等. 基于KNN和RVM的分类方法-KNN RVM分类器[J]. 化工学报, 2015, 6(11): 4540-4545.

【3】Li Xiaofeng, Li Xinghua, Huang Tao,et al. Application of PCA water quality classification method in water quality evaluation of Tongji[J]. Sichuan Environment, 2016, 35(3): 41-45(in Chinese).
李晓丰, 李兴华, 黄 涛,等. PCA水质分类法在通济堰水质评价中的应用[J]. 四川环境, 2016, 35(3):41-45.

【4】Zhang Ying, Gao Qianqian. Water quality evaluation of Chaohu lake based on random forest classification[J].Editorial Office of Environmental Engineering, 2016, 10(2): 992-998(in Chinese).
张 颖, 高倩倩. 基于随机森林分类算法的巢湖水质评价[J]. 环境工程学报, 2016, 10(2): 992-998.

【5】Modaresi F, Araghinejad S. A comparative assessment of support vector machines, probabilistic neural networks, and K-nearest neighbor algorithms for water quality classification[J].Water Resources Management, 2014, 28(12): 4095-4111.

【6】Yu H, Song Y, Gao H,et al. Applying fluorescence spectroscopy and multivariable analysis to characterize structural composition of dissolved organic matter and its correlation with water quality in an urban river[J]. Environmental Earth Sciences, 2015, 73(9): 5163-5171.

【7】Saghebian S M, Sattari M T, Mirabbasi R,et al. Ground water quality classification by decision tree method in Ardebil region, Iran[J]. Arabian Journal of Geosciences, 2014, 7(11): 4767-4777.

【8】Tang Bin, Wei Biao, Wu Decao,et al. Method for data processing of UV-Vis spectra based on principal component analysis combined with generalized discriminant classification[J]. Laser Journal, 2014(10): 112-114(in Chinese).
汤 斌, 魏 彪, 吴德操, 等. 主元分析降维联合广义判别分类的水质检测紫外-可见光谱数据处理方法[J]. 激光杂志, 2014(10): 112-114.

【9】López-Roldán R, Platikanov S, Martín-Alonso J,et al. Integration of Ultraviolet-Visible spectral and physicochemical data in chemometrics analysis for improved discrimination of water sources and blends for application to the complex drinking water distribution network of Barcelona[J]. Journal of Cleaner Production, 2016, 112: 4789-4798.

【10】Tang W J, Gong F, Dong R R,et al. Face recognition based on the fusion of wavelet packet sub-images and fisher linear discriminant[J]. Multimedia Tools and Applications, 2017, 7(21): 1-16.

【11】Feng Dongmei, Chen Xue, Wang Dan,et al. FA-IGA-LSSVM model for the influence of blasting vibration on slope stability[J]. Journal of Liaoning Technical University, 201(7): 717-721(in Chinese).
冯东梅, 陈 雪, 王 丹, 等. 爆破振动对边坡稳定性影响的FA-IGA-LSSVM模型[J]. 辽宁工程技术大学学报, 201(7): 717-721.

【12】Shan Yan, Li Lingjuan, Sun Dujing,et al. Study on parallel reduction of data stream based on principal component analysis[J]. Journal of Nanjing University of Posts and Telecommunications, 2015, 35(5): 99-104(in Chinese).
单 燕, 李玲娟, 孙杜靖,等. 基于主成分分析的并行化数据流降维算法研究[J]. 南京邮电大学学报自然科学版, 2015, 35(5):99-104.

【13】Tan Ping, Xing Yujuan. Study on speaker recognition based on GMM super-vector and Fisher-sparse representation[J].Journal of Qinghai University, 2016, 34(1): 51-57(in Chinese).
谭 萍, 邢玉娟. 基于GMM超向量和Fisher-稀疏表示分类的说话人确认[J]. 青海大学学报, 2016, 34(1): 51-57.

【14】Tang Bin, Wei Biao, Mao Benjiang,et al. Noise analysis and treatment of water quality detection system based on UV-Vis absorption spectroscopy[J]. Progress of Laser and Optoelectronics, 2014, 51(4): 197-203(in Chinese).
汤 斌, 魏 彪, 毛本将, 等. 紫外-可见吸收光谱法水质检测系统的噪声分析与处理研究[J]. 激光与光电子学进展, 2014, 51(4): 197-203.

【15】Yi Xiushuang, Liu Yong, Li Jie,et al. Principal component analysis algorithm based on MapReduce.[J]. Computer Science, 2017(2): 65-69(ini Chinese).
易秀双, 刘 勇, 李 婕, 等. 基于MapReduce的主成分分析算法研究[J]. 计算机科学, 2017(2): 65-69.

引用该论文

ZHAO Mingfu,TANG Ping,TANG Bin,XU Yangfei,DENG Sixing. Application of Principal Component Analysis Combined Fisher Discrimination in Water Quality Detection by UV-Vis Spectroscopy[J]. Journal of Atmospheric and Environmental Optics, 2018, 13(6): 436-446

赵明富,唐平,汤斌,徐杨非,邓思兴. 主成分分析联合Fisher判别在紫外-可见光谱法水质检测中的应用[J]. 大气与环境光学学报, 2018, 13(6): 436-446

被引情况

【1】黄平捷,李宇涵,俞巧君,王 柯,尹 航,侯迪波,张光新. 基于SPA和多分类SVM的紫外-可见光光谱饮用水有机污染物判别方法研究. 光谱学与光谱分析, 2020, 40(7): 2267-2272

【2】黄鸿,兰洪勇,黄云彪. 基于深度信念网络和极限学习机的SO2浓度检测. 大气与环境光学学报, 2020, 15(3): 207-216

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