支持向量机结合主成分分析辅助激光诱导击穿光谱技术识别鲜肉品种

引用本文: 朱毅宁, 杨平, 杨新艳, 李嘉铭, 郝中骐, 李秋实, 郭连波, 李祥友, 曾晓雁, 陆永枫. 支持向量机结合主成分分析辅助激光诱导击穿光谱技术识别鲜肉品种[J]. 分析化学, 2017, 45(3): 336-341. doi: 10.11895/j.issn.0253-3820.160570 shu

Citation: ZHU Yi-Ning, YANG Ping, YANG Xin-Yan, LI Jia-Ming, HAO Zhong-Qi, LI Qiu-Shi, GUO Lian-Bo, LI Xiang-You, ZENG Xiao-Yan, LU Yong-Feng. Classification of Fresh Meat Species Using Laser-induced Breakdown Spectroscopy with Support Vector Machine and Principal Component Analysis[J]. Chinese Journal of Analytical Chemistry, 2017, 45(3): 336-341. doi: 10.11895/j.issn.0253-3820.160570 shu

支持向量机结合主成分分析辅助激光诱导击穿光谱技术识别鲜肉品种

华中科技大学武汉光电国家实验室(筹)激光与太赫兹技术功能实验室, 武汉 430074
基金项目:
本文系国家重大科学仪器设备开发专项(No.2011YQ160017)、国家自然科学基金项目(No.6157031235)资助

摘要: 为提高激光诱导击穿光谱技术(Laser-induced breakdown spectroscopy，LIBS)对鲜肉品种的识别率，采用支持向量机结合主成分分析算法辅助LIBS技术对鲜肉品种进行识别。对鲜肉切片用载玻片压平，采用LIBS技术对鲜肉组织(猪肉、牛肉和鸡肉)表面进行光谱数据的采集，每种鲜肉采集150幅光谱并进行随机排列，取前75幅光谱作为训练集建立模型，后75幅作为测试集测试建模结果。研究选取K、Ca、Na、Mg、Al、H、O等元素的49条归一化谱线数据进行主成分分析，并用所得数据建立支持向量机分类模型。结果表明，通过主成分分析降维，输入变量从49个优化减少到18个，模型建模速度从88.91 s降至55.52 s，提高了支持向量机的建模效率；并使预测集的平均识别率提高到89.11%。本研究为激光诱导击穿光谱技术在鲜肉品种快速分类领域提供了方法和数据参考。

关键词:

English

Classification of Fresh Meat Species Using Laser-induced Breakdown Spectroscopy with Support Vector Machine and Principal Component Analysis

Wuhan National Laboratory for Optoelectronics, Laser and Tera-Hertz Technology Division, Huazhong University of Science and Technology, Wuhan 430074, China
Received Date: 27 July 2016
Revised Date: 23 December 2016
Fund Project:
This work was supported by the National Major Scientific Instrument and Equipment Development Project (No. 2011YQ160017)and the National Natural Science Foundation of China (No. 6157031235)

Abstract: To improve the classification accuracy of fresh meat species using laser-induced breakdown spectroscopy (LIBS), the support vector machine (SVM) and principal component analysis (PCA) were combined to classify fresh meat species (including pork, beef, and chicken). A simple sample preparation to flatten fresh meat by glass slides was proposed. For each meat sample, 150 spectra were recorded and randomly arranged. The first 75 spectra were used to train a model while the others were used for model validation. By analyzing the 49 normalized spectral lines (K, Ca, Na, Mg, Al, H, O, etc.) in the different tissues, the classification model was built. The results showed that the dimensionality of input variables was decreased from 49 to 10 and modeling time was reduced from 89.11 s to 55.52 s using PCA, thus improving the modeling efficiency. The mean classification accuracy of 89.11% was achieved. The method and reference data are provided for further study of fresh meat classification by laser-induced breakdown spectroscopy technique.

Key words:

1. [1]
  Rodríguez M A, García T, González I, Hernández P E, Martín R. Meat Sci., 2005,70(1):113-120
2. [2]
  Hites R A. Handbook of Instrumental Techniques For Analytical Chemistry, 1997:609-626
3. [3]
  Vallejo-Cordoba B, Cota-Rivas M. J. Capillary Electrophor., 1997,5(5-6):171-175
4. [4]
  Kumar A, Kumar R R, Sharma B D, Gokulakrishnan P, Mendiratta S K, Sharma D. Crit. Rev. Food Sci., 2015,55(10):1340-1351
5. [5]
  Radziemski L J. Spectrochim. Acta, 2002,57(7):1109-1113
6. [6]
  Radziemski L, Cremers D. Spectrochim. Part B, 2013,87:3-10
7. [7]
  CHEN Qi-Meng, DU Min, HAO Zhong-Qi, ZOU Xiao-Heng, LI Jia-Ming, YI Rong-Xing, LI Xiang-You, LU Yong-Feng, ZENG Xiao-Yan. Spectroscopy and Spectral Analysis, 2016,36(5):1473-1477 陈启蒙, 杜敏, 郝中骐, 邹孝恒, 李嘉铭, 易荣兴, 李祥友, 陆永枫, 曾晓雁.光谱学与光谱分析,2016,36(5):1473-1477
8. [8]
  Li C M, Zou Z M, Yang X Y, Hao Z Q, Guo L B, Li X Y, Lu Y F, Zeng X Y. J. Anal. Atom. Spectrom., 2014,29(8):1432-1437
9. [9]
  LI Jia-Ming, CHU Ying-Bo, ZHAO Nan, ZHOU Ran, YI Rong-Xing, GUO Lian-Bo, LI Jin-Yan, LI Xiang-You, ZENG Xiao-Yan, LU Yong-Feng. Chinese J. Anal. Chem., 2016,44(7):1042-1046 李嘉铭, 褚应波, 赵楠, 周冉, 易荣兴, 郭连波, 李进延, 李祥友,曾晓雁, 陆永枫.分析化学,2016,44(7):1042-1046
10. [10]
  SHAO Yan, ZHANG Yan-Bo, GAO Xun, DU Chuang,LIN Jing-Quan. Spectroscopy and Spectral Analysis, 2013,33(10):2593-2598 邵妍, 张艳波, 高勋, 杜闯, 林景全.光谱学与光谱分析,2013,33(10):2593-2598
11. [11]
  LIU Li. Las. Optoelect. Prog., 2015,52(7):295-299 刘莉.激光与光电子学进展,2015,52(7):295-299
12. [12]
  Zeng Q, Guo L, Li X, He C, Shen M, Li K, Duan J, Zeng X, Lu Y. J. Anal. Atom. Spectrom., 2015,30(2):403-409
13. [13]
  Hao Z, Guo L, Li C, Shen M, Zou X, Li X, Lu Y, Zeng X. J. Anal. Atom. Spectrom., 2014,29(12):2309-2314
14. [14]
  Sun L X, Yu H B, Cong Z B, Xin Y, Li Y, Qi L F. Spectrochim. Acta B, 2015,112:40-48
15. [15]
  Rehse S, Salimnia H, Miziolek A. J. Med. Eng. Technol., 2012,36(2):77-89
16. [16]
  CHEN Tian-Bing, LIU Mu-Hua, HUANG Lin, ZHOU Hua-Mao, WANG Cai-Hong, YANG Hui, HU Hui-Qin, YAO Ming-Yin. Chinese J. Anal. Chem., 2016,44(7):1029-1034 陈添兵, 刘木华, 黄林, 周华茂, 王彩虹, 杨晖, 胡慧琴, 姚明印.分析化学,2016,44(7):1029-1034
17. [17]
  Liu X Y, Zhang W J. J. Med. Biol. Eng., 2008,1(3):147
18. [18]
  Yao M, Huang L, Zheng J, Fan S, Liu M. Opt. Laser. Technol., 2013,52:70-74
19. [19]
  Singh V K, Rai A K. Laser Med. Sci., 2011, 26(5):673-687
20. [20]
  Kumar A, Yueh F Y, Singh J P, Burgess S. Appl. Optics, 2004,43(28):5399-5403
21. [21]
  Yueh F Y, Zheng H, Singh J P, Burgess S. Spectrochim. Acta B, 2009,64(10):1059-1067
22. [22]
  Bilge G, Velioglu H M, Sezer B, Eseller K E, Boyaci I H. Meat Sci., 2016,119:118-122
23. [23]
  Cortes C, Vapnik V. Mach. Learn., 1995,20(3):273-297
24. [24]
  Yu Y, Guo L, Hao Z, Li X, Shen M, Zeng Q, Li K, Zeng X, Lu Y, Ren Z. Opt. Express, 2014,22(4):3895-3901
25. [25]
  Shi Q, Niu G, Lin Q, Xu T, Li F, Duan Y. J. Anal. Atom. Spectrom., 2015,30(12):2384-2393
26. [26]
  Yu K Q, Zhao Y R, Liu F, He Y. Sci. Rep., 2015,6:27574-27574
27. [27]
  Yang H X, Fu H B, Wang D H, Jia J W, Dong F Z. Chinese Phys. B, 2016,25(6):290-295
28. [28]
  Sankaran S, Ehsani R, Morganc K T. Appl. Spectrosc., 2015,69(8):913-919
29. [29]
  Pokrajac D, Lazarevic A, Kecman V, Marcano A, Markushin Y, Vance T, Reljin N, McDaniel S, Melikechi N. Appl. Spectrosc., 2014,68(9):1067-1075
30. [30]
  Pearse R W B, Gaydon A G, Pearse R W B, Gaydon A G. The Identification Of Molecular Spectra (Chapman and Hall London), 1976,Vol. 297
31. [31]
  YIN Fei, FENG Da-Zheng. Comput. Technol. Dev., 2008,18(10):31-33 尹飞, 冯大政.计算机技术与发展,2008,18(10):31-33
32. [32]
  Chang C C, Lin C J. Acm. T. Intel. Syst. Tec., 2011,2(3):27
33. [33]
  YU Yang, HAO Zhong-Qi, LI Chang-Mao, GUO Lian-Bo, LI Kuo-Hu, ZENG Qin-Dong, LI Xiang-You, REN Zhao, ZENG Xiao-Yan. Acta. Phys. Sin, 2013,62(21):215201-215201 于洋, 郝中骐, 李常茂, 郭连波, 李阔湖, 曾庆栋, 李祥友, 任昭, 曾晓雁.物理学报,2013,62(21):215201-215201

扫一扫看文章

计量

PDF下载量: 6
文章访问数: 605
HTML全文浏览量: 42

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

支持向量机结合主成分分析辅助激光诱导击穿光谱技术识别鲜肉品种

English

Classification of Fresh Meat Species Using Laser-induced Breakdown Spectroscopy with Support Vector Machine and Principal Component Analysis

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

支持向量机结合主成分分析辅助激光诱导击穿光谱技术识别鲜肉品种

English

Classification of Fresh Meat Species Using Laser-induced Breakdown Spectroscopy with Support Vector Machine and Principal Component Analysis

CCS Chemistry：嵌段共聚物自组装成 “三明治”二维有机材料，实现纳米级压力传感功能

CCS Chemistry：颜徐州、鲍哲南： 你的皮肤可能是一片SPMs

CCS Chemistry：工作高效不疲劳，只须让催化剂动起来

CCS Chemistry：静电组装导向聚合- 聚电解质纳米凝胶量化制备新策略

CCS Chemistry：金黄色葡萄球菌醛基脱氢酶是如何识别特异性底物的？

计量

文章相关

通讯作者: 陈斌, bchen63@163.com

中国化学会秘书处

CCS Chemistry：颜徐州、鲍哲南：你的皮肤可能是一片SPMs