Spectroscopy and Spectral Analysis, Volume. 37, Issue 12, 3828(2017)

Feature Extraction and Classification of Animal Blood Spectra with Support Vector Machine

LU Peng-fei1、*, FAN Ya1, ZHOU Lin-hua1, QIAN Jun2, LIU Lin-na2, ZHAO Si-yan2, KONG Zhi-feng3, and GAO Bin1
Author Affiliations
  • 1[in Chinese]
  • 2[in Chinese]
  • 3[in Chinese]
  • show less

    It is of great significance to study how to use spectral detection technology and data mining technology to realize the accurate identification and classification of different animal blood spectral data, and it has not yet seen relevant complete research conclusions and methods on animal blood identification and classification. Therefore, the authors collected fluorescence spectra data of four kinds of animals, including pigeon, chicken, mouse and sheep. Based on the soft threshold denoising method of wavelet transform, the original spectral data were denoised, and the 717 original features were determined. Following the approach of “Distinguish statistic” proposed by the authors, 717 original features were extracted into 2 finally input features. Based on support vector machine, the whole blood solution of different animals were 100% recognized, while the red cell blood solution of different animals were 94.69%~99.12% correctly recognized. Finally, the Monte Carlo cross validation revealed that the method used in this paperhad a great generalization ability for whole blood solution of different animals, which can play an important role in the import and export inspection, food safety, medicine and other fields.

    Tools

    Get Citation

    Copy Citation Text

    LU Peng-fei, FAN Ya, ZHOU Lin-hua, QIAN Jun, LIU Lin-na, ZHAO Si-yan, KONG Zhi-feng, GAO Bin. Feature Extraction and Classification of Animal Blood Spectra with Support Vector Machine[J]. Spectroscopy and Spectral Analysis, 2017, 37(12): 3828

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Received: Jan. 8, 2017

    Accepted: --

    Published Online: Jan. 4, 2018

    The Author Email: Peng-fei LU (921010752@qq.com)

    DOI:10.3964/j.issn.1000-0593(2017)12-3828-05

    Topics