DOI QR코드

DOI QR Code

Improvement in the classification performance of Raman spectra using a hierarchical tree structure

계층적 트리 구조를 이용한 라만스펙트럼 판별 성능 개선

  • Park, Jun-Kyu (School of Electronics and Computer Engineering, Chonnam National University) ;
  • Baek, Sung-June (School of Electronics and Computer Engineering, Chonnam National University) ;
  • Seo, Yu-Gyeong (School of Electronics and Computer Engineering, Chonnam National University) ;
  • Seo, Sung-Il (School of Electronics Engineering, Honam University)
  • 박준규 (전남대학교 전자컴퓨터공학부) ;
  • 백성준 (전남대학교 전자컴퓨터공학부) ;
  • 서유경 (전남대학교 전자컴퓨터공학부) ;
  • 서성일 (호남대학교 전자공학과)
  • Received : 2014.04.22
  • Accepted : 2014.08.07
  • Published : 2014.08.31

Abstract

This paper proposes a method in which classes are grouped as a hierarchical tree structure for the effective classification of the Raman spectra. As experimental data, the Raman spectra of 28 chemical compounds were obtained, and pre-treated with noise removal and normalization. The spectra that induced a classification error were grouped into the same class and the hierarchical structure class was composed. Each high and low class was classified using a PCA-MAP method. According to the experimental results, the classification of 100% was achieved with 2.7 features on average when the proposed method was applied. Considering that the same classification rates were achieved with 6 features using the conventional method, the proposed method was found to be much better than the conventional one in terms of the total computational complexity and practical application.

본 논문에서는 라만스펙트럼의 효과적인 판별을 위해 계층 트리 구조로 클래스를 그룹화 하는 방식을 제안하였다. 실험데이터로는 28종 화학물질의 라만 스펙트럼을 준비하였고 잡음제거, 정규화 등의 전처리 수행하였다. 다음으로 사전실험을 통해 서로 간에 분류오류를 발생시키는 물질들을 그룹화 하여 계층 구조의 클래스를 구성하였고, 각각의 상위, 하위 클래스에 PCA(principal component analysis) 특징추출과 MAP(maximum a posteriori probability) 방식의 분류실험을 수행하였다. 실험 결과에 의하면 계층 구조의 클래스를 적용한 경우 평균 2.7개의 특징을 사용하여 분류가 100% 이루어짐을 확인할 수 있었다. 계층 구조를 적용하지 않는 기존의 방식에서 6개의 특징을 사용할 때 동일한 분류결과를 보였음을 감안해 보면, 제안한 방식이 전체 계산 복잡도의 측면에서 훨씬 뛰어남을 알 수 있다. 따라서 제안한 방식이 실제 응용에 보다 적합하다고 할 수 있다.

Keywords

References

  1. A. Park, S.-J.Baek, "A Diagnosis Method of Basal Cell Carcinoma by Raman Spectra of Skin Tissue using NMF Algorithm", Journal of The Institute of Electronics Engineers of Korea Vol.50, no.8, pp.2124-2130, Aug. 2013. DOI: http://dx.doi.org/10.5573/ieek.2013.50.8.196
  2. A. Park, S.-J.Baek, "Feature Ranking for Detection of Neuro-degeneration and Vascular Dementia in micro-Raman spectra of Platelet", Journal of The Institute of Electronics Engineers of Korea Vol.48-CI, no.4, pp.399-404, July. 2011.
  3. E.L. Izak, "Forensic and homeland security applications of modern potable Raman spectroscopy." Forrensic Sci. Int. Vol.202, issue 1-3, pp.1-8, Oct, 2010. DOI: http://dx.doi.org/10.1016/j.forsciint.2010.03.020
  4. J.S. Caygill, F. Davis, S.P.J. Higson, "Current trends in explosive detection techniques," Talanta, Vol.88, pp.14-29, 2012. DOI: http://dx.doi.org/10.1016/j.talanta.2011.11.043
  5. R.S. Golightly, W.E. Doering, M.J. Natan, "Surface-Enhanced Raman Spectroscopy and Homeland Security: A Perfect Match?," ACS nano, Vol.3, No.10, pp.2859-2869, 2009 DOI: http://dx.doi.org/10.1021/nn9013593
  6. Joonki Hwang, Namhyun Choi, "Fast and sensitive recognition of various explosive compounds using Raman spectroscopy and principal component analysis," J MOL STRUCT, Vol.1038, pp.130-136, April 2013. DOI: http://dx.doi.org/10.1016/j.molstruc.2013.01.079
  7. A. Savitzky and M. J. E. Golay, "Smoothing and Differentiation of Data by Simplified Least Squares Procedures," Analytical Chemistry, Vol. 36, pp.1627-1639, 1964. DOI: http://dx.doi.org/10.1021/ac60214a047
  8. Z. Jianhua, L. Harvey, M. David and Z. Haishan, "Automated Autofluorescence Background Subtraction Algorithm for Biomedical Raman Spectroscopy," Society for Applied Spectroscopy, Vol.61, pp.248A-270A, Nov. 2007. https://doi.org/10.1366/000370207782597049
  9. S.-J.Baek, A. Park, A. Shen and J. Hu, "A simple background delination method for Raman spectra," Chemometrics and Intelligent Laboratory Systems, Vol.98, issue.1, pp.24-30, Aug. 2009. DOI: http://dx.doi.org/10.1016/j.chemolab.2009.04.007
  10. I. T. Jolloffe, Principal Component Analysis 2nd Edition, Springer, 2002.
  11. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification Second Edition, Jone Wiley & Son, Inc.2001.