Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지
DOI QR코드

DOI QR Code

CNN based Raman Spectroscopy Algorithm That is Robust to Noise and Spectral Shift

잡음과 스펙트럼 이동에 강인한 CNN 기반 라만 분광 알고리즘

  • Park, Jae-Hyeon (Department of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Yu, Hyeong-Geun (Department of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Lee, Chang Sik (Department of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Chang, Dong Eui (Department of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Park, Dong-Jo (Department of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Nam, Hyunwoo (The 4th Research and Development Institute, Agency for Defense Development) ;
  • Park, Byeong Hwang (The 4th Research and Development Institute, Agency for Defense Development)
  • 박재현 (한국과학기술원 전기및전자공학부) ;
  • 유형근 (한국과학기술원 전기및전자공학부) ;
  • 이창식 (한국과학기술원 전기및전자공학부) ;
  • 장동의 (한국과학기술원 전기및전자공학부) ;
  • 박동조 (한국과학기술원 전기및전자공학부) ;
  • 남현우 (국방과학연구소 제4기술연구본부) ;
  • 박병황 (국방과학연구소 제4기술연구본부)
  • Received : 2021.01.29
  • Accepted : 2021.04.30
  • Published : 2021.06.05
Download PDF
⟨ Previous Next ⟩

Abstract

Raman spectroscopy is an equipment that is widely used for classifying chemicals in chemical defense operations. However, the classification performance of Raman spectrum may deteriorate due to dark current noise, background noise, spectral shift by vibration of equipment, spectral shift by pressure change, etc. In this paper, we compare the classification accuracy of various machine learning algorithms including k-nearest neighbor, decision tree, linear discriminant analysis, linear support vector machine, nonlinear support vector machine, and convolutional neural network under noisy and spectral shifted conditions. Experimental results show that convolutional neural network maintains a high classification accuracy of over 95 % despite noise and spectral shift. This implies that convolutional neural network can be an ideal classification algorithm in a real combat situation where there is a lot of noise and spectral shift.

Keywords

Acknowledgement

본 연구는 국방과학연구소의 연구비 지원으로 수행되었습니다.(계약번호 UD190007GD)

References

  1. R. L. McCreery, "Raman Spectroscopy for Chemical Analysis," John Wiley & Sons, Canada, pp. 15-34, 2000.
  2. M. A. Slamani, B. Fisk, T. Chyba, D. Emge and S. Waugh, "A Algorithm Benchmark Data Suite for Chemical and Biological(Chem/Bio) Defense Applications," SPIE Defense and Security Symposium, Vol. 6969, No. 696903, 2008.
  3. R. D. Palkki, and A. D. Lanterman, "Identifying Chemicals from Their Raman Spectra Using Minimum Description Length," Proc. of SPIE, Vol. 7698, Signal and Data Processing of Small Targets 2010, 769807, Apr. 2010.
  4. S. H. Melfi, D. N. Whiteman, and R. A. Ferrare, "Observation of Atmospheric Fronts Using Raman Lidar Moisture Measurements," Journal of Applied Meteorology, Vol. 28, pp. 789-806, 1989. https://doi.org/10.1175/1520-0450(1989)028<0789:OOAFUR>2.0.CO;2
  5. K. Xiiong, "UV Resonance Raman Spectroscopy: A Highly Sensitive, Selective and Fast Technique for Environmental Analysis," Environmental Analytial Chemistry, Vol. 2, No. 1, 2014.
  6. F. Foucher, G. Guimbretiere, N. Bost, and F. Westall, "Petrographical and Mineralogical Applications of Raman Mapping," Raman Spectroscopy and Applications, Khan Maaz, IntechOpen, Feb. 2017.
  7. E. V. Efremov, F. Ariese, and C. Gooijer, "Achievements in Resonance Raman Spectroscopy Review of a Technique with a Distinct Analytical Chemistry Potential," Analytica Chimica Acta 606, pp. 119-134, 2008. https://doi.org/10.1016/j.aca.2007.11.006
  8. Y. J. Koh, "The Design and Test of the Stand-off Surface Chemical Contaminant Detection System based on Spectroscopy," Journal of the KIMST, Vol. 22, No. 3, pp. 433-440, 2019.
  9. S. K. Choi, Y. S. Jeong, J. H. Lee, and Y. C. Ha, "Deep UV Raman Spectroscopic Study for the Standoff Detection of Chemical Warfare Agents from the Agent-Contaminated Ground Surface," Journal of the KIMST, Vol. 18, No. 5, pp. 612-620, 2015.
  10. A. J. Sedlacek, M. Ray, S. Higdon, and D. Richter, "Short-Range, Non-Contact Detection of Surface Contamination Using Raman Lidar," Proc. of SPIE, Vol. 4577, 2002.
  11. P. Ponsardin, S. Higdon, T. H. Chyba, W. T. Armstrong, A. J. Sedlacek III, S. Christesen, and A. Wong, "Expanding Applications for SurfaceContaminant Sensing Using the Laser Interrogation of Surface Agents(LISA) Technique," Proc. of SPIE, 2004.
  12. J. Smulko, M. S. Wrobel, and I, Barman, "Noise in Biological Raman Spectroscopy," International Conference on Noise and Fluctuations, 2015.
  13. H. Chen, W. Xu, N. Broderick, and J. Han, "An Adaptive Denoising Method for Raman Spectroscopy based on Lifting Wavelet Transform," Journal of Raman Spectroscopy, Vol. 49, Issue. 9, June, 2018.
  14. S. A. Kirillov, "Repulsion Forces in Vibrational Spectroscopy - I. Spectral Shifts in Vibrational Spectra of Condensed Media Caused by Repulsion Forces," Spectrochimica Acta, Vol. 48A, No. 6, pp. 861-866, 1992. https://doi.org/10.1016/0584-8539(92)80082-8
  15. R. Gautam, S. Vanga, F. Ariese, and S. Umapathy, "Review of Multidimensional Data Processing Approaches for Raman and Infrared Spectrocsopy," Vol. 2, No. 1, pp. 1-38, 2015, EPJ Techniques and Instrumentation. https://doi.org/10.1140/epjti/s40485-014-0011-5
  16. C. M. Bishop, "Pattern Recognition and Machine Learning," Springer Science + Business Media, LLC, 2006.
  17. C. Carey, T. Boucher, S. Mahadevan, P. Bartholomew, and M. D. Dyar, "Machine Learning Tools for Mineral Recognition and Classification from Raman Spectroscopy," Journal of Raman Spectroscopy, Vol. 46, Issue 10, pp. 894-903, 2015. https://doi.org/10.1002/jrs.4757
  18. J. dong, M. Hong, Y, xu, and X. Zheng, "A Practical Convolutional Neural Network Model for Discriminating Raman Spectra of Human and Animal Blood," Journal of Chemometrics, Vol. 33, Issue 11, 2019.
  19. I. Goodfellow, Y. Bengio, and A. Courville, "Deep Learning," MIT Press Cambridge, Massachusetts, pp. 326-366, 2016.
  20. Y. C. Ha, J. H. Lee, Y. J. Koh, S. K. Lee, and Y. K. Kim, "Development of an Ultraviolet Raman Spectrometer for Standoff Detection of Chemicals," Current Optics and Photonics, Vol. 1, No. 3, pp. 247-251, June, 2017. https://doi.org/10.3807/COPP.2017.1.3.247