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

Denoising Autoencoder based Noise Reduction Technique for Raman Spectrometers for Standoff Detection of Chemical Warfare Agents

비접촉식 화학작용제 탐지용 라만 분광계를 위한 Denoising Autoencoder 기반 잡음제거 기술

  • Lee, Chang Sik (School of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Yu, Hyeong-Geun (School of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Park, Jae-Hyeon (School of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Kim, Whimin (School of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Park, Dong-Jo (School of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Chang, Dong Eui (School of Electrical Engineering, Korea Advanced Institute of Science and Technology) ;
  • Nam, Hyunwoo (The 4th Research and Development Institute, Agency for Defense Development)
  • 이창식 (한국과학기술원 전기및전자공학부) ;
  • 유형근 (한국과학기술원 전기및전자공학부) ;
  • 박재현 (한국과학기술원 전기및전자공학부) ;
  • 김휘민 (한국과학기술원 전기및전자공학부) ;
  • 박동조 (한국과학기술원 전기및전자공학부) ;
  • 장동의 (한국과학기술원 전기및전자공학부) ;
  • 남현우 (국방과학연구소 제4기술연구본부)
  • Received : 2021.03.05
  • Accepted : 2021.06.04
  • Published : 2021.08.05
Download PDF
⟨ Previous Next ⟩

Abstract

Raman spectrometers are studied and developed for the military purposes because of their nondestructive inspection capability to capture unique spectral features induced by molecular structures of colorless and odorless chemical warfare agents(CWAs) in any phase. Raman spectrometers often suffer from random noise caused by their detector inherent noise, background signal, etc. Thus, reducing the random noise in a measured Raman spectrum can help detection algorithms to find spectral features of CWAs and effectively detect them. In this paper, we propose a denoising autoencoder for Raman spectra with a loss function for sample efficient learning using noisy dataset. We conduct experiments to compare its effect on the measured spectra and detection performance with several existing noise reduction algorithms. The experimental results show that the denoising autoencoder is the most effective noise reduction algorithm among existing noise reduction algorithms for Raman spectrum based standoff detection of CWAs.

Keywords

Acknowledgement

본 연구는 국방과학연구소의 연구비 지원으로 수행되었습니다.(계약번호: UD190007GD)

References

  1. A. W. Fountain 3, et. al., "Long Range Standoff Detection of Chemical, Biological and Explosive Hazards on Surfaces," Proc. SPIE 7679, Micro- and Nanotechnology Sensors, Systems, and Applications II, 76790H, 2010.
  2. 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, 2017. https://doi.org/10.3807/COPP.2017.1.3.247
  3. S. Wallin, et. al., "Laser-based Standoff Detection of Explosives: A Critical Review," Analytical and Bioanalytical Chemistry, Vol. 395, pp. 259-274, 2009. https://doi.org/10.1007/s00216-009-2844-3
  4. P. L. Ponsardin, et. al., "Expanding Applications for Surfacecontaminant Sensing Using the Laser Interrogation of Surface Agents(LISA) Technique," Proc. SPIE 5268, Chemical and Biological Standoff Detection, 2004.
  5. S. J. Barton, T. E. Ward, and B. M. Hennelly, "Algorithm for Optimal Denoising of Raman Spectra," Analytical Methods, Vol. 10, pp. 3759-3769, 2018. https://doi.org/10.1039/C8AY01089G
  6. J. Smulko, M. S. Wrobel, and I. Barman, "Noise in Biological Raman Spectroscopy," 2015 International Conference on Noise and Fluctuations(ICNF), 2015.
  7. P. A. Mosier-Boss, S. H. Lieberman, and R. Newbery, "Fluorescence Rejection in Raman Spectroscopy by Shifted-Spectra, Edge Detection, and FFT Filtering Techniques," Applied Spectroscopy, Vol. 49, No. 5, pp. 630-638, 1995. https://doi.org/10.1366/0003702953964039
  8. C. C. Soberon-Celedon, et. al., "Removal of Fluorescence and Shot Noises in Raman Spectra of Biological Samples Using Morphological and Moving Averages Filters," International Journal of Engineering and Technical Research, Vol. 6, No. 3, pp. 2454-4698, 2016.
  9. X. Wang, et. al., "Development of Weak Signal Recognition and an Extraction Algorithm for Raman Imaging," Analytic Chemistry, Vol. 91, No. 20, pp. 12909-12916, 2019. https://doi.org/10.1021/acs.analchem.9b02887
  10. B. Rasti, P. Scheunders, P. Ghamisi, G. Licciardi, and J. Chanussot, "Noise Reduction in Hyperspectral Imagery: Overview and Application," Remote Sensing, Vol. 10, No. 3, p. 482, 2018. https://doi.org/10.3390/rs10030482
  11. H.-G. Yu, J. H. Park, C. S. Lee, D.-J. Park, D. E. Chang, H. Nam, and B. H. Park, "Performance Analysis of the Denoising Algorithms for Detection of Chemical Warfare Agents with Raman Spectroscopy," KIMST Annual Conference Proceedings, pp. 284-285, 2020.
  12. C. C. Horgan, et. al., "High-Throughput Molecular Imaging via Deep Learning Enabled Raman Spectroscopy," arxiv:2009.13318, 2020.
  13. X. Lu, et. al., "Speech Enhancement based on Deep Denoising Autoencoder," INTERSPEECH, 2013.
  14. F. Schroff, D. Kalenichenko, and J. Philbin, "FaceNet: A Unified Embedding for Face Recognition and Clustering," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815-823, 2015.
  15. I. Loshchilov, and F. Hutter, "SGDR: Stochastic Gradient Descent with Warm Restarts," International Conference on Learning Representations, 2017.
  16. D. P. Kingma, and J. Ba, "Adam: A Method for Stochastic Optimization," International Conference on Learning Representations(ICLR), 2015.
  17. D. Manolakis, C. Siracusa, and G. Shaw, "Hyperspectral Subpixel Target Detection Using the Linear Mixing Model," IEEE Transactions on Geoscience and Remote Sensing, Vol. 39, No. 7, pp. 1392-1409, 2001. https://doi.org/10.1109/36.934072