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

Generating Synthetic Raman Spectra of DMMP and 2-CEES by Mathematical Transforms and Deep Generative Models

수학적 변환과 심층 생성 모델을 활용한 DMMP와 2-CEES의 모의 라만 분광 생성

  • Received : 2023.03.10
  • Accepted : 2023.11.17
  • Published : 2023.12.05
Download PDF
⟨ Previous Next ⟩

Abstract

To build an automated system detecting toxic chemicals from Raman spectra, we have to obtain sufficient data of toxic chemicals. However, it usually costs high to gather Raman spectra of toxic chemicals in diverse situations. Tackling this problem, we develop methods to generate synthetic Raman spectra of DMMP and 2-CEES without actual experiments. First, we propose certain mathematical transforms to augment few original Raman spectra. Then, we train deep generative models to generate more realistic and diverse data. Analyzing synthetic Raman spectra of toxic chemicals generated by our methods through visualization, we qualitatively verify that the data are sufficiently similar to original data and diverse. For conclusion, we obtain a synthetic dataset of DMMP and 2-CEES with the proposed algorithm.

Keywords

Acknowledgement

이 성과는 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2021R1F1A1054766).

References

  1. Young Jin Koh, "The Design and Test of the Stand-off Surface Chemical Contaminant Detection System based on Raman Spectroscopy," Journal of the Korea Institute of Military Science and Technology, 22.3, 433-440, 2019.
  2. Sun-Kyung Choi, et al., "Deep UV Raman spectroscopic study for the standoff detection of chemical warfare agents from the agent-contaminated ground surface," Journal of the Korea Institute of Military Science and Technology, 18.5, 612-620, 2015. https://doi.org/10.9766/KIMST.2015.18.5.612
  3. S. K. Choi, et al., "Analysis of Raman Spectral Characteristics of Chemical Warfare Agents by using a 248 nm UV Raman Spectroscopy," Bulletin of the Korean Chemical Society, 40(3): 279-284, 2019. https://doi.org/10.1002/bkcs.11679
  4. S. K. Choi, et al., "Detection of toxic chemicals on the surface by a stand-off Raman spectroscopy," Bulletin of the Korean Chemical Society, 40(6): 483-484, 2019. https://doi.org/10.1002/bkcs.11727
  5. J. H. Lee, et al., "Detection of hazardous chemical using dual-wavelength Raman spectroscopy in the ultraviolet region," Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 287: 122061, 2023.
  6. LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton, "Deep learning," nature, 521.7553, 436-444, 2015. https://doi.org/10.1038/nature14539
  7. Luo, Ruihao, Juergen Popp, and Thomas Bocklitz, "Deep Learning for Raman Spectroscopy: A Review," Analytica 3.3, 287-301, 2022. https://doi.org/10.3390/analytica3030020
  8. Goodfellow, Ian, Yoshua Bengio, and Aaron Courville, Deep learning, MIT press, 2016.
  9. Kingma, Diederik P., and Max Welling, "Auto-encoding variational Bayes," International Conference on Learning Representations, 2014.
  10. Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David WardeFarley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio, "Generative adversarial nets," Advances in Neural Information Processing Systems, 2014.
  11. Hao Chen, et al., "An adaptive denoising method for Raman spectroscopy based on lifting wavelet transform," Journal of Raman Spectroscopy, 49.9, 1529-1539, 2018. https://doi.org/10.1002/jrs.5399
  12. Chang Sik Lee, et al., "Denoising Autoencoder based Noise Reduction Technique for Raman Spectrometers for Standoff Detection of Chemical Warfare Agents," Journal of the Korea Institute of Military Science and Technology, 24.4, 374-381, 2021. https://doi.org/10.9766/KIMST.2021.24.4.374
  13. Xiangyun Ma, et al., "Conditional Generative Adversarial Network for Spectral Recovery to Accelerate Single-Cell Raman Spectroscopic Analysis," Analytical Chemistry, 94.2, 577-582, 2022. https://doi.org/10.1021/acs.analchem.1c04263
  14. Jae-Hyeon Park, et al., "CNN based Raman Spectroscopy Algorithm That is Robust to Noise and Spectral Shift," Journal of the Korea Institute of Military Science and Technology, 24.3, 264-271, 2021. https://doi.org/10.9766/KIMST.2021.24.3.264
  15. Yu, Shixiang, et al., "Classification of pathogens by Raman spectroscopy combined with generative adversarial networks," Science of The Total Environment, 726, 138477, 2020.
  16. Wen, Qingsong, et al., "Time series data augmentation for deep learning: A survey," International Joint Conference on Artificial Intelligence, 2021.
  17. Yoon, Jinsung, Daniel Jarrett, and Mihaela Van der Schaar, "Time-series generative adversarial networks," Advances in neural information processing systems, 2019.
  18. Xu, Tianlin, et al., "Cot-gan: Generating sequential data via causal optimal transport," Advances in Neural Information Processing Systems, 2020.
  19. T. T. Um et al., "Data augmentation of wearable sensor data for Parkinson's disease monitoring using convolutional neural networks," Proceedings of the 19th ACM ICMI, 2017.
  20. Lotte, Fabien, "Signal processing approaches to minimize or suppress calibration time in oscillatory  activity-based brain-computer interfaces," Proceedings of the IEEE 103.6, 871-890, 2015. https://doi.org/10.1109/JPROC.2015.2404941
  21. Mallat, Stephane, "A wavelet tour of signal processing," Elsevier, 1999.
  22. Guomin Luo and Daming Zhang, "Wavelet Denoising," Advances in Wavelet Theory and Their Applications in Engineering, Physics and Technology, 2012.
  23. Ishaan Gulrajani, et al., "Improved training of wasserstein gans," Advances in neural information processing systems, 2017.