|Generate QR code
Open Access
Subscription Access
Raman Spectrum Classification of Cinnabar and Cinnabar-Clam White Based on Data Augmentation and Convolutional Neural Network
Abstract
Mineral pigments are commonly used in cultural relics, which makes the analysis of mineral pigments helpful in such research. It is complicated and time-consuming work to establish the data set of mineral pigment Raman spectra, so it is necessary to study the method of data augmentation. In this paper, two methods of augmenting Raman spectra data are explored – translation transformation, adding noise; expanding the size of the data set from 20 to 320 – then a convolutional neural network model is proposed and trained with the expanded data set. Experimental results showed that the accuracy of the model can reach 100% when the SNR of the test set is not less than 40 dB.
About the Authors
Taotao Mu
Beijing Information Science and Technology University
China
China
Beijing
Wenbo Qi
Beijing Information Science and Technology University
China
China
Beijing
Shaohua Chen
Beijing Information Science and Technology University
China
China
Beijing
Haoru Li
Beijing University of Posts and Telecommunications
China
China
Beijing
References
1. J. A. Cayuela, J. F. Garcia-Martin, LWT – Food Sci. Technol., 88, 103–108 (2018).
2. D. Kim, M. H. Choi, H. J. Shin, Agriculture, 11, 135 (2021).
3. D. C. Leite, A. A. P. Correa, L. C. Cunha, K. M. G. de Lima, C. D. M. de Morais, V. F. Vianna, G. Teixeira, A. O. Di Mauro, S. H. Uneda-Trevisoli, J. Food Compos. Anal., 91, 103536 (2020).
4. B. Abu Izneid, M. I. Fadhel, T. Al-Kharazi, M. Ali, S. Miloud, J. Food Sci. Technol., 51, 3244–3252 (2012).
5. C. Hartmann, M. Elsner, R. Niessner, N. P. Ivleva, Appl. Spectrosc., 74, 193–203 (2020).
6. L. Mandrile, S. Rotunno, L. Miozzi, A. M. Vaira, A. M. Giovannozzi, A. M. Rossi, E. Noris, Anal. Chem., 91, 9025–9031 (2019).
7. D. R. Zhang, H. B. Pu, L. J. Huang, D. W. Sun, Trends Food Sci. Technol., 109, 690–701 (2021).
8. X. L. Li, C. J. Sun, L. B. Luo, Y. He, Sci. Rep., 5, 15729 (2015).
9. Y. Abe, R. Shikaku, I. Nakai, J. Archaeolog. Sci. Rep., 17, 212–219 (2018).
10. C. Gurin, M. Mazzuca, J. G. Otero, M. S. Maier, Archaeolog. Anthrop. Sci., 13, 54 (2021).
11. O. Petrova, D. Pankin, A. Povolotckaia, E. Borisov, T. Krivul'ko, N. Kurganov, A. Kurochkin, J. Cult. Herit., 37, 233–237 (2019).
12. D. Cosano, D. Esquivel, C. M. Costa, C. Jimenez-Sanchidrian, J. R. Ruiz, Spectrochim. Acta, A, 214, 139–145 (2019).
13. J. Jendeberg, P. Thunberg, M. Liden, Urolithiasis, 49, 41–49 (2021).
14. S. A. Lee, H. C. Cho, H. C. Cho, IEEE ACCESS, 9, 51847–51854 (2021).
15. G. H. Lian, Y. Peng, J. He, J. Yi, Y. N. Yin, X. W. Liu, F. Zeng, Results Phys., 22, 103912 (2021).
16. M. Gimnez, J. Palanca, V. Botti, Neurocomputing, 378, 315–323 (2020).
17. W. Huang, M. Huang, Int. J. Simulation and Process Modelling, 15, 120 (2020).
18. Y. F. Li, X. Y. Feng, Y. D. Liu, X. C. Han, Sci. Rep., 11, 16618 (2021).
19. S. Lingwal, K. K. Bhatia, M. S. Tomer, Multimedia Tools Appl., 80, 35441–35465 (2021).
20. K. L. Xu, D. W. Feng, H. B. Mi, B. Q. Zhu, D. Z. Wang, L. L. Zhang, H. X. Cai, S. W. Liu, Adv. Multimedia Inform. Proc., 11166, 14–23 (2018).
21. T. Hirasawa, K. Aoyama, T. Tanimoto, S. Ishihara, S. Shichijo, T. Ozawa, T. Ohnishi, M. Fujishiro, K. Matsuo, J. Fujisaki, T. Tada, Gastric Cancer, 21, 653–660 (2018).
22. Y. Wang, T. T. Mu, Y. G. Li, W. B. Qi, S. H. Chen, Anal. Lett., 54, 2423–2430 (2021).
23. M. Kazemzadeh, C. L. Hisey, K. Zargar-Shoshtari, W. L. Xu, N. G. R. Broderick, Opt. Commun., 510, 127977 (2022).
24. F. L. Yue, C. Chen, Z. W. Yan, C. Chen, Z. Q. Guo, Z. X. Zhang, Z. Y. Chen, F. B. Zhang, X. Y. Lv, Photodiagn. Photodyn. Ther., 32, 101923 (2020).
25. M. Jermyn, J. Desroches, J. Mercier, M. A. Tremblay, K. St-Arnaud, M. C. Guiot, K. Petrecca, F. Leblond, J. Biomed. Opt., 21, 094002 (2016).
26. J. Liu, M. Osadchy, L. Ashton, M. Foster, C. J. Solomon, S. J. Gibson, Analyst, 142, 4067–4074 (2017).
27. D. Y. Ma, L. W. Shang, J. L. Tang, Y. L. Bao, J. J. Fu, J. H. Yin, Spectrochim. Acta, A, 256, 119732 (2021).
28. Y. Zhao, S. Tian, L. Yu, Z. Zhang, W. Zhang, J. Appl. Spectrosc., 88, 441–451 (2021).
Review
For citations:
Mu T., Qi W., Chen Sh., Li H. Raman Spectrum Classification of Cinnabar and Cinnabar-Clam White Based on Data Augmentation and Convolutional Neural Network. Zhurnal Prikladnoii Spektroskopii. 2023;90(2):349-1 - 349-6.
Views: 142
Email this article 