Abstract：As a typical optical detective method, Raman spectroscopy has been widely used in many fields such as biological analysis, disease diagnosis and molecular recognition due to its unique non-invasive, fast, in-situ and extremely high specificity. The fingerprint characteristics of Raman Spectroscopy make it an important tool in the biomedical field. However, many problems greatly influence the application of this technology, including weak Raman scattering signal, the large dependence on analysts for data processing and analysis, and the low capabilities of automated processing. It is usually difficult to obtain an effective and stable Raman spectrum of various interference factors, including the noise from experimental equipment or environment and spontaneous fluorescence of the biological sample. All kinds of random noises will interfere with identifying fingerprint peak information in Raman spectroscopy and increase the difficulty of Raman feature extraction, so denoising is an important task in the preprocessing of Raman Spectroscopy analysis. In this paper, using the backpropagation algorithm and considering the characteristics of the data, we built the noise judgment and denoising neural network model respectively, based on the linear difference between the ideal spectral segment and the noisy spectral segment. For the simulation experiments, the data of Raman spectra are composed of a series of randomly generated mathematical models of the Lorentz peak. Different intensities of noises were added to the randomly generated single Raman spectrum and 100 groups of Raman spectra, respectively. In addition, the new method has been compared with the classic sliding window average method, Savitzky-Golay filter method, Fourier transforms, and wavelet threshold transform method. Using the Root mean square error and Signal to noise ratio indicators for analysis, the results show that all methods can complete the denoising task under low noise, but the denoising effect of the sliding window average method is obviously reduced at the edge of the spectrum. With the increase of the noise signal, the denoising performance of the sliding window average method, S-G filtering method, and Fourier transform method have all decreased significantly. Overall, the denoising method based on a backpropagation neural network is better than the Fourier transform method, sliding average window method, and S-G filter method. This method avoids complex parameter optimization settings and at the same time, obtains the denoising effect that is almost the same as the optimal wavelet transform method. It greatly simplifies the parameter setting and is more suitable for the automated denoising of the Raman spectrum.
王 忠，万冬冬，单 闯，李月娥，周庆国. 基于反向传播神经网络的拉曼光谱去噪方法[J]. 光谱学与光谱分析, 2022, 42(05): 1553-1560.
WANG Zhong, WAN Dong-dong, SHAN Chuang, LI Yue-e, ZHOU Qing-guo. A Denoising Method Based on Back Propagation Neural Network for
Raman Spectrum. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1553-1560.
[1] Cicchi R, Cosci A, Rossari S, et al. J. Biophotonics, 2014. 7(1-2): 86.
[2] Lin K, Zheng W, Lim C M, et al. Biomed. Opt. Express, 2016. 7(9): 3705.
[3] McKinney S M, Sieniek M, Godbole V, et al. Nature, 2020，577(7788): 89.
[4] Schleusener J, Gluszczynska P, Reble C, et al. Exp. Dermatol., 2015, 24(10): 767.
[5] LIANG Hao-yue, CHEN Xue-lian, YANG Wan-zhu, et al(梁昊岳，程雪莲，杨晚竹，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020，40(12): 3670.
[6] Tian Y，Burch K S. Appl. Spectrosc., 2016, 70(11): 1861.
[7] Xi Y, Li Y, Duan Z, et al. Appl. Spectrosc., 2018, 72(12): 1752.
[8] Leon-Bejarano F, Mendez M O, Ramirez-Elias M G, et al. Appl. Spectrosc., 2019, 73(12): 1436.
[9] Zhao X Y, Liu G Y, Sui Y T, et al. Spectrochim. Acta A: Mol. Biomol. Spectrosc., 2021, 250: 119374.
[10] Sun P, Shi Y, Li L, et al. International Conference on Optical Instruments and Technology-Optoelectronic Imaging/Spectroscopy and Signal Processing Technology, Beijing, 2019.
[11] Xie Junyuan, Chen Enhong. Proceedings of the 25th International Conference on Neural Information Processing Systems, 2012.
[12] Xu L, Ren J S J, Liu C, et al. Proceedings of 27th International Conference on Neural Information Processing Systems, 2014. 1790.
[13] Piriyatharawet T, Kumwilaisak W, Lasang P. 18th International Symposium on Communications and Information Technologies (ISCIT), 2018. 90.
[14] Kosko B, Audhkhasi K, Osoba O. Neural Networks, 2020, 129: 359.
[15] Kim J, Kwon D, Woo S Y, et al. Neurocomputing, 2021, 428: 153.
[16] Chen C, Wang H, Yuan F, et al. Neural Computing and Applications, 2020, 32(14): 10435.
