Research of Parameter Optimization of Preprocessing and Feature Extraction for NIRS Qualitative Analysis Based on PSO Method
LI Hao-guang1, 2, YU Yun-hua1, 2, PANG Yan1, SHEN Xue-feng1, 2
1. College of Mechanical and Control Engineering, Shandong Institute of Petrochemical and Chemical Technology，Dongying 257061，China
2. New Energy College，China University of Petroleum(East China)，Dongying 257061，China
Abstract：In the qualitative analysis of near-infrared spectroscopy, preprocessing and feature extraction are indispensable to achieve good recognition results. Preprocessing is mainly to eliminate the influence of various interference factors on the spectral data. The common preprocessing methods include smoothing, first-order derivatives, normalization, etc., while the feature extraction methods can eliminate the irrelevant information in the data and retain the effective information. The common feature extraction methods include partial least squares, principal component analysis, linear discriminant analysis, etc. Different preprocessing and feature extraction methods have different characteristics. When building a qualitative analysis model, it is often difficult to achieve ideal results by using a single preprocessing or feature extraction method. It is often necessary to use a combination of multiple preprocessing and feature extraction methods to improve the model’s performance. Variable parameters such as feature extraction dimension need to be set in each preprocessing and feature extraction process. These variable parameters have an important impact on the performance of the model. Therefore, multiple parameters need to be determined in multiple preprocessing and multiple feature extraction methods. In practice, the trial and error method is often used to find the optimal value of each parameter. In order to get the optimal value of one of the parameters, it is necessary to fix the other parameter values according to experience. Then a parameter to be optimized is substituted into the NIR qualitative analysis model for trial and error to get the corresponding parameter value of the optimal recognition rate of the model, and take it as the optimal value. After several parameters to be optimized are obtained one by one by trial and error method, the combination of parameters is set into the qualitative analysis model, and finally, qualitative identification is carried out. However, the combination of parameters obtained by the trial and error method is difficult to guarantee the optimal optimal solution. In addition to the trial and error method, the multiple loops nesting method can also be used to obtain the optimal combination of parameters in the preprocessing and feature extraction of the near qualitative analysis model. However, this method consumes a lot of computer memory and computing time and has the disadvantage of low efficiency. In this paper, a method based on particle swarm optimization (PSO) is proposed to optimize the parameters of pre-processing and feature extraction of the NIR qualitative analysis model, which can quickly obtain the optimal parameter combination of pre-processing and feature extraction and ensure that the qualitative analysis model with the optimal parameter combination has the best recognition performance. The experimental results show that the method is effective.
李浩光，于云华，逄 燕，沈学锋. 粒子群算法的近红外光谱定性分析预处理及特征提取参数优化方法研究[J]. 光谱学与光谱分析, 2021, 41(09): 2742-2747.
LI Hao-guang, YU Yun-hua, PANG Yan, SHEN Xue-feng. Research of Parameter Optimization of Preprocessing and Feature Extraction for NIRS Qualitative Analysis Based on PSO Method. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(09): 2742-2747.
[1] Chu X L, Shi Y Y, Chen B, et al. Journal of Instrumental Analysis，2019, 38(5): 603.
[2] YAN Yan-lu, CHEN Bin, ZHU Da-zhou(严衍禄, 陈 斌，朱大洲). Near Infrared Spectroscopy Analytical—Principles, Technology and Application(近红外光谱分析的原理、技术与应用). Beijing: China Light Industry Press(北京: 中国轻工业出版社), 2007.
[3] Mendes T O, Junqueira G M A, Porto B L S，et al. Journal of Raman Spectroscopy, 2016, 47(6)：692.
[4] Konstantinos E Parsopoulos, Michael N Vrahatis. Particle Swarm Optimization and Intelligence. 1st ed. Hershey, New York: Information Science Reference, 2010.
[5] Qin H, Ma J Y, Chen S J, et al. Infrared Technology，2015, 1(37): 78.
[6] LI Hao-guang, LI Wei-jun, QIN Hong, et al(李浩光，李卫军，覃 鸿，等). Transactions of the Chinese Society of Agricultural Machinery(农业机械学报)，2016, 47(6): 259.
[7] LI Hao-guang, LI Wei-jun, QIN Hong, et al(李浩光，李卫军，覃 鸿，等). Transactions of the Chinese Society of Agricultural Machinery(农业机械学报), 2017，(S1): 422.
[8] Kurtulmus F, Alibas I, Kavdir I. Int. J. Agric. Biol. Eng.，2016，9(1): 51.
[9] Le Cun Y, Bengio Y, Hinton G. Nature: Deep Learning，2015，521(7553): 436.
