Raman Spectra Combined with PSO-LSSVM Algorithm for Detecting the Components in Ternary Blended Edible Oil
ZHANG Yan-jun, HE Bao-dan, FU Xing-hu*, XU Jin-rui, ZHOU Kun-peng
School of Information Science and Engineering, The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province, Yanshan University, Qinhuangdao 066004, China
Abstract：The paper presents a method which combines the Raman spectrum and the least square support vector machine (LSSVM) based on particle swarm optimization (PSO) to detect the content of three components of edible blend oil rapidly and quantitatively. In this paper, three components of edible oil were investigated. The characteristic peak intensity of Raman spectra was extracted by four pretreatments of the spectra. Then in the training samples, the characteristic peak intensity and the percentage of mixed oil samples were used as the input values and the output values of the regression analysis model. The mathematical models of LSSVM and PSO-LSSVM were established after different pretreatments. The predictive ability of the model was analyzed by the correlation coefficient and mean square error in the test samples. The traditional LSSVM algorithm for nonlinear modeling has many issues, such as its kernel parameter σ and the regularization parameter γ have great influences on the learning model and generalization ability. The fitting precision and generalization ability of the model are dependent on its related parameters, and the time consuming is too long while the optimal step size is too little; however, the global optimal values are hardly to get while the optimization step size is large. Yet, the PSO-LSSVM algorithm has the PSO algorithm advantages of fast convergence and global search capability, which can overcome the problems of time consuming and blindness in LSSVM algorithm. So the kernel parameters σ and γ of LSSVM algorithm are optimized by Global optimization ability and fast convergence characteristics of PSO algorithm. In the quantitative analysis of the three components of edible blend oil, the validation set correlation coefficients of the model for soybean oil, peanut oil and sunflower kernel oil were 0.967 7, 0.997 2 and 0.995 3, respectively; in addition, the mean square errors were 0.054 9, 0.009 2 and 0.047 1, respectively. Compared with the LSSVM algorithm, the prediction accuracy of PSO-LSSVM model is higher and the convergence rate is faster which has been verified by the experiments. Thus, the method can detect the content of the three components of edible oil accurately.
Key words：Raman spectroscopy; Particle swarm optimization; Least square support vector machine; Blended edible oil; Quantitative detection
[1] TAN Meng-ru, LIN Hong, SHEN Chong-yu, et al(谭梦茹, 林 宏, 沈崇钰, 等). Journal of Chinese Mass Spectrometry Society(质谱学报), 2015, 36(4): 334.
[2] HE Rong, SHAN Xiao-lin, DONG Fang-yuan, et al(何 榕, 山晓琳, 董方圆, 等). Chinese Journal of Analytical Chemistry(分析化学), 2015，(9): 1377.
[3] CHEN Ting, LIU Qing-jun, WU Yan-wen, et al(陈 婷, 刘清珺, 武彦文, 等). Food Safety and Quality Detection Technology(食品安全质量检测学报), 2015，(3): 836.
[4] Boyaci I H, Uysal R S, Temiz T, et al. Biology of the Cell, 2014, 238(5): 53.
[5] YANG Jin-mei, ZHANG Hai-ming, WANG Xu, et al(杨金梅, 张海明, 王 旭, 等). Physics and Engineering, 2014, 24(4): 26.
[6] LIU Yan-de, JIN Tan-tan, WANG Hai-yang(刘燕德, 靳昙昙, 王海阳). Optics and Precision Engineering(光学精密工程), 2015, 23(9): 2490.
[7] LI Bing-ning, WU Yan-wen, WANG Yu, et al(李冰宁, 武彦文, 汪 雨，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014, 34(10): 2696.
[8] XU Jun, LU Hai-yan, SHI Gui-juan(许 君, 鲁海燕, 石桂娟). Journal of Computer Applications(计算机应用)，2015, 35(3): 668.
[9] ZHOU Xia, LIU Shan-jian(周 霞, 柳善建). Computer Measurement & Control(计算机测量与控制)，2014, 22(10): 3101.
[10] ZHOU Jin-ming, WANG Chuan-yu, HE Bang-qiang(周金明, 王传玉, 何帮强). Computer Engineering and Applications(计算机工程与应用)，2015, 51(4): 133.
[11] GONG Wen-long, YAO Jian-gang, JIN Xiao-ming(龚文龙, 姚建刚, 金小明). Journal of Electrical Engineering, 2014, 2(1): 1.
[12] Zhang Xiaofang, Qi Xiaohua, Zou Mingqiang, et al. Analytical Letters, 2011, 44(12): 2209.
