Raman Spectra Based on QPSO-MLSSVM Algorithm to Detect the Content of Four Components Blent Oil
ZHANG Yan-jun, ZHANG Fang-cao, FU Xing-hu*, XU Jin-rui
School of Information Science and Engineering, The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province, Yanshan University,Qinhuangdao 066004, China
摘要: 提出了一种运用量子粒子群(quantum-behaved particle swarm optimization,QPSO)算法优化多输出最小二乘支持向量机(multi-output least squares support vector machine,MLSSVM)的新混合优化算法。该算法结合激光拉曼光谱技术可实现对四组分食用调和油中花生油、芝麻油、葵花油和大豆油的快速定量鉴别。采用基线校正去除背景荧光,结合Savitzky-Golay Filters光谱平滑法对原始拉曼光谱进行预处理。构建基于QPSO-MLSSVM混合优化算法的定量分析模型,并采用20个组分组成的预测集对其进行模型校验。实验结果表明,基于QPSO-MLSSVM混合优化算法的定量分析模型对于四组分调和油的预测效果良好,均方差(mean square error, MSE)为0.0241,低于0.05,各油分预测相关系数均高于98%。研究结果充分表明, 应用激光拉曼光谱技术结合QPSO-MLSSVM算法,对四组分调和油中各油分进行快速定量检测可行,具备较强的自适应能力和良好的预测精度,可以满足多组分调和油的成分鉴别。
关键词:拉曼光谱;食用调和油;量子粒子群算法;最小二乘支持向量机;定量检测模型
Abstract:This paper presents a new hybrid optimization algorithm based on the multi-output least squares support vector machine (MLSSVM) which is optimized by quantum-behaved particle swarm optimization (QPSO). The rapid quantitative identification for the peanut oil,sesame oil, sunflower oil and soybean oil in the four - component edible blending oil can be realized with the algorithm combined with laser Raman spectroscopy. The background fluorescence was removed by baseline correction, and Savitzky-Golay filters spectral smoothing method is used for the pretreation of original Raman spectra. The quantitative analysis model based on QPSO-MLSSVM hybrid optimization algorithm is established, and the prediction set composed of 20 components is used to verify the model. The experimental result shows that it is effective for the prediction of four-component blending oil with the quantitative analysis model based on QPSO-MLSSVM hybrid optimization algorithm, and the Mean Square Error (MSE) is 0.024 1, which is less than 0.05, the correlation coefficients of each component were above 98%. The results show that it is feasible to detect the content of each oil of four-component blending oil by laser Raman spectroscopy combined with QPSO-MLSSVM algorithm, it has strong adaptive ability and good prediction accuracy that can satisfy the multi-component mixed oil component identification.
Key words:Raman spectroscopy; Edible blend oil; Quantum particle swarm optimization (QPSO); Least squares support vector machine (SVM); Quantitative detection model
张燕君,张芳草,付兴虎,徐金睿. 基于QPSO-MLSSVM算法的拉曼光谱检测四组分调和油含量[J]. 光谱学与光谱分析, 2018, 38(05): 1437-1443.
ZHANG Yan-jun, ZHANG Fang-cao, FU Xing-hu, XU Jin-rui. Raman Spectra Based on QPSO-MLSSVM Algorithm to Detect the Content of Four Components Blent Oil. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(05): 1437-1443.
[1] ZHANG Zhuo, QIAN Jun-lei(张 茁,钱俊磊). Chinese Science and Technology(中国科技技术), 2013,(9): 104.
[2] DENG Jian-ping, LI Hao, YANG Dong-yan, et al(邓建平,李 浩,杨冬燕,等). Journal of Food Safety & Quality(食品安全质量检测学报), 2014,(9): 2689.
[3] LIU Yan-de, JIN Tan-tan, WANG Hai-yang(刘燕德,靳昙昙,王海洋). Optics and Precision Engineering(光学精密工程), 2015, 23(9): 2490.
[4] TAO Chun-xian, RUAN Jun, SHU Shun-ming, et al(陶春先,阮 俊,舒顺明,等). Chinese Journal of Lasers(中国激光), 2016,(1): 213.
[5] ZHAO Yan-tao, SHAN Ze-yu, CHANG Yue-jin, et al(赵彦套,单泽宇,常跃进,等). Chinese Journal of Scientific Instrument(仪器仪表学报), 2017, 38(2): 489.
[6] ZHANG Yi, CHEN Guo-qing, ZHU Chun, et al(张 毅,陈国庆,朱 純,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2016, 36(12): 3978.
[7] XU Hui-rong, XU Wen-hao, CHEN Hua-rui, et al(徐惠荣,徐文豪,陈华瑞,等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报),2014, 45(2): 194.
[8] ZHUANG Jia-xiang, JIANG Hai-yan, LIU Lei-lei, et al(庄嘉祥,姜海燕,刘蕾蕾,等). Scientia Agricultura Sinica(中国农业科学), 2013, 46(11): 2220.
[9] Sun Jun, Wua Xiaojun, Vasile Paladeb, et al. Information Sciences, 2012, 193(15): 81.
[10] HUANG Guo-quan, YOU Xin-hua(黄国权,尤新华). Laser Journal(激光杂志),2015, 36(3): 96.
[11] GAO Guo-ming, LI Xue, QIN Zong-ding, et al(高国明,李 雪,覃宗定,等). Acta Optica Sinica(光学学报), 2013, 33(2): 258.
[12] Seong Joon Baeka, Aaron Parka, Jinyoung Kima, et al. Chemometrics and Intelligent Laboratory Systems, 2009, 98(1): 24.