首页 > 论文 > 激光与光电子学进展 > 57卷 > 20期(pp:203001--1)

核极限学习机和激光诱导荧光技术在食用油识别中的应用

Application of Kernel Extreme Learning Machine and Laser Induction Fluorescence Technique in Edible Oil Identification

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对现有的食用油检测技术无法快速、准确地识别市售食用油的问题,提出了一种快速辨识食用油的方法。采用激光诱导荧光技术(LIF)获取油样的荧光光谱数据,然后采用主成分分析法提取光谱数据的特征信息,之后采用飞蛾-扑火优化器和核极限学习机相结合的算法建立多元分类学习模型,最后用该模型识别油样的类别。实验油样选取5种样本,每种样本采集150组荧光光谱,然后随机抽取600个样本用于学习模型的训练,剩余的150个用于测试训练好的模型。结果表明:在测试集上的平均分类准确率方面,该模型与极限学习机、反向传播神经网络相差不大,但该模型分类准确率的标准差远小于其他两种模型。这说明所建模型具有较稳定的分类性能,可以满足快速鉴别食用油的要求。

Abstract

Existing edible oil detection technology cannot quickly and accurately identify edible oils sold in markets. Hence, in this paper, we propose a quick method of identifying edible oils. Fluorescence spectrum data of oil samples were obtained using the laser induction fluorescence(LIF) technique. Principal component analysis was used to extract characteristic information. Next, a multiclassification learning model was developed through the fusion algorithm of moth-flame optimization and kernel extreme learning machine (KELM) to identify the type of oil samples. Five types of oil samples were selected for experimental purposes, and 150 groups of fluorescence spectra were collected from each sample. Next, 600 samples were randomly selected to train the learning model, and the remaining 150 samples were used to test the trained model. Experimental results show that KELM model , extreme learning machine model and back propagation neural network model have similar average classification accuracy on the test set. However, the standard deviation of KELM model is less than those of other two models. This shows that KELM model has a stable classification performance and can quickly identify edible oils.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:O657.3

DOI:10.3788/LOP57.203001

所属栏目:光谱学

基金项目:国家重点研发计划、国家安全生产重大事故防治关键技术科技项目、安徽省青年科学基金;

收稿日期:2019-12-04

修改稿日期:2020-01-09

网络出版日期:2020-10-01

作者单位    点击查看

周孟然:安徽理工大学电气与信息工程学院, 安徽 淮南 232001
王锦国:安徽理工大学电气与信息工程学院, 安徽 淮南 232001
宋红萍:安徽理工大学电气与信息工程学院, 安徽 淮南 232001
胡锋:安徽理工大学电气与信息工程学院, 安徽 淮南 232001
来文豪:安徽理工大学电气与信息工程学院, 安徽 淮南 232001
卞凯:安徽理工大学电气与信息工程学院, 安徽 淮南 232001

联系人作者:王锦国(wangjinguo1023@163.com)

备注:国家重点研发计划、国家安全生产重大事故防治关键技术科技项目、安徽省青年科学基金;

【1】Luo J G. Determination of F-2 toxin in corn oil by immune-affinity column purification and HPLC [J]. China Oils and Fats. 2018, 43(5): 88-91.
罗建光. 免疫亲和柱净化-高效液相色谱法测定玉米油中F-2毒素含量的研究 [J]. 中国油脂. 2018, 43(5): 88-91.
Luo J G. Determination of F-2 toxin in corn oil by immune-affinity column purification and HPLC [J]. China Oils and Fats. 2018, 43(5): 88-91.
罗建光. 免疫亲和柱净化-高效液相色谱法测定玉米油中F-2毒素含量的研究 [J]. 中国油脂. 2018, 43(5): 88-91.

【2】Qiu R F, Huang Z P, Wang L L. Analysis of fatty acid composition in cottonseed by gas chromatography with on-line pyrolytic methylation [J]. Chinese Journal of Chromatography. 2018, 36(9): 925-930.
邱若风, 黄忠平, 王丽丽. 在线热辅助甲基化-气相色谱法分析棉籽仁中的脂肪酸组成 [J]. 色谱. 2018, 36(9): 925-930.
Qiu R F, Huang Z P, Wang L L. Analysis of fatty acid composition in cottonseed by gas chromatography with on-line pyrolytic methylation [J]. Chinese Journal of Chromatography. 2018, 36(9): 925-930.
邱若风, 黄忠平, 王丽丽. 在线热辅助甲基化-气相色谱法分析棉籽仁中的脂肪酸组成 [J]. 色谱. 2018, 36(9): 925-930.

【3】Zuo Q Q, Sun J M, Wang Q Y, et al. Optimization of identification model of adulterated peanut oil based on near infrared spectroscopy [J]. The Food Industry. 2019, 40(4): 318-322.
左倩倩, 孙金梦, 王倩玉, 等. 基于近红外光谱的掺伪花生油鉴别模型优化 [J]. 食品工业. 2019, 40(4): 318-322.
Zuo Q Q, Sun J M, Wang Q Y, et al. Optimization of identification model of adulterated peanut oil based on near infrared spectroscopy [J]. The Food Industry. 2019, 40(4): 318-322.
左倩倩, 孙金梦, 王倩玉, 等. 基于近红外光谱的掺伪花生油鉴别模型优化 [J]. 食品工业. 2019, 40(4): 318-322.

【4】Yan H, Zhang J X, Gao J X, et al. Towards improvement in prediction of iodine value in edible oil system based on chemometric analysis of portable vibrational spectroscopic data [J]. Scientific Reports. 2018, 8(1): 14729.Yan H, Zhang J X, Gao J X, et al. Towards improvement in prediction of iodine value in edible oil system based on chemometric analysis of portable vibrational spectroscopic data [J]. Scientific Reports. 2018, 8(1): 14729.

【5】Bi X, Jin Y B, Li S F, et al. Rapid and sensitive determination of fatty acids in edible oil by liquid chromatography-electrospray ionization tandem mass spectrometry [J]. Science China Chemistry. 2014, 57(3): 447-452.

【6】Chen Y, Luo Q S, Wang J, et al. Rapid identification and characterization of recovered edible oil, based on Raman and near-infrared spectroscopy[C]//Proceedings of the 2018 3rd International Conference on Modelling. Paris,. France: , 2018, 4.

【7】Hu F, Zhou M R, Yan P C, et al. Influence of temperature on laser induced fluorescence spectroscopy of mine goaf water [J]. Spectroscopy and Spectral Analysis. 2018, 38(8): 2583-2587.
胡锋, 周孟然, 闫鹏程, 等. 温度对矿井老空水激光诱导荧光光谱的影响 [J]. 光谱学与光谱分析. 2018, 38(8): 2583-2587.

【8】Zhou M R, Song Q, Wang Y, et al. Application of LIF technology and XGBoost algorithm in counterfeit wine recognition [J]. Applied Laser. 2019, 39(1): 130-135.
周孟然, 宋奇, 王亚, 等. LIF技术和XGBoost算法在假酒识别中的应用 [J]. 应用激光. 2019, 39(1): 130-135.

【9】Lai W H, Zhou M R, Wang Y, et al. Application of counterfeit liquor recognition based on deep learning and laser induced fluorescence [J]. Laser & Optoelectronics Progress. 2018, 55(4): 043001.
来文豪, 周孟然, 王亚, 等. 深度学习与激光诱导荧光在假酒识别中的应用 [J]. 激光与光电子学进展. 2018, 55(4): 043001.

【10】Zhou M R, Li D T, Hu F, et al. Research of the AdaBoost arithmetic in recognition and classifying of mine water inrush sources fluorescence spectrum [J]. Spectroscopy and Spectral Analysis. 2019, 39(2): 485-490.
周孟然, 李大同, 胡锋, 等. AdaBoost算法在矿井突水水源的荧光光谱识别中的研究 [J]. 光谱学与光谱分析. 2019, 39(2): 485-490.

【11】Wang Y, Zhou M R, Yan P C, et al. A rapid identification model of mine water inrush based on extreme learning machine [J]. Journal of China Coal Society. 2017, 42(9): 2427-2432.
王亚, 周孟然, 闫鹏程, 等. 基于极限学习机的矿井突水水源快速识别模型 [J]. 煤炭学报. 2017, 42(9): 2427-2432.

【12】Wang Y, Zhou M R, Yan P C, et al. Identification of coalmine water inrush source with PCA-BP model based on laser-induced fluorescence technology [J]. Spectroscopy and Spectral Analysis. 2017, 37(3): 978-983.
王亚, 周孟然, 闫鹏程, 等. PCA-BP模型在判别基于LIF技术煤矿突水水源的应用 [J]. 光谱学与光谱分析. 2017, 37(3): 978-983.

【13】Mirjalili S. Moth-flame optimization algorithm: a novel nature-inspired heuristic paradigm [J]. Knowledge-Based Systems. 2015, 89: 228-249.

【14】Deng C W, Huang G B, Xu J, et al. Extreme learning machines: new trends and applications [J]. Science China Information Sciences. 2015, 58(2): 1-16.

【15】Huang G B, Zhou H M, Ding X J, et al. Extreme learning machine for regression and multiclass classification [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B. 2012, 42(2): 513-529.Huang G B, Zhou H M, Ding X J, et al. Extreme learning machine for regression and multiclass classification [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B. 2012, 42(2): 513-529.

引用该论文

Zhou Mengran,Wang Jinguo,Song Hongping,Hu Feng,Lai Wenhao,Bian Kai. Application of Kernel Extreme Learning Machine and Laser Induction Fluorescence Technique in Edible Oil Identification[J]. Laser & Optoelectronics Progress, 2020, 57(20): 203001

周孟然,王锦国,宋红萍,胡锋,来文豪,卞凯. 核极限学习机和激光诱导荧光技术在食用油识别中的应用[J]. 激光与光电子学进展, 2020, 57(20): 203001

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF