• EI
  • Scopus
  • 食品科学与工程领域高质量科技期刊分级目录第一方阵T1
  • DOAJ
  • EBSCO
  • 北大核心期刊
  • 中国核心学术期刊RCCSE
  • JST China
  • FSTA
  • 中国精品科技期刊
  • 中国农业核心期刊
  • CA
  • WJCI
  • 中国科技核心期刊CSTPCD
  • 中国生物医学SinoMed
中国精品科技期刊2020
缪楠,张鑫,王首程,等. 基于电子舌和EEMD-WOA-LSSVM模型的红酒贮藏年限区分[J]. 食品工业科技,2021,42(19):275−282. doi: 10.13386/j.issn1002-0306.2020120105.
引用本文: 缪楠,张鑫,王首程,等. 基于电子舌和EEMD-WOA-LSSVM模型的红酒贮藏年限区分[J]. 食品工业科技,2021,42(19):275−282. doi: 10.13386/j.issn1002-0306.2020120105.
MIAO Nan, ZHANG Xin, WANG Shoucheng, et al. Identification of Red Wine Storage Years based on Electronic Tongue and EEMD-WOA-LSSVM Model[J]. Science and Technology of Food Industry, 2021, 42(19): 275−282. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2020120105.
Citation: MIAO Nan, ZHANG Xin, WANG Shoucheng, et al. Identification of Red Wine Storage Years based on Electronic Tongue and EEMD-WOA-LSSVM Model[J]. Science and Technology of Food Industry, 2021, 42(19): 275−282. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2020120105.

基于电子舌和EEMD-WOA-LSSVM模型的红酒贮藏年限区分

Identification of Red Wine Storage Years based on Electronic Tongue and EEMD-WOA-LSSVM Model

  • 摘要: 为了实现对不同贮藏年限的红酒进行客观的辨别分析,提出一种采用电子舌结合集合经验模态分解(Ensemble empirical modal decomposition, EEMD)、鲸鱼算法(whale optimization algorithm, WOA)和最小二乘支持向量机(least square support vector machine, LSSVM)组合模型的区分方法。首先采用电子舌对4种不同贮藏年限红酒的“特征图谱”进行信息采集;然后利用EEMD对原始信号进行分解,提取分解后的本征模态函数奇异谱熵和希尔伯特边际谱作为特征数据;最后,采用鲸鱼算法优化最小二乘支持向量机建立红酒贮藏年限分析模型。结果表明,EEMD-WOA-LSSVM组合模型对不同贮藏年限的红酒的分类准确率、精确率、召回率、F1-score和Kappa系数分别达到97.5%、97.75%、97.5%、0.98和0.97,其区分能力优于GA-LSSVM、PSO-LSSVM和SVM模型。该研究可为红酒贮藏年限区分提供一种新的研究思路和技术手段。

     

    Abstract: In order to achieve identification of different storage years of red wine, an electronic tongue identification method based on ensemble empirical modal decomposition(EEMD), whale optimization algorithm (WOA) and least square support vector machine (LSSVM) was proposed. The voltammetry electronic tongue was used to collect the "fingerprint" information of the aged red wine with four storage years, and then the ensemble empirical modal decomposition was used to carry out the original signal of the electronic tongue. The scale decomposition obtained a set of intrinsic mode functions, and finally obtained its singular spectral entropy and Hilbert marginal spectrum as feature data. Finally, the whale optimization algorithm was used to optimize the parameters of the least square support vector machine, and the analysis model of red wine storage age was established. The experimental results showed that the accuracy, precision, recall, F1-score and Kappa coefficient of EEMD-WOA-LSSVM model were 97.5%, 97.75%, 97.5%, 0.98 and 0.97, respectively, which had discrimination better performance for storage year of red wine compared with SVM, GA-LSSVM and PSO-LSSVM. This research can provide a technical reference and research approach of red wine storage year.

     

/

返回文章
返回