Abstract
Aiming at the problem of wine identification, the odor information of 7 kinds of wine was collected through the electronic nose, the LightGBM algorithm was used to learn the odor characteristics of the wine, and the TPE hyperparameter optimization algorithm is used to adaptively optimize the HyperGB parameter of the LightGBM algorithm. Verification is an indicator to evaluate the performance of the model. The experimental results showed that the discrimination model established by LightGBM had a 96.62% accuracy rate for wine samples, which was superior to traditional support vector machines, random forests, and neural networks. It verifies the superiority of LightGBM in wine variety identification and provides wine identification a fast, reliable and effective analysis method is also suggested, and more excellent algorithms can be introduced into the field of wine smell data mining machines.
Publication Date
5-28-2020
First Page
76
Last Page
79
DOI
10.13652/j.issn.1003-5788.2020.05.014
Recommended Citation
Miao, QIAO; Lei, ZHANG; and Fang-lin, MU
(2020)
"Research on discriminating wine varieties based on electronic nose and LightGBM algorithm,"
Food and Machinery: Vol. 36:
Iss.
5, Article 14.
DOI: 10.13652/j.issn.1003-5788.2020.05.014
Available at:
https://www.ifoodmm.cn/journal/vol36/iss5/14
References
[1] 郑青.不同陈酿年份、葡萄品种及葡萄产地葡萄酒香气成分的研究[D].南昌:南昌大学,2015:3-8.
[2] 陶永胜,彭传涛.中国霞多丽干白葡萄酒香气特征与成分关联分析[J].农业机械学报,2012,43(3):130-139.
[3] 陶永胜,刘吉彬,兰圆圆,等.人工贵腐葡萄酒香气的仪器分析与感官评价[J].农业机械学报,2016,47(2):270-279,315.
[4] 金新宇,吴时敏,黄明泉,等.2013—2018年进口葡萄酒市场及理化指标分析[J].粮食与油脂,2019,32(10):77-81.
[5] 张振,李臻锋,宋飞虎,等.电子鼻结合化学计量法用于检测黄酒酒龄[J].食品与机械,2015,31(3):57-61,118.
[6] 许春华,肖作兵,牛云蔚,等.电子鼻和电子舌在果酒风味分析中的应用[J].食品与发酵工业,2011,37(3):163-167.
[7] 刘弈彤,刘期成,李红娟,等.烟台产区不同品种干红葡萄酒香气差异分析[J].酿酒科技,2019(8):40-47.
[8] 宫雪.电子鼻和电子舌对葡萄酒的感官评价分析研究[D].杨凌:西北农林科技大学,2014:17-58.
[9] 高亚男,王文倩,王建新.集成模糊层级划分的LightGBM食品安全风险预警模型:以肉制品为例[J/OL].食品科学.[2020-04-01].http://kns.cnki.net/kcms/detail/11.2206.TS.20200330.1547.077.html.
[10] 马晓君,沙靖岚,牛雪琪.基于LightGBM算法的P2P项目信用评级模型的设计及应用[J].数量经济技术经济研究,2018,35(5):144-160.
[11] 周挺,杨军,周强明,等.基于改进LightGBM的电力系统暂态稳定评估方法[J].电网技术,2019,43(6):1 931-1 940.
[12] 张渊,冯聪,李开源,等.ICU患者急性肾损伤发生风险的LightGBM预测模型[J].解放军医学院学报,2019,40(4):316-320.
[13] FAN Jun-liang,MA Xin,WU Li-feng,et al.Light gradient boosting machine:An efficient soft computing model for estimating daily reference evapotranspiration with local and external meteorological data[J].Agricultural Water Management,2019,DOI:10.1016/j.agwat.2019.105758.
[14] LI Qiang,GU Yu.Classification of multiple Chinese liquors by means of a QCM-based E-Nose and MDS-SVM classifier[J].Sensors,2017,17(2):272-286.
[15] LI Qiang,GU Yu,WANG Nan-fei.Application of random forest classifier by means of a QCM-Based E-Nose in the identification of Chinese liquor flavors[J].IEEE Sensors Journal,2017,17(6):1 788-1 794.
[16] LIU Hui-xiang,LI Qiang,YAN Bin,et al.Bionic electronic nose based on MOS sensors array and machine learning algorithms used for wine properties detection[J].Sensors,2018,19(1):1-11.
[17] 崔佳旭,杨博.贝叶斯优化方法和应用综述[J].软件学报,2018,29(10):3 068-3 090.
[18] 李斌,王卫星.NCA萃取和贝叶斯优化调参对分类模型的改进[J].计算机应用与软件,2019,36(8):281-287.