|本期目录/Table of Contents|

[1]徐赛,张倩倩.基于特征融合与冗余剔除的普洱茶种类电子鼻识别方法[J].江苏农业科学,2020,48(16):222-227.
 Xu Sai,et al.Electronic nose recognition method for Puer tea types based on feature fusion and redundancy removal[J].Jiangsu Agricultural Sciences,2020,48(16):222-227.
点击复制

基于特征融合与冗余剔除的普洱茶种类电子鼻识别方法(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第48卷
期数:
2020年第16期
页码:
222-227
栏目:
贮藏加工与检测分析
出版日期:
2020-08-20

文章信息/Info

Title:
Electronic nose recognition method for Puer tea types based on feature fusion and redundancy removal
作者:
徐赛12 张倩倩2
1.广东省农业科学院农产品公共监测中心,广东广州 510640; 2.华南农业大学工程学院,广东广州 510640
Author(s):
Xu Saiet al
关键词:
普洱茶种类电子鼻特征融合冗余剔除
Keywords:
-
分类号:
TP212.9
DOI:
-
文献标志码:
A
摘要:
为更好地维护普洱茶的产业秩序,拟探究1种用电子鼻识别普洱茶种类的方法。采用电子鼻对7种普洱古树茶(拨玛、贺开、老班章、老曼峨、帕莎、那卡和易武)和1种普洱台地茶(易武)进行电子鼻采样后,先用线性判别分析(LDA)初步探究电子鼻传感器响应不同特征(最大值、平均值、平均微分值、稳定值和融合特征)对普洱茶种类的分类效果(将传感器R1~R10的特征按照最大值、平均值、平均微分值、稳定值的重复顺序进行提取,用编号1~40表示),再用简单相关分析(SCA)和互信息理论(MIT)结合偏最小二乘回归(PLSR)进行分析,揭示并剔除融合特征中的冗余特征,对去冗余数据进行归一化处理后,通过LDA、k-最近邻分析(KNN)和概率神经网络(PNN)建立普洱茶种类的识别模型。结果表明,多特征融合比单一特征提取的LDA普洱茶种类识别结果更佳,但识别精度仍有待提高。剔除冗余特征前,PLSR对普洱茶种类识别训练集、测试集的R2分别为0.864 5、0.834 5;采用SCA-PLSR剔除弱相关特征31、35、24、39、36、33后,PLSR对训练集、测试集识别的R2分别为0.885 2、0.864 3;采用MIT结合PLSR剔除重复信息特征6、7、14、18、22、25后,PLSR对训练集、测试集识别的R2分别为0.918 7、0.896 5。对去除冗余特征的融合特征数据进行归一化处理,再结合LDA可有效识别各普洱茶种类,结合KNN、PNN对普洱茶种类训练集的回判正确率分别为96.67%、97.50%,对测试集的识别正确率均为90.00%,可较好地识别普洱茶种类。试验结果可为普洱茶种类的识别及电子鼻传感响应特征的提取提供参考。
Abstract:
-

参考文献/References:

[1]杨崇仁,陈可可,张颖君. 茶叶的分类与普洱茶的定义[J]. 茶叶科学技术,2006(2):37-38.
[2]刘本英,李友勇,唐一春,等. 云南茶树资源遗传多样性与亲缘关系的ISSR分析[J]. 作物学报,2010,36(3):391-400.
[3]薇薇. 云南普洱茶产区地图[J]. 普洱,2017(5):71.
[4]吕海鹏,谷记平,林智,等. 普洱茶的化学成分及生物活性研究进展[J]. 茶叶科学,2007,27(1):8-18.
[5]Bandana D,Mahipal S. Molecular detection of cashew husk (Anacardium occidentale) adulteration in market samples of dry tea (Camellia sinensis)[J]. Planta Medica,2003,69(9):882-884.
[6]Cebi N,Yilmaz M T,Sagdic O. A rapid ATR-FTIR spectroscopic method for detection of sibutramine adulteration in tea and coffee based on hierarchical cluster and principal component analyses[J]. Food chemistry,2017,229(15):517-526.
[7]Hong M,Yan S,Jiao Y N,et al. Electronic nose sensors data feature mining:a synergetic strategy for the classification of beer[J]. Analytical Methods,2018,10:2016-2025.
[8]潘玉成,宋莉莉,叶乃兴,等. 电子鼻技术及其在茶叶中的应用研究[J]. 食品与机械,2016,32(9):213-218,224.
[9]杨春兰,薛大为. 基于电子鼻技术的茶叶贮藏时间检测方法[J]. 兰州文理学院学报(自然科学版),2016,30(5):51-54.
[10]何鲁南,赵苗苗,蔡昌敏,等. 电子鼻技术对不同贮藏地的普洱茶香气分析[J]. 西南农业学报,2018,31(4):717-724.
[11]潘磊庆,唐琳,詹歌,等. 电子鼻对芝麻油掺假的检测[J]. 食品科学,2010,31(20):318-321.
[12]Brudzewski K,Osowski S,Dwulit A. Recognition of coffee using differential electronic nose[J]. IEEE Transactions on Instrumentation and Measurement,2012,61(6):1803-1810.
[13]Wei Z B,Wang J,Zhang W L. Detecting internal quality of peanuts during storage using electronic nose responses combined with physicochemical methods[J]. Food Chemistry,2015,177:89-96.
[14]Sysoev V V,Button B K,Wepsiec K,et al. Toward the nanoscopic “electronic nose”:hydrogen vs carbon monoxide discrimination with an array of individual metal oxide nano- and mesowire sensors[J]. Nano Letters,2006,6(8):1584-1588.
[15]Yang Z R,Zwolinski M. Mutual information theory for adaptive mixture models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(4):396-403.
[16]Jia X M,Meng Q H,Jing Y Q,et al. A new method combining KECA-LDA with ELM for classification of chinese liquors using electronic nose[J]. IEEE Sensors Journal,2016,16(22):8010-8017.
[17]Qiu S S,Wang J. The prediction of food additives in the fruit juice based on electronic nose with chemometrics[J]. Food Chemistry,2017,230:208-214.
[18]Wang Z,Sun X Y,Miao J C,et al. Conformal prediction based on K-nearest neighbors for discrimination of ginsengs by a home-made electronic nose[J]. Sensors,2017,17:1-12.
[19]Bhattacharyya N,Metla A,Bandyopadhyay R,et al. Incremental PNN classifier for a versatile electronic nose[C]// IEEE. 3rd International Conference on Sensing Technology. Taiwan,2008.
[20]黄鹍,陈森发,孙燕,等. 基于小波网络和证据理论的多源信息融合系统研究[J]. 数据采集与处理,2003,18(4):434-439.
[21]段志梅,程加堂. 基于多源信息融合的异步电机故障诊断[J]. 煤矿机械,2014,35(2):235-237.
[22]唐向阳,张勇,丁锐,等. 电子鼻技术的发展及展望[J]. 机电一体化,2006,12(4):11-15.

相似文献/References:

[1]刘宗泉,李梅花,徐秀丽,等.江苏省丰县苹果树病虫发生种类与危害特点[J].江苏农业科学,2014,42(12):188.
 Liu Zongquan,et al.Types and damage characteristics of pests and diseases of apple trees in Fengxian County,Jiangsu Province[J].Jiangsu Agricultural Sciences,2014,42(16):188.
[2]王白娟.高压脉冲电场对普洱茶中茶水浸出物含量的影响[J].江苏农业科学,2013,41(10):243.
 Wang Baijuan.Effect of high-voltage pulsed electric field on extract content in Puer tea water[J].Jiangsu Agricultural Sciences,2013,41(16):243.
[3]何丽斯,苏家乐,刘晓青,等.扬州城市绿地中杜鹃花的种类、应用调查及分析[J].江苏农业科学,2013,41(11):197.
 He Lisi,et al.Investigation and analysis of species and application of azalea in urban green space of Yangzhou City[J].Jiangsu Agricultural Sciences,2013,41(16):197.
[4]马尧,王艳玲,王伟强.不同肥料不同施肥量对玉竹有效成分的影响[J].江苏农业科学,2015,43(06):234.
 Ma Yao,et al.Effects of different fertilizer application of different fertilizers on effective constituents of Polygonatum odoratum[J].Jiangsu Agricultural Sciences,2015,43(16):234.
[5]韩睿,陈来生.低温产甲烷菌厌氧消化研究进展[J].江苏农业科学,2015,43(06):11.
 Han Rui,et al.Research progress of anaerobic digestion of psychrophilic methanogens[J].Jiangsu Agricultural Sciences,2015,43(16):11.
[6]费云燕,盖钧镒,赵团结.南京大豆田间耐草甘膦杂草的种类与特性鉴定[J].江苏农业科学,2016,44(11):154.
 Fei Yunyan,et al.Species and characteristics identification of weeds with glyphosate resistance in soybean fields in Nanjing area[J].Jiangsu Agricultural Sciences,2016,44(16):154.
[7]张水花,史俊友,李艳丽.云南普洱茶茶褐素的理化性质[J].江苏农业科学,2016,44(12):335.
 Zhang Shuihua,et al.Chemical structure and functional features of theabrownine from Pu-erh Tea[J].Jiangsu Agricultural Sciences,2016,44(16):335.
[8]张霞,黄端杰.储藏条件对普洱茶品质的影响及其茶汤饮用安全性分析[J].江苏农业科学,2018,46(12):160.
 Zhang Xia,et al.Effects of storage conditions on quality of Pu-erh tea and safety analysis of its tea drink[J].Jiangsu Agricultural Sciences,2018,46(16):160.
[9]徐德进,徐广春,徐鹿,等.蔬菜田蜗牛的发生及防治对策[J].江苏农业科学,2021,49(19):134.
 Xu Dejin,et al.Occurrence and control of snails in vegetable fields[J].Jiangsu Agricultural Sciences,2021,49(16):134.

备注/Memo

备注/Memo:
收稿日期:2019-07-15
基金项目:广东省农业科学院院新兴学科团队建设项目(编号:201802XX);国家自然科学基金(编号:31901404);广州市科技计划(编号:201904010199);广东省农业科学院院长基金面上项目(编号:201920);广东省农业科学院院长基金重点项目(编号:202034);广东省农业科学院科技人才引进/培养专项资金。
作者简介:徐赛(1991—),男,湖南衡阳人,博士,副研究员,从事农产品品质智能检测技术与装备研究。E-mail:xusai@gdaas.cn。
更新日期/Last Update: 2020-08-20