[1]周红标,张宇林,丁友威,等.自适应概率神经网络及其在白酒电子鼻中的应用[J].智能系统学报,2013,8(02):177-182.[doi:10.3969/j.issn.1673-4785.201209026]
 ZHOU Hongbiao,ZHANG Yulin,DING Youwei,et al.Application of adaptive probabilistic neural network in Chinese liquor E-Nose[J].CAAI Transactions on Intelligent Systems,2013,8(02):177-182.[doi:10.3969/j.issn.1673-4785.201209026]
点击复制

自适应概率神经网络及其在白酒电子鼻中的应用(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第8卷
期数:
2013年02期
页码:
177-182
栏目:
出版日期:
2013-04-25

文章信息/Info

Title:
Application of adaptive probabilistic neural network in Chinese liquor E-Nose
文章编号:
1673-4785(2013)02-0177-06
作者:
周红标1张宇林1丁友威1刘佳佳2
1.淮阴工学院 电子与电气工程学院,江苏 淮安 223003;
2.南京师范大学 电气与自动化工程学院,江苏 南京 210042
Author(s):
ZHOU Hongbiao1 ZHANG Yulin1 DING Youwei1 LIU Jiajia2
1.Faculty of Electronic and Electrical Engineering, Huaiyin Institute of Technology, Huai’an 223003, China;
2.School of Electrical and Automation Engineering, Nanjing Normal University, Nanjing 210042, China
关键词:
差异演化算法自适应概率神经网络电子鼻白酒识别
Keywords:
differential evolution algorithmadaptive probabilistic neural networkelectronic nosehard liquor quality recognition
分类号:
TP183;TS262.3
DOI:
10.3969/j.issn.1673-4785.201209026
文献标志码:
A
摘要:
为了探索电子鼻对白酒品质鉴别的可能性,利用自制的新型无线白酒电子鼻对洋河海之蓝、今世缘省接待、安徽迎驾大曲和牛栏山陈酿进行了分析.对所采集的数据进行平滑处理后提取稳态响应值和斜率值,利用主成分分析对特征向量进行降维处理,并将获得的前2个主元得分作为概率神经网络识别模型的输入参量.针对传统概率神经网络平滑因子σ单一易导致分类错误的缺陷,利用差异演化算法优化σ参数集,建立了自适应概率神经网络识别模型.实验结果表明,DE-PNN相比BP-PNN、PSO-PNN和SVM等,识别精度更高,抗噪性能更好,同时也证明了电子鼻能有效地检出不同品牌的白酒.
Abstract:
In order to explore the possibility of hard liquor quality recognition by an electronic nose, the Chinese liquor of Yanghe Haizhilan, Jinshiyuan Shengjiedai, Anhui Yingjiadaqu, and Niulanshan Chenniang were analyzed by using self-made new wireless electronic nose for recognition of hard liquor quality. Firstly, the steady-state response and slope values were extracted after smoothing the collected data. Secondly, principal component analysis PCA was used to reduce the dimension of the eigenvector, and the obtained first two principal components scores were then used as the input parameters of the probabilistic neural network recognition model. Next, the aim was to overcome defect of traditional probabilistic neural network smoothing factor which would cause classification error easily. The method of adaptive probabilistic neural network identification model was presented, utilizing differential evolution algorithm to optimize the set of parameters. The results show that differential evolution-probabilistic neural network obtained a high recognition accuracy and noise immunity compared to back propagation, particle swarm optimization-probabilistic neural network and support vector machine. The experiment also proved that the electronic nose can effectively detect different liquor brands in China.

参考文献/References:

[1]杨国强,张淑娟.电子鼻技术在酒类识别应用中的研究进展[J]. 山西农业大学学报:自然科学版, 2010, 30(1): 92-96. 
 YANG Guoqiang, ZHANG Shujuan. Development of the electronic nose technology on the identification of spirit[J]. Journal of Shanxi Agric ultural University: Natural Science Edition, 2010, 30(1): 92-96. 
[2]YU Huichun, WANG Jun. Discrimination of longjing green-tea grade by electronic nose[J]. Sensors and Actuators B, 2007, 122: 134-140.
[3]ALEIXANDRE M, LOZANO J, GUITERREZ J, et al. Portable e-nose to classify different kinds of wine[J]. Sensors and Actuators B, 2008, 131: 71-76. 
[4]刘红秀,李洪波,李卫东,等.基于电子鼻的鱼类新鲜度估计研究[J].中山大学学报: 自然科学版, 2010, 49(2): 28-30.
LIU Hongxiu, LI Hongbo, LI Weidong, et al. Research on the fish freshness assessment based on electronic nose[J]. Acta Scientiarum Natralium Universitatis Sunyatseni, 2010, 49(2): 28-30.
[5] 李纯,卢志茂,杨朋. 基于快速谱聚类的图像分割算法[J]. 应用科技 , 2012, 39(2): 26-30.
 LI Chun, LU Zhimao, YANG Peng. Image segmentation based on fast spectral clustering algorithm[J]. Applied Science and Technology, 2012, 39(2): 26-30.
[6]姬东朝,宋笔锋,易华辉.基于概率神经网络的设备故障诊断及仿真分析[J]. 火力与指挥控制, 2009, 34(1): 82-85.
JI Dongchao, SONG Bifeng, YI Huahui. Equipment fault diagnosis based on probabilistic neural networks and simulation analysis[J]. Fire Control and Command Control, 2009, 34(1): 82-85.
[7]明利特, 蒋芸, 王勇, 等.基于邻域粗糙集和概率神经网络集成的基因表达谱分类方法[J]. 计算机应用研究, 2011, 28(12): 4440-4444.
MING Lite, JIANG Yun, WANG Yong, et al. Gene expression profiles classification method based on neighborhood rough set and probabilistic neural networks ensemble[J]. Application Research of Computers, 2011, 28(12): 4440-4444.
[8]KIM D, KIM D H, CHANG S. Application of probabilistic neural network to design breakwater armor blocks[J]. Ocean Engineering, 2008, 35: 294-300.
[9]严文娟, 林凌, 赵静. 概率神经网络用于舌诊的近红外光谱分类[J]. 激光与红外, 2010, 40(11): 1201-1204.
 YAN Wenjuan, LIN Ling, ZHAO Jing. Probability neural network for the classification of tongue diagnosis by near infrared spectroscopy[J]. Laser and Infrared, 2010, 40(11): 1201-1204.
[10]李鹏,王乐新,赵志敏.基于概率神经网络的荧光光谱法识别高甘油三脂血清[J].发光学报, 2011, 32(11): 1192-1196.
LI Peng, WANG Lexin, ZHAO Zhimin. Hypertriglyceridemia serum recognition using fluorescence spectroscopic analysis based on probabilistic neural networks[J]. Chinese Journal of Luminescence, 2011, 32(11): 1192-1196.
[11]卢青波, 张学良, 温淑花, 等. 差异演化算法改进与应用[J]. 农业机械学报, 2010, 41(2): 193-197.
 LU Qingbo, ZHANG Xueliang, WEN Shuhua, et al. Modified differential evolution and its application[J]. Transactions of the Chinese Society for Agricultural Machinery, 2010, 41(2): 193-197.
[12]蒋鼎国, 周红标, 耿忠华. 基于PSO-SVM的白酒品质鉴别电子鼻[J]. 中国酿造, 2011 (11): 149-152.
JIANG Dingguo, ZHOU Hongbiao, GENG Zhonghua. Liquor recognition electronic nose based on PSO-SVM[J]. China Brewing, 2011 (11): 149-152.

备注/Memo

备注/Memo:
收稿日期:2012-09-12.
网络出版日期:2013-03-26. 
基金项目:国家自然科学基金资助项目(61203056);淮安市科技公共服务平台资助项目(HAP201107). 
通信作者:周红标.
E-mail: hyitzhb@163.com.
作者简介:
周红标,男,1980年生,讲师,主要研究方向为模式识别.
张宇林,男,1970年生,教授,博士,主要研究方向为智能信息处理.
更新日期/Last Update: 2013-05-26