Comparison of Algorithms for an Electronic Nose in Identifying Liquors  

作　　者：Zhi-biao Shi Tao Yu Qun Zhao Yang Li Yu-bin Lan 

机构地区：[1]School of Energy Resources and Mechanical Engineering, Northeast Dianli University, Jilin 132012, P. R. China [2]School of Chemistry Engineering, Northeast Dianli University, Jilin 132012, P. R. China [3]School of Electrical Engineering, Northeast Dianli University, Jilin 132012, P. R. China [4]Aerial Application Technlogy, usDA-ARS-SPARC-APMRU, Co）lege Station, TX 77845, USA

出　　处：《Journal of Bionic Engineering》2008年第3期253-257,共5页仿生工程学报（英文版）

基　　金：the Science and Technology Plan Projects, Department of Education of Jilin Province, P R China (Grant no. 2006026)

摘　　要：When the electronic nose is used to identify different varieties of distilled liquors, the pattern recognition algorithm is chosen on the basis of the experience, which lacks the guiding principle. In this research, the different brands of distilled spirits were identified using the pattern recognition algorithms （principal component analysis and the artificial neural network）. The recognition rates of different algorithms were compared. The recognition rate of the Back Propagation Neural Network （BPNN） is the highest. Owing to the slow convergence speed of the BPNN, it tends easily to get into a local minimum. A chaotic BPNN was tried in order to overcome the disadvantage of the BPNN. The convergence speed of the chaotic BPNN is 75.5 times faster than that of the BPNN.When the electronic nose is used to identify different varieties of distilled liquors, the pattern recognition algorithm is chosen on the basis of the experience, which lacks the guiding principle. In this research, the different brands of distilled spirits were identified using the pattern recognition algorithms （principal component analysis and the artificial neural network）. The recognition rates of different algorithms were compared. The recognition rate of the Back Propagation Neural Network （BPNN） is the highest. Owing to the slow convergence speed of the BPNN, it tends easily to get into a local minimum. A chaotic BPNN was tried in order to overcome the disadvantage of the BPNN. The convergence speed of the chaotic BPNN is 75.5 times faster than that of the BPNN.

关 键 词：electronic nose LIQUOR ALGORITHM principal component analysis 

分 类 号：O42[理学—声学]