首页 | 本学科首页   官方微博 | 高级检索  
     

An Intelligent Approach to Sensory Evaluation: LVQ Neural Network
引用本文:丁香乾,杨宁,肖协忠. An Intelligent Approach to Sensory Evaluation: LVQ Neural Network[J]. 东华大学学报(英文版), 2004, 21(3)
作者姓名:丁香乾  杨宁  肖协忠
作者单位:Information Engineering Center,Ocean University of China,266071,Department of Computer Science,Ocean University of China,266071,Qingdao Etsong Tobacco Group,Qingdao,266071
摘    要:IntroductionAsanimportantaspectofproductQualityControl,sensoryevaluationtraditionallydependsonexpertassessmentorpanelassessment.Butitsresultsisstronglyrelatedtosomeuncertainfactorssuchascapacityofpanelist,individualsownpreference,emotionalstateandsoon.Thecostofevaluationisrelativelyhigh,anditisnoteasytoassessagreatquantityofsamples.Therefore,thereisanobviousrequirementforsomemoreobjectiveandfasterapproachesforsensoryevaluation.Sensoryqualityindexes,suchasmouthssensetobeer,stimulationtocigare…


An Intelligent Approach to Sensory Evaluation:LVQ Neural Network
DING Xiang-qianInformation Engineering Center,Ocean University of China, YANG Ning. An Intelligent Approach to Sensory Evaluation:LVQ Neural Network[J]. Journal of Donghua University, 2004, 21(3)
Authors:DING Xiang-qianInformation Engineering Center  Ocean University of China   YANG Ning
Affiliation:1. Information Engineering Center, Ocean University of China, 266071
2. Department of Computer Science, Ocean University of China, 266071
3. Qingdao Etsong Tobacco Group, Qingdao, 266071
Abstract:Converting between "fuzzy concept" and "numerical value" in computer aided assessment is rather difficult in many applications. This paper presents a LVQ neural network paradigm for sensory evaluation. This intelligent approach utilizes predefined class information for supervised learning in order to solve the converting problem and keep the fuzziness and imprecision of the whole sensory information. The method is validated by the experiment on stimulation evaluation of cigarette sensory.
Keywords:LVQ Network   Sensory Evaluation   Classification   Fuzzy Evaluation Index
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号