基于SVM的概念设计创新度机器评价模型  

Machine-evaluation model of the creative degree in conceptual design on Support Vector Machines

作　　者：魏志静 李洪洋[2] 刘楠[3] 井源 刘希玉[3] 

机构地区：[1]济宁市人事局,山东济宁272000 [2]山东省公安消防总队,山东济南250014 [3]山东师范大学信息科学与工程学院,山东济南250014 [4]山东省济宁市公安消防支队,山东济宁272000

出　　处：《山东轻工业学院学报（自然科学版）》2007年第3期18-22,共5页Journal of Shandong Polytechnic University

基　　金：山东省创新设计软构件与集成系统项目基金资助(03BS003)

摘　　要：针对概念设计创新度评价这一问题,本文首先提取概念设计中手机实体的外观造型特征,将特征量化后作为测试样本,然后利用一种改进的支持向量机分类器Shear-SVC-KNN进行评价,取得的评价结果准确率较高,效果较好。As for the evaluation of the creative degree in conceptual design, firstly, the paper extracts the qualified characteristics of the mobile telephone outline, rescales all characteristics with the specified range as the train samples, and evaluates the creativity degree of the conceptual design of the mobile telephone outline by using a reformative classification method Shear - SVC - KNN based on SVMs. The experiment shows that the result of evaluation is accurate and the conclusion of this experiment is satisfactory.

关 键 词：统计学习理论 支持向量机分类器 概念设计评价 K最近邻 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]