基于支持向量机的重大科技项目立项评价研究  

Study on evaluation of major S&T projects establishment based on SVM

作　　者：李书全[1] 朱孔国[1] 李武[2] 

机构地区：[1]天津财经大学商学院,天津300222 [2]天津大学科技处,天津300072

出　　处：《科技与管理》2010年第1期53-56,共4页Science-Technology and Management

基　　金：天津市科技发展战略研究计划(08ZLZLZT02200)

摘　　要：重大科技项目立项评价直接关系着国家科技计划实施的质量。然而由于立项评审的复杂性,对其进行评估往往面临许多问题。支持向量机作为结构风险最小化准则的具体实现工具,具有全局最优、结构简单、分类精确性好和泛化性能强等优点。将支持向量机用于重大科技项目的立项评审中,并取得了较好的识别效果。The establishment evaluation of the major S＆T S＆T plans. However, with the complexity of R＆D projects, projects is of significance for implementing the national the establishment evaluation would be faced with a lot of problems. As a tool of the structural risk minimization principle, support vector machine （SVM） brings along a bunch of advantages over other approaches, including global optimization, simple structure, better classification accuracy and good generalization properties. In this paper, SVM is applied to major S＆T projects establishment evaluation. The application example shows that SVM has made very good identification result.

关 键 词：立项评价 重大科技项目 支持向量机 预测模型 

分 类 号：F069.9[经济管理—政治经济学]