[1]史小伍 陶红 阚今中 高尚.组合代价敏感支持向量机及其应用[J].计算机技术与发展,2012,(05):71-74.
 SHI Xiao-wu,TAO Hong,KAN Jin-zhong,et al.Combination Cost-Sensitive Support Vector Machine and Application[J].,2012,(05):71-74.
点击复制

组合代价敏感支持向量机及其应用()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2012年05期
页码:
71-74
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
Combination Cost-Sensitive Support Vector Machine and Application
文章编号:
1673-629X(2012)05-0071-04
作者:
史小伍 陶红 阚今中 高尚
江苏科技大学计算机科学与工程学院
Author(s):
SHI Xiao-wu TAO Hong KAN Jin-zhong GAO Shang
School of Computer Science and Engineering, Jiangsu University of Science & Technology
关键词:
代价敏感学习组合支持向量机个人信用评价误分代价
Keywords:
cost-sensitive learning combination SVM personal credit scoring misclassification cost
分类号:
TP31
文献标志码:
A
摘要:
标准的分类器设计大多都是基于整体最小化错误率。在入侵检测、医疗诊断等领域中,不同类别的误分类通常具有不等的损失。文中采用支持向量机建立模型,在组合算法的思想下引入组合代价敏感支持向量机,弥补传统代价敏感支持向量机在分类精度上的不可控。在模型对比中引入了更为实际的对比方式,从而能更好地选取模型,以减少总体误分代价。文中考虑不同类别的误分代价的前提下建立合适的支持向量机模型,并成功地应用在个人信用分类上
Abstract:
The standard classifiers are generally based on minimizing the whole error rate. However, in intrusion detection, medical diagno- sis ,etc, different errors often have different costs. Using support vector machine build model,introduce combination cost sensitive support vector machine under the thinking of combination, patch the uncontrollable result of traditional cost sensitive support vector machine in the classification precision. Introduce a more practical way on model contrast,in order to select better model and reduce whole misclassifi- cation. Establish proper support vector machine ( SVM ) model based on different types of error price and successfully used in personal credit classification

相似文献/References:

[1]黄 琳,荆晓远,董西伟.基于多核集成学习的跨项目软件缺陷预测[J].计算机技术与发展,2019,29(06):27.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 006]
 HUANG Lin,JING Xiao-yuan,DONG Xi-wei.Cross-project Software Defect Prediction Based on Multiple Kernel Ensemble Learning[J].,2019,29(05):27.[doi:10. 3969 / j. issn. 1673-629X. 2019. 06. 006]

备注/Memo

备注/Memo:
人工智能四川省重点实验室开放基金(2009RY001);“青蓝工程”项目计划史小伍(1987-),男,湖北枣阳人,硕士研究生,从事模式识别与人工智能研究
更新日期/Last Update: 1900-01-01