摘要
结合粗糙集的属性约简和支持向量机的分类机理,研究了一种混合算法,即应用粗糙集的属性约简过程作为预处理器,可以把冗余的属性及值和冲突的对象从决策表中删去,但不损失任何有效信息;由于传统支持向量机在多分类问题时出现的不可分区域现象,使用了模糊支持向量机进行后面的分类建模和预测,使得训练时间大大缩短和分类性能显著提高。将这种混合方法应用到雷达信号识别中,仿真实验证明该方法是有效的。
A mixed algorithm based on attribute reduction of Rough Sets（RS） and classification principles of Support Vector Machine（SVM） is researched in this paper.Firstly,the attribute reduction of RS has been applied as preprocessor so that the redundant attributes,values and conflicting objects can be deleted from decision table but the efficient information remains lossless.For the unclassifiable regions existing in the problem of multiclass with SVM,fuzzy SVM is applied to settle this problem and be used in the succedent classification and forecast,which makes the training time reduced and classification performance enhanced greatly.The mixed method is used for radar signal recognition in this paper,simulation experiments and their results show this method is effective.
出处
《火力与指挥控制》
CSCD
北大核心
2010年第6期76-80,共5页
Fire Control & Command Control
