电子学报
電子學報
전자학보
ACTA ELECTRONICA SINICA
2013年
12期
2334-2338
,共5页
胎记特征选择%聚类分析%信息度量%关联系数
胎記特徵選擇%聚類分析%信息度量%關聯繫數
태기특정선택%취류분석%신식도량%관련계수
birthmark feature selection%clustering analysis%information measurement%correlation coefficient
软件胎记选择关系着软件的识别率。本文应用约束聚类分析软件特征，基于互信息度量特征的类内和类间距离，以同类和异类软件特征构建信息增益函数和惩罚函数，选择出具有高的类区分信息和最小冗余的软件胎记特征。通过分析和比较表明该算法为软件胎记特征的选择和优化提供了一种有效途径。
軟件胎記選擇關繫著軟件的識彆率。本文應用約束聚類分析軟件特徵，基于互信息度量特徵的類內和類間距離，以同類和異類軟件特徵構建信息增益函數和懲罰函數，選擇齣具有高的類區分信息和最小冗餘的軟件胎記特徵。通過分析和比較錶明該算法為軟件胎記特徵的選擇和優化提供瞭一種有效途徑。
연건태기선택관계착연건적식별솔。본문응용약속취류분석연건특정，기우호신식도량특정적류내화류간거리，이동류화이류연건특정구건신식증익함수화징벌함수，선택출구유고적류구분신식화최소용여적연건태기특정。통과분석화비교표명해산법위연건태기특정적선택화우화제공료일충유효도경。
The feature selection for software birthmark has a direct bearing on software recognition rate .We apply con-strained clustering to analyze software features .The within-and between-class distances of features are measured based on mutual in-formation .Information gain and penalty functions are constructed using homogeneous and heterogeneous software features respec-tively .Then the software birthmark features with high class distinction and minimum redundancy are selected .It is shown the algo-rithm provide an effective approach for software birthmark feature selection and optimization by analysis and comparison .
