·1086· 智能系统学报 第15卷 1.000 1.0 0.9 0.95 0.8 0.90 WIDAR 0.6 WIDAR -Labeled data ◆-Labeled data 0- Semi_D 0- Semi D 0.85 60 0. 0 50 70 80 90 40 50 60 70 80 90 标记数据所占比例/% 标记缺失比例% (e)Mushroom (①Letter recognition 图4CART分类器的分类精 Fig.4 Classification accuracy with the CART classifier 0.8 0.7 0.7 0.6 0.6 0.4 0.5 0.3 ◆-WIDAR 0.4 ◆-WIDAR 0.2 ▲-Labeled data ▲-Labeled data 0 o-Semi_D -o-Semi D 0.3 40 50 60 70 80 90 0 50 60 70 80 90 标记缺失比例/% 标记缺失比例% (a)Automobile (b)Soybean (Large) 0.9 1.0 08 0.9 0.7 0.6 0.5 0.79 0.4 0.3 WIDAR ◆-WIDAR 0.2 ▲-Labeled data 0.5 Labeled data o-Semi D -o-Semi D 0.1 0. 0 60 7080 90 40 50 60 70 80 90 标记缺失比例/% 标记缺失比例% (c)Dermatology (d)Cylinder bands 0.8 1.0 ● 0.7 0.9 0.89 0.6 0 0.7 ◆-VIDAR 0.5 -Labeled data o-Semi D 0.6 0.4 ◆WIDAR -Labeled data -o-Semi D 0. 0.3 40 50 60 70 80 90 0 50 60 70 80 90 标记缺失比例% 标记缺失比例/% (e)Mushroom (f)Letter recognition 图5 Naive Bayes分类器分类精度 Fig.5 Classification accuracy with the Naive Bayes classifier40 50 60 70 80 90 0.85 0.90 0.95 1.00 分类精度 标记数据所占比例/% (e) Mushroom 40 50 60 70 80 90 0.5 0.6 0.7 0.8 0.9 1.0 分类精度 标记缺失比例/% (f) Letter recognition WIDAR Labeled data Semi_D WIDAR Labeled data Semi_D 图 4 CART 分类器的分类精 Fig. 4 Classification accuracy with the CART classifier 40 50 60 70 80 90 0.1 0.2 0.3 0.4 0.5 0.6 0.7 分类精度 标记缺失比例/% WIDAR Labeled data Semi_D WIDAR Labeled data Semi_D WIDAR Labeled data Semi_D WIDAR Labeled data Semi_D WIDAR Labeled data Semi_D WIDAR Labeled data Semi_D (a) Automobile 40 50 60 70 80 90 0.3 0.4 0.5 0.6 0.7 0.8 分类精度 标记缺失比例/% (b) Soybean (Large) 40 50 60 70 80 90 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 分类精度 标记缺失比例/% (c) Dermatology 40 50 60 70 80 90 0.4 0.5 0.6 0.7 0.8 0.9 1.0 分类精度 标记缺失比例/% (d) Cylinder bands 40 50 60 70 80 90 0.5 0.6 0.7 0.8 0.9 1.0 分类精度 标记缺失比例/% (e) Mushroom 40 50 60 70 80 90 0.3 0.4 0.5 0.6 0.7 0.8 分类精度 标记缺失比例/% (f) Letter recognition 图 5 Naive Bayes 分类器分类精度 Fig. 5 Classification accuracy with the Naive Bayes classifier ·1086· 智 能 系 统 学 报 第 15 卷