基于密度峰值聚类和局部稀疏度的过采样算法
吕佳, 郭铭

Oversampling algorithm based on density peaks clustering and local sparsity
Lü Jia, Ming Guo
表3 各算法在KNN分类器上的各指标评价结果
Table 3 Evaluation results of each index of each algorithm on the KNN classifier
DatasetsEvaluationSMOBorSafeADASSM⁃IPFK⁃m SADAPRSMDPCLSO
D1F1⁃measure62.0333%62.1173%55.6688%61.5440%60.4950%54.6957%48.7924%58.6876%62.2829%
G⁃mean79.6812%78.4615%71.2518%80.0162%77.9393%73.2348%66.9467%75.8509%80.0405%
D2F1⁃measure85.9964%86.7993%86.3374%85.3952%87.9143%86.8775%85.4217%87.0937%88.2993%
G⁃mean90.3121%90.6767%90.2701%90.1816%92.0551%90.7103%89.7805%90.8855%91.7266%
D3F1⁃measure78.2442%76.8568%77.7085%77.4810%78.2107%78.4768%77.6307%77.4382%78.4280%
G⁃mean81.6440%80.5218%81.3824%80.7309%81.5465%82.1207%81.3010%81.2429%82.0311%
D4F1⁃measure56.6667%55.2083%56.7912%59.7166%65.1515%54.7297%46.1047%42.0513%57.8748%
G⁃mean59.6238%57.3185%58.2452%55.3644%49.1523%55.8029%53.8242%50.2559%61.3867%
D5F1⁃measure52.7560%49.7018%48.9448%53.0428%49.9616%52.7413%47.9911%54.4706%56.0870%
G⁃mean63.3895%60.4853%61.1482%63.3134%58.5940%64.5689%60.4762%66.0340%67.4871%
D6F1⁃measure56.3467%59.7222%61.1111%51.6340%52.3810%56.8627%60.7692%50.0000%60.0000%
G⁃mean76.4860%79.4070%81.3536%73.2013%71.7161%78.1713%75.9926%71.8818%81.2447%
D7F1⁃measure84.0336%81.1765%80.3571%84.0336%80.3571%81.1765%77.5000%74.3421%84.0336%
G⁃mean87.5140%84.9819%84.3065%87.5140%84.3065%84.9819%81.7744%79.0784%87.5140%
D8F1⁃measure51.3191%46.2766%46.9176%47.8095%52.1569%41.8762%41.2782%49.5541%49.7459%
G⁃mean65.7490%61.4930%62.1053%62.1248%65.7728%56.9598%57.9467%64.6729%64.4944%
D9F1⁃measure95.7412%94.7253%95.7412%92.5052%93.5185%94.392%93.5185%95.7412%95.7412%
G⁃mean97.8306%96.8547%97.8306%95.8093%96.7736%97.3521%96.7736%97.8306%97.8306%
D10F1⁃measure83.3056%84.1304%84.4078%81.6459%81.8952%82.5409%84.6341%85.6083%85.1662%
G⁃mean88.7784%89.1231%89.5641%87.4620%87.7329%88.2285%89.8910%90.3583%90.3027%
D11F1⁃measure79.6456%78.5138%79.6987%78.2845%79.4329%77.8749%80.5446%77.1168%81.0368%
G⁃mean77.2319%76.3439%78.7317%75.6164%75.5961%74.9554%78.3277%77.3277%79.6327%
D12F1⁃measure99.0321%99.1194%99.0758%98.9376%98.7178%99.0757%98.8969%98.8541%99.9314%
G⁃mean99.5399%99.5500%99.5449%99.5299%99.5046%99.5449%99.5248%99.5197%99.5599%
D13F1⁃measure69.0476%67.8161%68.0672%68.6275%73.8095%70.0000%68.2870%69.2951%73.2252%
G⁃mean58.1695%61.5895%60.5979%60.7131%65.6850%63.2075%64.1788%66.7669%66.5811%
D14F1⁃measure99.0909%99.0210%98.6777%98.2524%96.9538%99.1010%98.2712%96.1969%99.1211%
G⁃mean99.7417%99.6118%99.5918%99.7903%99.0551%99.6118%99.5517%99.5119%99.5852%
D15F1⁃measure69.6581%72.2222%61.8421%71.0084%70.8333%64.7727%70.8333%75.7143%74.7727%
G⁃mean77.0973%77.1389%72.3167%78.1661%74.0852%69.4628%74.0852%84.0976%79.3485%
D16F1⁃measure95.5630%95.5493%95.2310%96.0512%94.5915%95.4878%95.9256%94.4447%96.5470%
G⁃mean98.4711%97.9041%98.0402%98.4924%97.3255%98.0329%98.4806%98.4967%98.4418%
D17F1⁃measure98.5657%98.6980%98.2979%98.7261%98.2305%98.8469%98.4576%98.6974%98.9396%
G⁃mean99.2300%99.4004%99.0884%99.3136%99.0321%99.3256%99.1593%99.2671%99.3602%
D18F1⁃measure98.7282%99.3010%98.1242%98.6898%98.2638%99.1763%98.7282%99.3025%99.3043%
G⁃mean98.7595%99.3234%98.1586%98.7161%98.3042%99.2945%98.7595%99.3003%99.3043%