Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (6): 1842-1854.DOI: 10.11772/j.issn.1001-9081.2022050691
Special Issue: 数据科学与技术
• Data science and technology • Previous Articles Next Articles
Lin SUN1,2(), Jinxu HUANG1, Jiucheng XU1
Received:
2022-05-12
Revised:
2022-11-05
Accepted:
2022-11-15
Online:
2023-06-08
Published:
2023-06-10
Contact:
Lin SUN
About author:
HUANG Jinxu, born in 1995, M. S. candidate. His research interests include granular computing, data mining.Supported by:
通讯作者:
孙林
作者简介:
孙林(1979—),男,河南南阳人,副教授,博士,CCF会员,主要研究方向:粒计算、数据挖掘、机器学习、生物信息学Email:sunlin@htu.edu.cn基金资助:
CLC Number:
Lin SUN, Jinxu HUANG, Jiucheng XU. Feature selection for imbalanced data based on neighborhood tolerance mutual information and whale optimization algorithm[J]. Journal of Computer Applications, 2023, 43(6): 1842-1854.
孙林, 黄金旭, 徐久成. 基于邻域容差互信息和鲸鱼优化算法的非平衡数据特征选择[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1842-1854.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2022050691
函数 | 函数名 | 公式 | 变量范围 | 最优值 |
---|---|---|---|---|
f1 | Sphere | [-100,100] | 0 | |
f2 | Step | [-100,100] | 0 | |
f3 | Schwefel2.22 | [-10,10] | 0 | |
f4 | Quartic | [-1.28,1.28] | 0 | |
f5 | Ackley | [-32,32] | 0 | |
f6 | Griewank | [-600,600] | 0 | |
f7 | Rastrigin | [-5.12,5.12] | 0 | |
f8 | Levy | [-5.12,5.12] | 0 |
Tab. 1 Information of eight benchmark functions
函数 | 函数名 | 公式 | 变量范围 | 最优值 |
---|---|---|---|---|
f1 | Sphere | [-100,100] | 0 | |
f2 | Step | [-100,100] | 0 | |
f3 | Schwefel2.22 | [-10,10] | 0 | |
f4 | Quartic | [-1.28,1.28] | 0 | |
f5 | Ackley | [-32,32] | 0 | |
f6 | Griewank | [-600,600] | 0 | |
f7 | Rastrigin | [-5.12,5.12] | 0 | |
f8 | Levy | [-5.12,5.12] | 0 |
函数 | 算法 | dim=30 | dim=50 | ||||
---|---|---|---|---|---|---|---|
最优值 | 最差值 | 平均值 | 最优值 | 最差值 | 平均值 | ||
f1 | PSO算法 | 2.751 0E-78 | 2.489 2E-61 | 8.528 1E-63 | 1.133 2E-05 | 7.162 7E-04 | 2.748 1E-04 |
MPA | 2.522 9E-12 | 1.304 4E-10 | 4.447 0E-11 | 1.940 5E-13 | 1.257 5E-11 | 2.210 8E-12 | |
WOA | 2.772 9E-61 | 2.319 6E-38 | 8.296 2E-50 | 2.081 9E-15 | 5.951 2E-11 | 3.888 7E-12 | |
WWOA | 5.483 6E-54 | 3.403 7E-46 | 7.332 9E-52 | 3.584 0E-37 | 6.831 9E-25 | 4.634 0E-33 | |
CWOA | 4.880 4E-47 | 5.378 2E-39 | 8.501 7E-44 | 2.642 7E-42 | 2.479 0E-36 | 3.883 0E-39 | |
A-WOA | 6.613 4E-39 | 1.259 7E-31 | 9.013 3E-33 | 2.819 5E-39 | 2.545 7E-31 | 3.566 5E-32 | |
AWWOA | 7.8940E-96 | 3.0695E-70 | 1.0232E-71 | 5.1663E-59 | 3.8422E-46 | 7.9061E-48 | |
f2 | PSO算法 | 4.707 4E-06 | 0.001 6 | 2.577 9E-07 | 0.134 9 | 0.622 9 | 0.302 4 |
MPA | 5.552 1E-12 | 1.346 6E-06 | 1.031 8E-07 | 1.557 1E-04 | 4.386 7 | 0.103 9 | |
WOA | 3.688 9E-09 | 4.794 6E-06 | 2.577 9E-07 | 1.010 6E-10 | 1.858 4E-05 | 6.897 9E-07 | |
WWOA | 2.779 1E-14 | 6.290 1E-11 | 5.302 9E-13 | 1.056 1E-13 | 3.735 2E-06 | 9.462 9E-09 | |
CWOA | 3.438 0E-10 | 3.802 1E-08 | 9.490 3E-09 | 1.573 1E-11 | 8.904 3E-08 | 6.255 1E-10 | |
A-WOA | 5.440 9E-16 | 9.327 8E-09 | 7.467 7E-11 | 1.414 7E-09 | 2.887 6E-07 | 3.941 9E-08 | |
AWWOA | 1.6368E-16 | 4.0926E-10 | 1.4466E-11 | 6.0514E-16 | 4.4493E-09 | 1.4657E-10 | |
f3 | PSO算法 | 1.418 5E-08 | 7.536 3E-05 | 4.058 8E-06 | 2.3644E-39 | 3.174 3E-30 | 1.289 5E-31 |
MPA | 4.333 4E-09 | 3.505 3E-07 | 1.107 5E-07 | 6.253 5E-09 | 6.200 2E-07 | 1.468 6E-07 | |
WOA | 3.973 0E-37 | 3.171 9E-31 | 2.501 9E-32 | 1.080 1E-18 | 2.105 7E-16 | 7.628 3E-17 | |
WWOA | 4.680 3E-43 | 3.921 7E-39 | 5.690 3E-41 | 1.369 0E-20 | 7.496 3E-18 | 6.548 1E-19 | |
CWOA | 6.403 8E-45 | 2.997 4E-38 | 5.753 9E-41 | 2.884 8E-19 | 6.594 0E-17 | 8.390 2E-18 | |
A-WOA | 9.551 1E-25 | 3.978 3E-20 | 3.039 8E-21 | 5.942 9E-26 | 6.715 8E-20 | 3.690 6E-21 | |
AWWOA | 6.2757E-50 | 1.2039E-40 | 5.3386E-42 | 2.516 6E-38 | 7.5899E-32 | 5.0783E-33 | |
f4 | PSO算法 | 1.258 3E-05 | 3.1184E-04 | 1.395 3E-04 | 0.014 0 | 0.048 5 | 0.027 2 |
MPA | 5.512 9E-04 | 0.004 7 | 0.098 0 | 2.014 2E-04 | 0.0054 | 0.0018 | |
WOA | 1.133 2E-05 | 7.162 7E-04 | 2.748 1E-04 | 0.002 0 | 0.183 0 | 0.050 4 | |
WWOA | 6.773 2E-05 | 7.825 9E-03 | 2.906 4E-04 | 1.317 4E-04 | 0.093 5 | 0.040 8 | |
CWOA | 7.380 3E-05 | 1.624 8E-03 | 3.437 2E-04 | 0.001 7 | 0.097 4 | 0.063 0 | |
A-WOA | 5.479 0E-04 | 6.910 6E-02 | 1.302 7E-03 | 1.743 1E-03 | 3.063 6E-02 | 1.984 2E-03 | |
AWWOA | 7.6804E-06 | 5.120 4E-04 | 9.6231E-05 | 4.1881E-05 | 0.011 2 | 0.003 2 | |
f5 | PSO算法 | 2.213 6 | 13.615 0 | 5.793 5 | 2.788 8E-05 | 5.692 0 | 1.846 5 |
MPA | 1.946 3 | 9.836 8 | 3.521 0 | 5.012 4E-08 | 9.581 4E-07 | 2.873 8E-07 | |
WOA | 0.015 1 | 0.139 1 | 0.045 1 | 0.006 8 | 0.634 7 | 0.055 4 | |
WWOA | 3.485 1E-02 | 0.091 0 | 0.036 2 | 1.438 1E-10 | 3.967 6E-08 | 5.774 1E-09 | |
CWOA | 8.359 4E-06 | 1.378 0E-03 | 2.747 9E-05 | 6.093 1E-11 | 9.408 7E-08 | 1.968 9E-09 | |
A-WOA | 9.601 6E-03 | 7.334 8E-01 | 3.991 6E-02 | 7.411 2E-14 | 5.473 1E-11 | 4.866 4E-14 | |
AWWOA | 3.4936E-07 | 2.8868E-06 | 1.0987E-06 | 8.8818E-16 | 1.5099E-14 | 6.3594E-15 | |
f6 | PSO算法 | 0.205 5 | 41.184 4 | 6.686 5 | 6.994 4E-15 | 0.110 4 | 0.027 3 |
MPA | 0.041 1 | 0.856 0 | 0.288 5 | 2.310 4E-13 | 2.9767E-09 | 6.7740E-11 | |
WOA | 0.536 0 | 14.921 0 | 5.027 7 | 1.494 4E-10 | 0.044 3 | 0.009 1 | |
WWOA | 0.018 0 | 0.973 5 | 0.754 3 | 2.943 0E-11 | 0.365 0 | 0.108 4 | |
CWOA | 6.094 5E-03 | 1.764 6 | 1.335 8 | 0 | 0.847 5 | 0.504 9 | |
A-WOA | 0.026 4 | 0.731 1 | 0.493 6 | 0 | 0.563 7 | 0.047 9 | |
AWWOA | 2.3772E-05 | 0.0168 | 0.0048 | 0 | 0.160 3 | 0.003 2 | |
f7 | PSO算法 | 11.945 2 | 27.861 1 | 21.053 3 | 12.934 5 | 25.868 9 | 19.879 3 |
MPA | 5.684 3E-14 | 4.189 1E-09 | 1.699 9E-10 | 0 | 39.360 2 | 4.8523 | |
WOA | 0 | 34.523 5 | 6.597 0 | 13.930 9 | 32.837 7 | 20.655 2 | |
WWOA | 0 | 3.540 7 | 1.887 3 | 5.891 6 | 11.487 3 | 9.084 6 | |
CWOA | 0 | 0 | 0 | 3.021 8 | 26.070 1 | 19.066 2 | |
A-WOA | 0 | 0 | 0 | 0 | 24.462 9 | 18.782 2 | |
AWWOA | 0 | 0 | 0 | 3.979 8 | 16.9143 | 11.800 2 | |
f8 | PSO算法 | 1.4481E-08 | 25.364 3 | 5.424 1 | 3.183 0 | 32.543 1 | 15.350 1 |
MPA | 0.053 2 | 1.584 5 | 0.381 8 | 0.998 2 | 14.896 4 | 5.437 7 | |
WOA | 0.179 1 | 12.638 1 | 6.055 8 | 0.679 2 | 1.931 5 | 1.204 1 | |
WWOA | 0.843 0 | 9.601 9 | 7.964 3 | 0.533 2 | 0.875 9 | 0.741 8 | |
CWOA | 0.165 3 | 1.879 0 | 1.028 4 | 0.960 4 | 1.706 1 | 1.320 7 | |
A-WOA | 0.341 7 | 0.823 9 | 0.437 2 | 3.590 1E-01 | 0.843 7 | 0.663 1 | |
AWWOA | 0.089 6 | 0.6285 | 0.2646 | 6.0284E-04 | 0.4521 | 0.2325 |
Tab. 2 Experimental results of seven optimization algorithms on eight benchmark functions on two dimensions
函数 | 算法 | dim=30 | dim=50 | ||||
---|---|---|---|---|---|---|---|
最优值 | 最差值 | 平均值 | 最优值 | 最差值 | 平均值 | ||
f1 | PSO算法 | 2.751 0E-78 | 2.489 2E-61 | 8.528 1E-63 | 1.133 2E-05 | 7.162 7E-04 | 2.748 1E-04 |
MPA | 2.522 9E-12 | 1.304 4E-10 | 4.447 0E-11 | 1.940 5E-13 | 1.257 5E-11 | 2.210 8E-12 | |
WOA | 2.772 9E-61 | 2.319 6E-38 | 8.296 2E-50 | 2.081 9E-15 | 5.951 2E-11 | 3.888 7E-12 | |
WWOA | 5.483 6E-54 | 3.403 7E-46 | 7.332 9E-52 | 3.584 0E-37 | 6.831 9E-25 | 4.634 0E-33 | |
CWOA | 4.880 4E-47 | 5.378 2E-39 | 8.501 7E-44 | 2.642 7E-42 | 2.479 0E-36 | 3.883 0E-39 | |
A-WOA | 6.613 4E-39 | 1.259 7E-31 | 9.013 3E-33 | 2.819 5E-39 | 2.545 7E-31 | 3.566 5E-32 | |
AWWOA | 7.8940E-96 | 3.0695E-70 | 1.0232E-71 | 5.1663E-59 | 3.8422E-46 | 7.9061E-48 | |
f2 | PSO算法 | 4.707 4E-06 | 0.001 6 | 2.577 9E-07 | 0.134 9 | 0.622 9 | 0.302 4 |
MPA | 5.552 1E-12 | 1.346 6E-06 | 1.031 8E-07 | 1.557 1E-04 | 4.386 7 | 0.103 9 | |
WOA | 3.688 9E-09 | 4.794 6E-06 | 2.577 9E-07 | 1.010 6E-10 | 1.858 4E-05 | 6.897 9E-07 | |
WWOA | 2.779 1E-14 | 6.290 1E-11 | 5.302 9E-13 | 1.056 1E-13 | 3.735 2E-06 | 9.462 9E-09 | |
CWOA | 3.438 0E-10 | 3.802 1E-08 | 9.490 3E-09 | 1.573 1E-11 | 8.904 3E-08 | 6.255 1E-10 | |
A-WOA | 5.440 9E-16 | 9.327 8E-09 | 7.467 7E-11 | 1.414 7E-09 | 2.887 6E-07 | 3.941 9E-08 | |
AWWOA | 1.6368E-16 | 4.0926E-10 | 1.4466E-11 | 6.0514E-16 | 4.4493E-09 | 1.4657E-10 | |
f3 | PSO算法 | 1.418 5E-08 | 7.536 3E-05 | 4.058 8E-06 | 2.3644E-39 | 3.174 3E-30 | 1.289 5E-31 |
MPA | 4.333 4E-09 | 3.505 3E-07 | 1.107 5E-07 | 6.253 5E-09 | 6.200 2E-07 | 1.468 6E-07 | |
WOA | 3.973 0E-37 | 3.171 9E-31 | 2.501 9E-32 | 1.080 1E-18 | 2.105 7E-16 | 7.628 3E-17 | |
WWOA | 4.680 3E-43 | 3.921 7E-39 | 5.690 3E-41 | 1.369 0E-20 | 7.496 3E-18 | 6.548 1E-19 | |
CWOA | 6.403 8E-45 | 2.997 4E-38 | 5.753 9E-41 | 2.884 8E-19 | 6.594 0E-17 | 8.390 2E-18 | |
A-WOA | 9.551 1E-25 | 3.978 3E-20 | 3.039 8E-21 | 5.942 9E-26 | 6.715 8E-20 | 3.690 6E-21 | |
AWWOA | 6.2757E-50 | 1.2039E-40 | 5.3386E-42 | 2.516 6E-38 | 7.5899E-32 | 5.0783E-33 | |
f4 | PSO算法 | 1.258 3E-05 | 3.1184E-04 | 1.395 3E-04 | 0.014 0 | 0.048 5 | 0.027 2 |
MPA | 5.512 9E-04 | 0.004 7 | 0.098 0 | 2.014 2E-04 | 0.0054 | 0.0018 | |
WOA | 1.133 2E-05 | 7.162 7E-04 | 2.748 1E-04 | 0.002 0 | 0.183 0 | 0.050 4 | |
WWOA | 6.773 2E-05 | 7.825 9E-03 | 2.906 4E-04 | 1.317 4E-04 | 0.093 5 | 0.040 8 | |
CWOA | 7.380 3E-05 | 1.624 8E-03 | 3.437 2E-04 | 0.001 7 | 0.097 4 | 0.063 0 | |
A-WOA | 5.479 0E-04 | 6.910 6E-02 | 1.302 7E-03 | 1.743 1E-03 | 3.063 6E-02 | 1.984 2E-03 | |
AWWOA | 7.6804E-06 | 5.120 4E-04 | 9.6231E-05 | 4.1881E-05 | 0.011 2 | 0.003 2 | |
f5 | PSO算法 | 2.213 6 | 13.615 0 | 5.793 5 | 2.788 8E-05 | 5.692 0 | 1.846 5 |
MPA | 1.946 3 | 9.836 8 | 3.521 0 | 5.012 4E-08 | 9.581 4E-07 | 2.873 8E-07 | |
WOA | 0.015 1 | 0.139 1 | 0.045 1 | 0.006 8 | 0.634 7 | 0.055 4 | |
WWOA | 3.485 1E-02 | 0.091 0 | 0.036 2 | 1.438 1E-10 | 3.967 6E-08 | 5.774 1E-09 | |
CWOA | 8.359 4E-06 | 1.378 0E-03 | 2.747 9E-05 | 6.093 1E-11 | 9.408 7E-08 | 1.968 9E-09 | |
A-WOA | 9.601 6E-03 | 7.334 8E-01 | 3.991 6E-02 | 7.411 2E-14 | 5.473 1E-11 | 4.866 4E-14 | |
AWWOA | 3.4936E-07 | 2.8868E-06 | 1.0987E-06 | 8.8818E-16 | 1.5099E-14 | 6.3594E-15 | |
f6 | PSO算法 | 0.205 5 | 41.184 4 | 6.686 5 | 6.994 4E-15 | 0.110 4 | 0.027 3 |
MPA | 0.041 1 | 0.856 0 | 0.288 5 | 2.310 4E-13 | 2.9767E-09 | 6.7740E-11 | |
WOA | 0.536 0 | 14.921 0 | 5.027 7 | 1.494 4E-10 | 0.044 3 | 0.009 1 | |
WWOA | 0.018 0 | 0.973 5 | 0.754 3 | 2.943 0E-11 | 0.365 0 | 0.108 4 | |
CWOA | 6.094 5E-03 | 1.764 6 | 1.335 8 | 0 | 0.847 5 | 0.504 9 | |
A-WOA | 0.026 4 | 0.731 1 | 0.493 6 | 0 | 0.563 7 | 0.047 9 | |
AWWOA | 2.3772E-05 | 0.0168 | 0.0048 | 0 | 0.160 3 | 0.003 2 | |
f7 | PSO算法 | 11.945 2 | 27.861 1 | 21.053 3 | 12.934 5 | 25.868 9 | 19.879 3 |
MPA | 5.684 3E-14 | 4.189 1E-09 | 1.699 9E-10 | 0 | 39.360 2 | 4.8523 | |
WOA | 0 | 34.523 5 | 6.597 0 | 13.930 9 | 32.837 7 | 20.655 2 | |
WWOA | 0 | 3.540 7 | 1.887 3 | 5.891 6 | 11.487 3 | 9.084 6 | |
CWOA | 0 | 0 | 0 | 3.021 8 | 26.070 1 | 19.066 2 | |
A-WOA | 0 | 0 | 0 | 0 | 24.462 9 | 18.782 2 | |
AWWOA | 0 | 0 | 0 | 3.979 8 | 16.9143 | 11.800 2 | |
f8 | PSO算法 | 1.4481E-08 | 25.364 3 | 5.424 1 | 3.183 0 | 32.543 1 | 15.350 1 |
MPA | 0.053 2 | 1.584 5 | 0.381 8 | 0.998 2 | 14.896 4 | 5.437 7 | |
WOA | 0.179 1 | 12.638 1 | 6.055 8 | 0.679 2 | 1.931 5 | 1.204 1 | |
WWOA | 0.843 0 | 9.601 9 | 7.964 3 | 0.533 2 | 0.875 9 | 0.741 8 | |
CWOA | 0.165 3 | 1.879 0 | 1.028 4 | 0.960 4 | 1.706 1 | 1.320 7 | |
A-WOA | 0.341 7 | 0.823 9 | 0.437 2 | 3.590 1E-01 | 0.843 7 | 0.663 1 | |
AWWOA | 0.089 6 | 0.6285 | 0.2646 | 6.0284E-04 | 0.4521 | 0.2325 |
数据集 | 样本 数 | 特征 数 | 非平衡率 | %P/% | %N/% | 数据 类型 |
---|---|---|---|---|---|---|
Ionosphere | 351 | 34 | 1.79 | 35.90 | 64.10 | numerical |
Heart | 270 | 13 | 1.25 | 44.44 | 55.56 | mixed |
Pima | 768 | 8 | 1.87 | 34.90 | 65.10 | numerical |
Vehicle3 | 846 | 18 | 2.99 | 25.06 | 74.94 | numerical |
Wdbc | 569 | 30 | 1.68 | 37.26 | 62.74 | numerical |
Wpbc | 198 | 33 | 3.21 | 23.74 | 76.26 | numerical |
Zoo | 101 | 16 | 19.20 | 4.95 | 95.05 | nominal |
Arrhythmia | 452 | 279 | 9.27 | 9.73 | 90.27 | mixed |
Segment | 2 310 | 19 | 6.02 | 14.25 | 85.75 | numerical |
DLBCL | 77 | 6 285 | 3.05 | 24.68 | 75.32 | numerical |
Lung | 203 | 12 601 | 10.94 | 8.37 | 91.63 | numerical |
SRBCT | 83 | 2 308 | 6.55 | 13.25 | 86.75 | numerical |
Breast | 84 | 9 126 | 7.30 | 11.90 | 88.10 | numerical |
Tab. 3 Information of thirteen binary imbalanced datasets
数据集 | 样本 数 | 特征 数 | 非平衡率 | %P/% | %N/% | 数据 类型 |
---|---|---|---|---|---|---|
Ionosphere | 351 | 34 | 1.79 | 35.90 | 64.10 | numerical |
Heart | 270 | 13 | 1.25 | 44.44 | 55.56 | mixed |
Pima | 768 | 8 | 1.87 | 34.90 | 65.10 | numerical |
Vehicle3 | 846 | 18 | 2.99 | 25.06 | 74.94 | numerical |
Wdbc | 569 | 30 | 1.68 | 37.26 | 62.74 | numerical |
Wpbc | 198 | 33 | 3.21 | 23.74 | 76.26 | numerical |
Zoo | 101 | 16 | 19.20 | 4.95 | 95.05 | nominal |
Arrhythmia | 452 | 279 | 9.27 | 9.73 | 90.27 | mixed |
Segment | 2 310 | 19 | 6.02 | 14.25 | 85.75 | numerical |
DLBCL | 77 | 6 285 | 3.05 | 24.68 | 75.32 | numerical |
Lung | 203 | 12 601 | 10.94 | 8.37 | 91.63 | numerical |
SRBCT | 83 | 2 308 | 6.55 | 13.25 | 86.75 | numerical |
Breast | 84 | 9 126 | 7.30 | 11.90 | 88.10 | numerical |
数据集 | F2HARNRS | WAR | CfsSubsetEval | RSFSAID | FSIDN |
---|---|---|---|---|---|
Ionosphere | 1,3,4,5,7,8,10,12,24,25,28,29,30,31,32,34(16) | 3,5,6,14,17, 22,23,24( | 1,3,4,5,6,7,8,16,18, 20,21,24,27,28,29, 31,34(17) | 1,3,4,5,6,8,14,16( | 3,5,6,15,17, 31,32,33( |
Heart | 1,2,3,4,5,7,8,10,11,12,13(11) | 1,2,3,6,7,8,9,10,11,12,13(11) | 2,3,8,9,10,11,12, 13(8) | 3,5,11,12,13(5) | 2,6,7,9( |
Vehicle3 | 1,2,3,4,7,9,10,11,13,15,16,17,18(13) | 1,2,3,4,6,8,9,10,11,13,14,16,18(13) | 3,10,11,12,14,16(6) | 1,5,8,10,13,14,15,17,18(9) | 1,2,3,15,16( |
Wdbc | 2,9,12,22,23,25,26,28(8) | 8,13,22,24,26( | 2,7,8,14,19,21,23,24,25,27,28(11) | 3,4,5,6,8,21,22,28(8) | 7,8,9,16,29( |
Wpbc | 1,2,6,7,10,19,23,24,26,27,32,33(12) | 1( | 1,2,4,5,6,10,12,13,19, 27,30,32,33(13) | 1,4,5,6,12,13,15,19,26, 27,32,33(12) | 1,14,19,27(4) |
Zoo | 1,6,12,13,14(5) | 1,6,8,12,13(5) | 1,4,5,11,12,14,15(7) | 1,4,6,12,13,14(6) | 6,7,12,16( |
Arrhythmia | 1,14,64,176,212, 267( | 47,50,63,71,99,111, 118,135,179,207, 217,249,250,257, 269,270,277,279(18) | 11,22,25,36,59,110, 122,160,177,217,243, 247,249,250,257,260, 267,279(18) | 1,2,4,5,8,11,19,59,60,79,81,92, 110,111,122,173,177,178,179,181, 183,186,192,197,206,213,216,230, 232,236,247,249,253,254,257,259, 260,267,277,278,279(41) | 16,19,46,50,59, 114,160,177,180, 218,244,246,257, 267,277(15) |
Segment | 1,2,4,6,13,14, 15,16,18,19(10) | 1,2,4,5,6,7,8,10, 11,12,15(11) | 1,14,19(3) | 13,16,19(3) | 1,17( |
Tab. 4 Optimal feature subsets and the number of features selected by five algorithms on eight binary datasets
数据集 | F2HARNRS | WAR | CfsSubsetEval | RSFSAID | FSIDN |
---|---|---|---|---|---|
Ionosphere | 1,3,4,5,7,8,10,12,24,25,28,29,30,31,32,34(16) | 3,5,6,14,17, 22,23,24( | 1,3,4,5,6,7,8,16,18, 20,21,24,27,28,29, 31,34(17) | 1,3,4,5,6,8,14,16( | 3,5,6,15,17, 31,32,33( |
Heart | 1,2,3,4,5,7,8,10,11,12,13(11) | 1,2,3,6,7,8,9,10,11,12,13(11) | 2,3,8,9,10,11,12, 13(8) | 3,5,11,12,13(5) | 2,6,7,9( |
Vehicle3 | 1,2,3,4,7,9,10,11,13,15,16,17,18(13) | 1,2,3,4,6,8,9,10,11,13,14,16,18(13) | 3,10,11,12,14,16(6) | 1,5,8,10,13,14,15,17,18(9) | 1,2,3,15,16( |
Wdbc | 2,9,12,22,23,25,26,28(8) | 8,13,22,24,26( | 2,7,8,14,19,21,23,24,25,27,28(11) | 3,4,5,6,8,21,22,28(8) | 7,8,9,16,29( |
Wpbc | 1,2,6,7,10,19,23,24,26,27,32,33(12) | 1( | 1,2,4,5,6,10,12,13,19, 27,30,32,33(13) | 1,4,5,6,12,13,15,19,26, 27,32,33(12) | 1,14,19,27(4) |
Zoo | 1,6,12,13,14(5) | 1,6,8,12,13(5) | 1,4,5,11,12,14,15(7) | 1,4,6,12,13,14(6) | 6,7,12,16( |
Arrhythmia | 1,14,64,176,212, 267( | 47,50,63,71,99,111, 118,135,179,207, 217,249,250,257, 269,270,277,279(18) | 11,22,25,36,59,110, 122,160,177,217,243, 247,249,250,257,260, 267,279(18) | 1,2,4,5,8,11,19,59,60,79,81,92, 110,111,122,173,177,178,179,181, 183,186,192,197,206,213,216,230, 232,236,247,249,253,254,257,259, 260,267,277,278,279(41) | 16,19,46,50,59, 114,160,177,180, 218,244,246,257, 267,277(15) |
Segment | 1,2,4,6,13,14, 15,16,18,19(10) | 1,2,4,5,6,7,8,10, 11,12,15(11) | 1,14,19(3) | 13,16,19(3) | 1,17( |
分类器 | 数据集 | F2HARNRS | WAR | CfsSubsetEval | RSFSAID | SYMON | FSAWFN | FRSA | FSIDN |
---|---|---|---|---|---|---|---|---|---|
J48 | Ionosphere | 0.924 3 | 0.890 5 | 0.878 3 | 0.920 2 | 0.893 8 | 0.895 5 | 0.928 8 | 0.9291 |
Heart | 0.820 1 | 0.815 3 | 0.804 8 | 0.827 7 | 0.821 5 | 0.823 0 | 0.796 5 | 0.8337 | |
Pima | 0.776 8 | 0.726 7 | 0.765 9 | 0.767 9 | 0.755 9 | 0.774 8 | 0.622 0 | 0.7793 | |
Vehicle3 | 0.744 8 | 0.710 4 | 0.644 9 | 0.758 6 | 0.752 4 | 0.712 6 | 0.9272 | 0.769 3 | |
Wdbc | 0.954 0 | 0.935 6 | 0.937 2 | 0.944 3 | 0.939 0 | 0.899 1 | 0.904 6 | 0.9557 | |
Wpbc | 0.705 9 | 0.576 9 | 0.558 2 | 0.687 5 | 0.652 3 | 0.568 5 | 0.579 2 | 0.7217 | |
Zoo | 0.495 8 | 0.495 8 | 0.495 8 | 0.495 8 | 0.495 8 | 0.846 7 | 0.9793 | 0.887 0 | |
Arrhythmia | 0.811 0 | 0.730 5 | 0.726 4 | 0.789 4 | 0.686 8 | 0.801 3 | 0.812 3 | 0.8773 | |
Segment | 0.985 2 | 0.985 8 | 0.973 9 | 0.992 3 | 0.987 5 | 0.985 2 | 0.9981 | 0.993 7 | |
均值 | 0.802 0 | 0.763 1 | 0.753 9 | 0.798 2 | 0.776 1 | 0.811 9 | 0.838 7 | 0.8608 | |
Random Forest | Ionosphere | 0.981 4 | 0.979 6 | 0.971 7 | 0.981 1 | 0.975 7 | 0.975 4 | 0.982 6 | 0.9837 |
Heart | 0.893 6 | 0.887 8 | 0.877 9 | 0.888 7 | 0.880 7 | 0.886 4 | 0.886 4 | 0.9035 | |
Pima | 0.822 2 | 0.816 2 | 0.792 2 | 0.824 3 | 0.815 2 | 0.765 8 | 0.622 0 | 0.8377 | |
Vehicle3 | 0.870 5 | 0.867 4 | 0.716 9 | 0.870 5 | 0.868 4 | 0.865 3 | 0.9751 | 0.900 0 | |
Wdbc | 0.991 6 | 0.990 7 | 0.988 6 | 0.992 2 | 0.991 9 | 0.986 0 | 0.994 1 | 0.9976 | |
Wpbc | 0.753 1 | 0.681 9 | 0.627 9 | 0.713 5 | 0.723 8 | 0.709 1 | 0.708 7 | 0.7631 | |
Zoo | 0.729 2 | 0.989 6 | 0.788 5 | 0.989 6 | 0.963 5 | 0.925 9 | 0.9982 | 0.976 4 | |
Arrhythmia | 0.914 8 | 0.9407 | 0.917 3 | 0.939 2 | 0.926 6 | 0.918 5 | 0.849 1 | 0.935 5 | |
Segment | 0.999 8 | 0.999 6 | 0.997 3 | 0.9999 | 0.9999 | 0.996 4 | 0.9999 | 0.999 7 | |
均值 | 0.884 0 | 0.905 9 | 0.853 1 | 0.911 0 | 0.905 1 | 0.892 1 | 0.890 7 | 0.9219 | |
Naive Bayes | Ionosphere | 0.954 0 | 0.933 5 | 0.935 6 | 0.961 8 | 0.946 0 | 0.948 1 | 0.982 3 | 0.9830 |
Heart | 0.904 1 | 0.902 5 | 0.886 8 | 0.902 4 | 0.901 5 | 0.873 7 | 0.744 3 | 0.9035 | |
Pima | 0.833 3 | 0.817 7 | 0.822 9 | 0.821 8 | 0.825 3 | 0.754 9 | 0.674 5 | 0.8487 | |
Vehicle3 | 0.698 8 | 0.700 1 | 0.681 8 | 0.741 1 | 0.735 5 | 0.753 0 | 0.753 0 | 0.7641 | |
Wdbc | 0.988 9 | 0.984 7 | 0.983 0 | 0.988 7 | 0.990 8 | 0.983 0 | 0.9925 | 0.9925 | |
Wpbc | 0.7602 | 0.655 3 | 0.726 1 | 0.724 8 | 0.702 7 | 0.710 3 | 0.680 4 | 0.750 0 | |
Zoo | 0.645 8 | 0.762 5 | 0.664 6 | 0.827 1 | 0.740 6 | 0.799 5 | 0.9971 | 0.847 0 | |
Arrhythmia | 0.887 5 | 0.769 1 | 0.897 3 | 0.929 3 | 0.827 9 | 0.931 7 | 0.969 2 | 0.9880 | |
Segment | 0.997 5 | 0.986 5 | 0.982 9 | 0.9979 | 0.996 4 | 0.996 5 | 0.998 7 | 0.997 5 | |
均值 | 0.852 2 | 0.834 7 | 0.842 3 | 0.877 2 | 0.851 9 | 0.861 2 | 0.865 8 | 0.8971 | |
SVM | Ionosphere | 0.922 4 | 0.900 3 | 0.910 0 | 0.928 1 | 0.862 4 | 0.873 9 | 0.9316 | 0.905 3 |
Heart | 0.552 5 | 0.525 8 | 0.746 7 | 0.817 5 | 0.816 7 | 0.702 5 | 0.608 3 | 0.8198 | |
Pima | 0.613 4 | 0.500 0 | 0.485 0 | 0.590 5 | 0.704 9 | 0.500 0 | 0.527 1 | 0.7176 | |
Vehicle3 | 0.590 3 | 0.500 0 | 0.504 7 | 0.608 4 | 0.500 0 | 0.500 0 | 0.609 2 | 0.6560 | |
Wdbc | 0.940 4 | 0.748 3 | 0.507 1 | 0.945 6 | 0.945 3 | 0.937 8 | 0.507 1 | 0.9484 | |
Wpbc | 0.578 5 | 0.500 1 | 0.502 1 | 0.566 6 | 0.500 0 | 0.566 6 | 0.581 2 | 0.5823 | |
Zoo | 0.500 0 | 0.500 0 | 0.500 0 | 0.500 0 | 0.500 0 | 0.500 0 | 0.9550 | 0.631 0 | |
Arrhythmia | 0.500 0 | 0.500 0 | 0.521 5 | 0.708 6 | 0.500 0 | 0.784 1 | 0.502 1 | 0.7941 | |
Segment | 0.884 8 | 0.970 6 | 0.730 3 | 0.989 4 | 0.979 0 | 0.901 5 | 0.835 6 | 0.9927 | |
均值 | 0.675 8 | 0.627 2 | 0.600 8 | 0.739 4 | 0.700 9 | 0.696 3 | 0.673 0 | 0.7830 |
Tab. 5 AUC values of eight algorithms on nine binary datasets under four classifiers
分类器 | 数据集 | F2HARNRS | WAR | CfsSubsetEval | RSFSAID | SYMON | FSAWFN | FRSA | FSIDN |
---|---|---|---|---|---|---|---|---|---|
J48 | Ionosphere | 0.924 3 | 0.890 5 | 0.878 3 | 0.920 2 | 0.893 8 | 0.895 5 | 0.928 8 | 0.9291 |
Heart | 0.820 1 | 0.815 3 | 0.804 8 | 0.827 7 | 0.821 5 | 0.823 0 | 0.796 5 | 0.8337 | |
Pima | 0.776 8 | 0.726 7 | 0.765 9 | 0.767 9 | 0.755 9 | 0.774 8 | 0.622 0 | 0.7793 | |
Vehicle3 | 0.744 8 | 0.710 4 | 0.644 9 | 0.758 6 | 0.752 4 | 0.712 6 | 0.9272 | 0.769 3 | |
Wdbc | 0.954 0 | 0.935 6 | 0.937 2 | 0.944 3 | 0.939 0 | 0.899 1 | 0.904 6 | 0.9557 | |
Wpbc | 0.705 9 | 0.576 9 | 0.558 2 | 0.687 5 | 0.652 3 | 0.568 5 | 0.579 2 | 0.7217 | |
Zoo | 0.495 8 | 0.495 8 | 0.495 8 | 0.495 8 | 0.495 8 | 0.846 7 | 0.9793 | 0.887 0 | |
Arrhythmia | 0.811 0 | 0.730 5 | 0.726 4 | 0.789 4 | 0.686 8 | 0.801 3 | 0.812 3 | 0.8773 | |
Segment | 0.985 2 | 0.985 8 | 0.973 9 | 0.992 3 | 0.987 5 | 0.985 2 | 0.9981 | 0.993 7 | |
均值 | 0.802 0 | 0.763 1 | 0.753 9 | 0.798 2 | 0.776 1 | 0.811 9 | 0.838 7 | 0.8608 | |
Random Forest | Ionosphere | 0.981 4 | 0.979 6 | 0.971 7 | 0.981 1 | 0.975 7 | 0.975 4 | 0.982 6 | 0.9837 |
Heart | 0.893 6 | 0.887 8 | 0.877 9 | 0.888 7 | 0.880 7 | 0.886 4 | 0.886 4 | 0.9035 | |
Pima | 0.822 2 | 0.816 2 | 0.792 2 | 0.824 3 | 0.815 2 | 0.765 8 | 0.622 0 | 0.8377 | |
Vehicle3 | 0.870 5 | 0.867 4 | 0.716 9 | 0.870 5 | 0.868 4 | 0.865 3 | 0.9751 | 0.900 0 | |
Wdbc | 0.991 6 | 0.990 7 | 0.988 6 | 0.992 2 | 0.991 9 | 0.986 0 | 0.994 1 | 0.9976 | |
Wpbc | 0.753 1 | 0.681 9 | 0.627 9 | 0.713 5 | 0.723 8 | 0.709 1 | 0.708 7 | 0.7631 | |
Zoo | 0.729 2 | 0.989 6 | 0.788 5 | 0.989 6 | 0.963 5 | 0.925 9 | 0.9982 | 0.976 4 | |
Arrhythmia | 0.914 8 | 0.9407 | 0.917 3 | 0.939 2 | 0.926 6 | 0.918 5 | 0.849 1 | 0.935 5 | |
Segment | 0.999 8 | 0.999 6 | 0.997 3 | 0.9999 | 0.9999 | 0.996 4 | 0.9999 | 0.999 7 | |
均值 | 0.884 0 | 0.905 9 | 0.853 1 | 0.911 0 | 0.905 1 | 0.892 1 | 0.890 7 | 0.9219 | |
Naive Bayes | Ionosphere | 0.954 0 | 0.933 5 | 0.935 6 | 0.961 8 | 0.946 0 | 0.948 1 | 0.982 3 | 0.9830 |
Heart | 0.904 1 | 0.902 5 | 0.886 8 | 0.902 4 | 0.901 5 | 0.873 7 | 0.744 3 | 0.9035 | |
Pima | 0.833 3 | 0.817 7 | 0.822 9 | 0.821 8 | 0.825 3 | 0.754 9 | 0.674 5 | 0.8487 | |
Vehicle3 | 0.698 8 | 0.700 1 | 0.681 8 | 0.741 1 | 0.735 5 | 0.753 0 | 0.753 0 | 0.7641 | |
Wdbc | 0.988 9 | 0.984 7 | 0.983 0 | 0.988 7 | 0.990 8 | 0.983 0 | 0.9925 | 0.9925 | |
Wpbc | 0.7602 | 0.655 3 | 0.726 1 | 0.724 8 | 0.702 7 | 0.710 3 | 0.680 4 | 0.750 0 | |
Zoo | 0.645 8 | 0.762 5 | 0.664 6 | 0.827 1 | 0.740 6 | 0.799 5 | 0.9971 | 0.847 0 | |
Arrhythmia | 0.887 5 | 0.769 1 | 0.897 3 | 0.929 3 | 0.827 9 | 0.931 7 | 0.969 2 | 0.9880 | |
Segment | 0.997 5 | 0.986 5 | 0.982 9 | 0.9979 | 0.996 4 | 0.996 5 | 0.998 7 | 0.997 5 | |
均值 | 0.852 2 | 0.834 7 | 0.842 3 | 0.877 2 | 0.851 9 | 0.861 2 | 0.865 8 | 0.8971 | |
SVM | Ionosphere | 0.922 4 | 0.900 3 | 0.910 0 | 0.928 1 | 0.862 4 | 0.873 9 | 0.9316 | 0.905 3 |
Heart | 0.552 5 | 0.525 8 | 0.746 7 | 0.817 5 | 0.816 7 | 0.702 5 | 0.608 3 | 0.8198 | |
Pima | 0.613 4 | 0.500 0 | 0.485 0 | 0.590 5 | 0.704 9 | 0.500 0 | 0.527 1 | 0.7176 | |
Vehicle3 | 0.590 3 | 0.500 0 | 0.504 7 | 0.608 4 | 0.500 0 | 0.500 0 | 0.609 2 | 0.6560 | |
Wdbc | 0.940 4 | 0.748 3 | 0.507 1 | 0.945 6 | 0.945 3 | 0.937 8 | 0.507 1 | 0.9484 | |
Wpbc | 0.578 5 | 0.500 1 | 0.502 1 | 0.566 6 | 0.500 0 | 0.566 6 | 0.581 2 | 0.5823 | |
Zoo | 0.500 0 | 0.500 0 | 0.500 0 | 0.500 0 | 0.500 0 | 0.500 0 | 0.9550 | 0.631 0 | |
Arrhythmia | 0.500 0 | 0.500 0 | 0.521 5 | 0.708 6 | 0.500 0 | 0.784 1 | 0.502 1 | 0.7941 | |
Segment | 0.884 8 | 0.970 6 | 0.730 3 | 0.989 4 | 0.979 0 | 0.901 5 | 0.835 6 | 0.9927 | |
均值 | 0.675 8 | 0.627 2 | 0.600 8 | 0.739 4 | 0.700 9 | 0.696 3 | 0.673 0 | 0.7830 |
分类器 | 数据集 | NNRS | ARMDNRS | RSFSAID | ARIHISUD | FSIDN |
---|---|---|---|---|---|---|
Naive Bayes | Arrhythmia | 0.747 1 | 0.776 9 | 0.876 4 | 0.887 6 | 0.9324 |
Vehicle3 | 0.702 2 | 0.701 6 | 0.703 7 | 0.7066 | 0.7066 | |
Wdbc | 0.924 5 | 0.933 3 | 0.966 3 | 0.976 3 | 0.9894 | |
Wpbc | 0.691 6 | 0.672 4 | 0.763 7 | 0.774 2 | 0.8180 | |
Zoo | 0.643 2 | 0.666 7 | 0.719 6 | 0.7236 | 0.710 6 | |
Pima | 0.800 6 | 0.794 5 | 0.824 9 | 0.816 7 | 0.8348 | |
均值 | 0.751 5 | 0.757 6 | 0.809 1 | 0.814 2 | 0.8320 | |
SVM | Arrhythmia | 0.702 9 | 0.714 4 | 0.736 4 | 0.797 0 | 0.8301 |
Vehicle3 | 0.767 9 | 0.792 4 | 0.847 3 | 0.8574 | 0.855 3 | |
Wdbc | 0.877 4 | 0.868 5 | 0.922 7 | 0.943 9 | 0.9560 | |
Wpbc | 0.840 7 | 0.856 6 | 0.876 3 | 0.8999 | 0.886 2 | |
Zoo | 0.776 9 | 0.764 5 | 0.816 8 | 0.820 7 | 0.8264 | |
Pima | 0.832 7 | 0.863 5 | 0.8833 | 0.880 4 | 0.875 5 | |
均值 | 0.799 8 | 0.810 0 | 0.847 1 | 0.866 6 | 0.8716 |
Tab. 6 Classification accuracy of five algorithms on six binary datasets under Navie Bayes and SVM classifiers
分类器 | 数据集 | NNRS | ARMDNRS | RSFSAID | ARIHISUD | FSIDN |
---|---|---|---|---|---|---|
Naive Bayes | Arrhythmia | 0.747 1 | 0.776 9 | 0.876 4 | 0.887 6 | 0.9324 |
Vehicle3 | 0.702 2 | 0.701 6 | 0.703 7 | 0.7066 | 0.7066 | |
Wdbc | 0.924 5 | 0.933 3 | 0.966 3 | 0.976 3 | 0.9894 | |
Wpbc | 0.691 6 | 0.672 4 | 0.763 7 | 0.774 2 | 0.8180 | |
Zoo | 0.643 2 | 0.666 7 | 0.719 6 | 0.7236 | 0.710 6 | |
Pima | 0.800 6 | 0.794 5 | 0.824 9 | 0.816 7 | 0.8348 | |
均值 | 0.751 5 | 0.757 6 | 0.809 1 | 0.814 2 | 0.8320 | |
SVM | Arrhythmia | 0.702 9 | 0.714 4 | 0.736 4 | 0.797 0 | 0.8301 |
Vehicle3 | 0.767 9 | 0.792 4 | 0.847 3 | 0.8574 | 0.855 3 | |
Wdbc | 0.877 4 | 0.868 5 | 0.922 7 | 0.943 9 | 0.9560 | |
Wpbc | 0.840 7 | 0.856 6 | 0.876 3 | 0.8999 | 0.886 2 | |
Zoo | 0.776 9 | 0.764 5 | 0.816 8 | 0.820 7 | 0.8264 | |
Pima | 0.832 7 | 0.863 5 | 0.8833 | 0.880 4 | 0.875 5 | |
均值 | 0.799 8 | 0.810 0 | 0.847 1 | 0.866 6 | 0.8716 |
数据集 | 样本数 | 特征数 | 类别数 | 每个类的样本数 |
---|---|---|---|---|
Lymphography | 148 | 19 | 4 | 50/49/46/3 |
Solar-flare_2 | 1 066 | 13 | 6 | 202/200/200/155/155/154 |
Vehicle | 846 | 19 | 4 | 229/226/203/188 |
Car_df | 1 728 | 7 | 4 | 1 210/384/77/57 |
Tab. 7 Information of four multi-class imbalanced datasets
数据集 | 样本数 | 特征数 | 类别数 | 每个类的样本数 |
---|---|---|---|---|
Lymphography | 148 | 19 | 4 | 50/49/46/3 |
Solar-flare_2 | 1 066 | 13 | 6 | 202/200/200/155/155/154 |
Vehicle | 846 | 19 | 4 | 229/226/203/188 |
Car_df | 1 728 | 7 | 4 | 1 210/384/77/57 |
分类器 | 数据集 | Original | RSFSAID-M | SYMON | FSIDN |
---|---|---|---|---|---|
J48 | Lympho-graphy | 0.672 4 | 0.780 4 | 0.702 3 | 0.8047 |
Solar-flare_2 | 0.598 0 | 0.607 0 | 0.598 5 | 0.6827 | |
Vehicle | 0.721 1 | 0.721 8 | 0.718 6 | 0.7348 | |
Car_df | 0.796 7 | 0.796 7 | 0.815 9 | 0.8246 | |
SVM | Lympho-graphy | 0.400 8 | 0.4177 | 0.404 2 | 0.4177 |
Solar-flare_2 | 0.565 1 | 0.5776 | 0.576 6 | 0.568 1 | |
Vehicle | 0.198 6 | 0.450 4 | 0.613 6 | 0.6175 | |
Car_df | 0.687 9 | 0.710 9 | 0.792 9 | 0.8020 | |
Naive Bayes | Lympho-graphy | 0.728 9 | 0.745 4 | 0.717 4 | 0.7844 |
Solar-flare_2 | 0.613 6 | 0.618 4 | 0.623 3 | 0.6304 | |
Vehicle | 0.418 6 | 0.420 0 | 0.511 4 | 0.5241 | |
Car_df | 0.6163 | 0.6163 | 0.6163 | 0.6163 | |
Random Forest | Lympho-graphy | 0.588 6 | 0.763 2 | 0.690 3 | 0.8093 |
Solar-flare_2 | 0.613 4 | 0.615 7 | 0.603 3 | 0.7261 | |
Vehicle | 0.756 0 | 0.762 0 | 0.7742 | 0.771 1 | |
Car_df | 0.847 7 | 0.848 5 | 0.871 8 | 0.8724 |
Tab. 8 MFM of four algorithms on four multi-class datasets under four classifiers
分类器 | 数据集 | Original | RSFSAID-M | SYMON | FSIDN |
---|---|---|---|---|---|
J48 | Lympho-graphy | 0.672 4 | 0.780 4 | 0.702 3 | 0.8047 |
Solar-flare_2 | 0.598 0 | 0.607 0 | 0.598 5 | 0.6827 | |
Vehicle | 0.721 1 | 0.721 8 | 0.718 6 | 0.7348 | |
Car_df | 0.796 7 | 0.796 7 | 0.815 9 | 0.8246 | |
SVM | Lympho-graphy | 0.400 8 | 0.4177 | 0.404 2 | 0.4177 |
Solar-flare_2 | 0.565 1 | 0.5776 | 0.576 6 | 0.568 1 | |
Vehicle | 0.198 6 | 0.450 4 | 0.613 6 | 0.6175 | |
Car_df | 0.687 9 | 0.710 9 | 0.792 9 | 0.8020 | |
Naive Bayes | Lympho-graphy | 0.728 9 | 0.745 4 | 0.717 4 | 0.7844 |
Solar-flare_2 | 0.613 6 | 0.618 4 | 0.623 3 | 0.6304 | |
Vehicle | 0.418 6 | 0.420 0 | 0.511 4 | 0.5241 | |
Car_df | 0.6163 | 0.6163 | 0.6163 | 0.6163 | |
Random Forest | Lympho-graphy | 0.588 6 | 0.763 2 | 0.690 3 | 0.8093 |
Solar-flare_2 | 0.613 4 | 0.615 7 | 0.603 3 | 0.7261 | |
Vehicle | 0.756 0 | 0.762 0 | 0.7742 | 0.771 1 | |
Car_df | 0.847 7 | 0.848 5 | 0.871 8 | 0.8724 |
1 | LEE G K K, KASIM H, SIRIGINA R P, et al. Smart robust Feature selection (SoFt) for imbalanced and heterogeneous data[J]. Knowledge-Based Systems, 2022, 236: No.107197. 10.1016/j.knosys.2021.107197 |
2 | SUN L, WANG L Y, DING W P, et al. Feature selection using fuzzy neighborhood entropy-based uncertainty measures for fuzzy neighborhood multigranulation rough sets [J]. IEEE Transactions on Fuzzy Systems, 2021, 29(1): 19-33. 10.1109/tfuzz.2020.2989098 |
3 | 孙林,黄苗苗,徐久成. 基于邻域粗糙集和Relief的弱标记特征选择方法[J]. 计算机科学, 2022, 49(4): 152-160. 10.11896/jsjkx.210300094 |
SUN L, HUANG M M, XU J C. Weak label feature selection method based on neighborhood rough sets and Relief[J]. Computer Science, 2022, 49(4): 152-160. 10.11896/jsjkx.210300094 | |
4 | 康雁,王海宁,陶柳,等. 混合改进的花授粉算法与灰狼算法用于特征选择[J]. 计算机科学, 2022, 49(6A): 125-132. 10.11896/jsjkx.210600135 |
KANG Y, WANG H N, TAO L, et al. Hybrid improved flower pollination algorithm and gray wolf algorithm for feature selection[J]. Computer Science, 2022, 49(6A): 125-132. 10.11896/jsjkx.210600135 | |
5 | ARAM K Y, LAM S S, KHASAWNEH M T. Linear cost-sensitive max-margin embedded feature selection for SVM[J]. Expert Systems with Applications, 2022, 197: No.116683. 10.1016/j.eswa.2022.116683 |
6 | 刘艳,程璐,孙林. 基于K-S检验和邻域粗糙集的特征选择方法[J]. 河南师范大学学报(自然科学版), 2019, 47(2): 21-28. 10.16366/j.cnki.1000-2367.2019.02.004 |
LIU Y, CHENG L, SUN L. Feature selection method based on K-S test and neighborhood rough set [J]. Journal of Henan Normal University (Natural Science Edition), 2019, 47(2): 21-28. 10.16366/j.cnki.1000-2367.2019.02.004 | |
7 | SUN L, WANG L Y, DING W P, et al. Neighborhood multi-granulation rough sets-based attribute reduction using Lebesgue and entropy measures in incomplete neighborhood decision systems [J]. Knowledge-Based Systems, 2020, 192: No.105373. 10.1016/j.knosys.2019.105373 |
8 | WANG C Z, HU Q H, WANG X Z, et al. Feature selection based on neighborhood discrimination index[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(7): 2986-2999. 10.1109/tnnls.2018.2830700 |
9 | 姚晟,徐风,吴照玉,等. 基于邻域粗糙互信息熵的非单调性属性约简[J]. 控制与决策, 2019, 34(2): 353-361. 10.13195/j.kzyjc.2017.1065 |
YAO S, XU F, WU Z Y, et al. Non-monotonic attribute reduction based on neighborhood rough mutual information entropy[J]. Control and Decision, 2019, 34(2): 353-361. 10.13195/j.kzyjc.2017.1065 | |
10 | SUN L, ZHANG X Y, QIAN Y H, et al. Feature selection using neighborhood entropy-based uncertainty measures for gene expression data classification[J]. Information Sciences, 2019, 502: 18-41. 10.1016/j.ins.2019.05.072 |
11 | 李懿恒,杜晨曦,杨燕燕,等. 基于伪标签一致度的不平衡数据特征选择算法[J]. 计算机应用, 2022, 42(2): 475- 484. 10.11772/j.issn.1001-9081.2021050957 |
LI Y H, DU C X, YANG Y Y, et al. Feature selection algorithm for imbalanced data based on pseudo-label consistency [J]. Journal of Computer Applications, 2022, 42(2): 475- 484. 10.11772/j.issn.1001-9081.2021050957 | |
12 | 林耀进,陈祥焰,白盛兴,等. 基于最大决策边界的高维类不平衡数据在线流特征选择[J]. 模式识别与人工智能, 2020, 33(9): 820-829. |
LIN Y J, CHEN X Y, BAI S X, et al. Online streaming feature selection for high-dimensional and class-imbalanced data based on max-decision boundary[J]. Pattern Recognition and Artificial Intelligence, 2020, 33(9): 820-829. | |
13 | CHEN H M, LI T R, FAN X, et al. Feature selection for imbalanced data based on neighborhood rough sets[J].Information Sciences, 2019, 483: 1-20. 10.1016/j.ins.2019.01.041 |
14 | 张亚钏,李浩,宋晨明,等. 混合人工化学反应优化和狼群算法的特征选择[J]. 计算机科学, 2021, 48(11A): 93-101,129. 10.11896/jsjkx.210100067 |
ZHANG Y C, LI H, SONG C M, et al. Hybrid artificial chemical reaction optimization with wolf colony algorithm for feature selection[J]. Computer Science, 2021, 48(11A): 93-101, 129. 10.11896/jsjkx.210100067 | |
15 | 贾鹤鸣,姜子超,李瑶,等. 基于改进斑点鬣狗优化算法的同步优化特征选择[J]. 计算机应用, 2021, 41(5): 1290-1298. |
JIA H M, JIANG Z C, LI Y, et al. Simultaneous feature selection optimization based on improved spotted hyena optimizer algorithm [J]. Journal of Computer Applications, 2021, 41(5): 1290-1298. | |
16 | MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51-67. 10.1016/j.advengsoft.2016.01.008 |
17 | AGRAWAL R K, KAUR B, SHARMA S. Quantum based whale optimization algorithm for wrapper feature selection [J]. Applied Soft Computing, 2020, 89: No.106092. 10.1016/j.asoc.2020.106092 |
18 | TAWHID M A, IBRAHIM A M. Feature selection based on rough set approach, wrapper approach, and binary whale optimization algorithm[J]. International Journal of Machine Learning and Cybernetics, 2020, 11(3): 573-602. 10.1007/s13042-019-00996-5 |
19 | 谢娟英,吴肇中. 基于可辨识矩阵的完全自适应2D特征选择算法[J]. 软件学报, 2022, 33(4): 1338-1353. |
XIE J Y, WU Z Z. Totally adaptive 2D feature selection algorithm based on discernibility matrix [J]. Journal of Software, 2022, 33(4): 1338-1353. | |
20 | 王生武,陈红梅. 基于粗糙集和改进鲸鱼优化算法的特征选择方法[J]. 计算机科学, 2020, 47(2): 44-50. 10.11896/jsjkx.181202285 |
WANG S W, CHEN H M. Feature selection method based on rough sets and improved whale optimization algorithm[J]. Computer Science, 2020, 47(2): 44-50. 10.11896/jsjkx.181202285 | |
21 | 姚晟,李初宴,陈悦. 基于非平衡数据下不完备混合型信息系统的属性约简[J]. 计算机应用研究, 2021, 38(5): 1331-1335. |
YAO S, LI C Y, CHEN Y. Attribute reduction of incomplete hybrid information system based on unbalanced data[J]. Application Research of Computers, 2021, 38(5): 1331-1335. | |
22 | 汤安迪,韩统,徐登武,等. 混沌精英哈里斯鹰优化算法[J]. 计算机应用, 2021, 41(8): 2265-2272. 10.11772/j.issn.1001-9081.2020101610 |
TANG A D, HAN T, XU D W, et al. Chaotic elite Harris hawk optimization algorithm [J]. Journal of Computer Applications, 2021, 41(8): 2265-2272. 10.11772/j.issn.1001-9081.2020101610 | |
23 | 张磊,刘升,高文欣,等 多子群改进的海洋捕食者算法 [J]. 微电子学与计算机, 2022, 39(2): 51-59. 10.3969/j.issn.1000-7180.2022.1.wdzxyjsj202201007 |
ZHANG L, LIU S, GAO W X, et al. Improved marine predators algorithm with multi-subpopulation [J]. Microelectronics and Computer, 2022, 39(2): 51-59. 10.3969/j.issn.1000-7180.2022.1.wdzxyjsj202201007 | |
24 | POLI R, KENNEDY J, BLACKWELL T. Particle swarm optimization [J]. Swarm Intelligence, 2007, 1(1): 33-57. 10.1007/s11721-007-0002-0 |
25 | 孙林,黄金旭,徐久成,等. 基于自适应鲸鱼优化算法和容错邻域粗糙集的特征选择算法[J]. 模式识别与人工智能, 2022, 35(2): 150- 165. |
SUN L, HUANG J X, XU J C, et al. Feature selection based on adaptive whale optimization algorithm and fault-tolerance neighborhood rough sets[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(2): 150-165. | |
26 | SUN L, ZHANG J X, DING W P, et al. Feature reduction for imbalanced data classification using similarity-based feature clustering with adaptive weighted K-nearest neighbors[J]. Information Sciences, 2022, 593: 591-613. 10.1016/j.ins.2022.02.004 |
27 | HU Q H, YU D R, LIU J F, et al. Neighborhood rough set based heterogeneous feature subset selection [J]. Information Sciences, 2008, 178(18): 3577-3594. 10.1016/j.ins.2008.05.024 |
28 | LIU J F, HU Q H, YU D R. A weighted rough set-based method developed for class imbalance learning [J]. Information Sciences, 2008, 178(4): 1235-1256. 10.1016/j.ins.2007.10.002 |
29 | FRANK E, HALL M, HOLMES G, et al. Data Mining and Knowledge Discovery Handbook[M]. Boston: Springer, 2009: 1269-1277. 10.1007/978-0-387-09823-4_66 |
30 | MOAYEDIKIA A, ONG K L, BOO Y L, et al. Feature selection for high dimensional imbalanced class data using harmony search[J]. Engineering Applications of Artificial Intelligence, 2017, 57: 38-49. 10.1016/j.engappai.2016.10.008 |
31 | WANG C Z, SHI Y P, FAN X D, et al. Attribute reduction based on k-nearest neighborhood rough sets [J]. International Journal of Approximate Reasoning, 2019, 106: 18-31. 10.1016/j.ijar.2018.12.013 |
32 | 盛魁,卞显福,董辉,等. 基于邻域粗糙集组合度量的混合数据属性约简算法[J]. 计算机应用与软件, 2020, 37(2): 234-239. 10.3969/j.issn.1000-386x.2020.02.036 |
SHENG K, BIAN X F, DONG H, et al. Attribute reduction of mixed data based on neighborhood rough set combination metrics[J]. Computer Applications and Software, 2020, 37(2): 234-239. 10.3969/j.issn.1000-386x.2020.02.036 | |
33 | WU X D, YU K, DING W, et al. Online feature selection with streaming features [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(5): 1178-1192. 10.1109/tpami.2012.197 |
34 | YU K, WU X D, DING W, et al. Scalable and accurate online feature selection for big data [J]. ACM Transactions on Knowledge Discover from Data, 2016, 11(2): No.16. 10.1145/2976744 |
35 | ZHOU P, HU X G, LI P P, et al. Online streaming feature selection using adapted neighborhood rough set[J]. Information Sciences, 2019, 481: 258-279. 10.1016/j.ins.2018.12.074 |
36 | ZHOU P, HU X G, LI P P, et al. OFS-Density: a novel online streaming feature selection method[J]. Pattern Recognition, 2018, 86: 48-61. 10.1016/j.patcog.2018.08.009 |
37 | ZHOU J, FOSTER D P, STINE R A, et al. Streamwise feature selection[J]. Journal of Machine Learning Research, 2006, 7: 1861-1885. 10.1145/1081870.1081914 |
[1] | Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703. |
[2] | Hong CHEN, Bing QI, Haibo JIN, Cong WU, Li’ang ZHANG. Class-imbalanced traffic abnormal detection based on 1D-CNN and BiGRU [J]. Journal of Computer Applications, 2024, 44(8): 2493-2499. |
[3] | Qiangkui LENG, Xuezi SUN, Xiangfu MENG. Oversampling method for imbalanced data based on sample potential and noise evolution [J]. Journal of Computer Applications, 2024, 44(8): 2466-2475. |
[4] | Mingzhu LEI, Hao WANG, Rong JIA, Lin BAI, Xiaoying PAN. Oversampling algorithm based on synthesizing minority class samples using relationship between features [J]. Journal of Computer Applications, 2024, 44(5): 1428-1436. |
[5] | Lin GAO, Yu ZHOU, Tak Wu KWONG. Evolutionary bi-level adaptive local feature selection [J]. Journal of Computer Applications, 2024, 44(5): 1408-1414. |
[6] | Lin SUN, Menghan LIU. K-means clustering based on adaptive cuckoo optimization feature selection [J]. Journal of Computer Applications, 2024, 44(3): 831-841. |
[7] | Dapeng XU, Xinmin HOU. Feature selection method for graph neural network based on network architecture design [J]. Journal of Computer Applications, 2024, 44(3): 663-670. |
[8] | Shengjie MENG, Wanjun YU, Ying CHEN. Feature selection algorithm for high-dimensional data with maximum correlation and maximum difference [J]. Journal of Computer Applications, 2024, 44(3): 767-771. |
[9] | Jingxin LIU, Wenjing HUANG, Liangsheng XU, Chong HUANG, Jiansheng WU. Unsupervised feature selection model with dictionary learning and sample correlation preservation [J]. Journal of Computer Applications, 2024, 44(12): 3766-3775. |
[10] | Du CHEN, Yuanyuan LI, Yu CHEN. Directed gene regulatory network inference algorithm based on t-test and stepwise network search [J]. Journal of Computer Applications, 2024, 44(1): 199-205. |
[11] | Tian HE, Zongxin SHEN, Qianqian HUANG, Yanyong HUANG. Adaptive learning-based multi-view unsupervised feature selection method [J]. Journal of Computer Applications, 2023, 43(9): 2657-2664. |
[12] | Hanchen LI, Shunxiang ZHANG, Guangli ZHU, Tengke WANG. Chinese homophonic neologism discovery method based on Pinyin similarity [J]. Journal of Computer Applications, 2023, 43(9): 2715-2720. |
[13] | Xiang GUO, Wengang JIANG, Yuhang WANG. Encrypted traffic classification method based on improved Inception-ResNet [J]. Journal of Computer Applications, 2023, 43(8): 2471-2476. |
[14] | Jinghuan LAO, Dong HUANG, Changdong WANG, Jianhuang LAI. Multi-view ensemble clustering algorithm based on view-wise mutual information weighting [J]. Journal of Computer Applications, 2023, 43(6): 1713-1718. |
[15] | Dongliang MU, Meng HAN, Ang LI, Shujuan LIU, Zhihui GAO. Overview of classification methods for complex data streams with concept drift [J]. Journal of Computer Applications, 2023, 43(6): 1664-1675. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||