卷积神经网络与人工水母搜索的图特征选择方法
|
|
孙林, 蔡怡文
|
Convolutional Neural Network and Artificial Jellyfish Search⁃based graph feature selection method
|
|
Lin Sun, Yiwen Cai
|
|
表4 六种算法在10个基准测试函数上的四种评价指标的对比
|
Table 4 Four metrics of six algorithms on ten benchmark test functions
|
|
| Functions | Metrics | WOA | MPA | LSA | WCA | AJS | CSAJS |
|---|
| f1 | Best | 1.09E-85 | 2.60E-26 | 1.74E-11 | 7.91E-15 | 5.31E-96 | 3.98E-110 | | Worst | 3.80E-71 | 1.37E-22 | 9.24E-04 | 1.38E-11 | 1.07E-88 | 1.18E-102 | | Mean | 1.90E-72 | 3.93E-23 | 8.73E-05 | 1.51E-12 | 1.96E-89 | 1.32E-103 | | STD | 8.50E-72 | 3.97E-23 | 2.40E-04 | 3.09E-12 | 3.11E-89 | 2.89E-103 | | f2 | Best | 3.67E-58 | 6.69E-15 | 3.36E+03 | 1.00E-08 | 5.43E-83 | 4.55E-95 | | Worst | 5.11E-51 | 1.17E-12 | 6.78E+01 | 1.00E+01 | 7.49E-79 | 2.11E-92 | | Mean | 4.10E-52 | 3.02E-13 | 1.64E+01 | 5.00E-01 | 1.71E-79 | 2.67E-93 | | STD | 1.15E-51 | 3.60E-13 | 1.91E-01 | 2.24E+00 | 2.09E-79 | 5.24E-93 | | f3 | Best | 1.23E+00 | 8.64E-10 | 1.40E+00 | 2.56E+00 | 3.83E-83 | 1.02E-87 | | Worst | 8.90E+01 | 1.07E-08 | 3.07E+01 | 9.89E+00 | 1.89E-80 | 1.81E-85 | | Mean | 5.02E+01 | 4.40E-09 | 1.01E+01 | 5.37E+00 | 1.43E-80 | 1.44E-85 | | STD | 3.19E+01 | 2.72E-09 | 7.12E+00 | 2.01E+00 | 3.77E-81 | 3.59E-86 | | f4 | Best | 0.00E+00 | 0.00E+00 | 4.98E+1 | 4.68E+01 | 0.00E+00 | 0.00E+00 | | Worst | 1.94E+02 | 0.00E+00 | 1.07E+02 | 2.14E+02 | 0.00E+00 | 0.00E+00 | | Mean | 9.7E+00 | 0.00E+00 | 7.58E+1 | 8.07E+01 | 0.00E+00 | 0.00E+00 | | STD | 4.34E+01 | 0.00E+00 | 1.51E+1 | 3.583E+01 | 0.00E+00 | 0.00E+00 | f5 | Best | 8.88E-16 | 8.88E-16 | 2.12E+0 | 2.65E-05 | 4.44E-15 | 8.88E-16 | | Worst | 7.99E-15 | 8.88E-16 | 7.16E+0 | 3.25E+00 | 4.44E-15 | 8.88E-16 | | Mean | 4.80E-15 | 8.88E-16 | 3.53E+0 | 1.41E+00 | 4.44E-15 | 8.88E-16 | | STD | 2.80E-15 | 0.00E+00 | 1.38E+0 | 1.05E+00 | 3.94E-30 | 3.94E-31 | | f6 | Best | 0.00E+00 | 0.00E+00 | 2.38E-10 | 6.77E-15 | 0.00E+00 | 0.00E+00 | | Worst | 0.00E+00 | 0.00E+00 | 3.61E-2 | 7.60E-02 | 7.66E-15 | 0.00E+00 | | Mean | 0.00E+00 | 0.00E+00 | 8.72E-3 | 1.56E-02 | 6.06E-16 | 0.00E+00 | | STD | 0.00E+00 | 0.00E+00 | 1.10E-2 | 2.24E-02 | 6.95E-15 | 0.00E+00 | | f7 | Best | 1.92E+04 | 1.50E-08 | 3.52E+01 | 2.5E+02 | 6.81E-41 | 6.81E-41 | | Worst | 6.96E+04 | 6.69E-04 | 2.83E+02 | 7.26E-01 | 2.57E-35 | 2.57E-35 | | Mean | 3.89E+04 | 8.84E-05 | 1.35E+02 | 2.15E-01 | 4.02E-37 | 1.22E-36 | | STD | 1.54E+04 | 1.57E-04 | 6.27E+01 | 2.21E-01 | 4.94E-37 | 5.44E-27 | f8 | Best | 5.62E-05 | 1.17E-04 | 1.42E-02 | 1.55E-02 | 1.55E-05 | 5.61E-05 | | Worst | 1.20E-02 | 2.88E-03 | 5.20E-02 | 9.61E-02 | 3.87E-05 | 8.30E-05 | | Mean | 2.77E-03 | 1.21E-03 | 3.34E-02 | 3.35E-02 | 2.78E-05 | 6.21E-05 | | STD | 3.48E-03 | 6.51E-04 | 9.21E-03 | 1.92E-02 | 1.09E-05 | 9.87E-05 | | f9 | Best | 2.70E+01 | 2.46E+01 | 2.20E+01 | 2.08E+00 | 2.90E+01 | 2.90E+01 | | Worst | 2.88E+01 | 2.61E+01 | 4.26E+02 | 1.21E+02 | 2.90E+01 | 2.90E+01 | | Mean | 2.81E+01 | 2.35E+01 | 1.09E+02 | 4.97E+01 | 2.90E+01 | 2.90E+01 | | STD | 6.07E-01 | 4.27E-01 | 8.96E+01 | 3.74E+01 | 0.00E+00 | 0.00E+00 | | f10 | Best | 6.89E+02 | 8.43E-08 | 2.50E-11 | 1.31E-14 | -6.25E+04 | -6.25E+04 | | Worst | 1.26E+00 | 9.74E+02 | 6.22E+01 | 4.34E+03 | -6.25E+04 | -6.25E+04 | | Mean | 4.77E+01 | 1.56E+02 | 5.61E+02 | 2.17E-04 | -6.25E+04 | -6.25E+04 | | STD | 2.53E+00 | 2.47E+02 | 1.37E+01 | 9.70E-04 | 0.00E+00 | 0.00E+00 |
|
|
|