Research Article

A Model of High-Dimensional Feature Reduction Based on Variable Precision Rough Set and Genetic Algorithm in Medical Image

Table 16

The statistical results of the second group for experiment 3 with the SVM classifier.

Experiment timesAccuracy (%)Sensitivity (%)Specificity (%)Time (s)

Reduction 1192.7586.0099.5018.8497
297.2598.0096.5015.7162
398.5099.0098.0015.8691
498.0099.0097.0016.4603
599.50100.0099.0016.1914
Average value97.2096.4098.0016.6173
Reduction 2194.5089.5099.5019.0813
296.7598.0095.5020.0251
397.7598.0097.5019.7008
498.5099.0098.0020.0924
598.7599.0098.5020.9245
Average value97.2596.7097.8019.9648
Reduction 3194.0088.00100.0013.1369
297.2598.0096.5014.4797
398.0098.0098.0014.2662
497.2598.5096.0014.7190
599.25100.0098.5014.8799
Average value97.1596.5097.8014.2963
Reduction 4193.5087.5099.5024.0456
297.0097.5096.5025.2082
398.0098.0098.0025.1175
497.7599.5096.0027.0188
598.25100.0096.5026.7471
Average value96.9096.5097.3025.6274
Reduction 5193.2588.0098.5018.0959
296.0098.0094.0019.6563
397.5097.5097.5019.6723
498.0099.0097.0020.7829
598.5099.5097.5021.9703
Average value96.6596.4096.9020.0355