Research Article

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

Table 6

The statistical results of the second group for experiment 1 with the SVM classifier.

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

Reduction 1193.0086.00100.0011.6488
296.2596.0096.5012.5511
398.5099.0098.0013.1509
497.2598.5096.0013.4468
599.25100.0098.5014.4839
Average value96.8595.9097.8013.0563
Reduction 2194.2589.0099.5012.1096
297.2597.0097.5012.8636
398.0098.0098.0013.5677
497.5098.0097.0013.8196
598.7599.0098.5013.6691
Average value97.1596.2098.1013.2059
Reduction 3193.0087.5098.508.7757
297.2597.5097.0010.3424
397.7598.0097.5010.7411
497.7598.5097.0011.2344
599.00100.0098.0011.3006
Average value96.9596.3097.6010.4788
Reduction 4193.7587.50100.0014.6417
296.5097.5095.5015.4736
397.5097.0098.0015.7621
498.0099.0097.0016.1355
599.25100.0098.5016.3381
Average value97.0096.2097.8015.6702
Reduction 5192.5086.5098.5012.4933
296.7598.0095.5014.0057
398.0098.0098.0014.5194
498.0099.0097.0014.5792
599.5099.5099.5015.0400
Average value96.9596.2097.7014.1275