Computational and Mathematical Methods in Medicine / 2015 / Article / Tab 4

Research Article

Binary Matrix Shuffling Filter for Feature Selection in Neuronal Morphology Classification

Table 4

Classification results with different classification models.

Feature selection methodsNaïve Bayes (%)BPNN (%)SVC (%)Average (%)

All features61.35 ± 26.8291.46 ± 1.2297.10 ± 0.4383.30
SVM-RFE30.78 ± 12.9491.38 ± 0.8393.29 ± 1.2071.82
Rough set51.30 ± 3.5992.75 ± 0.4693.05 ± 1.4579.03
BMSF70.53 ± 6.3691.46 ± 1.4597.84 ± 0.5786.61

Average (%)50.8791.8694.73