Research Article

Network Intrusion Detection Based on Sparse Autoencoder and IGA-BP Network

Table 5

The comparison result of AC (%).

MethodsG1G2G3G4G5

BPNN [31]94.592.795.1295.5793.35
PCA-PSO-BP [8]90.689.590.1291.2790.44
PCA-ANN [6]94.3592.795.1295.5793.35
KPCA-SVM [9]95.494.195.896.4595.32
RNN [32]97.195.697.2197.196.51
DBN [33]97.3195.0197.1297.5796.65
CNN-WDLSTM [34]97.5296.0497.4597.7197.10
Proposed97.6897.2697.7298.2797.25