Research Article

A New Generalized Deep Learning Framework Combining Sparse Autoencoder and Taguchi Method for Novel Data Classification and Processing

Table 5

Autoencoder 1 S/N ratios obtained in the Taguchi experimental design for DDOS attack detection.

LevelsHSMEL2SRSP

1-27.72-27.72-27.33-27.59-27.83
2-27.54-27.69-27.28-27.09-27.33
3-27.31-27.31-27.49-27.54-27.25
4-26.91-27.44-27.49-27.54-27.25
5-27.68-27.51-27.32-27.34-27.18
Delta 0.80 0.46 0.48 0.51 0.65
Rank 1 5 4 3 2