Calibrating Network Traffic with One-Dimensional Convolutional Neural Network with Autoencoder and Independent Recurrent Neural Network for Mobile Malware Detection

Table 4

Test set accuracy of 1DCAE-IndRNN models with different hidden layer structures.

IndRNN1DCAE	1 (%)	2	3	4 (%)
1	86.21	87.16%	91.79%	91.23
2	91.32	95.74%	98.32%	97.32
3	93.29	96.48%	97.11%	95.23