TR-IDS: Anomaly-Based Intrusion Detection through Text-Convolutional Neural Network and Random Forest

Table 2

Preprocessing results of the ISCX2012 dataset.

Category	Count	Percentage	Training count	Testing count
Normal	10000	28.28%	6971	3029
Infiltration	9925	28.07%	6930	2995
BFSSH	7042	19.92%	4911	2131
DDoS	4963	14.04%	3513	1450
HttpDoS	3427	9.69%	2424	1003
Total	35357	100%	24749	10608