A Novel Framework Design of Network Intrusion Detection Based on Machine Learning Techniques

Algorithm 3

The tree classifier generation process.

	Input: training dateset
	Output: tree structured classifier
	S: number of training samples
	M: number of features. m: number of features input (m << M)
	N: number of trees generated
	If the tree to be generated is less than N,
	Step 1: from the S training samples, take samples S times in a way with a put-back sampling to form a training set
	Step 2: use unselected samples to make predictions and evaluate their errors
	Step 3: for each node, m features are randomly selected
	Step 4: according to these m features, calculate the best split method
	Step 5: grow to be largest extent possible without pruning
	Return tree structured classifier