K-Modes Clustering Algorithm Based on Weighted Overlap Distance and Its Application in Intrusion Detection
Algorithm 2
The clustering algorithm used in the experiment.
Input: Information table IS = (U, A, V, f), where U = {x1,..., xn}, A = {a1,..., am}; the number of clusters k expected.
Output: A collection of k clusters.
Step 1: according to the previously proposed Ini_Weight algorithm, select k objects from the universe U as the initial center point: z1, ..., zk.
Step 2: calculate the weighted overlap distance between each object x in U and each center point zi, and divide the object x into the cluster represented by the nearest center point.
Step 3: for each current cluster c, recalculate the center point of c based on the frequency of the object’s value on each attribute in c.
Step 4: repeat steps 2 and 3 until the value of the objective function does not change. After each iteration, let t ++.
