关键词: 效果评估, 聚类, 熵, K均值

Abstract:

A K-means cluster evaluation technique using bi-dimensional entropy components was proposed. The attack dataset on the basis of network entropy was preprocessed, a two-dimensional plane was mapped. The output of preprocess as the input of clustering was utilized. And a relation between the attack dataset and the effect category on the basis of K-means algorithm was established, thus an explicit division of attack effect set was achieved. Efficient evaluation was given. Experiment shows that the method can process attack dataset with high efficiency, as well as provide a visualized evaluation result by form of evaluation cluster diagram.

Key words: effect evaluation, clustering, entropy, K-means algorithm