This paper aimed to evaluate the impact of Euclidean and Manhattan distance metrics on Kmeans algorithm using for clustering KDD cup99 intrusion detection data. Experimental results indicate that Manhattan distance metric performs better in terms of performance evaluation metrics than Euclidean distance metric.
Nội dung trích xuất từ tài liệu:
The impact of distance metrics on K-means clustering algorithm using in network intrusion detection data
The impact of distance metrics on K-means clustering algorithm using in network intrusion detection data
Số trang: 4
Loại file: pdf
Dung lượng: 226.38 KB
Lượt xem: 37
Lượt tải: 0
Thông tin tài liệu:
Tìm kiếm theo từ khóa liên quan:
International Journal of Computer Networks and Communications Security Distance metrics on K-means clustering algorithm Network intrusion detection data Performance evaluation metrics Euclidean distance metricTài liệu có liên quan:
-
Design of a neural controller applied a level system in hart protocol
6 trang 218 0 0 -
Web spam detection inspired by the immune system
13 trang 37 0 0 -
Securing the sip communications with XML security mechanisms in VoIP application awareness
7 trang 36 0 0 -
The factors affecting the performance of foreign direct investment (FDI) enterprises in Vietnam
8 trang 36 0 0 -
Review: Information retrieval techniques and applications
5 trang 35 0 0 -
Studying performance in supply chain management using data mining software
6 trang 30 0 0 -
The application of cellular learning automata in individuals
5 trang 29 0 0 -
A review: Distributed file system
6 trang 28 0 0 -
Land cover classification using hidden markov models
8 trang 27 0 0 -
5 trang 25 0 0
