PROJECT TITLE :
MUCM: Multilevel User Cluster Mining Based on Behavior Profiles for Network Monitoring
Mastering user's behavior character is important for economical network management and security monitoring. In this paper, we develop a completely unique framework named as multilevel user cluster mining (MUCM) to measure user's behavior similarity below different network prefix levels. That specialize in aggregated traffic behavior under completely different network prefixes cannot only scale back the amount of traffic flows however conjointly reveal detailed patterns for a cluster of users sharing similar behaviors. 1st, we have a tendency to use the bidirectional flow and bipartite graphs to model network traffic characteristics in massive-scale networks. Four traffic features are then extracted to characterize the user's behavior profiles. Second, an economical methodology with adjustable weight factors is used to calculate the user's behavior similarity, and entropy gain is applied to select the weight issue adaptively. Using the behavior similarity metrics, a simple clustering algorithm based mostly on -means is employed to perform user clustering primarily based on behavior profiles. Finally, we tend to examine the applications of behavior clustering in profiling network traffic patterns and detecting anomalous behaviors. The potency of our strategies is verified with intensive experiments using actual traffic traces collected from the northwest region center of China Education and Analysis Network (CERNET), and also the cluster results will be used for flow management and traffic security monitoring.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here