Automatic Spotting of Sceptical Activity with Visualization Using Elastic Cluster for Network Traffic in Educational Campus

Abstract

An automatic sceptical recognition model to identify the suspicious or the malicious activity in the network of the educational institutional campus is laid out in the paper. The carried out work in the paper kindles the network traffic flow in the educational campus and identifies the unwanted activities and stops them. The detected activities are visualized in the real time using a personalized reportage dash board. The design integrates the open source tools to provide an accurate evaluation utilizing the engine for the identifying and preventing the suspicious activities. The suspicious events identified are computed in the elastic cluster to visualize the intimidations. The laid out model computes the events identified and raises alarms. The elastic cluster founded on the No-SQL reports the happenings occurring in real time. The system is initially allowed to learn the various type of network attacks, once trained it the designed model automatically stops the malicious activities in the network traffic. This enhances the security for the campus networks by utilizing the open source libraries as well as minimizes cost imposed by the commercial identification and the prevention system.