Effective and efficient network anomaly detection system using machine learning algorithm

Abstract

Network anomaly detection system enables to monitor computer network that behaves differently from the network protocol and it is many implemented in various domains. Yet, the problem arises where different application domains have different defining anomalies in their environment. These make a difficulty to choose the best algorithms that suit and fulfill the requirements of certain domains and it is not straightforward. Additionally, the issue of centralization that cause fatal destruction of network system when powerful malicious code injects in the system. Therefore, in this paper we want to conduct experiment using supervised Machine Learning (ML) for network anomaly detection system that low communication cost and network bandwidth minimized by using UNSW-NB15 dataset to compare their performance in term of their accuracy (effective) and processing time (efficient) for a classifier to build a model. Supervised machine learning taking account the important features by labelling it from the datasets. The best machine learning algorithm for network dataset is AODE with a comparable accuracy is 97.26% and time taken approximately 7 seconds. Also, distributed algorithm solves the issue of centralization with the accuracy and processing time still a considerable compared to a centralized algorithm even though a little drop of the accuracy and a bit longer time needed.

Partial discharge measurement in solid dielectric of H.V Cross-linked polyethylene (XLPE) submarine cable

“…The main factors which lead to insulation break-down of in solid dielectrics are by thermal, intrinsic, treeing phenomenon, electromechanical and the presence of voids. The break-down of solid insulation not only depend on the applied voltage magnitude but also on the time, for which voltage is applied [23].…”

Design and development of Bi directional power meter using microcontroller

“…The positive power that is absorbed by the load can be determined by the difference between the phases of voltage and current coming from the grid to the load. If there is no phase difference between the voltage and current, then the power is positive [15][16][17][18][19][20].…”

Fault isolation technique for decentralized survivable communication network systems via regions and paths

“…Fault isolation is very important, since a minor fault might generate costly damages to whole network due to the spread of the fault [6]. In computer network, varieties of techniques are available to agree on accurate location of faults [7].…”