Garuda - Garba Rujukan Digital

Effective and efficient network anomaly detection system using machine learning algorithm Mukrimah Nawir; Amiza Amir; Naimah Yaakob; Ong Bi Lynn
Bulletin of Electrical Engineering and Informatics Vol 8, No 1: March 2019
Publisher : Institute of Advanced Engineering and Science

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.

Effective and efficient network anomaly detection system using machine learning algorithm Mukrimah Nawir; Amiza Amir; Naimah Yaakob; Ong Bi Lynn
Bulletin of Electrical Engineering and Informatics Vol 8, No 1: March 2019
Publisher : Institute of Advanced Engineering and Science

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.

Corrupted packets discarding mechanism to alleviate congestion in wireless body area network Wan Aida Nadia Wan Abdullah; Naimah Yaakob; R. Badlishah Ahmad; Mohamed Elshaikh Elobaid; Siti Asilah Yah
Indonesian Journal of Electrical Engineering and Computer Science Vol 14, No 2: May 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v14.i2.pp581-587

Generation of high traffic from continuous sensing and collection of medical data from various biosensors on multiple body is most likely to occur in the Wireless Body Area Network (WBAN). This could be a factor to the congestion in the network. Occurrence of congestion would collapse the performances in the WBAN network in terms of increment in delay, high packets loss, reduction in throughput and packet deliver ratio (PDR). The crucial concerns in WBAN are prevention from the loss of critical data and longer delay in the network as they could result to late delivery of medical treatment and possibility of the increase in mortality. Therefore, this study proposes a mechanism to alleviate the congestion from happening in the first place through discarding the corrupted packets before the beginning of data transmission to the base station. Extensive simulations are done in OMNeT+ to analyze the performance of the proposed mechanism by varying traffic from low to high under different number of nodes and constant Bit Error Rate (BER) and packet size. From the finding, it can be concluded that the proposed mechanism shows better performances in terms of low delay and packet loss as well as high throughput and PDR compared to typical WBAN.

Black hole attack behavioral analysis general network scalability Layth A. Khalil Al Dulaimi; R. Badlishah Ahmad; Naimah Yaakob; Mohd Hafiz Yusoff; Mohamed Elshaikh
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 2: February 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v13.i2.pp677-682

A mobile ad hoc network (MANET) is a frameworkless system of different mobile devices known for its self-arranging conduct. MANETs can convey over moderately data transfer capacity compelled routing connections. In a blackhole assault, a malicious node falsely advertises the shortest path to the destination node, intending to disrupt communication. Our objective was to review the impact of a blackhole assault on networks. To accomplish this, we simulated MANET situations, which include the blackhole node, using the OMNET++ simulator to demonstrate the effects of a single blackhole attack and multiple blackhole attacks on MANET performance have examined for networks. We analysed MANET performance under blackhole assaults through the use of performance grids. A mobile ad hoc network (MANET) is a frameworkless system of different mobile devices known for its self-arranging conduct. MANETs can convey over moderately data transfer capacity compelled routing connections. In a blackhole assault, a malicious node falsely advertises the shortest path to the destination node, intending to disrupt communication. Our objective was to review the impact of a blackhole assault on networks. To accomplish this, we simulated MANET situations, which include the blackhole node, using the OMNET++ simulator to demonstrate the effects of a single blackhole attack and multiple blackhole attacks on MANET performance have examined for networks. We analysed MANET performance under blackhole assaults through the use of performance grids..

Behavioral and performance jellyfish attack Layth A. Khalil Al Dulaimi; R. Badlishah Ahmad; Naimah Yaakob; Syadiah Nor Wan Shamsuddin; Mohamed Elshaikh
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 2: February 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v13.i2.pp683-688

Wwe provide a simulation-based study of the effects of jellyfish attacks on mobile ad hoc networks (MANETs). For this purpose we suggest a simulation based on the effects of jellyfish attacks on the network through a number of different scenarios. In particular, we examine how the number of attackers affects performance measures such as the ratio of packet delivery, throughput, and end-to-end delays. The results have enabled us to propose measures to reduce the effects of jellyfish attacks on MANETs.

Impact of clustering in AODV routing protocol for wireless body area network in remote health monitoring system Wan Aida Nadia Wan Abdullah; Naimah Yaakob; R. Badlishah Ahmad; Mohamed Elshaikh Elobaid; Siti Asilah Yah
Indonesian Journal of Electrical Engineering and Computer Science Vol 13, No 2: February 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v13.i2.pp689-695

Proper selection of routing protocol in transmitting and receiving medical data in Wireless Body Area Network (WBAN) is one of the approaches that would help in ensuring high network performances. However, a continuous monitoring of health status through sensing of various vital body signals by multiple biosensors could produce a bulk of medical data and lead to the increase of network traffic. Occurrence of high traffic could result to network’s congestion which have high tendency to loss some of important (critical) data and cause longer delay that would lead to false diagnosis of diseases. In order to analyze and validate this issue, Ad-Hoc On Demand Distance Vector (AODV) which is known as reactive routing protocol is evaluated in WBAN scenario through varying number of nodes and clusters. The presence of clustering helps in reducing the burden of the sink nodes in handling high traffics. The network’s performances of this protocol are measured in terms of end to end delay, percentage packet loss, throughput and energy consumption using Network Simulator (NS-2). Based on the experimental results, the presence of cluster helps in improving network performances by achieving reduction in delay, packet loss and energy consumption. However, low throughput is achieved as number of clusters are increase due to low duty cycle of the nodes.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search