Data mining based wireless network traffic forecasting

2012 ◽  
Author(s):  
Cristina Stolojescu-Crisan
Keyword(s):  
Data Mining ◽  
Wireless Network ◽  
Network Traffic ◽  
Traffic Forecasting

Wireless Network Topology Control: Adjustable Resiliency and Network Traffic Delivery

2021 ◽  
Author(s):  
Joseph P. Macker ◽  
Caleb Bowers ◽  
Sastry Kompella ◽  
Clement Kam ◽  
Jeffery W. Weston
Keyword(s):  
Wireless Network ◽  
Network Topology ◽  
Network Traffic ◽  
Topology Control

Research of wireless network traffic analysis using big data processing technology

2021 ◽  
Author(s):  
Kovtsur Maxim ◽  
Kistruga Anton ◽  
Mikhailova Anastasiya ◽  
Potemkin Pavel ◽  
Volkogonov Vladimir
Keyword(s):  
Big Data ◽  
Data Processing ◽  
Wireless Network ◽  
Network Traffic ◽  
Traffic Analysis ◽  
Processing Technology ◽  
Big Data Processing ◽  
Network Traffic Analysis

scholarly journals Wireless Network Traffic Analysis and Troubleshooting using Raspberry Pi

2018 ◽  
Vol 7 (2.15) ◽  
pp. 58
Author(s):  
Mohamad Nur Haziq Mohd Safri ◽  
Wan Nor Shuhadah Wan Nik ◽  
Zarina Mohamad ◽  
Mumtazimah Mohamad
Keyword(s):  
Wireless Network ◽  
Network Traffic ◽  
Computer Network ◽  
Low Cost ◽  
Access Point ◽  
Traffic Analysis ◽  
Raspberry Pi ◽  
Network Access ◽  
Actual Problem ◽  
Network Traffic Analysis

In the past five decades, computer network has kept up growing with the increases of its complexity. In such situation, the management, monitoring and maintenance of such computer network requires special attention to ensure optimal network access capability is achieved. Wireless network traffic analysis is a process of recording, studying and analyzing packets in wireless network for network performance analysis purposes. In some cases, the quality of network access performance can be very low without knowing the actual problem. Therefore, in this paper, the performance of wireless network traffic is proposed to be analyzed by using a Raspberry Pi which further able to send an alert to network admin to lessen the downtime. Raspberry Pi is a low cost, a small and portable size of a computer board that can be used to plug-in to monitor, keyboard, mouse, pen drive, etc. In this project, a MyTraceroute (MTR) program is installed on the Raspberry Pi to capture the IP of the Access Point (AP) and show packets loss percentage in the network. The results will be saved in the form of text file and sent to network admin by using email. The solution proposed in this paper is able to support solution to a problem on efficient monitoring, managing and maintaining wireless network traffics.    

CLUSTERING-BASED NETWORK INTRUSION DETECTION

2007 ◽  
Vol 14 (02) ◽  
pp. 169-187 ◽  
Author(s):  
SHI ZHONG ◽  
TAGHI M. KHOSHGOFTAAR ◽  
NAEEM SELIYA
Keyword(s):  
Data Mining ◽  
Network Security ◽  
Intrusion Detection ◽  
Unsupervised Learning ◽  
Network Traffic ◽  
Clustering Algorithms ◽  
Network Intrusion Detection ◽  
Learning Methods ◽  
High Detection Rate ◽  
Network Intrusion

Recently data mining methods have gained importance in addressing network security issues, including network intrusion detection — a challenging task in network security. Intrusion detection systems aim to identify attacks with a high detection rate and a low false alarm rate. Classification-based data mining models for intrusion detection are often ineffective in dealing with dynamic changes in intrusion patterns and characteristics. Consequently, unsupervised learning methods have been given a closer look for network intrusion detection. We investigate multiple centroid-based unsupervised clustering algorithms for intrusion detection, and propose a simple yet effective self-labeling heuristic for detecting attack and normal clusters of network traffic audit data. The clustering algorithms investigated include, k-means, Mixture-Of-Spherical Gaussians, Self-Organizing Map, and Neural-Gas. The network traffic datasets provided by the DARPA 1998 offline intrusion detection project are used in our empirical investigation, which demonstrates the feasibility and promise of unsupervised learning methods for network intrusion detection. In addition, a comparative analysis shows the advantage of clustering-based methods over supervised classification techniques in identifying new or unseen attack types.

Sign in / Sign up

Export Citation Format

Share Document