A new system for identifying potential Internet threats, which may also have application in areas such as health-care monitoring, is under development at the University of Texas at Dallas. Designed to analyze behavioral data, the system monitors network traffic and provides an alert when it notices worrisome deviations in normal activity. "We proposed a novel platform that thoroughly analyzes network traffic behavior to identify potential Internet threats," says UT Dallas professor Mehrdad Nourani.
The technology uses two subsystems that work in parallel to reach a high speed and use memory efficiently, which allows for faster results and optimal use of resources. A bell-shaped curve of normal activity is built, and it can achieve nearly zero false positives and negatives when identifying abnormalities outside the curve. Nourani says the technology also could be used to analyze health data and detect abnormal health issues such as heart arrhythmia, sleep apnea, or epileptic seizure.
From UT Dallas News
View Full Article
Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA