By Topic

Randomized algorithm based entropy norm computation in hardware for anomaly detection of IP data streams

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Nagalakshmi, S.J. ; Minist. of Health & Long-Term Care, ON, Canada

Entropy measurements have been used for anomaly detection purposes in IP data streams. Randomized algorithms with efficient storage requirements for estimating entropy of data streams are now available in the literature. The main challenge in software implementation for IP data streams has been in storing large volumes of data, along with, the requirement of analysis at high speed. Although hardware architectures for executing such algorithms would be several orders of magnitude faster than software, no attempts to explore hardware for this purpose have been made so far. In this paper, a randomized algorithm available in literature is evaluated for hardware implementation. First the chosen randomized algorithm is improved to obtain a 30.0% reduction in memory requirements. Next two hardware architectural designs are described and analyzed for possible FPGA implementation. The corresponding trade-offs, limitations and resource requirements are discussed.

Published in:

Science and Technology for Humanity (TIC-STH), 2009 IEEE Toronto International Conference

Date of Conference:

26-27 Sept. 2009