Title :
Memory reduction by intermediate result value encoding for content-based classification
Author :
Oh, H.-S. ; Kyung, C.M.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., KAIST, Daejeon, South Korea
Abstract :
A method for content-based classification using results from a string search and a layer 3-4 lookup is proposed. Encoding of the intermediate result value enables wire-speed processing while reducing the memory by over 70% compared to the dependent search scheme. Rule partitioning by range types helps to encode ranges within a minute for an intrusion-detection rule set having about 1000 rules.
Keywords :
content-addressable storage; encoding; knowledge based systems; logic partitioning; packet switching; pattern classification; table lookup; content-based classification; intermediate result value encoding; intrusion-detection rule; layer 3-A lookup; memory reduction; rule partitioning; string search; wire-speed processing;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20045115
