Adaptive Information Filtering: Improvement of the Matching Technique and Derivation of the Evolutionary Algorithm
This document has been relocated to http://scholarsmine.mst.edu/comsci_facwork/232
There was 1 download as of 28 Jun 2016.
Abstract
Adaptive Information Filtering is concerned with filtering information streams in changing environments. The changes may occur both on the transmission side (the nature of the streams can change) and on the reception side (the interests of a user can change). The research described in this report details the progress made in a prototype Adaptive Information Filtering system based on weighted trigram analysis and evolutionary computation. The main improvements of the algorithms employed by the system concern the computation of the distance between weighted trigram vectors and a further analysis of the two-pool evolutionary algorithm. We tested our new prototype system on the Reuters-21578 text categorization test collection.
