This paper describes rough genetic algorithms based on the notion of interv
al values. A gene in a rough genetic algorithm can be represented using an
interval. The paper explains how this generalization facilitates developmen
t of new genetic operators and evaluation measures. Various operations of r
ough genetic algorithms arc illustrated using a simple document retrieval e
xample. An experiment involving classification of interval-valued traffic p
atterns demonstrates the usefulness of rough genetic algorithms for real-wo
rld applications. A discussion on further extensions of rough genetic algor
ithms to rough sets is also included.