Abstract: A new discretized approach for continuous attributes was presented. As we know, the basic rough set theory can not deal with continuous attributes, so the continuous attributes need to be discretization. Firstly, the disadvantages of original information entropy were analyzed. Secondly, the distance factor was introduced to expand the information entropy. At last two basic rules were presented to calculate expanded information entropy and DS evidential theory was used to process the mass up-focus. Simulation results show the availability of this new information fusion algorithm.