Abstract: The applications of generalized rough set theory were researched for the construction and optimization of radar anti-jamming performance evaluation index system. A mass of real-valued data was converted to some interval-valued data to avoid the difficulty of classification. The H'- information entropy-based information filling technique was employed to solve the problem of missing evaluation data. The E-condition entropy-based heuristic algorithm was applied to make attribute reduction, optimize evaluation index system, and extract final decision rules. The feasibility, validity and practicability of proposed method were testified by a simulation example.

Key words: generalized rough set, radar anti-jamming performance evaluation, construction and optimization of evaluation index system, simulation and analysis