MOGA algorithm for multi-objective optimization of aircraft detection

This paper presents effective multi-objective genetic algorithms (MOGA) method, whose character lies in that evolutionary population is preference ranked based on concordance model, which was applied to a multi-objective optimization of aircraft, measure of fitness degree was discussed as an emphasis. The solutions were analyzed and compares with original BP neural networks algorithm, which is better than the network trained only on alternating momentum, which can performed well neural networks and have shown the superiority to the network structure. Based the pareto optimal approaches are equipped with a fast identifying ability in capturing the learned objects, and in the meantime it can adapt the new objects. The experiments with variety of image show that the method proposed is efficient and useful, the result demonstrates that convergence speed is faster than traditional algorithm; target was recognized by this algorithm and can increase recognition precision.