2002 · 37 citations · 0 references
ComputingAerospace EngineeringComputer ScienceArtificial IntelligenceMachine LearningOptimizationEvolutionary ComputationEvolutionary OptimizationGenetic AlgorithmsNeural NetworksPattern RecognitionRadar SystemsFeedforward Neural NetworksGenetic Algorithm OptimizationHybrid Evolutionary AlgorithmsHybrid Genetic AlgorithmsNeural Network ModelingRadar Classification Training DataTarget Classification
In this paper, a general purposed real valued genetic algorithm model is presented. For the training of neural networks, the hybrid algorithm integrates the real valued algorithm with the well known BP algorithm. It is used to the training of a feedforward neural networks for radar target classification based on 1-D range profile. 50 range profile samples from the real radar data of each of the three aircrafts are used to train the neural network and another 50 range profile samples are used to test the classification performance. The proposed method can also be used to other optimization problems.