论文部分内容阅读
来自多传感器的目标特征往往是高维数的,并且包含了更多的冗余信息和噪声。为了减小数据获取的代价,提高目标识别器的性能和效率,提出了基于遗传算法(GA)的多传感器目标识别系统特征优化方法。将遗传算法与神经网络目标分类器结合,通过识别结果的反馈信息,控制GA的遗传进化方向,从而实现特征优化。为了克服遗传算法的未成熟收敛问题,提出了相关选择与自适应遗传算子相结合的改进遗传算法。仿真实验结果验证了方法的有效性。
The target features from the multi-sensor tend to be high-dimensional and contain more redundant information and noise. In order to reduce the cost of data acquisition and improve the performance and efficiency of target recognizer, a method of feature optimization based on genetic algorithm (GA) for multi-sensor target recognition system is proposed. By combining genetic algorithm with neural network target classifier, the genetic evolution direction of GA is controlled by the feedback information of recognition result, so as to realize feature optimization. In order to overcome the immature convergence problem of genetic algorithm, an improved genetic algorithm combining related selection with adaptive genetic operator is proposed. Simulation results verify the effectiveness of the method.