摘要
将人工神经网络的方法用于汽车防撞雷达中的信号处理,该方法基于自相关矩阵分解,通过对Hopfield神经网络能量函数变换,将分解问题转化为一个简单的迭代问题来求解。该方法可用来替代传统的FFT方法,以实现对目标距离的超分辨提取。通过计算机仿真和硬件系统的实际测试研究了它的性能,并与AR算法、MU-SIC算法进行了比较,结果表明该方法具有更好的信噪比和分辨性能。
An artificial neural network method for signal processing of car collision avoidance radar is proposed, It is based on decomposition of auto-correlation matrix. And then decomposition problem is mapped into an iterative one by transforming the energy function of the Hopfield neural network. Simulation results show that this method has higher resolution than the theoreti- cal limit of FFT method and other popular algorithms and its SNR threshold is lower.
出处
《计算机应用研究》
CSCD
北大核心
2005年第11期154-156,共3页
Application Research of Computers
