The EML registration is achieved by two step recursive optimization. The quick convergence is assured through the improved Gauss Newton algorithm.
该算法通过两步 递 归最优化方法来实现 ,并采用改进的高斯—牛顿法来确保算法的快速收敛 性。
A cost function is presented, and by applying Gaussian-Newton type recursive prediction error based method, a stable and efficient online frequency estimation algorithm is derived.
在此基础上,建立了最小方差损失函数,并结合高斯·牛顿预测误差方法,提出了稳定的,高性能的,在线的复频率直接估计算法。
应用推荐