Broadband ML estimation under model order uncertainty

摘要: The number of signals hidden in data plays a crucial role array processing. When this information is not available, conventional approaches apply theoretic criteria or multiple hypothesis tests to simultaneously estimate model order and parameter. These methods are usually computationally intensive, since ML estimates required for hierarchy nested models. In contribution, we propose efficient solution avoid full search procedure address issues unique the broadband case. Our max-search approach computes only maximally hypothesized signals, selects relevant components through testing. Furthermore, introduce criterion based on rank steering matrix reduce indistinguishable caused by overparameterization. Numerical experiments show that despite uncertainty, proposed method achieves comparable estimation detection accuracy as standard methods, but at much lower computational expense.