Optimal constraint vectors for set-membership affine projection algorithms

详细信息    查看全文

• 作者：Wallace A. Martins^a ; ^{wallace.martins@smt.ufrj.br} ; Markus V.S. Lima^a ; ^{markus.lima@ieee.org} ; Paulo S.R. Diniz^a ; ^{diniz@smt.ufrj.br} ; Tadeu N. Ferreira^b ; ^{tadeu_ferreira@id.uff.br}
• 关键词：Adaptive signal processing ; Set-membership filtering ; Affine projection ; Convex optimization
• 刊名：Signal Processing
• 出版年：2017
• 出版时间：May 2017
• 年：2017
• 卷：134
• 期：Complete
• 页码：285-294
• 全文大小：1701 K
• 卷排序：134

文摘

We show that, in general, the heuristically de ned constraint vectors (CVs) lead to suboptimal solutions. We show how to obtain the optimal CV that agrees with the fundamentals of the set-membership ltering. We show when the widespread used SC-CV coincides with the optimal CV through geometric and formal algebraic arguments. We demonstrate that the simple-choice CV (SC-CV) is asymptotically optimal for statistically white inputs. We conclude that there is no closed-form expression for the optimal CV. The advantages of the proposed optimal CV are better noticed for very statistically colored inputs.