Graph Filter Design for Distributed Network Processing: A Comparison between Adaptive Algorithms
Graph Filter Design for Distributed Network Processing: A Comparison between Adaptive Algorithms
复制标题
DOI：
10.1109/sspd51364.2021.9541468
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Atiyeh Alinaghi;Stephan Weiss;V. Stanković;I. Proudler
中科院分区：
文献类型：
--
作者：
Atiyeh Alinaghi;Stephan Weiss;V. Stanković;I. Proudler
图过滤器（GF）由于可以直接以扩散的方式实现而引起了人们极大的兴趣。因此，研究GF以分布式方式实现信号处理操作是有趣的。然而，在大多数GF模型中，输入信号被假设为时不变的、静态的或以非常低的速率变化。除此之外，GF系数通常被设置为节点不变的，即对于所有节点都相同。然而，一般而言，输入信号可以随时间演进，并且底层GF可以具有取决于节点的参数。因此，在本文中，我们考虑动态输入信号和两种类型的GF系数，节点变量，即在不同节点上变化，和节点不变。然后，我们将LMS和RLS算法应用于GF设计，沿着与另外两种称为自适应然后联合收割机（ATC）和联合RLS（CRLS）的算法一起估计GF系数。我们研究和比较的算法的性能，并表明，在节点不变的GF系数的情况下，CRLS给出了最好的性能与最低的均方位移（MSD），而对于节点变化的情况下，RLS代表最好的结果。还研究了输入信号中的偏置效应。
Graph filters (GFs) have attracted great interest since they can be directly implemented in a diffused way. Thus it is interesting to investigate GFs to implement signal processing operations in a distributed manner. However, in most GF models, the input signals are assumed to be time-invariant, static, or change at a very low rate. In addition to that, the GF coefficients are usually set to be node-invariant, i.e. the same for all the nodes. Yet, in general, the input signals may evolve with time and the underlying GF may have parameters dependent on the nodes. Therefore, in this paper, we consider dynamic input signals and both types of GF coefficients, node-variant, i.e. vary on different nodes, and node-invariant. Then, we apply LMS and RLS algorithms for GF design, along with two others called adapt-then-combine (ATC) and combined RLS (CRLS) to estimate the GF coefficients. We study and compare the performance of the algorithms and show that in the case of node-invariant GF coefficients, CRLS gives the best performance with lowest mean-square-displacement (MSD), whereas, for node-variant case, RLS represents the best results. The effect of bias in the input signal has also been examined.