Spatio-temporal diffusion mechanisms for adaptation over networks

摘要

This work develops diffusion algorithms for adaptation over networks that endow nodes with both cooperation abilities and temporal processing abilities. Each node is allowed to share information locally with its neighbors. At the same time, each node filters past data and uses them to enhance the collaborative process. In this manner, the resulting algorithms consist of three stages: adaptation, spatial processing, and temporal processing. The order of these operations can be inter-changed leading to a total of six variations. The results indicate that the version that performs adaptation prior to the steps of spatial cooperation and temporal processing leads to best performance.