Signal denoising on graphs via graph filtering
GlobalSIP(2014)
摘要
Signal recovery from noisy measurements is an important task that arises in many areas of signal processing. In this paper, we consider this problem for signals represented with graphs using a recently developed framework of discrete signal processing on graphs. We formulate graph signal denoising as an optimization problem and derive an exact closed-form solution expressed by an inverse graph filter, as well as an approximate iterative solution expressed by a standard graph filter. We evaluate the obtained algorithms by applying them to measurement denoising for temperature sensors and opinion combination for multiple experts.
更多查看译文
关键词
signal recovery,optimisation,noisy measurements,signal denoising,signal representation,temperature sensors,approximation theory,approximate iterative solution,graph filtering,graph signal denoising,exact closed-form solution,optimization problem,measurement denoising,discrete signal processing,inverse graph filter,filtering theory,graph theory,standard graph filter,opinion combination,iterative methods,noise reduction,noise,noise measurement,sparse matrices,temperature measurement
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络