• Corpus ID: 211126870

Sampling Policy Design for Tracking Time-varying Graph Signals with Adaptive Budget Allocation

@article{Xie2020SamplingPD,
  title={Sampling Policy Design for Tracking Time-varying Graph Signals with Adaptive Budget Allocation},
  author={Xuan Xie and Hui Feng and Bo Hu},
  journal={2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)},
  year={2020},
  pages={205-210}
}
  • Xuan XieHui FengBo Hu
  • Published 14 February 2020
  • Computer Science
  • 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
There have been many works that focus on the sampling policy design for static graph signals (GS), but few for time-varying GS. In this paper, we concentrate on how to select vertices to sample and how to allocate the sampling budget for a time-varying GS to reduce tracking error. In the Kalman Filter (KF) framework, the problem of sampling policy design and budget allocation is formulated as an infinite horizon sequential decision process, in which the optimal sampling policy is obtained by… 
View on IEEE
arxiv.org

Figures and Tables from this paper

References

SHOWING 1-10 OF 28 REFERENCES

Sensor Selection Based on Generalized Information Gain for Target Tracking in Large Sensor Networks

An equivalent Kalman filter for sensor selection is derived, i.e., generalized information filter, and it is proved that the multistage look-ahead policy that minimizes either the final or the average estimation error covariances of next multiple time steps is equivalent to a myopic sensor selection policy that maximizes the trace of the generalized information gain at each time step.

Adaptive Graph Signal Processing: Algorithms and Optimal Sampling Strategies

This paper recast two classical adaptive algorithms in the graph signal processing framework, namely the least mean squares (LMS) and the recursive least squares (RLS) adaptive estimation strategies, and proposes novel strategies for adaptive learning of signals defined over graphs.

Sparsity-promoting adaptive sensor selection for non-linear filtering

  • S. P. ChepuriG. Leus
  • Computer Science
    2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
This work considers the problem of adaptive sensor selection for applications in which the observations follow a non-linear model, e.g., target/bearing tracking, and designs a sparse selection vector based on the dynamical state model and state estimate.

Design of sampling set for bandlimited graph signal estimation

This work formularizes the problem as the experimental design of a linear regression model if the authors allow multiple measurements on a single node, and uses a probabilistic quantization to get the proportion of sample for each node given the budget of total sample size.

Observing and Tracking Bandlimited Graph Processes

This work jointly considering the graph-time nature of graph signals, named graph processes, for two main tasks: i) observability of graph processes; and ii) tracking ofgraph processes via Kalman filtering; both from a (possibly time-varying) subset of nodes.

Optimal Sampling in Joint Time- and Graph-Domains for Dynamic Complex Networks

It is proved that the dynamic signals can be sampled and fully recovered if the networked dynamics is stable and their initialization is bandlimited, which can inform the optimal placement of experimental probes and sensors on dynamical networks as well as inform the design of each sensor's optimal sampling rate.

Dynamic Programming and Optimal Control

The leading and most up-to-date textbook on the far-ranging algorithmic methododogy of Dynamic Programming, which can be used for optimal control, Markovian decision problems, planning and sequential…

Efficient Sampling Set Selection for Bandlimited Graph Signals Using Graph Spectral Proxies

This work introduces quantities called graph spectral proxies, defined using the powers of the variation operator, in order to approximate the spectral content of graph signals, and forms a direct sampling set selection approach that does not require the computation and storage of the basis elements.

Discrete Signal Processing on Graphs: Sampling Theory

It is shown that perfect recovery is possible for graph signals bandlimited under the graph Fourier transform and the connection to the sampling theory of finite discrete-time signal processing and previous work on signal recovery on graphs is established.

Time-Varying Graph Signal Reconstruction

A new batch reconstruction method of time-varying graph signals is proposed by exploiting the smoothness of the temporal difference signals, and the uniqueness of the solution to the corresponding optimization problem is theoretically analyzed.