Active Surveillance via Group Sparse Bayesian Learning
Lists
Only you see this
Abstract
The key to the effective control of a diffusion system lies in how accurately we could predict its unfolding dynamics based on the observation of its current state. However, in the real-world applications, it is often infeasible to conduct a timely and yet comprehensive observation due to resource constraints. In view of such a practical challenge, the goal of this work is to develop a novel computational method for performing active observations, termed active surveillance, with limited resources. Specifically, we aim to predict the dynamics of a large spatio-temporal diffusion system based on the observations of some of its components. Towards this end, we introduce a novel measure, the <inline-formula><tex-math notation="LaTeX">$\boldsymbol{\gamma }$</tex-math></inline-formula> value, that enables us to identify the key components by means of modeling a sentinel network with a row sparsity structure. Having obtained a theoretical understanding of the <inline-formula><tex-math notation="LaTeX">$\boldsymbol{\gamma }$</tex-math></inline-formula> value, we design a backward-selection sentinel network mining algorithm (SNMA) for deriving the sentinel network via <i>group sparse Bayesian learning</i> . In order to be practically useful, we further address the issue of scalability in the computation of SNMA, and moreover, extend SNMA to the case of a non-linear dynamical system that could involve complex diffusion mechanisms. We show the effectiveness of SNMA by validating it using both synthetic datasets and five real-world datasets. The experimental results are appealing, which demonstrate that SNMA readily outperforms the state-of-the-art methods.
BibTeX
@article{pei2022active,
author = {Hongbin Pei and Bo Yang and Jiming Liu and Kevin Chen-Chuan Chang},
title = {{Active Surveillance via Group Sparse Bayesian Learning}},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
year = {2022},
doi = {10.1109/tpami.2020.3023092},
}Loading related content...