Dynamic Weight Importance Sampling for Low Cost Spatiotemporal Sensing

TL;DR

This paper introduces a low-cost, dynamic importance sampling method for spatiotemporal sensing that uses contour lines to efficiently select sensors and maintain accurate signal estimation with limited observations.

Contribution

It presents a novel dynamic weight importance sampling approach that adapts sensor selection in real-time for efficient spatiotemporal signal monitoring.

Findings

DWIS achieves low-cost spatial signal estimation.

The method maintains accuracy with limited sensor observations.

Performance is validated across different contour level schemes.

Abstract

A simple and low cost dynamic weight importance sampling (DWIS) implementation is presented and discussed for spatiotemporal sensing of unknown correlated signals in sensor field. The spatial signal is compressed into its contour lines and a partitioned subset of sensors that their observations are in a given margin of the contour levels, is used for importance sampling. The selected sensor population is changed dynamically to maintain the low cost and acceptable spatial signal estimation from limited observations. The estimation performance, cost and convergence of the proposed approach is evaluated for spatial and temporal monitoring, using three different contour level definition schemes. The results show that using DWIS and modeling the spatial signal with contour lines is low cost. In this study the presence of noise in sensor observations is ignored. The number of participant sensors is taken as modeling cost.