Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Learnable WSN Deployment of Evidential Collaborative Sensing Model

Ruijie Liu, Tianxiang Zhan, Zhen Li, Yong Deng

TL;DR

This work tackles the problem of achieving high-quality area coverage in wireless sensor networks under uncertainty. It introduces an evidential collaborative sensing framework based on Dempster-Shafer theory and a Learnable Sensor Deployment Network (LSDNet) that optimizes sensor coordinates by balancing contribution and detection capability. The approach yields two practical tools: (1) an optimal LSDNet-based deployment that maximizes coverage with gradient-based sensor relocation, and (2) a greedy minimum-sensor algorithm that guarantees full coverage. Numerical and real-world forest monitoring experiments demonstrate superior coverage, robustness to initialization, and favorable computational efficiency compared with traditional swarm-based methods, highlighting the method’s potential for scalable, uncertainty-aware WSN deployment.

Abstract

In wireless sensor networks (WSNs), coverage and deployment are two most crucial issues when conducting detection tasks. However, the detection information collected from sensors is oftentimes not fully utilized and efficiently integrated. Such sensing model and deployment strategy, thereby, cannot reach the maximum quality of coverage, particularly when the amount of sensors within WSNs expands significantly. In this article, we aim at achieving the optimal coverage quality of WSN deployment. We develop a collaborative sensing model of sensors to enhance detection capabilities of WSNs, by leveraging the collaborative information derived from the combination rule under the framework of evidence theory. In this model, the performance evaluation of evidential fusion systems is adopted as the criterion of the sensor selection. A learnable sensor deployment network (LSDNet) considering both sensor contribution and detection capability, is proposed for achieving the optimal deployment of WSNs. Moreover, we deeply investigate the algorithm for finding the requisite minimum number of sensors that realizes the full coverage of WSNs. A series of numerical examples, along with an application of forest area monitoring, are employed to demonstrate the effectiveness and the robustness of the proposed algorithms.

Learnable WSN Deployment of Evidential Collaborative Sensing Model

TL;DR

This work tackles the problem of achieving high-quality area coverage in wireless sensor networks under uncertainty. It introduces an evidential collaborative sensing framework based on Dempster-Shafer theory and a Learnable Sensor Deployment Network (LSDNet) that optimizes sensor coordinates by balancing contribution and detection capability. The approach yields two practical tools: (1) an optimal LSDNet-based deployment that maximizes coverage with gradient-based sensor relocation, and (2) a greedy minimum-sensor algorithm that guarantees full coverage. Numerical and real-world forest monitoring experiments demonstrate superior coverage, robustness to initialization, and favorable computational efficiency compared with traditional swarm-based methods, highlighting the method’s potential for scalable, uncertainty-aware WSN deployment.

Abstract

In wireless sensor networks (WSNs), coverage and deployment are two most crucial issues when conducting detection tasks. However, the detection information collected from sensors is oftentimes not fully utilized and efficiently integrated. Such sensing model and deployment strategy, thereby, cannot reach the maximum quality of coverage, particularly when the amount of sensors within WSNs expands significantly. In this article, we aim at achieving the optimal coverage quality of WSN deployment. We develop a collaborative sensing model of sensors to enhance detection capabilities of WSNs, by leveraging the collaborative information derived from the combination rule under the framework of evidence theory. In this model, the performance evaluation of evidential fusion systems is adopted as the criterion of the sensor selection. A learnable sensor deployment network (LSDNet) considering both sensor contribution and detection capability, is proposed for achieving the optimal deployment of WSNs. Moreover, we deeply investigate the algorithm for finding the requisite minimum number of sensors that realizes the full coverage of WSNs. A series of numerical examples, along with an application of forest area monitoring, are employed to demonstrate the effectiveness and the robustness of the proposed algorithms.
Paper Structure (24 sections, 39 equations, 15 figures, 4 tables, 2 algorithms)

This paper contains 24 sections, 39 equations, 15 figures, 4 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Problem description and formulation
  3. Classic Sensing Models
  4. D-S Evidence Theory
  5. Performance Evaluation of Evidential Fusion System
  6. Evidential Collaborative Sensing Model
  7. Evidential Sensing Model
  8. Collaborative Sensing Model Based on Evidential Fusion
  9. A Learnable Framework for WSN Deployment
  10. Optimal WSN Deployment of LSDNet
  11. Minimum Sensors Acquisition for WSN Full Coverage
  12. Applications
  13. Numerical Examples
  14. Comparative Experiments
  15. Sensitivity Analysis
  16. ...and 9 more sections

Figures (15)

  • Figure 1: The probability of detection using two sensing models.
  • Figure 2: The collaborative sensing system $k$ to detect the target $t_j$.
  • Figure 3: Change of the belief entropy and Hartley entropy with respect to $a$.
  • Figure 4: Learnable framework of WSN deployment.
  • Figure 5: An example of sensors overlap.
  • ...and 10 more figures

Theorems & Definitions (9)

  • Definition II.1: Boolean sensing model
  • Definition II.2: Probabilistic sensing model
  • Definition II.3: Frame of Discernment
  • Definition II.4: Mass function
  • Definition II.5: Dempster combination rule
  • Definition II.6: Uncertainty measures
  • proof
  • proof
  • proof