Utilizing Machine Learning Approach to Forecast Average Location Determination Errors in Wireless Sensor Networks

This paper introduces collaborative localization algorithms for wireless sensor networks (WSNs) in outdoor environments without GPS. Using a limited number of beacons and anchor nodes, the proposed approach leverages machine learning techniques, specifically Random Forest Regression (RFR) enhanced b...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhihui Zhu, Meifang Zhu
Format: Article
Language:English
Published: Bilijipub publisher 2024-03-01
Series:Journal of Artificial Intelligence and System Modelling
Subjects:
Online Access:https://jaism.bilijipub.com/article_193319_903aa4d1a35807fe9b2b0c44210c9378.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper introduces collaborative localization algorithms for wireless sensor networks (WSNs) in outdoor environments without GPS. Using a limited number of beacons and anchor nodes, the proposed approach leverages machine learning techniques, specifically Random Forest Regression (RFR) enhanced by Smell Agent Optimization (SAO) and Golden Jackal Optimization Algorithm (GJOA), to optimize network performance and minimize localization errors. The scheme employs up to three beacon nodes to accurately determine ordinary nodes' positions. Evaluation shows that employing three beacon nodes reduces the average localization error (ALE) by up to 40% compared to using two. Moreover, the proposed model, RFGJ, exhibits resilience to increased node density, maintaining accuracy even with higher node densities. The RFGJ model outperforms the other evaluated models, consistently achieving lower ALE values and faster localization times than both the RFSA and RF models. This is evident from the RFGJ model's superior performance metrics during training, including the highest R2 value of 0.996 and the lowest Root Mean Squared Error (RMSE) value of 0.028. These findings establish the RFGJ model as a promising tool for optimizing collaborative localization in WSNs, enabling more efficient and reliable localization across various applications.
ISSN:3041-850X