Evaluation of advanced Kalman filter on real-time agricultural soil parameters through an IoT resources-constrained device

Abstract Effective sensor denoising is crucial for accurate, real-time agricultural decision-support systems. This study explores the application of Unscented Kalman Filter (UKF) extensions on resource-constrained devices to improve sensor denoising and enhance the reliability of Internet of Things...

Full description

Saved in:
Bibliographic Details
Main Authors: Egas Jose Armando, Damien Hanyurwimfura, Omar Gatera, Kwang Soo Kim, Athanase Nduwumuremyi
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-05427-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334981268078592
author Egas Jose Armando
Damien Hanyurwimfura
Omar Gatera
Kwang Soo Kim
Athanase Nduwumuremyi
author_facet Egas Jose Armando
Damien Hanyurwimfura
Omar Gatera
Kwang Soo Kim
Athanase Nduwumuremyi
author_sort Egas Jose Armando
collection DOAJ
description Abstract Effective sensor denoising is crucial for accurate, real-time agricultural decision-support systems. This study explores the application of Unscented Kalman Filter (UKF) extensions on resource-constrained devices to improve sensor denoising and enhance the reliability of Internet of Things (IoT) based agricultural soil monitoring. The study was conducted in Ruhango district, Rwanda, utilizing a wireless sensor node equipped with a Raspberry Pi 5 (ARM v8) and an integrated seven-in-one soil sensor measuring temperature, humidity, electrical conductivity, pH, nitrogen, phosphorus, and potassium. The sensor was placed at a depth of 20 cm in ten cassava farms, collecting data every 30 min for eight months. Four real-time sensor denoising models were implemented: UKF, Cubature Kalman Filter (CKF), UKF with Artificial Neural Network (UKF_ANN), and UKF with Fuzzy Logic (UKF_FL). Models’ performance was evaluated using boxplot, square root(R2), mean absolute error (MAE), root mean square error (RMSE), computation memory (CM), and computation time (CT). Data analysis was performed using Python 3.12 on ARM v8. Results demonstrated that CKF outperformed the other models, reducing RMSE by up to 32% and lowering CM and CT by 75%. CKF and UKF_ANN maintained the integrity of the censored data while effectively removing Gaussian, uniform, and salt-and-pepper noise, making them suitable for IoT-based soil monitoring systems.
format Article
id doaj-art-1068ff0eefb04fdb9071378146105e73
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-1068ff0eefb04fdb9071378146105e732025-08-20T03:45:26ZengNature PortfolioScientific Reports2045-23222025-07-0115111710.1038/s41598-025-05427-wEvaluation of advanced Kalman filter on real-time agricultural soil parameters through an IoT resources-constrained deviceEgas Jose Armando0Damien Hanyurwimfura1Omar Gatera2Kwang Soo Kim3Athanase Nduwumuremyi4African Center of Excellence in Internet of Things, University of RwandaAfrican Center of Excellence in Internet of Things, University of RwandaAfrican Center of Excellence in Internet of Things, University of RwandaDepartment of Agriculture Forestry and Bioresources, Seoul National UniversityRwanda Agriculture BoardAbstract Effective sensor denoising is crucial for accurate, real-time agricultural decision-support systems. This study explores the application of Unscented Kalman Filter (UKF) extensions on resource-constrained devices to improve sensor denoising and enhance the reliability of Internet of Things (IoT) based agricultural soil monitoring. The study was conducted in Ruhango district, Rwanda, utilizing a wireless sensor node equipped with a Raspberry Pi 5 (ARM v8) and an integrated seven-in-one soil sensor measuring temperature, humidity, electrical conductivity, pH, nitrogen, phosphorus, and potassium. The sensor was placed at a depth of 20 cm in ten cassava farms, collecting data every 30 min for eight months. Four real-time sensor denoising models were implemented: UKF, Cubature Kalman Filter (CKF), UKF with Artificial Neural Network (UKF_ANN), and UKF with Fuzzy Logic (UKF_FL). Models’ performance was evaluated using boxplot, square root(R2), mean absolute error (MAE), root mean square error (RMSE), computation memory (CM), and computation time (CT). Data analysis was performed using Python 3.12 on ARM v8. Results demonstrated that CKF outperformed the other models, reducing RMSE by up to 32% and lowering CM and CT by 75%. CKF and UKF_ANN maintained the integrity of the censored data while effectively removing Gaussian, uniform, and salt-and-pepper noise, making them suitable for IoT-based soil monitoring systems.https://doi.org/10.1038/s41598-025-05427-wAgricultural soil sensor denoisingUnscented Kalman filtersCubature Kalman filterArtificial Neural NetworkFuzzy Logic
spellingShingle Egas Jose Armando
Damien Hanyurwimfura
Omar Gatera
Kwang Soo Kim
Athanase Nduwumuremyi
Evaluation of advanced Kalman filter on real-time agricultural soil parameters through an IoT resources-constrained device
Scientific Reports
Agricultural soil sensor denoising
Unscented Kalman filters
Cubature Kalman filter
Artificial Neural Network
Fuzzy Logic
title Evaluation of advanced Kalman filter on real-time agricultural soil parameters through an IoT resources-constrained device
title_full Evaluation of advanced Kalman filter on real-time agricultural soil parameters through an IoT resources-constrained device
title_fullStr Evaluation of advanced Kalman filter on real-time agricultural soil parameters through an IoT resources-constrained device
title_full_unstemmed Evaluation of advanced Kalman filter on real-time agricultural soil parameters through an IoT resources-constrained device
title_short Evaluation of advanced Kalman filter on real-time agricultural soil parameters through an IoT resources-constrained device
title_sort evaluation of advanced kalman filter on real time agricultural soil parameters through an iot resources constrained device
topic Agricultural soil sensor denoising
Unscented Kalman filters
Cubature Kalman filter
Artificial Neural Network
Fuzzy Logic
url https://doi.org/10.1038/s41598-025-05427-w
work_keys_str_mv AT egasjosearmando evaluationofadvancedkalmanfilteronrealtimeagriculturalsoilparametersthroughaniotresourcesconstraineddevice
AT damienhanyurwimfura evaluationofadvancedkalmanfilteronrealtimeagriculturalsoilparametersthroughaniotresourcesconstraineddevice
AT omargatera evaluationofadvancedkalmanfilteronrealtimeagriculturalsoilparametersthroughaniotresourcesconstraineddevice
AT kwangsookim evaluationofadvancedkalmanfilteronrealtimeagriculturalsoilparametersthroughaniotresourcesconstraineddevice
AT athanasenduwumuremyi evaluationofadvancedkalmanfilteronrealtimeagriculturalsoilparametersthroughaniotresourcesconstraineddevice