Integrating LoRaWAN sensor network and machine learning models to classify beef cattle behavior on arid rangelands of the southwestern United State

Monitoring cattle on large, often rugged, rangelands is a daunting task that can be improved using Long Range Wide Area Network (LoRaWAN) tracking and monitoring technology. This study tested the performance of five machine learning classifiers to discriminate between active and stationary states, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Andres Perea, Sajidur Rahman, Huiying Chen, Andrew Cox, Shelemia Nyamuryekung’e, Mehmet Bakir, Huping Cao, Richard Estell, Brandon Bestelmeyer, Andres F. Cibils, Santiago A. Utsumi
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525002357
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850140652611829760
author Andres Perea
Sajidur Rahman
Huiying Chen
Andrew Cox
Shelemia Nyamuryekung’e
Mehmet Bakir
Huping Cao
Richard Estell
Brandon Bestelmeyer
Andres F. Cibils
Santiago A. Utsumi
author_facet Andres Perea
Sajidur Rahman
Huiying Chen
Andrew Cox
Shelemia Nyamuryekung’e
Mehmet Bakir
Huping Cao
Richard Estell
Brandon Bestelmeyer
Andres F. Cibils
Santiago A. Utsumi
author_sort Andres Perea
collection DOAJ
description Monitoring cattle on large, often rugged, rangelands is a daunting task that can be improved using Long Range Wide Area Network (LoRaWAN) tracking and monitoring technology. This study tested the performance of five machine learning classifiers to discriminate between active and stationary states, and among walking, grazing, ruminating and resting behaviors of cattle. Models were trained and tested using a single motion index (MI) collected at 1-minute intervals by LoRaWAN cattle collars equipped with a Global Navigation Satellite System (GNSS) receptor and triaxial accelerometer. Twenty-four mature cows of four breeds were monitored across four periods between July and November 2022. Behavioral observations were made using 168 h of video records, which resulted in a dataset of 9222 instances of labeled sensor data. Logistic regression, support vector machine, multilayer perceptron, XGBoost and random forest algorithms were trained and tested. No differences in MI were detected between ruminating and resting; therefore, subsequent model testing considered the combination of rumination and resting as one class. All classifiers correctly differentiated between the two states and among grazing, walking and resting behaviors with an accuracy and macro-F 1 scores of >0.95 and >0.90, respectively. The results suggest satisfactory application of trained models to monitor cattle behavior on desert rangeland. The annotated dataset used in this study is publicly available at Perea et al. [1].
format Article
id doaj-art-2337da0366d640cc8c27b7da2647dffc
institution OA Journals
issn 2772-3755
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-2337da0366d640cc8c27b7da2647dffc2025-08-20T02:29:43ZengElsevierSmart Agricultural Technology2772-37552025-08-011110100210.1016/j.atech.2025.101002Integrating LoRaWAN sensor network and machine learning models to classify beef cattle behavior on arid rangelands of the southwestern United StateAndres Perea0Sajidur Rahman1Huiying Chen2Andrew Cox3Shelemia Nyamuryekung’e4Mehmet Bakir5Huping Cao6Richard Estell7Brandon Bestelmeyer8Andres F. Cibils9Santiago A. Utsumi10Department of Animal and Range Sciences, New Mexico State University, Las Cruces, NM 88003, USADepartment of Computer Science, New Mexico State University, Las Cruces, NM 88003, USADepartment of Computer Science, New Mexico State University, Las Cruces, NM 88003, USADepartment of Animal and Range Sciences, New Mexico State University, Las Cruces, NM 88003, USADivision of Food Production and Society, Norwegian Institute of Bioeconomy Research (NIBIO), PB 115, N-1431 Ås, NorwayDepartment of Animal and Range Sciences, New Mexico State University, Las Cruces, NM 88003, USADepartment of Computer Science, New Mexico State University, Las Cruces, NM 88003, USAUnited States Department of Agriculture-Agriculture Research Service, Jornada Experimental Range, Las Cruces, NM 88003, USAUnited States Department of Agriculture-Agriculture Research Service, Jornada Experimental Range, Las Cruces, NM 88003, USAUnited States Department of Agriculture Southern Plains Climate Hub, United States Department of Agriculture-Agriculture Research Service, Oklahoma and Central Plains Agricultural Research Center, El Reno, OK 73036, USADepartment of Animal and Range Sciences, New Mexico State University, Las Cruces, NM 88003, USA; Corresponding author.Monitoring cattle on large, often rugged, rangelands is a daunting task that can be improved using Long Range Wide Area Network (LoRaWAN) tracking and monitoring technology. This study tested the performance of five machine learning classifiers to discriminate between active and stationary states, and among walking, grazing, ruminating and resting behaviors of cattle. Models were trained and tested using a single motion index (MI) collected at 1-minute intervals by LoRaWAN cattle collars equipped with a Global Navigation Satellite System (GNSS) receptor and triaxial accelerometer. Twenty-four mature cows of four breeds were monitored across four periods between July and November 2022. Behavioral observations were made using 168 h of video records, which resulted in a dataset of 9222 instances of labeled sensor data. Logistic regression, support vector machine, multilayer perceptron, XGBoost and random forest algorithms were trained and tested. No differences in MI were detected between ruminating and resting; therefore, subsequent model testing considered the combination of rumination and resting as one class. All classifiers correctly differentiated between the two states and among grazing, walking and resting behaviors with an accuracy and macro-F 1 scores of >0.95 and >0.90, respectively. The results suggest satisfactory application of trained models to monitor cattle behavior on desert rangeland. The annotated dataset used in this study is publicly available at Perea et al. [1].http://www.sciencedirect.com/science/article/pii/S2772375525002357Animal monitoringAccelerometerLoRaWANMachine learningRangeland cattleReal time
spellingShingle Andres Perea
Sajidur Rahman
Huiying Chen
Andrew Cox
Shelemia Nyamuryekung’e
Mehmet Bakir
Huping Cao
Richard Estell
Brandon Bestelmeyer
Andres F. Cibils
Santiago A. Utsumi
Integrating LoRaWAN sensor network and machine learning models to classify beef cattle behavior on arid rangelands of the southwestern United State
Smart Agricultural Technology
Animal monitoring
Accelerometer
LoRaWAN
Machine learning
Rangeland cattle
Real time
title Integrating LoRaWAN sensor network and machine learning models to classify beef cattle behavior on arid rangelands of the southwestern United State
title_full Integrating LoRaWAN sensor network and machine learning models to classify beef cattle behavior on arid rangelands of the southwestern United State
title_fullStr Integrating LoRaWAN sensor network and machine learning models to classify beef cattle behavior on arid rangelands of the southwestern United State
title_full_unstemmed Integrating LoRaWAN sensor network and machine learning models to classify beef cattle behavior on arid rangelands of the southwestern United State
title_short Integrating LoRaWAN sensor network and machine learning models to classify beef cattle behavior on arid rangelands of the southwestern United State
title_sort integrating lorawan sensor network and machine learning models to classify beef cattle behavior on arid rangelands of the southwestern united state
topic Animal monitoring
Accelerometer
LoRaWAN
Machine learning
Rangeland cattle
Real time
url http://www.sciencedirect.com/science/article/pii/S2772375525002357
work_keys_str_mv AT andresperea integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate
AT sajidurrahman integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate
AT huiyingchen integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate
AT andrewcox integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate
AT shelemianyamuryekunge integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate
AT mehmetbakir integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate
AT hupingcao integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate
AT richardestell integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate
AT brandonbestelmeyer integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate
AT andresfcibils integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate
AT santiagoautsumi integratinglorawansensornetworkandmachinelearningmodelstoclassifybeefcattlebehavioronaridrangelandsofthesouthwesternunitedstate