Cargando…

Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud

SIMPLE SUMMARY: Digital transformation in modern farms is triggered by the development of technologies. It allows the monitoring of livestock and evaluation of animal welfare by using data from an increasing number of sensors and IoT devices. This research supports farmers with information on cow he...

Descripción completa

Detalles Bibliográficos
Autores principales: Dineva, Kristina, Atanasova, Tatiana
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10603760/
https://www.ncbi.nlm.nih.gov/pubmed/37893978
http://dx.doi.org/10.3390/ani13203254
_version_ 1785126675203227648
author Dineva, Kristina
Atanasova, Tatiana
author_facet Dineva, Kristina
Atanasova, Tatiana
author_sort Dineva, Kristina
collection PubMed
description SIMPLE SUMMARY: Digital transformation in modern farms is triggered by the development of technologies. It allows the monitoring of livestock and evaluation of animal welfare by using data from an increasing number of sensors and IoT devices. This research supports farmers with information on cow health status classification based on the non-invasive IoT sensors and information on the micro- and macroenvironment of the cow. The collected data from various sources are processed, modeled, and integrated following the proposed workflow. Several machine learning (ML) models are trained and tested to classify cow health status into three categories. The results are visualized for the farmer’s use. This approach is different from other studies because we investigate how microenvironments, macroenvironments, and cow’s information influences the cow health status and whether a combination of these can support and increase accuracy and reliability in the classification process. It provides a practical solution for monitoring large farms, particularly suitable for the livestock industry. ABSTRACT: The health and welfare of livestock are significant for ensuring the sustainability and profitability of the agricultural industry. Addressing efficient ways to monitor and report the health status of individual cows is critical to prevent outbreaks and maintain herd productivity. The purpose of the study is to develop a machine learning (ML) model to classify the health status of milk cows into three categories. In this research, data are collected from existing non-invasive IoT devices and tools in a dairy farm, monitoring the micro- and macroenvironment of the cow in combination with particular information on age, days in milk, lactation, and more. A workflow of various data-processing methods is systematized and presented to create a complete, efficient, and reusable roadmap for data processing, modeling, and real-world integration. Following the proposed workflow, the data were treated, and five different ML algorithms were trained and tested to select the most descriptive one to monitor the health status of individual cows. The highest result for health status assessment is obtained by random forest classifier (RFC) with an accuracy of 0.959, recall of 0.954, and precision of 0.97. To increase the security, speed, and reliability of the work process, a cloud architecture of services is presented to integrate the trained model as an additional functionality in the Amazon Web Services (AWS) environment. The classification results of the ML model are visualized in a newly created interface in the client application.
format Online
Article
Text
id pubmed-10603760
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106037602023-10-28 Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud Dineva, Kristina Atanasova, Tatiana Animals (Basel) Article SIMPLE SUMMARY: Digital transformation in modern farms is triggered by the development of technologies. It allows the monitoring of livestock and evaluation of animal welfare by using data from an increasing number of sensors and IoT devices. This research supports farmers with information on cow health status classification based on the non-invasive IoT sensors and information on the micro- and macroenvironment of the cow. The collected data from various sources are processed, modeled, and integrated following the proposed workflow. Several machine learning (ML) models are trained and tested to classify cow health status into three categories. The results are visualized for the farmer’s use. This approach is different from other studies because we investigate how microenvironments, macroenvironments, and cow’s information influences the cow health status and whether a combination of these can support and increase accuracy and reliability in the classification process. It provides a practical solution for monitoring large farms, particularly suitable for the livestock industry. ABSTRACT: The health and welfare of livestock are significant for ensuring the sustainability and profitability of the agricultural industry. Addressing efficient ways to monitor and report the health status of individual cows is critical to prevent outbreaks and maintain herd productivity. The purpose of the study is to develop a machine learning (ML) model to classify the health status of milk cows into three categories. In this research, data are collected from existing non-invasive IoT devices and tools in a dairy farm, monitoring the micro- and macroenvironment of the cow in combination with particular information on age, days in milk, lactation, and more. A workflow of various data-processing methods is systematized and presented to create a complete, efficient, and reusable roadmap for data processing, modeling, and real-world integration. Following the proposed workflow, the data were treated, and five different ML algorithms were trained and tested to select the most descriptive one to monitor the health status of individual cows. The highest result for health status assessment is obtained by random forest classifier (RFC) with an accuracy of 0.959, recall of 0.954, and precision of 0.97. To increase the security, speed, and reliability of the work process, a cloud architecture of services is presented to integrate the trained model as an additional functionality in the Amazon Web Services (AWS) environment. The classification results of the ML model are visualized in a newly created interface in the client application. MDPI 2023-10-18 /pmc/articles/PMC10603760/ /pubmed/37893978 http://dx.doi.org/10.3390/ani13203254 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Dineva, Kristina
Atanasova, Tatiana
Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud
title Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud
title_full Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud
title_fullStr Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud
title_full_unstemmed Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud
title_short Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud
title_sort health status classification for cows using machine learning and data management on aws cloud
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10603760/
https://www.ncbi.nlm.nih.gov/pubmed/37893978
http://dx.doi.org/10.3390/ani13203254
work_keys_str_mv AT dinevakristina healthstatusclassificationforcowsusingmachinelearninganddatamanagementonawscloud
AT atanasovatatiana healthstatusclassificationforcowsusingmachinelearninganddatamanagementonawscloud