Beemon: An IoT-based beehive monitoring system

Tashakkori, Rahman; Hamza, Abdelbaset S.; Crawford, Michael

doi:10.1016/j.compag.2021.106427

Cited by 53 publications

(25 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…4.4), many studies tried to assess or predict hive health using measurable proxies. Understanding traffic at the hive entrance is a very commonly used proxy for hive health [Tashakkori et al, 2021, Cunha et al, 2020]. Internal hive condition such as temperature [Braga et al, 2020, Seritan et al, 2018, Meikle et al, 2017, Murphy et al, 2016], CO 2 concentration [Seritan et al, 2018,Murphy et al, 2016], humidity [Paffhausen et al, 2021,Murphy et al, 2016], audio [Sharif et al, 2020,Pérez et al, 2016] and weight [Paffhausen et al, 2021,Hladun et al, 2016] have also been used extensively as proxies for hive health.…”

Section: Resultsmentioning

confidence: 99%

“…If rapid response is not of concern, then the data generated from devices can be collected on-site and manually transferred off-site for subsequent analysis, eliminating the requirement for network connectivity. Possible networking choices include GSM [Seritan et al, 2018, Zacepins et al, 2017], Lora-WAN [Poposki and Gjorgjevikj, 2020, Zacepins et al, 2020], 3G [Kviesis et al, 2020, Murphy et al, 2016], ZigBee [Murphy et al, 2016], and MQTT [Tashakkori et al, 2021, Zabasta et al, 2019, Ochoa et al, 2019]. The choice depends on the monitoring technology, infrastructure availability and suitability.…”

Section: Resultsmentioning

confidence: 99%

“…Forager workforce size and/or dynamics: Population loss rate [Ngo et al, 2021b]; activity at the hive entrance [Paffhausen et al, 2021]; size of the overwintering colony [Becher et al, 2013]; traffic at the hive entrance [Tashakkori et al, 2021]; bee behaviour at the hive entrance [Schurischuster et al, 2018]; overwintering loss rate [Meikle et al, 2017].…”

Section: Hive Healthmentioning

confidence: 99%

See 2 more Smart Citations

A Framework for Better Sensor-Based Beehive Health Monitoring

Zaman

Dorin

2022

Preprint

View full text Add to dashboard Cite

Hive bees provide essential pollination services to human agriculture. Managed honey bees in particular pollinate many crops, but also create honey and other bee products that are now of global economic importance. Key aspects of honey bee behaviour can be understood by observing hives. Hence, the limitations of manual observation are increasingly being addressed by new technologies that automate and extend the reach of hive monitoring. Here we propose a framework to classify and clarify the potential for sensor-assisted hive monitoring to inform apiculture and, ultimately, improve hive bee management. This framework considers hive monitoring approaches across three newly proposed categories: Operational monitoring, Investigative monitoring, and Predictive monitoring. These categories constitute a new ``OIP Framework'' of hive monitoring. Each category has its own requirements for underlying technology that includes sensors and ICT resources we outline. Each category is associated with particular outcomes and benefits for apiculture and hive health monitoring detailed here. Application of these three classes of sensor-assisted hive monitoring can simplify understanding and improve best-practice management of hive bees. Our survey and classification of hive monitoring to date show that it is seldom practiced beyond honey bees, despite the need to understand bumble bees and stingless bees also. Perhaps unsurprisingly, sensor-based hive monitoring is shown to remain primarily a practice of developed nations. Yet we show how all countries, especially developing nations, stand to gain substantially from the benefits improved sensor-based hive monitoring offers. These include a better understanding of environmental change, an increased ability to manage pollination, an ability to respond rapidly to hive health issues such as pests and pathogens, and even an ability to react quickly to the danger posed to insects and humans alike by extreme events such as floods and fires. Finally, we anticipate that the future of hive monitoring lies in the application of Predictive monitoring, such that a hive's anticipated future state can be preemptively managed by beekeepers working iteratively with novel hive monitoring technologies.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Hive Healthmentioning

confidence: 99%

See 1 more Smart Citation

A Framework for Better Sensor-Based Beehive Health Monitoring

Zaman

Dorin

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Para os experimentos, todas as imagens utilizadas são da plataforma BeeStream 1 [Tashakkori et al 2021] da Appalachian State University (Appstate), a qual disponibiliza gravac ¸ões públicas da entrada (alvado) de colmeias localizadas no campus da Appstate e permite escolher a câmera, a data e o horário da filmagem, recursos que levaram a plataforma a ser o alicerce para construc ¸ão da base de imagens. A fim de maximizar as amostras de zangões, que apresentam-se naturalmente em menor quantidade [Seeley 2006], 07 dos vídeos escolhidos, responsáveis por 342 imagens distintas, os quais foram gerados entre os dias 4 e 7 de abril de 2021 (início da primavera no Hemisfério Norte) e no período da tarde, entre 13h e 15h, intervalo tido na literatura como o de maior fluxo de entrada e saída de zangões durante seus voos de orientac ¸ão (voos curtos que precedem o de acasalamento) [Winston 2003] além de outras 22 fotos sem identificac ¸ão da data de obtenc ¸ão.…”

Section: Base De Imagensunclassified

Aplicando um modelo YOLO para detectar e diferenciar por imagem castas de abelhas melíferas de forma automatizada

Albuquerque

Braga

Bomfim³

et al. 2022

Anais Do XIII Workshop De Computação Aplicada À Gestão Do Meio Ambiente E Recursos Naturais (WCAMA 2022)

View full text Add to dashboard Cite

Em uma colônia de abelhas melíferas (Apis mellifera L.) há três tipos de casta: rainha, operária e zangão. Detectá-las e diferenciá-las é de suma importância para o apicultor, pois a flutuação e o desbalanço fora do normal no número e na proporção natural entre indivíduos fornecem predições sobre eventos que podem impactar negativamente o bem-estar e a produção da colônia. Neste artigo, aplicamos o conceito de Processamento Digital de Imagens, através do detector de objetos YOLO, para diferenciar entre operárias e zangões de abelhas melíferas a fim de fornecer subsídios para o avanço da apicultura de precisão. Por meio de validação cruzada, a arquitetura escolhida reconheceu e classificou corretamente a maioria das abelhas presentes nas imagens, obtendo valores de mAP@50 acima de 94%. Além disso, mesmo com um conjunto de dados desbalanceados e a maior parte das abelhas sendo de operárias, o modelo proposto conseguiu encontrar e classificar a maioria dos zangões, refletindo nos valores de recall acima de 85%.

show abstract

“…Finally, when predators threaten bees, the entire colony produces a characteristic sound as a defensive behavior [ 9 ]. To capture and analyze the bee colony acoustics, several researchers have been interested in developing monitoring systems based on low resources computers such as Raspberry Pi (RPi) [ 8 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 ]. The main goal is to identify colony states automatically by using these technologies and reduce invasive inspections that cause stress in colony members and reduction of the productivity.…”

Section: Introductionmentioning

confidence: 99%

Comparative Study of Machine Learning Models for Bee Colony Acoustic Pattern Classification on Low Computational Resources

Robles-Guerrero

Saucedo-Anaya

Guerrero-Mendez

et al. 2023

Sensors

View full text Add to dashboard Cite

In precision beekeeping, the automatic recognition of colony states to assess the health status of bee colonies with dedicated hardware is an important challenge for researchers, and the use of machine learning (ML) models to predict acoustic patterns has increased attention. In this work, five classification ML algorithms were compared to find a model with the best performance and the lowest computational cost for identifying colony states by analyzing acoustic patterns. Several metrics were computed to evaluate the performance of the models, and the code execution time was measured (in the training and testing process) as a CPU usage measure. Furthermore, a simple and efficient methodology for dataset prepossessing is presented; this allows the possibility to train and test the models in very short times on limited resources hardware, such as the Raspberry Pi computer, moreover, achieving a high classification performance (above 95%) in all the ML models. The aim is to reduce power consumption and improves the battery life on a monitor system for automatic recognition of bee colony states.

show abstract

Beemon: An IoT-based beehive monitoring system

Cited by 53 publications

References 44 publications

A Framework for Better Sensor-Based Beehive Health Monitoring

A Framework for Better Sensor-Based Beehive Health Monitoring

Aplicando um modelo YOLO para detectar e diferenciar por imagem castas de abelhas melíferas de forma automatizada

Comparative Study of Machine Learning Models for Bee Colony Acoustic Pattern Classification on Low Computational Resources

Contact Info

Product

Resources

About