Monitoring Of Bee Colonies Research Articles

MFCC Selection by LASSO for Honey Bee Classification

The recent advances in smart beekeeping focus on remote solutions for bee colony monitoring and applying machine learning techniques for automatic decision making. One of the main applications is a swarming alarm, allowing beekeepers to prevent the bee colony from leaving their hive. Swarming is a naturally occurring phenomenon, mainly during late spring and early summer, but it is extremely hard to predict its exact time since it is highly dependent on many factors, including weather. Prevention from swarming is the most effective way to keep bee colonies; however, it requires constant monitoring by the beekeeper. Drone bees do not survive the winter and they occur in colonies seasonally with a peak in late spring, which is associated with the creation of drone congregation areas, where mating with young queens takes place. The paper presents a method of early swarming mood detection based on the observation of drone bee activity near the entrance to a hive. Audio recordings are represented by Mel Frequency Cepstral Coefficients and their first and second derivatives. The study investigates which MFCC coefficients, selected by the Least Absolute Shrinkage and Selection Operator, are significant for the worker bee and drone bee classification task. The classification results, obtained by an autoencoder neural network, allow to improve the detection performance, achieving accuracy slightly above 95% for the chosen set of signal features, selected by the proposed method, compared to the standard set of MFCC coefficients with only up to 90% accuracy.

Bee colony remote monitoring based on IoT using ESP-NOW protocol.

Information and communication technologies, specifically the Internet of Things (IoT), have been widely used in many agricultural practices, including beekeeping, where the adoption of advanced technologies has an increasing trend. Implementation of precision apiculture methods into beekeeping practice depends on availability and cost-effectiveness of honey bee colony monitoring systems. This study presents a developed bee colony monitoring system based on the IoT concept and using ESP8266 and ESP32 microchips. The monitoring system uses the ESP-NOW protocol for data exchange within the apiary and a GSM (Global System for Mobile communication)/GPRS (General packet radio service) external interface for packet-based communication with a remote server on the Internet. The local sensor network was constructed in a star type logical topology with one central node. The use of ESP-NOW protocol as a communication technology added an advantage of longer communication distance between measurement nodes in comparison to a previously used Wi-Fi based approach and faster data exchange. Within the study, five monitoring devices were used for real-time bee colony monitoring in Latvia. The bee colony monitoring took place from 01.06.2022 till 31.08.2022. Within this study, the distance between ESP-NOW enabled devices and power consumption of the monitoring and main nodes were evaluated as well. As a result, it was concluded that the ESP-NOW protocol is well suited for the IoT solution development for honeybee colony monitoring. It reduces the time needed to transmit data between nodes (over a large enough distance), therefore ensuring that the measurement nodes operate in an even lower power consumption mode.

Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification.

Bee colony sound is a continuous, low-frequency buzzing sound that varies with the environment or the colony's behavior and is considered meaningful. Bees use sounds to communicate within the hive, and bee colony sounds investigation can reveal helpful information about the circumstances in the colony. Therefore, one crucial step in analyzing bee colony sounds is to extract appropriate acoustic feature. This article uses VGGish (a visual geometry group-like audio classification model) embedding and Mel-frequency Cepstral Coefficient (MFCC) generated from three bee colony sound datasets, to train four machine learning algorithms to determine which acoustic feature performs better in bee colony sound recognition. The results showed that VGGish embedding performs better than or on par with MFCC in all three datasets.

Analysis of temperature characteristics for overwintering bee colonies based on long-term monitoring data

Honey Bees are very important to ecological environment and human society. However, the collapse of bee colonies in winter has frequently occurred in recent years, so condition monitoring of bee colonies is vital to maintain bee colonies health. Considering that the temperature has the strongest ability of recognizing the status of bee colonies, this paper uses a multi-sensor system to investigate the long-term air temperature inside beehives for overwintering bee colonies. Firstly, different from other studies in which it is usually a single temperature observation or a small number of samples and a short observation time, the multi-sensor monitoring system is adopted to carry out a continuous experiment for more than 30 Italian bee colonies. The experiment time covers two complete overwintering periods. Subsequently, considering the impact of different time scales on the monitoring of bee colony status, the long-term (several months) data analysis is based on the daily average data, while the short-term (typical weeks) data analysis is performed on the hourly data. Finally, the correlation between air temperature and other monitoring parameters (entrance counts, humidity, sound) was computed. The results demonstrate that the air temperature change inside the beehive has an evident regularity during the overwintering period, such as the fixed temperature threshold for the outdoor activities of bees, periodic fluctuation by the hour and the smallest temperature difference between inside and outside. These findings will enable the assessment of the health state of overwintering bee colonies by use of temperature-derived indicators.

Visual Diagnosis of the Varroa Destructor Parasitic Mite in Honeybees Using Object Detector Techniques.

The Varroa destructor mite is one of the most dangerous Honey Bee (Apis mellifera) parasites worldwide and the bee colonies have to be regularly monitored in order to control its spread. In this paper we present an object detector based method for health state monitoring of bee colonies. This method has the potential for online measurement and processing. In our experiment, we compare the YOLO and SSD object detectors along with the Deep SVDD anomaly detector. Based on the custom dataset with 600 ground-truth images of healthy and infected bees in various scenes, the detectors reached the highest F1 score up to 0.874 in the infected bee detection and up to 0.714 in the detection of the Varroa destructor mite itself. The results demonstrate the potential of this approach, which will be later used in the real-time computer vision based honey bee inspection system. To the best of our knowledge, this study is the first one using object detectors for the Varroa destructor mite detection on a honey bee. We expect that performance of those object detectors will enable us to inspect the health status of the honey bee colonies in real time.

Temperature and Weight Monitoring of the Apis Cerana Bee Colony Indonesia

Abstract Remote and automatic monitoring of two Apis Cerana bee colonies was conducted in Indonesia to demonstrate precision beekeeping approach in that region. Successful implementation of the precision beekeeping system includes development of the bee colony monitoring hardware and software for data collection, analysis and visualisation. This paper focuses on development and installation of such systems at the private apiary in Indonesia. For bee colony monitoring at the apiary a developed monitoring unit was used, which is based on ESP microchip, and for the data storage SAMS data warehouse was used. The monitoring results showed that the choice of the location of the temperature sensor is important, as the temperature at the hive sides changes synchronously with the outside temperature. Also, feedback from the beekeeper is collected to further improve the system and monitoring process. This research is conducted within the SAMS – Smart Apiculture Management Services project, which is funded by the European Union within the H2020-ICT-39-2016-2017 call and with close collaboration with the local private beekeeper. To find out more, visit the project website https://sams-project.eu/.

AUTOMATED SYSTEM FOR BEE COLONY WEIGHT MONITORING

Real time, continuous and remote monitoring of the honeybee colonies with application of information and communication technologies (ICT) is becoming increasingly frequent in industry and in a scientific research. Combination of ICT and beekeeping led to the development of the Precision Beekeeping approach. Successful implementation of the Precision Beekeeping system includes development of the bee colony monitoring hardware solution and computer software for data collection and further analysis. This paper describes developed and implemented bee colony monitoring unit for weight and temperature monitoring. Bee colony weight is one of the key metrics of the strength of a colony. Changes in weight can reflect the productivity rate of the colony, as well as its health and state. Developed monitoring system is based on Raspberry Pi Zero W single board computer with several connected sensors for bee colony temperature and environmental parameter monitoring. Weight is measured using single point load cell with possibility to measure weight up to 200kg, which is enough for the beehive measurements. Data transfer from the remote bee colony is provided by the external 3G router. For data storage and analysis cloud-based data warehouse is developed. Collected data is accessible in the web system with user friendly interface for data visualisation and reporting. Within this research scale calibration process is described and accuracy of the weighting is evaluated and possible challenges are discussed. Described monitoring system is developed within the Horizon 2020 project SAMS, which is funded by the European Union within the H2020-ICT-39-2016-2017 call. To find out more visit the project website https://sams-project.eu/.

Cuticular pheromones stimulate hygienic behavior in the honey bee (Apis mellifera)

The health of western honey bee (Apis mellifera) colonies is challenged by the parasitic mite Varroa destructor and the numerous harmful pathogens it vectors. Selective breeding for the naturally occurring social immune trait “hygienic behavior” has emerged as one sustainable approach to reducing the mites’ impact on honey bees. To expand our understanding of hygienic triggers and improve hygienic selection tools, we tested the hypothesis that the cuticular compounds (Z)-10-tritriacontene and (Z)-6-pentadecene, previously associated with unhealthy honey bee brood and/or brood targeted for hygiene, are triggers of honey bee hygienic behavior independent of brood health. In support of our hypothesis, application of synthetic (Z)-10-tritriacontene and (Z)-6-pentadecene onto brood and brood cell caps significantly increased hygienic behavior compared to application of similarly structured hydrocarbon controls (Z)-16-dotriacontene and (Z)-7-pentadecene. Furthermore, we demonstrate a significant positive correlation between colony-level hygienic responses to (Z)-10-tritriacontene and the traditional freeze-killed brood assay for selection of hygienic honey bee stocks. These results confirm biological activity of (Z)-6-pentadecene and reveal (Z)-10-tritriacontene as a novel hygiene trigger. They also support development of improved tools for honey bee colony monitoring and hygienic selection, and thus may accelerate development of honey bee stocks with greater resistance to Varroa and associated pathogens.

Long-Term and Extensive Monitoring for Bee Colonies Based on Internet of Things

The pollination during bees' foraging is vital to continue species on the Earth. However, the losses of bee colonies are being more extensive problems in recent decades, which have seriously impacted the global environment but have not received enough attention from human beings yet. Based on widely investigating detectable features, this article presents an IoT-based system for long-term and extensive monitoring of bee colonies. Multiple features, including temperature and humidity inside the hive, bee combs' weight, bee colony's sounds, and a number of bees passing through the hive entrance, can be detected hourly by the proposed system. Furthermore, a four-month practical monitoring indicates that the system can continuously operate without human intervention and the data can reveal the activity and growth of bee colonies. Especially, a swarming activity was successfully observed by the data, which shows a significant potential to recognize various activities of bee colonies. The highlights of this system are the capabilities of detecting diverse features, transmitting data wirelessly and that with a strong self-support ability. Because of these advantages, the system can operate for an exceeding long time without maintenance, which will largely benefit system deployment in the field. In the visible future, this system could contribute to the study of bee's behavior and the development of precision beekeeping.

Monitoring of Bee Colonies’ Activity During the Major Gatherings in 2017

The assessment of the meteorological factors, in direct correlation with the nectar release and honey production, helps beekeepers with the organization of the technological activities within the apiary (determination of the pastoral schedule, supplementary feedings, reproduction of bee colonies, honey harvest, etc.). The study was carried out between 14th of April and 20th of July 2017, on 20 Apis mellifera carpatica bee colonies, maintained in multi-layer and Dadant beehives. The bee colonies were transported in field for rape, acacia and sunflower gathering and monitored with the help of the BeeWatch Professional device. The rape and acacia gatherings were negatively influenced by low temperatures and heavy rainfall, which impeded the capitalization of the melliferous potential. The bee colonies gathered only 5 kg rape honey and 3.9 kg acacia honey/bee colony/period. As regards the sunflower, the weather conditions were optimal for gathering, and the bee colonies gathered the supplies necessary for winter and also 5 kg honey extra. The honey production obtained by the bee colonies studied was not influenced by the beehive type; it was strongly influenced by the environmental factors, temperature and humidity.

Monitoring of Bee Colonies’ Activity During the Major Gatherings in 2017

Monitoring of Bee Colonies’ Activity During the Major Gatherings in 2017

ASSESSMENT OF CORRESPONDENCE DEGREE BETWEEN CHANGED STATE AND PREVIOUS STATES OF THE BEE COLONY AT THEIR ACOUSTIC NOISE

In order to evaluate the ecological conditions of the area, it is proposed to use the bee colony, the state of which can be identified with acoustic noise. Bees of particular colony fly on a particular type of honey plants, which corresponds to a particular direction of their flight. During the acoustic monitoring of bee colonies, the researchers identify those ones in which there is not a typical change of acoustic signals. To do this, the researchers must compare the information components of the acoustic noise of bee colonies corresponding previous state of ecological conditions and terrain altered state, which can occur in case of a sudden change in the ecological status of the area, for example, during exposure of pesticides. In order to determine whether the changed state of the bee colony belongs to previous ones, it is proposed to use the fuzzy representation of informative signs.

ECOBEE: a tool for long-term honey bee colony monitoring at the landscape scale in West European intensive agroecosystems

SummaryIn Central Western France, as in many other areas, traditional apiculture has been replaced by more intensive practices to compensate for colony losses and current decreasing honey yields. One neglected aspect concerns the choice by professional beekeepers of apiary sites in intensive agrosystems, with regard to landscape features, a choice which appears to be largely empirical. ECOBEE is a colony monitoring scheme specifically intended to provide beekeepers and researchers with basic ecological data on honeybees in intensive agrosystems, as well as colony population dynamics. ECOBEE was launched in 2008 as a long-term ecological project with three specific aims: 1. to monitor seasonal and inter-annual population dynamic parameters of honeybee colonies in a heterogeneous farming system; 2. to provide relevant and robust datasets to test specific hypotheses about bees such as the influence of landscape planning, agricultural inputs or human pressure; and 3. to offer opportunities for assessing the effectiveness of agro-environmental schemes or the effects of changes in agricultural policies on honey bee wellbeing. Here we present an overview of ECOBEE, the type of datasets collected over the first four years of monitoring, and their possible application and use. We found that colony dynamics were largely influenced by the phenology of the main mass-flowering crops foraged by bees, namely oilseed rape and sunflowers. Furthermore, we detected a sharp food shortage period in late spring between the flowering of oilseed rape and sunflowers, possibly temporarily constraining colony sustainability. We further discuss the research perspectives offered by ECOBEE, especially with regard to spatial ecotoxicology.