ChapterPDF Available

Abstract and Figures

This work describes the system and methods of data analysis we use for beehive monitoring. We present overview of the hardware infrastructures used in hive monitoring systems and we describe algorithms used for analysis of this kind of data. Based on acquisited signals we construct the application that is capable to detect an absence of honey bee queen. We describe our method of signal analysis and present results that allow us to drown conclusions on honey bee behaviour.
Content may be subject to copyright.
Detection of the Bee Queen Presence
using Sound Analysis
Tymoteusz Cejrowski1, Julian Szymański1, Higinio Mora2, David Gil2
1Gdańsk University of Technology, Faculty of Electronics,
Telecommunications and Informatics, Poland,
2Department of Computer Science Technology and Computation,
University of Alicante, Spain,,,
Abstract. This work describes the system and methods of data analy-
sis we use for beehive monitoring. We present overview of the hardware
infrastructures used in hive monitoring systems and we describe algo-
rithms used for analysis of this kind of data. Based on acquisited signals
we construct the application that is capable to detect an absence of honey
bee queen. We describe our method of signal analysis and present results
that allow us to drown conclusions on honey bee behaviour.
Keywords: Honey Bees ·Hive monitoring ·Signal analysis
1 Introduction
Honeybee (Apis mellifera) is probably one of the most important insects in the
agriculture. This extremely valuable insects are treated as the key factor in
plants pollination [1, 2]. It is crucial that the number of bees increases. Their
work is considered as the guiding light for the hard-workers and is appreciated
for ages. People and especially beekeepers should provide special care for this
insects. Unfortunately today’s beekeeping is facing many issues which cause the
number of insects to decrease [3]. Disease or uncontrolled swarming can be the
cause of bee distinction. Also insufficient care of the beekeeper is very often the
main factor of collapsing the whole bee’s families.
One of the important tasks for beekeeper is to check whether the queen bee is
healthy and capable to lay eggs. This is done by opening the hive and inspecting
the hive frames. If there is no eggs or larvae, the queen bee might be dead, ill or
just not present in the hive. In such situations life of the whole swarm could be in
danger and an immediate action is required. Whenever there is no reproduction
because of the death or disability of the queen bee there is also no more younger
bees that could replace the older ones [4]. Usually the bee worker lives only up
to 40 days and after that her work should be overtaken by another bee [5]. The
lack of healthy queen bee is extremely unfavorable and should be detected as
soon as it is possible. But on the other side, daily hive inspections and checking
whenever queen bee is present can be harmful for the whole bee family. Frequent
disturbances can be a stressful factor and introduce the anxiety to the swarm.
To avoid such situations it is necessary to use a non-invasive method that is able
to detect lack of the queen bee.
In this paper we present the remote, non-invasive system that monitors and
analyzes the honey bees behavior according to different conditions. For our study
we create the situation where the queen bee is not present inside the hive. We
monitor that situation with the set of the sensors and based on it we create the
classifier that indicates whether the bee family becomes aware of the missing
queen. The system presented in this paper can possibly detect different illnesses
of bee colony such as presence of Varroa Destructor or predict bee swarming but
that analysis is a plan for the future work.
2 Related works
In recent years the interest in bees and their habits is increasing rapidly. Such
situation cause growth the number of systems which are capable of collecting
data from the hives.
For example, the commercial Arnia3system is designed for collecting weight,
temperature and humidity measurements. The device is also equipped with mi-
crophone to obtain sound samples from inside the beehive. All data is transferred
remotely to the server and then presented to the user. There are many similar
projects with the same core objectives. For example, projects presented in [6] and
[7] differ only in the set of sensors. Some of them like the BuzzBox4additionally
provides open access to recorded data.
There are also number of scientific projects which are focused on detecting
particular situations inside the beehive. For example, problem of bee swarming
(when the insects leave the hive because of newborn queen) has been studied in
[8]. The proposed solution uses cyclic temperature measurements and pattern
recognition techniques which are based for a predictive algorithm. System is able
to detect the preswarming moment by evaluating the increase in temperature
inside the hive. Authors found five patterns that may occur during the year.
Anomalies, which are accompanied by elevated temperatures within the hive,
and hence the inability to classify data from a particular moment may be a sign
of the incoming swarming.
Ferrari’s work about the bee swarming prediction [9] describes wireless net-
work of sensors that collect sounds, temperature and humidity values from the
hive during the swarming periods. Based on empirical graphs observations some
patterns were specified and determined.
There are also some projects focused on bee’s diseases detection. Project
which was developed at Edith Cowan University in Australia [10] aims to com-
pletely eliminate external parasitic mite Varroa Destructor from the Australian
continent. Device collects sound samples and converts them to feature vector,
at the end the data is classified using SVM or LDA algorithms. Mite detection
3Arnia system:, access 10 Sep 2017
4BuzzBox:, access 10 Sep 2017
such as Varroa Destructor can also be solved using image analysis processing. In
Larissa Chazette’s work [11] camera-equipped system has been developed which
recognizes Varroa Destructor infected bees by using Convolutional Neural Net-
works (CNN). In Schurischuster’s work [12] a Raspberry Pi 3 based device is
able to collects high resolution and well-exposed pictures of bees entering the
hive. The combination of [11] and [12] systems could lead to even better results.
3 System design
Our system is composed from three parts: server, client and embedded mod-
ule. The wireless network of embedded devices was made according to master-
slave architecture. The endpoints which are mounted directly inside the hive are
responsible for collecting measurements and passing them to accesspoint. The
accesspoint uploads raw data to the server where is processed.
Analysis of bees behavior can only be performed by usage of sensors that
provide case-essential data. Significant type of data can be specified basing on the
related work. Bees like most of the insects produce sound during the flight. The
bee worker emits sounds at 250 Hz on the air. But bees can be also considered
as one super-organism where their sounds accumulates to one, common buzz.
Seemingly irrelevant noise emanating from the center of the hive can be a source
of valuable information. For example, when bees are preparing for swarming,
they also change their extremely ordered behavior. Some of the insects start
becoming restless, bring excitement to the hive and finally change nature of the
common buzz. Without doubt sound is one of the most important factors in bee
analysis. In presented work, sound samples are collected by specially designed
microphone. The band-pass filters have been selected so that the microphone
will be sensitive for bee’s sounds (20 -2000 Hz).
Bees also need proper level of temperature and humidity inside the hive.
Without suitable conditions the colony can leave their current place of occupa-
tion [8]. Invalid humidity level is causing multiple bee diseases so it is also sig-
nificant value for monitoring. Temperature and humidity are the most sensitive
factors among the bees and these two values are monitored using an integrated
sensor HDC1008.
In our system the microphone, temperature and humidity sensors was in-
serted into a specially designed bee hive frame in order to not disturb the bees.
The designed frame is shown in the Fig 1. Single data set contains one second
sound sample and information about levels of temperature and humidity. Data
is acquired every 15 minutes and then uploaded to the server.
4 Data processing
In our approach we divide the data into two sets: one derived from normal
bees work and one from abnormal, where there is a lack of bee queen in the
hive. Thanks to that it is possible to extract the pattern, which will allow us
to differentiate particular behaviors. At the beginning of the analysis process
Fig. 1. Bee hive frame used in experiment.
the data is downloaded from server. This step must ensure data consistency
in which the sound, temperature and humidity values must be available at a
given moment. Then, the features are extracted from the available data and
classification potential is tested. At the end the model is worked out and final
classification is performed.
4.1 Feature extraction - Linear Predictive Coding (LPC)
The process of the data analysis start from the transformation of the input data
from the hive into a form that can be used as input for algorithms. Sound signal
should be compressed into the finite element vector of the size significantly less
than the original length of the sound sample vector. For this purpose Linear
Predictive Coding was used.
LPC is a method used in a speech audio compression. This method assumes
that signal is produced by a buzzer located at the end of the tube [13]. For the
correct sound characterization it is important to determine the output signal
parameters as the inverse of the impulse response of FIR filter that represents
the vocal tract. In order to facilitate the use, the input is the Dirac delta function.
Model can be represented as in (1)
H(z) = G
k=1 akzk(1)
where Gis the gain, mlevel of the model and akrepresents searched char-
acteristic coefficients.
Using Z transform, and Levinson-Durbin algorithm a coefficient vector is
obtained [14]. It is assumed that 10-14 LPC coefficients describe well the signal
and further increasing this number results in an insignificant improvement in
signal approximation. In this work the given sound sample with a dimension of
3000 was characterized using LPC algorithm by vector of size N= 14. The final
data was extended by temperature and humidity values collected from the same
moment of time as the sound sample.
4.2 Classification potential - t-SNE
Having some set of a data it is crucial to determine if the classification and model
extraction is possible at all. This process is a supportive step and performed only
in the case of recognizing new features. Could be carried out by viewing the 2D
or 3D points which corresponds to input data. If there is possibility for data
separation it means that examined feature can be used in hive modeling. To get
2D points from multidimensional input vector it is necessary to use technique
for dimensionality reduction such as t-SNE.
Algorithm was introduced by Laurens van der Maaten in 2008 and is the
variation of previously existing algorithm called SNE developed by Geoffrey
Hinton and Sam Roweis in 2002. T-SNE converts multidimensional set of data
χ={x1, x2, ..., xn}to 2D or 3D vectors Υ={y1, y2, ..., yn}. The basis of this
algorithm is to compare the density distribution of multivariate variables with
the distribution of their projection on a two or three-dimensional plane [15].
The difference between these two distributions is calculated by Kullback–Leibler
divergence and minimized by gradient descent.
In our work the t-SNE algorithm was used to evaluate the potential of the
hive classification according to presence of the queen bee inside the hive. We
treat LPC coefficients vectors, extended with humidity and temperature values,
as the input for t-SNE algorithm. We perform dimension reduction on vectors
of size n= 16 to obtain 2D or 3D map of points that corresponds to state of the
colony at given moment. Then we can decide if future classification is reasonable.
It is desired to observe clusters of data representing samples taken during the
normal work and a separate set representing anomalies. If so, we can perform
the last step which was the classification according to previously chosen feature.
4.3 Learning - SVM
Information of the separation capacity is important for the next stage of the
mathematical bees modeling. Input data in the form of n-dimensional vector is
given as the input to the classifier. Presented system use SVM classifier developed
by Vapnik [16] in 1963 with the modification [17] from 1992 introduced by Boser,
Guyon and Vapnik himself.
The basic SVM classifier is capable of separating two sets that are linearly
separated so that the hyperplane spreading the training data maximizes the
value of the geometric margin. The output of SVM algorithm is the separating
hyperplane which form is presented in (2)
y(x) = wTx+b= 0 (2)
where w= [w1, w2, ..., wN]Tis the Ndimension weight vector and x=
[x1, x2, xN]Tis the input vector. As a matter of fact the input data rarely can
be linearly divided into two separate sets. Separation of the data that can not
be linearized is solved with the help of a so-called kernel trick [18]. It transforms
nonlinearly input data so that they are likely to be linearly separable.
In presented work non-linear, Gaussian-kernel, SVM classifier was used to
obtain a model of the hive in relation to the designated feature. We have used
SVM method on two data sources: previously described n= 16 dimensional
vectors and the output of t-SNE. Both approaches provide similar results. The
SVM output is the hyperplane dividing learning set into two separate clusters,
one indicating anomaly and second describing normal swarm behavior. Such
model can be later evaluated on testing data and relevant conclusions regard to
the behavior of bees can be learned.
5 Experimental results
Bee colony was monitored in the period from February 2017 to August 2017.
Unfortunately, the bees did not swarm in that time also they were not infected
by any of the diseases. To test our classification system, it was decided to force
a critical situation for the bees. Absence of a bee’s queen in the hive was chosen
and it was caused manually by a beekeeper. The aim of the experiment is to
develop a hive model in which will be possible to observe and specify the patterns
characteristic for bees living without the queen.
The experiment was carried out using embedded system described in Section
3. Bee hive frame was inserted into the hive as third frame from the entrance.
The mother exchange process together with periods of downloading of sound
data is presented in Fig 2.
Fig. 2. Queen exchange workflow.
In the first step, two data sets previously designated as "Before picking up
the queen" and "Without the queen" were used as input data. The audio samples
were compressed into a feature vector, which was the LPC coefficients. These
vectors were also extended with temperatures and humidity values. At the end
data was normalized. Such prepared vector was provided for the input of the
t-SNE dimension reduction algorithm to identify the classification potential. Re-
sult was shown in Fig 3.
Fig. 3. Output of t-SNE algorithm with data "Before picking up the queen" and "With-
out the queen".
Based on output of t-SNE algorithm it is clear that bees with and without
the queen act differently. Thus detection of this two cases can be performed using
classification method. For that purpose Support Vector Machine algorithm with
C-classification was used. Cost was set to C= 100 and kernel was defined as
K(xj,x) = expγkxxjk2with γ= 0.4. Result as shown in Fig 4.
Fig. 4. SVM classification borders plot. Modeling the hive with absence queen bee as
feature: queen inside the hive (Before) and Queen taken (Missing).
Such defined model was tested with test data presented in Fig 2. Table 1
presents classification on the test data.
Data named as "Test old queen" and "Test old queen 2" indicates normal
work of the swarm. Such situations was classified correctly and model was very
accurate. It is possible to determine the moment when the queen bee may suffer
Table 1. Test data classification.
Name Samples With queen Without queen Error
Test old queen 92 90 2 2.17%
Test old queen 2 72 70 2 2.77%
Test new queen 130 98 32 75.38%
or even die for example from a pest attack. In such cases we should found samples
which significantly differ from the others.
It was also expected that after some time the data and situation inside the
hive should return to the situation before the mother’s removal. The experiment
showed that the colony did not return to the same state even 15 days after new
queen bee insertion. To more precisely examine this situation it was decided
to check classification potential between "Test data for the old queen bee" and
"Test data for the new queen". Result as shown in Fig 5.
Fig. 5. Swarm classification with two different queen bees.
Output data is quite easy separable what indicates that different bee queens
cause different behaviors across the swarm. For queen bee collapse detection
the system should only analyze changes of the behavior patterns but expecting
same behavior patters with fresh and old queen could be misleading. These
observations was discussed with two independent beekeepers who confirmed that
queen bee influences the behavior of the whole family. The new queen bee after
introduction into the family makes the bees subordinate to her disposition and
sound significantly changes. Model derived from "normal state" of two different
bee queens has been tested on two extra test datasets.
Results presented in Table 2 show that it is necessary to calculate a new
model for the newly introduced queen bee in order to detect next possible swarm
collapse. New queen is significantly different from her predecessor, and thus the
old model loses its usefulness.
Table 2. Classification of two test datasets from two different queen.
Name Samples Old queen New queen Error
Test data old queen 72 68 4 5.55%
Test data new queen 183 17 166 9.28%
6 Conclusion and future work
The experiment and its results confirm the validity of the proposed model. It
has been proved that there is a pattern that characterizes the normal work of
the swarm and it can be correctly identified using the system presented in this
paper. The anomalies such as the exchange of the mother are distinguishable
and extracted by the presented system.
The developed classification system can also be significantly improved. It is
necessary to collect much more data from different anomalies occurring inside the
hive in order to develop a global model of bees behavior. Detection of swarming
or diseases with usage of the described system can be real. For that purpose we
plan to use more sophisticated classifiers [19] ant their parallel implementation
[20] that should allow us to process larger set of the data in more effective way.
We can also obtain some improvement on the level of the data representation.
Here, we plan to add to Linear Predictive Coding analysis of particular feature
context in the similar way done in [21].
Our system is only a starting point for further work that is currently being
conducted. The life and behavior of animals in particular bees can be a source
of valuable information. Researchers at Nanchang University in China [22] have
found that bees work harder the day before the expected rain. This observation
is the basis for extending the system for predicting temperature and humidity
based on data coming from the hive.
Acknowledgments: This work has been supported partially by COST project
CA15118 "Mathematical and Computer Science Methods for Food Science and
Industry" and founds of the Department of Computer Architecture, Faculty of
Electronics, Telecommunications and Informatics, Gdańsk University of Tech-
1. Gill, R.: The value of honeybee pollination to society. Acta Hortic 228 (1991)
2. Svensson, B.: The importance of honeybee-pollination for the quality and quantity
of strawberries. Acta Hortic 228 (1991) 260–264
3. Cox-Foster, D.L., Conlan, S., Holmes, E.C., Palacios, G., Evans, J.D., Moran, N.A.,
Quan, P.L., Briese, T., Hornig, M., Geiser, D.M., et al.: A metagenomic survey of
microbes in honey bee colony collapse disorder. Science 318(5848) (2007) 283–287
4. Ratnieks, F.L.: Egg-laying, egg-removal, and ovary development by workers in
queenright honey bee colonies. Behavioral Ecology and Sociobiology 32(3) (Mar
1993) 191–198
5. Tautz, J.: The Buzz about Bees. Springer Science (2008)
6. Zacepins, A., Kviesis, A., Ahrendt, P., Richter, U., Tekin, S., Durgun, M.: Beekeep-
ing in the future—smart apiary management. In: Carpathian Control Conference
(ICCC), 2016 17th International, IEEE (2016) 808–812
7. Strob, M., Kašparu, M.: Beehive electronic measuring system
8. Kridi, D.S., Carvalho, C.G.N.d., Gomes, D.G.: A predictive algorithm for mitigate
swarming bees through proactive monitoring via wireless sensor networks. In:
Proceedings of the 11th ACM symposium on Performance evaluation of wireless
ad hoc, sensor, & ubiquitous networks, ACM (2014) 41–47
9. Ferrari, S., Silva, M., Guarino, M., Berckmans, D.: Monitoring of swarming sounds
in bee hives for early detection of the swarming period. Computers and electronics
in agriculture 64(1) (2008) 72–77
10. Qandour, A., Ahmad, I., Habibi, D., Leppard, M.: Remote beehive monitoring
using acoustic signals. (2014)
11. Chazette, L., Becker, M., Szczerbicka, H.: Basic algorithms for bee hive monitoring
and laser-based mite control. In: Computational Intelligence (SSCI), 2016 IEEE
Symposium Series on, IEEE (2016) 1–8
12. Schurischuster, S., Z.S.: Sensor study for monitoring varroa mites on honey bees
(apis mellifera)
13. Atal, B.S., Hanauer, S.L.: Speech analysis and synthesis by linear prediction of
the speech wave. The journal of the acoustical society of America 50(2B) (1971)
14. Makhoul, J.: Linear prediction: A tutorial review. Proceedings of the IEEE 63(4)
(1975) 561–580
15. Maaten, L.v.d., Hinton, G.: Visualizing data using t-sne. Journal of Machine
Learning Research 9(Nov) (2008) 2579–2605
16. Cortes, C., Vapnik, V.: Support-vector networks. Machine learning 20(3) (1995)
17. Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin
classifiers. In: Proceedings of the fifth annual workshop on Computational learning
theory, ACM (1992) 144–152
18. Schölkopf, B.: The kernel trick for distances. In: Advances in neural information
processing systems. (2001) 301–307
19. Draszawka, K., Szymański, J.: Thresholding strategies for large scale multi-label
text classifier. In: Human System Interaction (HSI), 2013 The 6th International
Conference on, IEEE (2013) 350–355
20. Czarnul, P., Rościszewski, P., Matuszek, M., Szymański, J.: Simulation of parallel
similarity measure computations for large data sets. In: Cybernetics (CYBCONF),
2015 IEEE 2nd International Conference on, IEEE (2015) 472–477
21. Szymański, J.: Words context analysis for improvement of information retrieval.
In: International Conference on Computational Collective Intelligence, Springer
(2012) 318–325
22. He, X.J., Tian, L.Q., Wu, X.B., Zeng, Z.J.: Rfid monitoring indicates honeybees
work harder before a rainy day. Insect science 23(1) (2016) 157–159
... That is why a colony holding a queen bee is considered a healthy colony while a queen-less colony is unhealthy. Because unhealthy queen and queen-less states both are extremely unfavorable therefore should be recognized as soon as possible to adopt proper management strategies [11]. ...
... They are considered efficient markers to estimate abnormal changes occurring in the beehive because their measure can be simple and low-cost, moreover can be used in multiple hives for their continuous monitoring [17,19,32]. In climate-smart agriculture, a myriad of data on hives' acoustics can be used to extract novel information [47] regarding colony health, colony strength, swarming, weather condition, pests and disease infection, and pesticide impact [10,11,38,40,46,57]. ...
... Cejrowski, et al. [11] used the Support vector machine (SVM) approach on two data sources, the first is input data in the form of an n-dimensional vector, and the second is the output of t-SNE. The t-SNE ( t-distributed stochastic neighbor embedding) is a technique to work on high dimensional data. ...
Full-text available
Honeybees, a key pollinator of the world’s most cultivated crops, are experiencing colony collapses due to a variety of factors. The existence of honeybees and queens is critical to the sociality of a colony, and the presence of bees in agricultural settings is vital to the ecological balance. Moreover, beehives without a queen may lead to the decline of an entire colony therefore finding them through effective and an accurate approach is a critical task. In this scenario, we analyzed acoustic/sound data of various classes (i.e. Bee, NoBee, and NoQueen) from beehive colonies. This study examines five distinct features including spectral centroid, zero-crossing rate, Mel-frequency cepstral coefficients (MFCC), chromagram, and constant Q-transform characteristics for their suitability in detecting bees using the acoustic data. In addition, selective features using principal component analysis (PCA), Chi-square analysis (Chi2), and singular value decomposition (SVD) are used. Moreover, the study proposes hybrid features where selective PCA, Chi2, and SVD characteristics are integrated to create a suitable feature set. Experimental results exhibit the suitability of the hybrid feature set which outperformed individual features for “Bee”, “NoBee” and “NoQueen” classes prediction. Cross-validation and T-test results also confirm the superior performance of hybrid MFCC features. The results indicate that RF and KNN show better performance than other machine learning models with maximum accuracy scores of 0.82 and 0.83, respectively.
... In the model proposed by Andrijević et al. [5] a push notification is set up and sent, informing about changes in the hive, especially when the internal temperature exceeds 35 • C. On the contrary, in the model proposed by Ochoa et al. [16], when the temperature drops below the threshold of When monitoring the internal temperature of the hive it is important to consider the position of the sensors; those placed close to the brood, in the central and warmest part of the hive, are less affected by external conditions, while in the periphery, closer to the walls of the hive, they will be more affected [3]. Individual sensors can be inserted in a small box placed longitudinally in the center of a normal frame [20] or suspended in the center of the hive near the brood [21], or in the center of a frame which is positioned between the body of the hive and the honeycomb [22]. In the model proposed by Zabasta et al. [23] two more sensors are added to the central one between the external frames, while in Ref. [24] the authors use two Humidity Temperature Sensors (DHT22) installed in the center of lateral side and in the center of the back side, directly in the wood panels of the hive. ...
... The machine learning model based on the long-term memory algorithm (LSTM) has also been used to detect when a bee colony is about to lose control of its temperature [26]. [20], (b) frame with four load cells applied in Ref. [24], (c) sensor placed in the center of the hive in three different points [23], (d) 3D representation of an intelligent hive with relative positioning of the sensors in Ref. [14]. ...
... Continuous sound monitoring can provide important information on bee health. It can be used to detect the presence of the queen [20], predict swarming [45] or pillaging [46], colony strength [47], the presence of parasites and predators [44]. ...
... Supervised learning occurs when the algorithm is trained using data that is well labelled and can be separated in classification or regression. Support Vector Machines (SVMs) (Cejrowski et al., 2018;Nolasco et al., 2019), Logistic Regression (LR) (Robles-Guerrero et al., 2019), Multilayer Layer Perceptron (MLP) (Peng et al., 2020), Convolution Neural Networks (CNNs) (Nolasco et al., 2019) and Long Short-term Memory Network (LSTM) (Ruvinga et al., 2021) represent some examples of supervised learning methods in honeybee acoustic and vibration signal classification. ...
... The performance of ML algorithms for either honeybees swarming detection or queen presence classification by sound signal processing is evaluated by using a set of metrics, comprising accuracy, error, Receiver Operating Characteristic curve (ROC), and Area under the Curve (AUC) (Cejrowski et al., 2018;Peng, unpublished;Robles-Guerrero et al., 2019). Accuracy refers to the percentage of correctly classified signals, while error indicates how often a classifier is wrong. ...
... This issue of overfitting has been discussed in a study done by Cejrowski et al. (2018). Electret microphones with an increased range of 20 -2000 Hz (due to a specific band pass filter) were integrated into the comb of a frame which was then inserted into the brood box of one colony. ...
Full-text available
Honeybees are social insects that use a range of signals and cues to communicate with one another. While many of these communications have been identified and studied, the use of acoustic and vibration recordings to automatically monitor colony behaviour and health is yet an upcoming field of research. Two indicators that are important for beekeepers to assess colony state are queen presence and swarming preparation, as their absence and presence, respectively, can lead to colony collapse and honey harvest loss. Microphones and accelerometers have been used to record hives that are showing those indicators and resulting data was used to analyse and classify different colony states. Although some studies have been quite successful in using data resulting from such recordings to detect queen presence and swarming, there are also many challenges and limitations; small sample sizes, the need for a standardised feature engineering approach and more robust models in terms of generalisability being just some of them. This review aims to give an overview of studies using acoustic and vibration recordings to determine queen presence and indicators of swarming, by presenting common methods and analyses and discussing challenges, as well as their limitations and future areas of improvement, to increase their use in precision beekeeping.
... Among the collected data used for monitoring beehives, bee sound is one of the important data containing information regarding the health and behavior of the bees such as feeling airborne toxicants, missing queen or swarming [4][5][6]. The first basic task of any sound-based hive monitoring technology is to recognize bee sounds and distinguish them from non-bee sounds. ...
... Results pointed out that the potential of ML methods for generalizing the system to new hives. In [5], Cejrowski et al. used SVM algorithm to detect the swarming in beehive based on acquisited bee sound signals. In [16], Zgank applied deep neural networks and HMM to classify acoustic swarm based on the audio data collected by an IoT system. ...
Conference Paper
Full-text available
Honey bees (Apis mellifera) play a very important role in agriculture thanks to their ability of plants' pollination. However, the number of honey bees decreases every year because of the effects of climate change, environmental pollution, and so on. As a result, finding a useful solution to this problem has been more and more attracting scientists and companies. Applying machine learning (ML) methods based on audio data recording inside the hive is a promising solution to detect changes in the beehive. In this study, we investigate the genetic programming (GP) method, one of the powerful ML methods, for identifying bee sound data. We also compare our proposal with the results from a previous study. The experiment results show that with the right configuration of parameters, GP can achieve better results than well-known methods for the task of classifying bee sound samples.
... Sensor assisted beehive monitoring articles that used deep and ''shallow'' learning as analysis tools were common (e.g. Cejrowski et al. (2018), Bjerge et al. (2019), Kviesis et al. (2020) and Zhao et al. (2021)). Zgank (2019) used Gaussian Mixture Models (GMMs) and Hidden Markov Models (HMMs), and later deep neural networks (Zgank, 2021), to analyse beehive audio data to classify honeybee swarming events. ...
Full-text available
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 and colony health 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 and bee health. 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 practised 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 countries with upper-middle and high income economies. Yet we show benefits from which all countries, especially countries with lower-middle and low income economies, stand to gain through improved sensor-based hive monitoring. 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. Hive health is a critical issue for bees, beekeepers, horticulture and ecosystem sustainability. We show that its assessment requires a rigorous and coherent approach that has not yet been adequately formalised. 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.
... The majority of the global experts rate the factors mentioned above in the well-established category (low amount of disagreement) because they are highly confident in the fact that there are considerable and very comprehensive shreds of evidence for acoustically monitoring these factors. These results are reinforced by significant evidence in several publications [20,24,25,54,55]. The majority of experts with the highest confidence (Table 3, Figure 5) assessed swarming as a more important factor relative to the others mentioned above (Figure 3). ...
Full-text available
Because the sounds emitted by a managed honeybee colony embrace a wealth of information about the status within and outside the beehive, researchers are interested in developing a beehive sound-based assessment of the colony situation. However, how the global experts rank this approach is unclear. We assessed the importance of beehive sound-based colony monitoring using formal expert elicitation. Our results indicate that policy-making bodies should focus on a non-invasive acoustic approach to monitor swarming, honeybee health, pesticides, and environmental pollution at apiaries, as these were considered very important factors with high confidence by global experts. Moreover, all other factors (pests and pathogens, weather conditions, predators, food availability, and spatiotemporal patterns) are rated as important, but experts’ confidence in acoustically monitoring a few of the factors differs. Because experienced forager bees emit bursting sounds during the waggle dance (particularly during the waggle-run phase) at a specific angle on a vertical comb within the hive, we propose an acoustics-based recording setup using a Raspberry Pi and a QuadMic Array to investigate how this sound can predict the spatial and temporal information of the available food sources. In this article, we highlight how the factors falling into the inconclusive category of confidence have the potential to be acoustically monitored. Besides, this paper suggests new and unexplored directions for opening a window for future research in beehive acoustics.
... Bee buzzing carries information on colony behavior and phenology. Honey bees emit specific sounds when exposed to stressors such as pest infection (Qandour et al., 2014), airborne toxicant (Zhao et al., 2021), swarming detection (Ferrari et al., 2008;Zlatkova, Kokolanski & Tashkovski, 2020), and failing queens (Cejrowski et al., 2018;Soares et al., 2022). Using both statistical and Artificial Intelligence (A.I.) analysis of colony sounds, Bromenshenk et al. (2009), in their patents (Bromenshenk et al., 2009) and in their review article (Bromenshenk et al., 2015) showed that their A.I. could detect a diverse variety of chemicals and eight colony health variables, by simply putting a microphone into the bottom of a beehive and recording bee colony sounds for 30 or 60 s. ...
Full-text available
Background 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. Methods 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. Results The results showed that VGGish embedding performs better than or on par with MFCC in all three datasets.
... However, the results show that the model cannot classify the beehive state; however, the problem can be related to the dataset's characteristics. Another study to detect queen presence was made by Cejrowski et al. [32]. A series of experiments were conducted to reproduce the queen's absence. ...
Full-text available
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.
Full-text available
70 page. The main goal of the work was to develop an information technology for teaching programming that can provide useful knowledge in a form accessible to schoolchildren. To familiarize them with the basics, to help them understand the algorithms and structures of certain programs. Explain what variables, arrays, objects are for, loops, functions, etc. Explain each part of the material provided step by step so that it is clear, fun and interesting. It is mandatory to test knowledge at the end of each theoretical part of the material provided. This is is realized through tests or certain tasks, the solution of which gives points for the work done correctly. work. Translated with (free version)
Honeybees are the most specialized insect pollinators and are critical not only for honey production but, also, for keeping the environmental balance by pollinating the flowers of a wide variety of crops. Recording and analyzing bee sounds became a fundamental part of recent initiatives in the development of so-called smart hives. The majority of researches on beehive sound analytics are focusing on swarming detection, a relatively simple binary classification task (due to the obvious difference in the sound of a swarming and a non-swarming bee colony) where machine learning models achieve good performance even when trained on small data. However, in the case of more complex tasks of beehive sound analytics, even modern machine learning approaches perform poorly. First, training such models would need a large dataset but, according to our knowledge, there is no publicly available large-scale beehive audio data. Second, due to the specifics of beehive sounds, efficient noise filtering methods would be required, however, we could not find a noise filtering method that would increase the performance of machine learning models substantially. In this paper, we propose a dynamic noise filtering method applicable on spectrograms (image representations of audio data) which is superior to the most popular image noise filtering baselines. Further, we introduce a multi-class classification task of bee sounds and a large-scale dataset consisting of 10.000 beehive audio recordings. Finally, we provide the results of a large-scale experiment involving various combinations of audio feature extraction and noise filtering methods together with various deep learning models. We believe that the contributions of this paper will facilitate further research in the area of (beehive) sound analytics.
Conference Paper
Full-text available
The work in progress described in this paper has the objective to implement a beehive monitoring system to monitor essential parameters of a bee hive (such as temperature, sound, weight) and additionally including an image recognition algorithm to observe the degree of infestation with Varroa mites. Mites should be detected at the entrance and statistics about the degree of infestation should be made available by a web interface. As ultimate approach to fight mites without chemicals the coordinates of the mites are to be detected and a laser will be used to kill them. This work describes approaches relevant to all steps of the aforementioned procedure, however it is still work in progress and the components of the approach still have to be integrated into one system that is deployable in practice.
Full-text available
Storms are usually accompanied by a drop in temperature, and an increase in wind and barometric pressure and rainfall, which have negative impacts on most activities, survival and reproduction in insects (Gillot, 2005). The majority of studies mainly focused on how the flight activity of various flying insects such as honeybees, bumble bees, horse flies and leafminer were directly influenced by intraday weather changes (Burnett & Hays, 1974; Lundberg, 1980; Casas, 1989; Vicens & Bosch, 2000). However, accumulating evidences showed that animals can make behavioral changes before storms, which is enormously important for their survival in severe weather condition. Before upcoming storms birds unusually chirp and bathe with sand; native frogs croak and hide their eggs masses; spiders spin shorter and produce thicker webs and wasps hide their comb before rains (Galacgac & Balisacan, 2009; Acharya, 2011). In early 1893, honeybees were reported more active before storms (Inwards, 1893). In this study, we compared the working habits of foragers on days that were followed by a sunny day and those that followed by a rainy day using the Radio Frequency Identification (RFID) which was developed and manufactured by the Honeybee Research Institute of Jiangxi Agricultural University in collaboration with the Guangzhou Invengo Information Technology Co., Ltd., and we firstly showed that honeybees worked harder before a rainy day. This article is protected by copyright. All rights reserved.
Full-text available
Recent developments in Wireless Sensor Networks (WSNs) have led to their use in remote data acquisition and automatic data analysis applications, which have proven to be an invaluable tool in a diverse range of fields including biosecurity. Further indications have been found that honeybee health can be monitored and determined through the use of acoustic analysis. In this paper, we present a system that has the ability to remotely detect the presence of pest infestation on a colony of honeybees by comparing the acoustic fingerprint of a hive to a fingerprint of known status. This will aid the goals of increasing surveillance programs by reducing the labour time and costs that are associated with managing and maintaining monitoring programs. Other benefits of the system proposed in this article include the ability to make available a collection of deterministic, standardised and nondiscriminatory statistical data for the purpose of research into determining the causes of colony collapse disorder
Conference Paper
Full-text available
Swarming is the massive outflow of the bees in a hive, whose most common causes are high temperatures, lack of food, stress and humidity changes. Among the types of swarming, one in which the complete abandonment of the hive occurs, has created large losses to Brazilian beekeepers, especially the Northeast. In an attempt to mitigate this problem, we propose in this paper a system for monitoring hive, via a wireless sensors network capable of identifying the preswarming colony behavior. Through a pattern of collections obtained from the cyclical behavior daily temperatures, we developed a predictive algorithm based on pattern recognition techniques, able to detect the increase in temperature in the hive (microclimate) responsible for the typical stress of bees that culminates in swarming. This mechanism is also able to recognize and avoid sending redundant information over the network in order to reduce radio communication, thereby reducing costs of data transmission and energy
“Whereas bee colonies were once seen as perfect societies of selfless workers and drones ruled by a queen, Tautz presents them as a self-organized, complex adaptive system that he considers “a mammal in many bodies”. This comprehensive introduction to honeybee biology (originally published as Phänomen Honigbiene) explores such topics as how bees obtain and communicate information about flowers, “whole-animal gametes”, and the comb’s contributions to the sociophysiology of the colony. The author has been honored for making research accessible to the public, and his lucid text will reward lay readers, apiarists, students, and professional biologists alike. The book is profusely illustrated with Heilmann’s spectacular photos, which capture the full range of bee activities—including some, such as the living chains formed where combs are being built or repaired, whose function remains unknown.” (SCIENCE, Vol. 322, 19 December 2008) “With spectacularly beautiful colour photographs and an easy understandable text The Buzz about Bees tells the story of honeybees in a new perspective. Based on the latest data, notably from his own research group, Jürgen Tautz provides a wonderful insight into the realms of bees. In contrast to the view of bee colonies as perfect societies of selfless individuals ruled by a queen, Tautz introduces them as a “superorganism”, a self organizing and complex adaptive system based on a network of communication; a fascinating result of evolution – a mammal in several bodies. The entire range of astonishing bee activities is described. Remarkable action photographs never shown before present bees busy with cell cleaning, caring for the brood, serving in the queen’s court, visiting flowers, receiving nectar, producing honey, comb building, entrance guarding, heating and cooling. Spotlights include bees grooming, swarming, fighting, telephoning, sleeping and communicating by high-toned beeping, scents and dances.”
Thesupport-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data.High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Conference Paper
Future of the traditional beekeeping is to implement smart apiary management and start to use automatic and remote tools for bee colony monitoring together with beehive control mechanisms to improve bee colony productivity. Within the ERA-NET ICT-Agri project “ITAPIC” different bee colony monitoring and control systems together with its combinations were introduced and analysed. This paper presents authors vision for implementation of Precision Beekeeping together with the smart apiary concept. Different parameters of the bee colony can be monitored: temperature, humidity, gas content, sound, vibration etc. Continuous monitoring of some bee colony parameters is very challenging and not user friendly, allowing using it only for research purposes, not for practical implementation by the beekeepers. Precision beekeeping idea is to introduce tools that can be easily implemented into beekeeping practice. This paper describes developed systems and its combinations for successful smart apiary management. Developed systems are based on temperature, sound and video monitoring. Both data transmission types: wired and wireless are applied and compared. As well discussion of automatic beehive heating or/and cooling system implementation into practice is opened. As apiaries usually are placed outside in rural areas, important part of the smart beekeeping is usage of alternative energy for powering all the devices. Most suitable alternative power supply to this moment is usage of solar power with solar panels, which can be mounted on the hive. Together with hardware part it is needed to develop software part for data observation. Software part should be developed as a web system or/and mobile application. Cloud system with decision support functionality and with additional option for informing the beekeepers about changes in the state of the bee colonies could be considered as well.
Conference Paper
The paper presents our approach to implementation of similarity measure for big data analysis in a parallel environment. We describe the algorithm for parallelisation of the computations. We provide results from a real MPI application for computations of similarity measures as well as results achieved with our simulation software. The simulation environment allows us to model parallel systems of various sizes with various components such as CPUs, GPUs, network interconnects, and model parallel applications in a meta language. The simulations allow us to determine in details how computations will be performed on a particular hardware. They also allow to predict the shapes of time curves beyond the area where empirical results can be obtained due to limited computational resources such as memory capacity.