Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification.
Ontology highlight
ABSTRACT: 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.
SUBMITTER: Di N
PROVIDER: S-EPMC9884476 | biostudies-literature | 2023
REPOSITORIES: biostudies-literature
Publications
Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification.
Di Nayan N Sharif Muhammad Zahid MZ Hu Zongwen Z Xue Renjie R Yu Baizhong B
PeerJ 20230126
<h4>Background</h4>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.<h4>Methods</h4>This article uses VGGish (a visual geometry group-like audi ...[more]
Similar Datasets
Project description: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.
| S-EPMC10280558 | biostudies-literature
Project description:Modulation classification is one of the essential requirements in the various cognitive radio applications where prior information about the incoming signal is unknown. The modulation classification using a pattern recognition approach can be achieved in 2 modules: first, parameters are extracted from the noisy signal, and then feature selection is carried out using a Gabor filter network (GFN). In the second module, features are exploited for classification purposes. The modulation formats considered for the purpose of classification are BPSK, QPSK, 8PSK, 16PSK, 64PSK, 4FSK, 8FSK, 16FSK, QAM, 8QAM, 16QAM, 32QAM, and 64QAM. The Gabor filter parameters and weights of the adaptive filter are attuned using the Delta rule and recursive least square (RLS) algorithm until the cost function is minimized. In the end, the artificial bee colony (ABC) algorithm is used to optimize the Gabor parameters as well as the classifier's performance. The simulation results show the supremacy of the proposed classifier structure.
| S-EPMC9546654 | biostudies-literature
Project description:Honey bee (Apis mellifera) colonies continue to experience high annual losses that remain poorly explained. Numerous interacting factors have been linked to colony declines. Understanding the pathways linking pathophysiology with symptoms is an important step in understanding the mechanisms of disease. In this study we examined the specific pathologies associated with honey bees collected from colonies suffering from Colony Collapse Disorder (CCD) and compared these with bees collected from apparently healthy colonies. We identified a set of pathological physical characteristics that occurred at different rates in CCD diagnosed colonies prior to their collapse: rectum distension, Malpighian tubule iridescence, fecal matter consistency, rectal enteroliths (hard concretions), and venom sac color. The multiple differences in rectum symptomology in bees from CCD apiaries and colonies suggest effected bees had trouble regulating water. To ensure that pathologies we found associated with CCD were indeed pathologies and not due to normal changes in physical appearances that occur as an adult bee ages (CCD colonies are assumed to be composed mostly of young bees), we documented the changes in bees of different ages taken from healthy colonies. We found that young bees had much greater incidences of white nodules than older cohorts. Prevalent in newly-emerged bees, these white nodules or cellular encapsulations indicate an active immune response. Comparing the two sets of characteristics, we determined a subset of pathologies that reliably predict CCD status rather than bee age (fecal matter consistency, rectal distension size, rectal enteroliths and Malpighian tubule iridescence) and that may serve as biomarkers for colony health. In addition, these pathologies suggest that CCD bees are experiencing disrupted excretory physiology. Our identification of these symptoms is an important first step in understanding the physiological pathways that underlie CCD and factors impacting bee health.
| S-EPMC5513415 | biostudies-literature
Project description:Strength auditing of European honey bee (Apis mellifera Linnaeus, 1758 [Hymenoptera: Apidae]) colonies is critical for apiarists to manage colony health and meet pollination contracts conditions. Colony strength assessments used during pollination servicing in Australia typically use a frame-top cluster-count (Number of Frames) inspection. Sensing technology has potential to improve auditing processes, and commercial temperature sensors are widely available. We evaluate the use and placement of temperature sensing technology in colony strength assessment and identify key parameters linking temperature to colony strength. Custom-built temperature sensors measured hive temperature across the top of hive brood boxes. A linear mixed-effect model including harmonic sine and cosine curves representing diurnal temperature fluctuations in hives was used to compare Number of Frames with temperature sensor data. There was a significant effect of presence of bees on hive temperature and range: hives without bees recorded a 5.5°C lower mean temperature and greater temperature ranges than hives containing live bees. Hives without bees reach peak temperature earlier than hives with bees, regardless of colony strength. Sensor placement across the width of the hive was identified as an important factor when linking sensor data with colony strength. Data from sensors nearest to the hive geometric center were found to be more closely linked to colony strength. Furthermore, a one unit increase in Number of Frames was significantly associated with a mean temperature increase of 0.36°C. This demonstrates that statistical models that account for diurnal temperature patterns could be used to predict colony strength from temperature sensor data.
| S-EPMC9175291 | biostudies-literature
Project description:Healthcare professionals usually should make complex decisions with far reaching consequences and associated risks in health care fields. As it was demonstrated in other industries, the ability to drill down into pertinent data to explore knowledge behind the data can greatly facilitate superior, informed decisions to ensue the facts. Nature has always inspired researchers to develop models of solving the problems. Bee colony algorithm (BCA), based on the self-organized behavior of social insects is one of the most popular member of the family of population oriented, nature inspired meta-heuristic swarm intelligence method which has been proved its superiority over some other nature inspired algorithms. The objective of this model was to identify valid novel, potentially useful, and understandable correlations and patterns in existing data. This review employs a thematic analysis of online series of academic papers to outline BCA in medical hive, reducing the response and computational time and optimizing the problems. To illustrate the benefits of this model, the cases of disease diagnose system are presented.
| S-EPMC4236990 | biostudies-literature
Project description:Current bee population declines and colony failures are well documented yet poorly understood and no single factor has been identified as a leading cause. The evidence is equivocal and puzzling: for instance, many pathogens and parasites can be found in both failing and surviving colonies and field pesticide exposure is typically sublethal. Here, we investigate how these results can be due to sublethal stress impairing colony function. We mathematically modelled stress on individual bees which impairs colony function and found how positive density dependence can cause multiple dynamic outcomes: some colonies fail while others thrive. We then exposed bumblebee colonies to sublethal levels of a neonicotinoid pesticide. The dynamics of colony failure, which we observed, were most accurately described by our model. We argue that our model can explain the enigmatic aspects of bee colony failures, highlighting an important role for sublethal stress in colony declines.
| S-EPMC4299506 | biostudies-literature
Project description:We compare two different sizes of honey bee colony units: singles (one brood chamber) and doubles (two brood chambers) in hybrid seed canola pollination in southern Alberta in 2014 and 2015. Currently, canola seed production companies only contract double-brood chamber units to pollinate canola in southern Alberta, but it may be advantageous to the industry if singles could also be contracted for pollination, as they are in many other crops. To evaluate the differences between the colony units, we measured population size, nectar and pollen foraging, nectar and pollen load weights, pollen collection, and honey production. The colony populations of both the single- and double-brood chamber hives in this study were highly variable. In 2015, there was no difference between the single- and the double-brood chamber colonies in adult bee populations, and the singles had more sealed brood than did the double-brood chamber colonies. Our findings indicate that in comparison to doubles, on a per-frame basis, singles yield more pollen, more nectar foragers, similar or more pollen foragers, and similar amounts of honey. Therefore, we conclude that singles could be used to provide the same level of pollination services as doubles currently do in hybrid seed canola pollination, and growers should focus on receiving healthy populous colonies, regardless of the number of brood boxes.
| S-EPMC6075627 | biostudies-literature
Project description:From cells in tissue, to bird flocks, to human crowds, living systems display a stunning variety of collective behaviors. Yet quantifying such phenomena first requires tracking a significant fraction of the group members in natural conditions, a substantial and ongoing challenge. We present a comprehensive, computational method for tracking an entire colony of the honey bee Apis mellifera using high-resolution video on a natural honeycomb background. We adapt a convolutional neural network (CNN) segmentation architecture to automatically identify bee and brood cell positions, body orientations and within-cell states. We achieve high accuracy (~10% body width error in position, ~10° error in orientation, and true positive rate > 90%) and demonstrate months-long monitoring of sociometric colony fluctuations. These fluctuations include ~24 h cycles in the counted detections, negative correlation between bee and brood, and nightly enhancement of bees inside comb cells. We combine detected positions with visual features of organism-centered images to track individuals over time and through challenging occluding events, recovering ~79% of bee trajectories from five observation hives over 5 min timespans. The trajectories reveal important individual behaviors, including waggle dances and crawling inside comb cells. Our results provide opportunities for the quantitative study of collective bee behavior and for advancing tracking techniques of crowded systems.
| S-EPMC7979864 | biostudies-literature
Project description:Sound is one of the primary forms of sensory information that we use to perceive our surroundings. Usually, a sound event is a sequence of an audio clip obtained from an action. The action can be rhythm patterns, music genre, people speaking for a few seconds, etc. The sound event classification address distinguishes what kind of audio clip it is from the given audio sequence. Nowadays, it is a common issue to solve in the following pipeline: audio pre-processing→perceptual feature extraction→classification algorithm. In this paper, we improve the traditional sound event classification algorithm to identify unknown sound events by using the deep learning method. The compact cluster structure in the feature space for known classes helps recognize unknown classes by allowing large room to locate unknown samples in the embedded feature space. Based on this concept, we applied center loss and supervised contrastive loss to optimize the model. The center loss tries to minimize the intra- class distance by pulling the embedded feature into the cluster center, while the contrastive loss disperses the inter-class features from one another. In addition, we explored the performance of self-supervised learning in detecting unknown sound events. The experimental results demonstrate that our proposed open-set sound event classification algorithm and self-supervised learning approach achieve sustained performance improvements in various datasets.
| S-EPMC10787752 | biostudies-literature
Project description:In the Artificial Bee Colony (ABC) algorithm, the employed bee and the onlooker bee phase involve updating the candidate solutions by changing a value in one dimension, dubbed one-dimension update process. For some problems which the number of dimensions is very high, the one-dimension update process can cause the solution quality and convergence speed drop. This paper proposes a new algorithm, using reinforcement learning for solution updating in ABC algorithm, called R-ABC. After updating a solution by an employed bee, the new solution results in positive or negative reinforcement applied to the solution dimensions in the onlooker bee phase. Positive reinforcement is given when the candidate solution from the employed bee phase provides a better fitness value. The more often a dimension provides a better fitness value when changed, the higher the value of update becomes in the onlooker bee phase. Conversely, negative reinforcement is given when the candidate solution does not provide a better fitness value. The performance of the proposed algorithm is assessed on eight basic numerical benchmark functions in four categories with 100, 500, 700, and 900 dimensions, seven CEC2005's shifted functions with 100, 500, 700, and 900 dimensions, and six CEC2014's hybrid functions with 100 dimensions. The results show that the proposed algorithm provides solutions which are significantly better than all other algorithms for all tested dimensions on basic benchmark functions. The number of solutions provided by the R-ABC algorithm which are significantly better than those of other algorithms increases when the number of dimensions increases on the CEC2005's shifted functions. The R-ABC algorithm is at least comparable to the state-of-the-art ABC variants on the CEC2014's hybrid functions.
| S-EPMC6049945 | biostudies-literature