Search Results (34)

This study investigates the impact of microphone placement on honey bee audio monitoring for time-of-day classification, a key step toward automated activity monitoring and anomaly detection. Recognizing the time-dependent nature of bee behavior, we aimed to establish a baseline diurnal pattern recognition method. A custom apparatus enabled simultaneous audio acquisition from internal (brood frame, protected from propolization) and external hive locations. Sound signals were preprocessed using Power Spectral Density (PSD). Extra Trees and Convolutional Neural Network (CNN) classifiers were trained to identify diurnal activity patterns. Analysis focused on feature importance, particularly spectral characteristics. Interestingly, Extra Trees performance varied significantly. While achieving near-perfect accuracy (98–99%) with internal recordings, its accuracy was considerably lower (61–72%) with external recordings, even lower than CNNs trained on the same data (76–87%). Further investigation using Extra Trees and feature selection methods using Mean Decrease Impurity (MDI) and Recursive Feature Elimination with Cross-Validation (RFECV) revealed the importance of the 100–600 Hz band, with peaks around 100 Hz and 300 Hz. These findings inform future monitoring setups, suggesting potential for reduced sampling frequencies and underlining the need for monitoring of sound inside the beehive in order to validate methods being tested. Full article

Honeydew honey represents a bee-derived product with different organoleptic characteristics and distinct properties with respect to floral honey. The market interest in honeydew honey has been growing in recent years due to its higher bioactive characteristics with respect to floral honey. The need for a deeper chemical characterization aimed to evaluate a possible botanical differentiation attracted the use of different analytical approaches. The present work aims to distinguish the botanical honeydew origin by using Nuclear Magnetic Resonance (NMR) spectroscopy and a multivariate approach. Two different data pretreatments have been considered to obtain the best sample discrimination. The saccharide content significantly affects the differentiation of the botanical variety consisting of fir, oak, citrus fruits, eucalyptus, and forest mainly by using a classification approach taking advantage of the Orthogonal Signal Correction filters. Notwithstanding the botanical diversity of the honeydew honey (HDH) samples, fir honeydew (F-HDH), oak honeydew (O-HDH), and eucalyptus honeydew (E-HDH) resulted always well discriminated among all the botanical varieties investigated, while citrus fruits honeydew (CF-HD) and forest honeydew (FO-HDH) did not. In particular, F-HDH resulted characterized by sucrose, erlose, maltose, maltotriose, maltotetraose, and melezitose, E-HDH resulted enriched in α, β-glucose and β-fructose in furanosidic form, and O-HDH enriched in β-fructose in furanosidic form, isomaltose. Full article

Heterotrigona itama, a widely reared stingless bee species, produces highly valued honey. These bees naturally secure their colonies within logs, accessed via a single entrance tube, but remain vulnerable to intruders and predators. Guard bees play a critical role in colony defense, exhibiting the ability to discriminate between nestmates and non-nestmates and employing strategies such as pheromone release, buzzing, hissing, and vibrations to alert and recruit hive mates during intrusions. This study investigated the acoustic signals produced by H. itama guard bees during intrusions to determine their potential for intrusion detection. Using a Jetson Nano equipped with a microphone and camera, guard bee sounds were recorded and labeled. After preprocessing the sound data, Mel Frequency Cepstral Coefficients (MFCCs) were extracted as features, and various dimensionality reduction techniques were explored. Among them, Linear Discriminant Analysis (LDA) demonstrated the best performance in improving class separability. The reduced feature set was used to train both Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) classifiers. KNN outperformed SVM, achieving a Precision of 0.9527, a Recall of 0.9586, and an F1 Score of 0.9556. Additionally, KNN attained an Overall Cross-Validation Accuracy of 95.54% (±0.67%), demonstrating its superior classification performance. These findings confirm that H. itama produces distinct alarm sounds during intrusions, which can be effectively classified using machine learning; thus, demonstrating the feasibility of sound-based intrusion detection as a cost-effective alternative to image-based approaches. Future research should explore real-world implementation under varying environmental conditions and extend the study to other stingless bee species. Full article

The main drawback in using coloration to identify honey bee subspecies is the lack of knowledge regarding genetic background, subjectivity of coloration grading, and the effect of the environment. The aim of our study was to evaluate the effect of environmental temperature on the abdominal coloration of honey bee workers and to develop a tool for quantifying abdominal coloration. We obtained four frames of honey bee brood from two colonies and incubated them at two different temperatures (30 and 34 °C). One colony had workers exhibiting yellow marks on the abdomen, while the other did not. We collected hatched workers and photographed abdomens. Images were analyzed using custom-written R script to obtain vectors that summarize the coloration over the abdomen length in a single value—coloration index. We used UMAP to reduce the dimensions of the vectors and to develop a classification procedure with the support vector machine method. We tested the effect of brood origin and temperature on coloration index with ANOVA. UMAP did not distinguish individual abdomens according to experimental group. The trained classifier sufficiently separated abdomens incubated at different temperatures. We improved the performance by preprocessing data with UMAP. The differences among the mean coloration index values were not significant between the gray groups incubated at different temperatures nor between the yellow groups. However, the differences between the gray and yellow groups were significant, permitting options for application of our tool and the newly developed coloration index. Our results indicate that the environmental temperature in the selected range during development does not seem to impact honey bee coloration significantly. The developed color-recording protocol and statistical analysis provide useful tools for quantifying abdominal coloration in honey bees. Full article

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. Full article

Determining the productive potential of flowering vegetation is crucial in obtaining bee products. The application of a remote sensing approach of terrestrial objects can provide accurate information for the preparation of maps of the potential bee pasture in a given region. The study is aimed at the creation of a novel algorithm to identify and distinguish white flowering honey plants, such as black locust (Robinia pseudo-acacia) and to determine the areas occupied by this forest species in mixed forest ecosystems using UAV-based RGB imaging. In our study, to determine the plant cover of black locust in mixed forest ecosystems we used a DJI (Da-Jiang Innovations, Shenzhen, China) Phantom 4 Multispectral drone with 6 multispectral cameras with 1600 × 1300 image resolution. The monitoring was conducted in the May 2023 growing season in the village of Yuper, Northeast Bulgaria. The geographical location of the experimental region is 43°32′4.02″ N and 25°45′14.10″ E at an altitude of 223 m. The UAV was used to make RGB and multispectral images of the investigated forest massifs, which were thereafter analyzed with the software product QGIS 3.0. The spectral images of the observed plants were evaluated using the newly created criteria for distinguishing white from non-white colors. The results obtained for the scanned area showed that approximately 14–15% of the area is categorized as white-flowered trees, and the remaining 86–85%—as non-white-flowered. The comparison of the developed algorithm with the Enhanced Bloom Index (EBI) approach and with supervised Support Vector Machine (SVM) classification showed that the suggested criterion is easy to understand for users with little technical experience, very accurate in identifying white blooming trees, and reduces the number of false positives and false negatives. The proposed approach of detecting and mapping the areas occupied by white flowering honey plants, such as black locust (Robinia pseudo-acacia) in mixed forest ecosystems is of great importance for beekeepers in determining the productive potential of the region and choosing a place for an apiary. Full article

Beekeeping is an extremely difficult field of agriculture. It requires efficient management of the bee nest so that the bee colony can develop efficiently and produce as much honey and other bee products as possible. The beekeeper, therefore, must constantly monitor the contents of the bee comb. At the University of Warmia and Mazury in Olsztyn, research is being carried out to develop methods for efficient management of the apiary. One of our research goals was to test whether a gas detector (MCA-8) based on six semiconductor sensors—TGS823, TGS826, TGS832, TGS2600, TGS2602, and TGS2603 from the company FIGARO—is able to recognize the contents of bee comb cells. For this purpose, polystyrene and wooden test chambers were created, in which fragments of bee comb with different contents were placed. Gas samples were analyzed from an empty comb, a comb with sealed brood, a comb with open brood, a comb with carbohydrate food in the form of sugar syrup, and a comb with bee bread. In addition, a sample of gas from an empty chamber was tested. The results in two variants were analyzed: (1) Variant 1, the value of 270 s of sensor readings from the sample measurement (exposure phase), and (2) Variant 2, the value of 270 s of sensor readings from the sample measurement (measurement phase) with baseline correction by subtracting the last 600 s of surrounding air measurements (flushing phase). A five-time cross-validation 2 (5xCV2) test and the Monte Carlo cross-validation 25 (trained and tested 25 times) were performed. Fourteen classifiers were tested. The naive Bayes classifier (NB) proved to be the most effective method for distinguishing individual classes from others. The MCA-8 device brilliantly differentiates an empty comb from a comb with contents. It differentiates better between an empty comb and a comb with brood, with results of more than 83%. Lower class accuracy was obtained when distinguishing an empty comb from a comb with food and a comb with bee bread, with results of less than 73%. The matrix of six TGS sensors in the device shows promising versatility in distinguishing between various types of brood and food found in bee comb cells. This capability, though still developing, positions the MCA-8 device as a potentially invaluable tool for enhancing the efficiency and effectiveness of beekeepers in the future. Full article

Stingless bee honey (SBH) is rich in phenolic compounds and available in limited quantities. Authentication of SBH is important to protect SBH from adulteration and retain the reputation and sustainability of SBH production. In this research, we use portable LED-based fluorescence spectroscopy to generate and measure the fluorescence intensity of pure SBH and adulterated samples. The spectrometer is equipped with four UV-LED lamps (peaking at 365 nm) as an excitation source. Heterotrigona itama, a popular SBH, was used as a sample. 100 samples of pure SBH and 240 samples of adulterated SBH (levels of adulteration ranging from 10 to 60%) were prepared. Fluorescence spectral acquisition was measured for both the pure and adulterated SBH samples. Principal component analysis (PCA) demonstrated that a clear separation between the pure and adulterated SBH samples could be established from the first two principal components (PCs). A supervised classification based on soft independent modeling of class analogy (SIMCA) achieved an excellent classification result with 100% accuracy, sensitivity, specificity, and precision. Principal component regression (PCR) was superior to partial least squares regression (PLSR) and multiple linear regression (MLR) methods, with a coefficient of determination in prediction (R²_p) = 0.9627, root mean squared error of prediction (RMSEP) = 4.1579%, ratio prediction to deviation (RPD) = 5.36, and range error ratio (RER) = 14.81. The LOD and LOQ obtained were higher compared to several previous studies. However, most predicted samples were very close to the regression line, which indicates that the developed PLSR, PCR, and MLR models could be used to detect HFCS adulteration of pure SBH samples. These results showed the proposed portable LED-based fluorescence spectroscopy has a high potential to detect and quantify food adulteration in SBH, with the additional advantages of being an accurate, affordable, and fast measurement with minimum sample preparation. Full article

Cultivation and grazing since the mid-nineteenth century in Texas has caused dramatic changes in grassland vegetation. Among these changes is the encroachment of native and introduced brush species. The distribution and quantity of brush can affect livestock production and water holding capacity of soil. Still, at the same time, brush can improve carbon sequestration and enhance agritourism and real estate value. The accurate identification of brush species and their distribution over large land tracts are important in developing brush management plans which may include herbicide application decisions. Near-real-time imaging and analyses of brush using an Unoccupied Aerial System (UAS) is a powerful tool to achieve such tasks. The use of multispectral imagery collected by a UAS to estimate the efficacy of herbicide treatment on noxious brush has not been evaluated previously. There has been no previous comparison of band combinations and pixel- and object-based methods to determine the best methodology for discrimination and classification of noxious brush species with Random Forest (RF) classification. In this study, two rangelands in southern Texas with encroachment of huisache (Vachellia farnesianna [L.] Wight & Arn.) and honey mesquite (Prosopis glandulosa Torr. var. glandulosa) were studied. Two study sites were flown with an eBee X fixed-wing to collect UAS images with four bands (Green, Red, Red-Edge, and Near-infrared) and ground truth data points pre- and post-herbicide application to study the herbicide effect on brush. Post-herbicide data were collected one year after herbicide application. Pixel-based and object-based RF classifications were used to identify brush in orthomosaic images generated from UAS images. The classification had an overall accuracy in the range 83–96%, and object-based classification had better results than pixel-based classification since object-based classification had the highest overall accuracy in both sites at 96%. The UAS image was useful for assessing herbicide efficacy by calculating canopy change after herbicide treatment. Different effects of herbicides and application rates on brush defoliation were measured by comparing canopy change in herbicide treatment zones. UAS-derived multispectral imagery can be used to identify brush species in rangelands and aid in objectively assessing the herbicide effect on brush encroachment. Full article

In this work, a novel analytical methodology for the extraction and determination of polycyclic aromatic hydrocarbon derivatives, nitrated (NPAH) and oxygenated (OPAH), in bee honey samples was developed. The extraction approach resulted in being straightforward, sustainable, and low-cost. It was based on a salting-out assisted liquid-liquid extraction followed by liquid chromatography-tandem mass spectrometry determination (SALLE-UHPLC-(+)APCI-MS/MS). The following figures of merit were obtained, linearity between 0.8 and 500 ng g⁻¹ for NPAH and between 0.1 and 750 ng g⁻¹ for OPAH compounds, coefficients of determination (r2) from 0.97 to 0.99. Limits of detection (LOD) were from 0.26 to 7.42 ng g⁻¹ for NPAH compounds and from 0.04 to 9.77 ng g⁻¹ for OPAH compounds. Recoveries ranged from 90.6% to 100.1%, and relative standard deviations (RSD) were lower than 8.9%. The green assessment of the method was calculated. Thus, the Green Certificate allowed a classification of 87 points. This methodology was reliable and suitable for application in honey samples. The results demonstrated that the levels of nitro- and oxy-PAHs were higher than those reported for unsubstituted PAHs. In this sense, the production chain sometimes transforms foods as direct carriers of contaminants to consumers, representing a concern and demonstrating the need for routine control. Full article

Improving the performance of Deep Learning (DL) algorithms is a challenging problem. However, DL is applied to different types of Deep Neural Networks, and Long Short-Term Memory (LSTM) is one of them that deals with time series or sequential data. This paper attempts to overcome this problem by optimizing LSTM parameters using the Bees Algorithm (BA), which is a nature-inspired algorithm that mimics the foraging behavior of honey bees. In particular, it was used to optimize the adjustment factors of the learning rate in the forget, input, and output gates, in addition to cell candidate, in both forward and backward sides. Furthermore, the BA was used to optimize the learning rate factor in the fully connected layer. In this study, artificial porosity images were used for testing the algorithms; since the input data were images, a Convolutional Neural Network (CNN) was added in order to extract the features in the images to feed into the LSTM for predicting the percentage of porosity in the sequential layers of artificial porosity images that mimic real CT scan images of products manufactured by the Selective Laser Melting (SLM) process. Applying a Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) yielded a porosity prediction accuracy of 93.17%. Although using Bayesian Optimization (BO) to optimize the LSTM parameters mentioned previously did not improve the performance of the LSTM, as the prediction accuracy was 93%, adding the BA to optimize the same LSTM parameters did improve its performance in predicting the porosity, with an accuracy of 95.17% where a hybrid Bees Algorithm Convolutional Neural Network Long Short-Term Memory (BA-CNN-LSTM) was used. Furthermore, the hybrid BA-CNN-LSTM algorithm was capable of dealing with classification problems as well. This was shown by applying it to Electrocardiogram (ECG) benchmark images, which improved the test set classification accuracy, which was 92.50% for the CNN-LSTM algorithm and 95% for both the BO-CNN-LSTM and BA-CNN-LSTM algorithms. In addition, the turbofan engine degradation simulation numerical dataset was used to predict the Remaining Useful Life (RUL) of the engines using the LSTM network. A CNN was not needed in this case, as there was no feature extraction for the images. However, adding the BA to optimize the LSTM parameters improved the prediction accuracy in the testing set for the LSTM and BO-LSTM, which increased from 74% to 77% for the hybrid BA-LSTM algorithm. Full article

Wisdom-of-Crowds-Bots (WoC-Bots) are simple, modular agents working together in a multi-agent environment to collectively make binary predictions. The agents represent a knowledge-diverse crowd, with each agent trained on a subset of available information. A honey-bee-derived swarm aggregation mechanism is used to elicit a collective prediction with an associated confidence value from the agents. Due to their multi-agent design, WoC-Bots can be distributed across multiple hardware nodes, include new features without re-training existing agents, and the aggregation mechanism can be used to incorporate predictions from other sources, thus improving overall predictive accuracy of the system. In addition to these advantages, we demonstrate that WoC-Bots are competitive with other top classification methods on three datasets and apply our system to a real-world sports betting problem, producing a consistent return on investment from 1 January 2021 through 15 November 2022 on most major sports. Full article

DeepWings© is a software that uses machine learning to automatically classify honey bee subspecies by wing geometric morphometrics. Here, we tested the five subspecies classifier (A. m. carnica, Apis mellifera caucasia, A. m. iberiensis, Apis mellifera ligustica, and A. m. mellifera) of DeepWings© on 14,816 wing images with variable quality and acquired by different beekeepers and researchers. These images represented 2601 colonies from the native ranges of the M-lineage A. m. iberiensis and A. m. mellifera, and the C-lineage A. m. carnica. In the A. m. iberiensis range, 92.6% of the colonies matched this subspecies, with a high median probability (0.919). In the Azores, where the Iberian subspecies was historically introduced, a lower proportion (85.7%) and probability (0.842) were observed. In the A. m mellifera range, only 41.1 % of the colonies matched this subspecies, which is compatible with a history of C-derived introgression. Yet, these colonies were classified with the highest probability (0.994) of the three subspecies. In the A. m. carnica range, 88.3% of the colonies matched this subspecies, with a probability of 0.984. The association between wing and molecular markers, assessed for 1214 colonies from the M-lineage range, was highly significant but not strong (r = 0.31, p < 0.0001). The agreement between the markers was influenced by C-derived introgression, with the best results obtained for colonies with high genetic integrity. This study indicates the good performance of DeepWings© on a realistic wing image dataset. Full article

Honey is a natural substance produced by bees of the genus Apis. Depending on the raw material used for its production, honey can be classified into two large groups: blossom honey, which results from the metabolization of nectar extracted from flowers; and honeydew honey, in which bees use plant or insect secretions for its production. The physicochemical characteristics are different between these two types of honey. For example, honeydew honey is darker and is characterized by a high content of phenolic acids. On the contrary, blossom honey stands out for its abundance of flavonoids. Blossom honey can be also classified based on the pollen origin. Thus, honey with more than 45% of the pollen coming from the same species can be considered monofloral; otherwise, it is considered multifloral. Honey is one of the food products with the highest level of fraudulent practices. Most of the adulterations consist of ingredient dilution, adding sweet substances, such as syrups, sugar cane, or corn syrup, among others. In the market, this was reflected in the dubious drop in prices for this product. In the last few years, several instance of honey fraud have come to light. This work aimed to develop a non-targeted ultra-high-performance liquid chromatography–high-resolution mass spectrometry (UHPLC–HRMS) fingerprinting method to address the characterization, classification, and authentication of Spanish honey samples considering their botanical and geographical origin. A total of 136 kinds of honey from different Spanish production regions belonging to different botanical varieties were analyzed, including: blossom honey (orange blossom, rosemary, thyme, eucalyptus, and heather) and honeydew honey (holm oak, forest, and mountain). A simple sample treatment was carried out, consisting of dissolving 1 g of honey in 10 mL of water, followed by a 1:1 dilution with methanol. The chromatographic separation of the obtained extracts was performed using a Kinetex^® C-18 core–shell column (100 × 4.6 mm I.D., 2.6 μm), working under gradient elution, using an aqueous solution of 0.1% formic acid and acetonitrile as the mobile phase components. HRMS acquisition was performed using electrospray in negative ionization mode (−2500 V) in an LTQ-Orbitrap working in full scan MS (m/z 100–1000) at a resolution of 50,000 full-width at half maximum (FWHM). The obtained non-targeted UHPLC–HRMS fingerprints (peak signals as a function of retention time and m/z) were considered as chemical descriptors of the analyzed honey samples for principal component analysis (PCA) and partial least squares-discriminant analysis (PLS-DA). PLS-DA revealed good discrimination between blossom and honeydew honey. Furthermore, the obtained chemometric models allowed the achievement of very good classification among the different botanical varieties under study for both blossom and honeydew honey. The discrimination of honey regarding the different Spanish climate production regions was more limited, although some trends were observed. Thus, the non-targeted UHPLC–HRMS fingerprinting approach proved to be an appropriate methodology to address honey characterization, classification, and authentication based on their different botanical origin. Full article

Honey is a highly consumed natural product produced by bees which is susceptible to fraudulent practices, some of them regarding its botanical origin. Two HPLC-UV non-targeted fingerprinting approaches were evaluated in this work to address honey characterization, classification, and authentication based on honey botanical variety. The first method used no sample treatment and a universal reversed-phase chromatographic separation. On the contrary, the second method was based on an off-line SPE preconcentration method, optimized for the isolation and extraction of polyphenolic compounds, and a reversed-phase chromatographic separation optimized for polyphenols as well. For the off-line SPE method, the use of HLB (3 mL, 60 mg) cartridges, and 6 mL of methanol as eluent, allowed to achieve acceptable recoveries for the selected polyphenols. The obtained HPLC-UV fingerprints were subjected to an exploratory principal component analysis (PCA) and a classificatory partial least squares-discriminant analysis (PLS-DA) to evaluate their viability as sample chemical descriptors for authentication purposes. Both HPLC-UV fingerprints resulted to be appropriate to discriminate between blossom honeys and honeydew honeys. However, a superior performance was accomplished with off-line SPE HPLC-UV polyphenolic fingerprints, being able to differentiate among the different blossom honey samples under the study (orange/lemon blossom, rosemary, thyme, eucalyptus, and heather). In general, this work demonstrated the feasibility of HPLC-UV fingerprints, especially those obtained after off-line SPE polyphenolic isolation and extraction, to be employed as honey chemical descriptors to address the characterization and classification of honey samples according to their botanical origin. Full article