Explore the vast range of titles available.

We explored the stationarity, trend, and seasonality of the hive weight and in-hive temperature of ten managed honey bee (Apis mellifera) colonies at a research apiary of the Carl Hayden Bee Research Center in Tucson, Arizona, USA. The hives were monitored with electronic scales and in-hive temperature sensors from June to October 2022. The weight and temperature were recorded every five minutes around the clock. The collected data were curated into 2160 timestamped weight and 2160 timestamped temperature observations. We performed a systematic autoregressive integrated moving average (ARIMA) time series analysis to answer three fundamental questions: (a) Does seasonality matter in the ARIMA forecasting of hive weight and in-hive temperature? (b) To what extent do the best forecasters of one hive generalize to other hives? and (c) Which time series type (i.e., hive weight or in-hive temperature) is better predictable? Our principal findings were as follows: (1) The hive weight and in-hive temperature series were not white noise, were not normally distributed, and, for most hives, were not difference- or trend-stationary; (2) Seasonality matters, in that seasonal ARIMA (SARIMA) forecasters outperformed their ARIMA counterparts on the curated dataset; (3) The best hive weight and in-hive temperature forecasters of the ten monitored colonies appeared to be colony-specific; (4) The accuracy of the hive weight forecasts was consistently higher than that of the in-hive temperature forecasts; (5) The weight and temperature forecasts exhibited common qualitative patterns.

The Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) is a heterogeneous meta ensemble for time series classification. HIVE-COTE forms its ensemble from classifiers of multiple domains, including phase-independent shapelets, bag-of-words based dictionaries and phase-dependent intervals. Since it was first proposed in 2016, the algorithm has remained state of the art for accuracy on the UCR time series classification archive. Over time it has been incrementally updated, culminating in its current state, HIVE-COTE 1.0. During this time a number of algorithms have been proposed which match the accuracy of HIVE-COTE. We propose comprehensive changes to the HIVE-COTE algorithm which significantly improve its accuracy and usability, presenting this upgrade as HIVE-COTE 2.0. We introduce two novel classifiers, the Temporal Dictionary Ensemble and Diverse Representation Canonical Interval Forest, which replace existing ensemble members. Additionally, we introduce the Arsenal, an ensemble of ROCKET classifiers as a new HIVE-COTE 2.0 constituent. We demonstrate that HIVE-COTE 2.0 is significantly more accurate on average than the current state of the art on 112 univariate UCR archive datasets and 26 multivariate UEA archive datasets.

In 2017, a research paper (Bagnall et al. Data Mining and Knowledge Discovery 31(3):606-660. 2017) compared 18 Time Series Classification (TSC) algorithms on 85 datasets from the University of California, Riverside (UCR) archive. This study, commonly referred to as a ‘bake off’, identified that only nine algorithms performed significantly better than the Dynamic Time Warping (DTW) and Rotation Forest benchmarks that were used. The study categorised each algorithm by the type of feature they extract from time series data, forming a taxonomy of five main algorithm types. This categorisation of algorithms alongside the provision of code and accessible results for reproducibility has helped fuel an increase in popularity of the TSC field. Over six years have passed since this bake off, the UCR archive has expanded to 112 datasets and there have been a large number of new algorithms proposed. We revisit the bake off, seeing how each of the proposed categories have advanced since the original publication, and evaluate the performance of newer algorithms against the previous best-of-category using an expanded UCR archive. We extend the taxonomy to include three new categories to reflect recent developments. Alongside the originally proposed distance, interval, shapelet, dictionary and hybrid based algorithms, we compare newer convolution and feature based algorithms as well as deep learning approaches. We introduce 30 classification datasets either recently donated to the archive or reformatted to the TSC format, and use these to further evaluate the best performing algorithm from each category. Overall, we find that two recently proposed algorithms, MultiROCKET+Hydra (Dempster et al. 2022) and HIVE-COTEv2 (Middlehurst et al. Mach Learn 110:3211-3243. 2021), perform significantly better than other approaches on both the current and new TSC problems.

In precision apiculture, the portable digital camera is a cost-effective sensor for capturing hive images or videos used to quantify different colony variables. Openly accessible, well-annotated, interoperable cell-level image datasets are still the exception rather than the norm. This shortage constitutes a major barrier to AI-driven approaches aimed at automating image-based comb analysis. In this article, we present FAIRHiveFrames-1K, a publicly available dataset of 1265 annotated hive frame images (1920 × 1080 PNG) designed to facilitate research in AI-intensive image-based comb analysis automation. The dataset, derived from a 2013–2022 U.S. Department of Agriculture–Agricultural Research Service multi-sensor research reservoir, includes 124,669 annotated regions of interest for seven biologically meaningful categories consistent with comb analysis literature and standard hive inspection protocols. FAIRHiveFrames-1K is curated according to FAIR principles (Findable, Accessible, Interoperable, Reusable) and distributed under CC-BY 4.0 with standard annotation formats, fixed training and validation splits, and reproducible benchmarking artifacts. To establish preliminary baseline performance, we iteratively tuned four YOLO architectures (YOLOv8n, YOLOv8s, YOLOv11n, YOLOv11s) under a shared tuning protocol over the period of dataset growth.

A phase IIa clinical trial shows that the administration of the broadly neutralizing antibody 3BNC117 delays viral rebound following the discontinuation of antiretroviral therapy in patients who were chronically infected with HIV-1. Super anti-HIV antibody tested A phase IIa clinical trial shows that the administration of the broadly neutralizing antibody 3BNC117, which targets the CD4 binding site of the HIV-1 Env protein, delays viral rebound following the discontinuation of antiretroviral therapy in patients who were chronically infected with HIV-1. The authors conclude that 3BNC117 effectively blocks emergence of antibody-sensitive viruses from HIV-1 reservoirs during analytical treatment interruption, a finding that could have significant implications for HIV-1 treatment initiatives. Interruption of combination antiretroviral therapy (ART) in HIV-1-infected individuals leads to rapid viral rebound. Here we report the results of a phase IIa open label clinical trial evaluating 3BNC117, a broad and potent neutralizing antibody (bNAb) against the CD4 binding site of HIV-1 Env 1 , in the setting of analytical treatment interruption (ATI) in 13 HIV-1-infected individuals. Participants with 3BNC117-sensitive virus outgrowth cultures were enrolled. Two or four 30 mg/kg infusions of 3BNC117, separated by 3 or 2 weeks, respectively, were generally well tolerated. The infusions were associated with a delay in viral rebound for 5-9 weeks after 2 infusions, and up to 19 weeks after 4 infusions, or an average of 6.7 and 9.9 weeks respectively, compared with 2.6 weeks for historical controls (p=<1e-5). Rebound viruses arose predominantly from a single provirus. In most individuals, emerging viruses showed increased resistance indicating escape. However, 30% of participants remained suppressed until antibody concentrations waned below 20 μg/ml, and the viruses emerging in all but one of these individuals showed no apparent resistance to 3BCN117, suggesting failure to escape over a period of 9-19 weeks. We conclude that administration of 3BNC117 exerts strong selective pressure on HIV-1 emerging from latent reservoirs during ATI in humans.

From June to October, 2022, we recorded the weight, the internal temperature, and the hive entrance video traffic of ten managed honey bee (Apis mellifera) colonies at a research apiary of the Carl Hayden Bee Research Center in Tucson, AZ, USA. The weight and temperature were recorded every five minutes around the clock. The 30 s videos were recorded every five minutes daily from 7:00 to 20:55. We curated the collected data into a dataset of 758,703 records (280,760–weight; 322,570–temperature; 155,373–video). A principal objective of Part I of our investigation was to use the curated dataset to investigate the discrete univariate time series forecasting of hive weight, in-hive temperature, and hive entrance traffic with shallow artificial, convolutional, and long short-term memory networks and to compare their predictive performance with traditional autoregressive integrated moving average models. We trained and tested all models with a 70/30 train/test split. We varied the intake and the predicted horizon of each model from 6 to 24 hourly means. Each artificial, convolutional, and long short-term memory network was trained for 500 epochs. We evaluated 24,840 trained models on the test data with the mean squared error. The autoregressive integrated moving average models performed on par with their machine learning counterparts, and all model types were able to predict falling, rising, and unchanging trends over all predicted horizons. We made the curated dataset public for replication.

What the honey bee can teach us about evolution--and ourselves.

The foraging activity of honey bees used to pollinate almonds was examined in relation to their hive entrance orientation and colony strength. Twenty-four colonies of honey bees, twelve in each group, were situated with their entrances facing east and west cardinal points. Bee out counts were recorded continuously and hive weight data at ∼10 min intervals from 17 February to 15 March 2023. Colony strength was assessed using the frames of adult bees (FOB) metric. East-facing hives started flight 44.2 min earlier than west-facing hives. The hive direction did not affect the timing of the cessation of foraging activity. The hive strength played a significant role: hives assessed as weak (≤3.0 FOB) commenced foraging activity 45 min later than strong hives (>3.0 FOB) and ceased foraging activity 38.3 min earlier. Hive weight data did not detect effects of either the hive direction or colony strength on the commencement and cessation of foraging activity, as determined using piecewise regression on 24 h datasets. However, the hive weight loss due to foraging activity at the start of foraging activity was significantly affected by both direction (East > West) and colony strength (Strong > Weak). Our study showed that, during almond pollination, both hive entrance exposure and hive strength have quantifiable effects on colony foraging behaviour and that these effects combine to regulate the overall foraging activity of the pollinating colonies.

The European bee, Apis mellifera L. (Hymenoptera: Apidae), is a fundamental resource for the pollination of a great variety of botanical species used by humans for sustenance. Over the last few decades, bee colonies have become vulnerable to a new pest that has advanced beyond its native sub-Saharan territory: the small hive beetle, Aethina tumida Murray (Coleoptera: Nitidulidae). This currently presents a pressing problem in the United States and Australia, but it has also been recorded in Portugal and Italy and it is likely to spread in the rest of Europe too. This study represents a systematic review, based on EFSA guidelines, of the various control treatments for small hive beetles in order to identify the most effective methods as well as, those with no effects on bee colonies. The results show that the bulk of these studies were performed in the United States and that a number of treatments are suitable for the control of A. tumida, though some have negative effects on bees while others have low effectiveness or are ineffective. The best results are those with the entomopathogenic nematodes of the genus Steinernema and Heterorhabditis, but also with formic acid or diatomaceous earth. Various products containing insecticides have been effective, for example, Perizin (Bayer), GardStar (Y-Tex), CheckMite+ strips (Bayer), but Apithor (Apithor) cannot be used in Europe because it contains Fipronil, which has been banned since 2013. Some common products like bleach and detergent have also been effective.