Explore the vast range of titles available.

The geometry of the sea floor immediately beyond Antarctica's marine-terminating glaciers is a fundamental control on warm-water routing, but it also describes former topographic pinning points that have been important for ice-shelf buttressing. Unfortunately, this information is often lacking due to the inaccessibility of these areas for survey, leading to modelled or interpolated bathymetries being used as boundary conditions in numerical modelling simulations. At Thwaites Glacier (TG) this critical data gap was addressed in 2019 during the first cruise of the International Thwaites Glacier Collaboration (ITGC) project. We present more than 2000 km2 of new multibeam echo-sounder (MBES) data acquired in exceptional sea-ice conditions immediately offshore TG, and we update existing bathymetric compilations. The cross-sectional areas of sea-floor troughs are under-predicted by up to 40 % or are not resolved at all where MBES data are missing, suggesting that calculations of trough capacity, and thus oceanic heat flux, may be significantly underestimated. Spatial variations in the morphology of topographic highs, known to be former pinning points for the floating ice shelf of TG, indicate differences in bed composition that are supported by landform evidence. We discuss links to ice dynamics for an overriding ice mass including a potential positive feedback mechanism where erosion of soft erodible highs may lead to ice-shelf ungrounding even with little or no ice thinning. Analyses of bed roughnesses and basal drag contributions show that the sea-floor bathymetry in front of TG is an analogue for extant bed areas. Ice flow over the sea-floor troughs and ridges would have been affected by similarly high basal drag to that acting at the grounding zone today. We conclude that more can certainly be gleaned from these 3D bathymetric datasets regarding the likely spatial variability of bed roughness and bed composition types underneath TG. This work also addresses the requirements of recent numerical ice-sheet and ocean modelling studies that have recognised the need for accurate and high-resolution bathymetry to determine warm-water routing to the grounding zone and, ultimately, for predicting glacier retreat behaviour.

The Body Condition Score (BCS) is a key indicator of dairy cattle’s health, production efficiency, and environmental impact. Manual BCS assessment is subjective and time-consuming, limiting its scalability in precision agriculture. This study utilizes computer vision to automatically assess cattle body condition by analyzing tail features, categorizing BCS into five levels (3.25, 3.50, 3.75, 4.0, 4.25). SE attention improves feature selection by adjusting channel importance, while spatial attention enhances spatial information processing by focusing on key image regions. EfficientNet-B0, enhanced by SE and spatial attention mechanisms, improves feature extraction and localization. To facilitate edge device deployment, model distillation reduces the size from 23.8 MB to 8.7 MB, improving inference speed and storage efficiency. After distillation, the model achieved 91.10% accuracy, 91.14% precision, 91.10% recall, and 91.10% F1 score. The accuracy increased to 97.57% for ±0.25 BCS error and 99.72% for ±0.5 error. This model saves space and meets real-time monitoring requirements, making it suitable for edge devices with limited resources. This research provides an efficient, scalable method for automated livestock health monitoring, supporting intelligent animal husbandry development.

Laser weld point detection is crucial in modern industrial manufacturing, yet it faces challenges such as a limited number of samples, uneven distribution, and diverse, irregular shapes. To address these issues, this paper proposes an innovative model, YOLO-Weld, which achieves lightweight design while enhancing detection accuracy. Firstly, a targeted data augmentation strategy is employed to increase both the quantity and diversity of samples from minority classes. Following this, a Diverse Class Normalization Loss (DCNLoss)function is designed to emphasize the importance of tail data in the model’s training. Secondly, the Adaptive Hierarchical Intersection over Union Loss (AHIoU Loss)function is introduced, which assigns varying levels of attention to different Intersections over Union (IoU) samples, with a particular focus on moderate IoU samples, thereby accelerating the bounding box regression process. Finally, a lightweight multi-scale feature processing module, MSBCSPELAN, is proposed to enhance multi-scale feature handling while reducing the number of model parameters. Experimental results indicate that YOLO-Weld significantly improves the accuracy and efficiency of laser weld point detection, with mean Average Precision at 50 ( ) and mean Average Precision at 50:95 ( ) increasing by 15.6% and 15.8%, respectively. Additionally, the model’s parameter count is reduced by 0.4 M, GFLOPS decreases by 1.1, precision improves by 4.3%, recall rises by 22.2%, and the F1 score increases by 15.1%.

Greenhouse tomato cultivation cycles recognition is often impeded by the long-tailed challenge, arising from significant differences in cycle lengths affecting data distribution. This imbalance hinders accurate recognition, particularly for rare stages, limiting intelligent management in precision agriculture. This study proposes a lightweight framework integrating a novel multi-expert grouping strategy with knowledge distillation. The dataset is divided into three groups (Head, Balanced, Tail) based on sample quantity. Separate expert models are trained on each group. Knowledge distillation then transfers the expertise of these models to a lightweight student model (MSC-MobileViT). MSC-MobileViT enhances the MobileViT foundation by incorporating a multi-scale convolution module to improve feature extraction across different scales, capturing both local details and global structure. Experimental results demonstrate superior performance. The framework achieves an overall accuracy of 95.99%, precision of 91.03%, recall of 93.57%, and F1-score of 92.02%, outperforming state-of-the-art models (ResNet50, MobileNetV3, MobileViT variants). Crucially, it excels in handling tail classes, improving accuracy from 79.27% (baseline) to 93.83% for rare stages like \"Substrate Soaking\" and \"Early Production\". The maximum performance gap across categories is minimized to only 3.49 percentage points. The student model achieves this high performance while maintaining an extremely low parameter count (0.95M). The proposed framework effectively addresses the long-tailed recognition challenge in greenhouse tomato cultivation cycles. The multi-expert grouping strategy optimizes learning for different data distributions, while knowledge distillation enables high performance within a lightweight model suitable for edge deployment. The integration of multi-scale convolution significantly enhances feature extraction in complex agricultural scenes. This research provides a new paradigm for long-tail recognition in agriculture and demonstrates the viability of deploying efficient, high-accuracy intelligent systems in real-world greenhouse environments.

Juno's highly inclined orbits provide opportunities to sample high‐latitude magnetic field lines connected to the orbit of Io, among the other Galilean satellites. Its payload offers both remote‐sensing and in‐situ measurements of the Io‐Jupiter interaction. These are at discrete points along Io's footprint tail and at least one event (12th perijove) was confirmed to be on a flux tube Alfvénically connected to Io, allowing for an investigation of how the interaction evolves down‐tail. Here we present Alfvén Poynting fluxes and field‐aligned current densities along field lines connected to Io and its orbit. We explore their dependence as a function of down‐tail distance and show the expected decay as seen in UV brightness and electron energy fluxes. We show that the Alfvén Poynting and electron energy fluxes are highly correlated and related by an efficiency that is fully consistent with acceleration from Alfvén wave filamentation via a turbulent cascade process. Plain Language Summary Io and Jupiter are electrodynamically coupled resulting in the Io footprint tail. This is one of the most persistent, stable, and recognizable features of Jupiter's aurora. The Juno spacecraft routinely samples magnetic field lines connected to Io's orbit, allowing for an investigation of this powerful coupling. We use data recorded by Juno to estimate a proxy for the strength of this interaction, that is, electromagnetic energy, and show its dependence downstream of Io and how the interaction decays. We further show that the available electromagnetic energy and electron energy are intimately linked, suggesting a transfer of energy between wave and particles. This is the basis upon which electrons end up precipitating into Jupiter's upper atmosphere and generate some of the brightest auroras. Key Points Alfvénic Poynting fluxes and electron energy fluxes are highly correlated on magnetic field lines connected to Io's orbit The efficiency in the Main Alfvén Wing is ∼10%, fully consistent with Alfvén wave filamentation via a turbulent cascade process Field‐aligned current densities are quantified and exhibit a decay in magnitude down‐tail of Io

A new species of the cricetid rodent genus Thomasomys is described from the montane forests of the Cordilleras del Cóndor and Kutukú, southeastern Ecuador, at elevations between 1,770 and 2,215 m. The species has a large body size (head and body length 137–147 mm) in comparison with other species in the genus, and also is distinguished from its congeners by presenting a tail longer than the head–body length, presence of genal vibrissae 1 and 2, wide presphenoid, first and second lower molars with ectolophid, and third lower molar slightly shorter than the second. A molecular phylogeny based on mitochondrial genes resolved the new species a member of the “aureus” group, most closely related to Thomasomys aureus sensu stricto (genetic distance 8.57%) and as well as an additional undescribed species from southeastern Ecuador. This finding increases the diversity of Thomasomys to 46 species, of which 17 species are present in Ecuador. In addition, the species described herein is the first Thomasomys from the Amazonian basin, a genus that up to now was thought to be restricted to Andean ranges.

The expansion of the Internet of Medical Things (IoHT) presents significant advantages for healthcare over improved data-driven insights and connectivity and offers critical cybersecurity challenges. Attacks are a serious risk for neural network security; recent defence mechanisms remain restricted concerning their applicability to real-world environments. The influence of adversarial attacks is essential, as they can challenge the security and reliability of Artificial Intelligence (AI) methods in crucial applications. Dealing with these vulnerabilities is vital to develop strong and reliable NNs. Therefore, the study of adversarial defence mechanisms and attack detection became an important area in the domain of AI. Machine learning (ML) and specific deep learning (DL) models have recently influenced excellent performance on challenging perceptual tasks like adversarial attack detection. Meanwhile, the federated learning (FL) method is susceptible to attacks by malicious clients. FL can complete a considerable training task effectively by attracting participants for training a DL method cooperatively, and the user privacy should be completely protected for the users only upload model parameters to the centralized server. This study presents an Adversarial Attack Detection Framework Using Federated Learning Empowered IoT Medical (AADF-FLEIoTM) model. The main intention of the AADF-FLEIoTM model is to develop adversarial attack detection using FL and an advanced hybrid model. The data normalization stage initially uses min-max normalization to scale and transform data into a consistent range. The proposed AADF-FLEIoTM employs the marine predator algorithm (MPA) model to identify and retain the most relevant features for the feature selection process. Besides, the integration of convolutional neural networks, bidirectional long short-term memory, and self-attention (SA-CNN-BiLSTM) technique is utilized for the detection and classification process. Finally, the Red-Tail Hawk (RTH)-optimizer algorithm alters the hyperparameter values of the SA-CNN-BiLSTM technique optimally and results in more excellent classification performance. The AADF-FLEIoTM approach is examined on the IoT healthcare security dataset. The performance validation of the AADF-FLEIoTM approach illustrated a superior accuracy value of 98.24% over existing models.

Due to the severe class imbalance between head classes and tail classes of long-tailed data, deep learning algorithms face significant challenges when dealing with long-tailed data distribution. The class rebalancing methods are generally considered to address class imbalance, however they disrupt the feature distribution in the feature space while improving the performance of tail classes. In this paper, Enhanced Multi-Branch Learning (EMBL), a novel visual recognition model, is designed for long-tailed data. EMBL not only effectively addresses the issue of class imbalance but also avoids the damage of feature distribution, and reduces training overhead. In EMBL, the data augmentation method called Oversampling-Based Hybrid CutMix and Mixup (OHCM) is designed to generate an image with rich semantic information to expand tail classes. In addition, a Dynamic Supervised Contrastive Learning (DSCL) is proposed. In DSCL, the temperature coefficient τ is dynamically varied to allow for the adaptive learning of feature representation based on the training epoch and sample similarity. Finally, an information supplementary branch is introduced in addition to a class rebalancing branch and a conventional learning branch to construct a multi-branch learning framework. A linear decay fusion strategy is employed to perform weighted fusion for those branches. EMBL is validated on four datasets consisting of the CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT and Places-LT. Specially, EMBL achieves state-of-the-art accuracy on multiple datasets.

Automated monitoring of pigs for timely detection of changes in behavior and the onset of tail biting might enable farmers to take immediate management actions, and thus decrease health and welfare issues on-farm. Our goal was to develop computer vision-based methods to detect tail biting in pigs using a convolutional neural network (CNN) to extract spatial information, combined with secondary networks accounting for temporal information. Two secondary frameworks were utilized, being a long short-term memory (LSTM) network applied to sequences of image features (CNN-LSTM), and a CNN applied to image representations of sequences (CNN-CNN). To achieve our goal, this study aimed to answer the following questions: (a) Can the methods detect tail biting from video recordings of entire pens? (b) Can we utilize principal component analyses (PCA) to reduce the dimensionality of the feature vector and only use relevant principal components (PC)? (c) Is there potential to increase performance in optimizing the threshold for class separation of the predicted probabilities of the outcome? (d) What is the performance of the methods with respect to each other? The study utilized one-hour video recordings of 10 pens with pigs prior to weaning, containing a total of 208 tail-biting events of varying lengths. The pre-trained VGG-16 was used to extract spatial features from the data, which were subsequently pre-processed and divided into train/test sets before input to the LSTM/CNN. The performance of the methods regarding data pre-processing and model building was systematically compared using cross-validation. Final models were run with optimal settings and evaluated on an independent test-set. The proposed methods detected tail biting with a major-mean accuracy (MMA) of 71.3 and 64.7% for the CNN-LSTM and the CNN-CNN network, respectively. Applying PCA and using a limited number of PCs significantly increased the performance of both methods, while optimizing the threshold for class separation did result in a consistent but not significant increase of the performance. Both methods can detect tail biting from video data, but the CNN-LSTM was superior in generalizing when evaluated on new data, i.e., data not used for training the models, compared to the CNN-CNN method.

Named entity recognition (NER) is one of the fundamental tasks in building knowledge graphs. For some domain-specific corpora, the text descriptions exhibit limited standardization, and some entity structures have entity nesting. The existing entity recognition methods have problems such as word matching noise interference and difficulty in distinguishing different entity labels for the same character in sequence label prediction. This paper proposes a span-based feature reuse stacked bidirectional long short term memory network (BiLSTM) nested named entity recognition (SFRSN) model, which transforms the entity recognition of sequence prediction into the problem of entity span suffix category classification. Firstly, character feature embedding is generated through bidirectional encoder representation of transformers (BERT). Secondly, a feature reuse stacked BiLSTM is proposed to obtain deep context features while alleviating the problem of deep network degradation. Thirdly, the span feature is obtained through the dilated convolution neural network (DCNN), and at the same time, a single-tail selection function is introduced to obtain the classification feature of the entity span suffix, with the aim of reducing the training parameters. Fourthly, a global feature gated attention mechanism is proposed, integrating span features and span suffix classification features to achieve span suffix classification. The experimental results on four Chinese-specific domain datasets demonstrate the effectiveness of our approach: SFRSN achieves micro-F1 scores of 83.34% on ontonotes, 73.27% on weibo, 96.90% on resume, and 86.77% on the supply chain management dataset. This represents a maximum improvement of 1.55%, 4.94%, 2.48%, and 3.47% over state-of-the-art baselines, respectively. The experimental results demonstrate the effectiveness of the model in addressing nested entities and entity label ambiguity issues.