Search Results (192)

Increased food production demands, labor shortages, and environmental concerns are driving the need for innovative agricultural technologies. However, effective adoption depends critically on aligning robot innovations with the needs of farmers. This paper examines the alignment between the needs of farmers and the robotic systems used in row crop farming. We review current commercial agricultural robots and research, and map these to the needs of farmers, as expressed in the literature, to identify the key issues holding back large-scale adoption. From initial pool of 184 research articles, 19 survey articles, and 82 commercial robotic solutions, we selected 38 peer-reviewed academic studies, 12 survey articles, and 18 commercially available robots for in-depth review and analysis for this study. We identify the key challenges faced by farmers and map them directly to the current and emerging capabilities of agricultural robots. We supplement the data gathered from the literature review of surveys and case studies with in-depth interviews with nine farmers to obtain deeper insights into the needs and day-to-day operations. Farmers reported mixed reactions to current technologies, acknowledging efficiency improvements but highlighting barriers such as capital costs, technical complexity, and inadequate support systems. There is a notable demand for technologies for improved plant health monitoring, soil condition assessment, and enhanced climate resilience. We then review state-of-the-art robotic solutions for row crop farming and map these technological capabilities to the farmers’ needs. Only technologies with field validation or operational deployment are included, to ensure practical relevance. These mappings generate insights that underscore the need for lightweight and modular robot technologies that can be adapted to diverse farming practices, as well as the need for farmers’ education and simpler interfaces to robotic operations and data analysis that are actionable for farmers. We conclude with recommendations for future research, emphasizing the importance of co-creation with the farming community to ensure the adoption and sustained use of agricultural robotic solutions. Full article

The Buades Gallery (1973–2003) was not merely a commercial space in Madrid. In the history of art in Spain, it served as a professional and political node for Spanish conceptualism, an art form which, due to its idiosyncrasies, required its own channels of distribution. This article seeks to examine the trajectory of Mercedes Buades in alignment with this movement, re-evaluating her role from a feminist perspective and highlighting the importance of certain agents who have traditionally been invisibilised. To this end, a theoretical approach is adopted, following the sociology of art and the social history of art, paying particular attention to the contributions of Enrico Castelnuovo, Pierre Bourdieu and Núria Peist. These frameworks enable an analysis of the role of the gallerist as a structuring agent within the artistic field, capable of generating symbolic capital and establishing dynamics of production, circulation and consumption in the context of post-Franco Spain, a country that lacked a consolidated museum infrastructure at the time. Even so, Mercedes Buades established a model of gallery practice that, beyond its commercial dimension, contributed decisively to the symbolic configuration of contemporary art in Spain and formed part of a network of artistic visibility that promoted experimental art. Full article

Understanding flood scenes is essential for effective disaster response. Previous research has primarily focused on computer vision-based approaches for analyzing flood scenes, capitalizing on their ability to rapidly and accurately cover affected regions. However, most existing methods emphasize static image analysis, with limited attention given to dynamic video analysis. Compared to image-based approaches, video analysis in flood scenarios offers significant advantages, including real-time monitoring, flow estimation, object tracking, change detection, and behavior recognition. To address this gap, this study proposes a computer vision-based multi-object tracking (MOT) framework for intelligent flood scene understanding. The proposed method integrates an optical-flow-based module for short-term undetected mask estimation and a deep re-identification (ReID) module to handle long-term occlusions. Experimental results demonstrate that the proposed method achieves state-of-the-art performance across key metrics, with a HOTA of 69.57%, DetA of 67.32%, AssA of 73.21%, and IDF1 of 89.82%. Field tests further confirm its improved accuracy, robustness, and generalization. This study not only addresses key practical challenges but also offers methodological insights, supporting the application of intelligent technologies in disaster response and humanitarian aid. Full article

For the first time, the numerous scattered data on birds (wild and domestic) have been collected based on their medieval bone remains discovered on the modern territory of the Republic of Bulgaria. The collected information is about a total of 37 medieval settlements from the time of the First and Second Bulgarian Empires. Among the settlements studied are both the two medieval Bulgarian capitals (Pliska and Veliki Preslav), as well as other cities, smaller settlements, military fortresses, monasteries, and inhabited caves. The data refer to a total of 48 species of wild birds and 6 forms of domestic birds of 11 avian orders: Accipitriformes, Anseriformes, Ciconiiformes, Columbiformes, Falconiformes, Galliformes, Gruiformes, Otidiformes, Passeriformes, Pelecaniformes, and Strigiformes. The established composition of wild birds amounts to over one tenth (to 11.5%) of the modern avifauna in the country. Five of the established species (10.4%) have disappeared from the modern nesting avifauna of the country—the bearded vulture, the great bustard, the little bustard, the gray crane, and the saker falcon (the latter two species have reappeared as nesters in the past few years). First Bulgarian Empire (681–1018): Investigated settlements—22. Period covered—five centuries (7th to 11th c.). Found in total: at least 44 species/forms of birds, of which 39 species of wild birds and 5 forms of poultry. Second Bulgarian Empire (1185–1396): Investigated settlements—15. Period covered—3 centuries (12th to 14th c.). Found in total: at least 39 species/forms of birds, of which 33 species of wild birds and 6 forms of poultry. The groups of raptors, water, woodland, openland, synanthropic and domestic birds were analyzed separately. The conclusion was made that during the two periods of the Middle Ages, birds had an important role in the material and spiritual life of the population of the Bulgarian lands. Birds were mainly used for food (domestic birds), although some were objects of hunting. No traces of processing were found on the bones. Birds were subjects of works of applied and monumental art. Their images decorated jewelry, tableware, walls of buildings and other structures. Full article

Because neural networks pervade many industrial domains and are increasingly complex and accurate, the trained models themselves have become valuable intellectual properties. Developing highly accurate models demands increasingly higher investments of time, capital, and expertise. Many of these models are commonly deployed in cloud services and on resource-constrained edge devices. Consequently, safeguarding them is critically important. Neural network watermarking offers a practical solution to address this need by embedding a unique signature, either as a hidden bit-string or as a distinctive response to specially crafted “trigger” inputs. This allows owners to subsequently prove model ownership even if an adversary attempts to remove the watermark through attacks. In this manuscript, we adapt three state-of-the-art watermarking methods to “tiny” neural networks deployed on edge platforms by exploiting symmetry-related properties that ensure robustness and efficiency. In the context of machine learning, “tiny” is broadly used as a term referring to artificial intelligence techniques deployed in low-energy systems in the mW range and below, e.g., sensors and microcontrollers. We evaluate the robustness of the selected techniques by simulating attacks aimed at erasing the watermark while preserving the model’s original performances. The results before and after attacks demonstrate the effectiveness of these watermarking schemes in protecting neural network intellectual property without degrading the original accuracy. Full article

The acquisition of real-world sonar data necessitates substantial investments of manpower, material resources, and financial capital, rendering it challenging to obtain sufficient authentic samples for sonar-related research tasks. Consequently, sonar image simulation technology has become increasingly vital in the field of sonar data analysis. Traditional sonar simulation methods predominantly focus on low-level physical modeling, which often suffers from limited image controllability and diminished fidelity in multi-category and multi-background scenarios. To address these limitations, this paper proposes a Conditional Dual-Branch Attention Generative Adversarial Network (CDBA-GAN). The framework comprises three key innovations: The conditional information fusion module, dual-branch attention feature fusion mechanism, and cross-layer feature reuse. By integrating encoded conditional information with the original input data of the generative adversarial network, the fusion module enables precise control over the generation of sonar images under specific conditions. A hierarchical attention mechanism is implemented, sequentially performing channel-level and pixel-level attention operations. This establishes distinct weight matrices at both granularities, thereby enhancing the correlation between corresponding elements. The dual-branch attention features are fused via a skip-connection architecture, facilitating efficient feature reuse across network layers. The experimental results demonstrate that the proposed CDBA-GAN generates condition-specific sonar images with a significantly lower Fréchet inception distance (FID) compared to existing methods. Notably, the framework exhibits robust imaging performance under noisy interference and outperforms state-of-the-art models (e.g., DCGAN, WGAN, SAGAN) in fidelity across four categorical conditions, as quantified by FID metrics. Full article

Context plays a critical role in talent development, yet most national analyses continue to rely on individual-centered talent concepts. This paper highlights the limitations of traditional models for assessing how countries support talent and proposes a resource-oriented, systemic alternative. Building on the Educational and Learning Capital Approach (ELCA), this study argues that national talent development depends on the availability, accessibility, and orchestration of both endogenous and exogenous learning resources across systemic levels. By analyzing the clumping patterns of excellence in STEM, the arts, sports, and innovation, this paper illustrates the unequal global distribution of talent-supportive environments. Seven key principles for effective resource orchestration are outlined, offering a framework for evaluating and strengthening national talent ecosystems. The paper concludes that systematic assessment and strategic enhancement of national resource landscapes are critical for sustainable talent development and for ensuring that human potential can flourish more equitably across countries. Full article

Volatile fatty acids (VFAs) are important precursors used in various industrial applications. Generally, these carboxylic acids are produced from oil, but recently focus has been on the development of biological methods for substituting the fossil raw material with organic waste and lignocellulosic materials. This is possible by stopping the anaerobic digestion process at the level of VFA through elimination of the final step of methanogenesis. The primary barrier to commercial viability of VFA production is the costly downstream processing needed for separation of the VFA’s. Existing separation techniques, such as adsorption and liquid–liquid extraction, achieve nearly complete VFA recovery from fermentation broths but require substantial chemical inputs and extensive preprocessing. In contrast, membrane-based separation processes could potentially overcome the need for chemical additions and provide a more sustainable way of separation. In this review we examine the current state of the art of membrane technology for VFA separation. We assessed and compared the capital and operational costs associated with different membrane technologies and identified the major hurdles impeding their commercialization. Furthermore, we examine hybrid and emerging membrane technologies that previous studies have suggested to reduce both energy and capital costs. Finally, we present future perspectives for the development of cost-effective membrane technologies suitable for industrial-scale applications. Full article

Traditional single neural network-based geo-localization methods for cross-view imagery primarily rely on polar coordinate transformations while suffering from limited global correlation modeling capabilities. To address these fundamental challenges of weak feature correlation and poor scene adaptation, we present a novel framework termed ICT-Net (Integrated CNN-Transformer Network) that synergistically combines convolutional neural networks with Transformer architectures. Our approach harnesses the complementary strengths of CNNs in capturing local geometric details and Transformers in establishing long-range dependencies, enabling comprehensive joint perception of both local and global visual patterns. Furthermore, capitalizing on the Transformer’s flexible input processing mechanism, we develop an attention-guided non-uniform cropping strategy that dynamically eliminates redundant image patches with minimal impact on localization accuracy, thereby achieving enhanced computational efficiency. To facilitate practical deployment, we propose a deep embedding clustering algorithm optimized for rapid parsing of geo-localization information. Extensive experiments demonstrate that ICT-Net establishes new state-of-the-art localization accuracy on the CVUSA benchmark, achieving a top-1 recall rate improvement of 8.6% over previous methods. Additional validation on a challenging real-world dataset collected at Beihang University (BUAA) further confirms the framework’s effectiveness and practical applicability in complex urban environments, particularly showing 23% higher robustness to vegetation variations. Full article

Bloom’s taxonomy provides a well-established framework for categorizing the cognitive complexity of assessment questions, ensuring alignment with course learning outcomes (CLOs). Achieving this alignment is essential for constructing meaningful and valid assessments that accurately measure student learning. However, in higher education, the large volume of questions that instructors must develop each semester makes manual classification of cognitive levels a time-consuming and error-prone process. Despite various attempts to automate this classification, the highest accuracy reported in existing research has not exceeded 93.5%, highlighting the need for further advancements in this area. Furthermore, the best-performing deep learning models only reached an accuracy of 86%. These results emphasize the need for improvement, particularly in the application of deep learning models, which have not been fully exploited for this task. In response to these challenges, our study explores a novel approach to enhance the accuracy of cognitive level classification. We leverage a combination of augmentation through synonym substitution, advanced feature extraction techniques utilizing DistilBERT and TF-IDF, and a robust ensemble model incorporating soft voting. These methods were selected to capture both semantic meaning and term frequency, allowing the model to benefit from contextual depth and statistical relevance. Additionally, Bayesian optimization is employed for hyperparameter tuning to refine the model’s performance further. The novelty of our approach lies in the fusion of sparse TF-IDF features with dense DistilBERT embeddings, optimized through Bayesian search across multiple classifiers. This hybrid design captures both term-level salience and deep contextual semantics, something not fully exploited in prior models focused solely on transformer architectures. Our soft-voting ensemble capitalizes on classifier diversity, yielding more stable and accurate results. Through this integrated approach outperformed previous configurations with an accuracy of 96%, surpassing the current state-of-the-art results and setting a new benchmark for automated cognitive level classification. These findings have significant implications for the development of high-quality, scalable assessments in educational settings. Full article

Cloud detection is a critical preprocessing step for optical remote sensing imagery. However, traditional CNN-based methods have limitations in global feature modeling, while Transformer models, despite their strong global modeling capability, struggle to capture fine-grained local details effectively. To tackle these challenges, this study introduces a dual-path neural network framework that synergistically combines convolutional neural networks (CNNs) and architectures. By capitalizing on their complementary strengths, this work proposed a dual-branch feature extraction architecture that utilizes two different feature aggregation modes to effectively aggregate features of CNN and Transformer at different levels. Specifically, two novel modules are introduced: the Dual-branch Lightweight Aggregation Module (DLAM), which fuses CNN and Transformer features in the early encoding stage and emphasizes key information through a feature weight allocation mechanism; and the Dual-branch Attention Aggregation Module (DAAM), which further integrates local and global features in the late encoding stage, improving the model’s differentiation performance between cloud and cloud shadow areas. The collaboration between DLAM and DAAM enables the model to efficiently learn multi-scale and spatially hierarchical information, thereby improving detection performance. The experimental findings validate the superior performance of our model over state-of-the-art methods on diverse remote sensing datasets, attaining enhanced accuracy in cloud detection. Full article

Debt levels are a crucial factor when assessing the financial stability of agricultural firms, and excessive indebtedness is usually the most important indicator of financial distress. As agriculture is a capital-intensive sector with a high reliance on borrowed funds, firms in this sector are more vulnerable to insolvency. This study examines the performance of artificial neural networks (ANNs) and decision trees (DTs) in predicting the bankruptcy of Slovak agricultural enterprises. In an attempt to compare the models’ performances, the most consequential indebtedness ratios are investigated through machine learning approaches. ANN and DT models are found to perform significantly better than traditional forecast methods. ANN achieved an AUC of 0.9500, accuracy of 96.37%, precision of 96.60%, recall of 99.68%, and an F1-score of 98.12%, determining its robust predictive ability. DT performed a little better on AUC (0.9550) and achieved an accuracy of 97.78%, precision of 98.69%, recall of 99.01%, and an F1-score of 98.85%, determining its predictive ability and interpretability. These findings confirm the potential for applying AI-based models to enhance financial risk assessment. This study provides informative results for financial analysts, policymakers, and corporate managers in support of early intervention strategies. Additional research would be required to explore state-of-the-art AI techniques to further refine bankruptcy forecasting and financial decision-making in vulnerable sectors like agriculture. Full article

Skeleton representation learning offers substantial advantages for action recognition by encoding intricate motion details and spatial–temporal dependencies among joints. However, fully supervised approaches necessitate large amounts of annotated data, which are often labor-intensive and costly to acquire. In this work, we propose the Spatial–Temporal Heatmap Masked Autoencoder (STH-MAE), a novel self-supervised framework tailored for skeleton-based action recognition. Unlike coordinate-based methods, STH-MAE adopts heatmap volumes as its primary representation, mitigating noise inherent in pose estimation while capitalizing on advances in Vision Transformers. The framework constructs a spatial–temporal heatmap (STH) by aggregating 2D joint heatmaps across both spatial and temporal axes. This STH is partitioned into non-overlapping patches to facilitate local feature learning, with a masking strategy applied to randomly conceal portions of the input. During pre-training, a Vision Transformer-based autoencoder equipped with a lightweight prediction head reconstructs the masked regions, fostering the extraction of robust and transferable skeletal representations. Comprehensive experiments on the NTU RGB+D 60 and NTU RGB+D 120 benchmarks demonstrate the superiority of STH-MAE, achieving state-of-the-art performance under multiple evaluation protocols. Full article

In the era of information explosion, recommendation systems play a crucial role in filtering vast amounts of content for users. Traditional recommendation models leverage knowledge graphs, sentiment analysis, social capital, and generative AI to enhance personalization. However, existing models still struggle to adapt dynamically to users’ evolving interests across multiple content domains in real-time. To address this gap, the cross-domain adaptive recommendation system (CDARS) is proposed, which integrates real-time behavioral tracking with multi-domain knowledge graphs to refine user preference modeling continuously. Unlike conventional methods that rely on static or historical data, CDARS dynamically adjusts its recommendation strategies based on contextual factors such as real-time engagement, sentiment fluctuations, and implicit preference drifts. Furthermore, a novel explainable adaptive learning (EAL) module was introduced, providing transparent insights into recommendations’ evolving nature, thereby improving user trust and system interpretability. To enable such real-time adaptability, CDARS incorporates multimodal sentiment analysis of user-generated content, behavioral pattern mining (e.g., click timing, revisit frequency), and learning trajectory modeling through time-aware embeddings and incremental updates of user representations. These dynamic signals are mapped into evolving knowledge graphs, forming continuously updated learning charts that drive more context-aware and emotionally intelligent recommendations. Our experimental results on datasets spanning social media, e-commerce, and entertainment domains demonstrate that CDARS significantly enhances recommendation relevance, achieving an average improvement of 7.8% in click-through rate (CTR) and 8.3% in user engagement compared to state-of-the-art models. This research presents a paradigm shift toward truly dynamic and explainable recommendation systems, creating a way for more personalized and user-centric experiences in the digital landscape. Full article

Achieving net-zero greenhouse gas emissions by 2050 requires CO₂-neutral industrial process heat, with seasonal energy storage (SES) playing a crucial role in balancing supply and demand. This study reviews thermal energy storage (TES) and Power-to-X (P2X) technologies for applications without thermal grids, assessing their feasibility, state of the art, opportunities, and challenges. Underground TES (UTES), such as aquifer and borehole storage, offer 1–26 times lower annual heat storage costs than above-ground tanks. For P2X, hydrogen storage in salt caverns is 80% less expensive than in high-pressure tanks. Methane and methanol storage costs depend on CO₂ sourcing, while Renewable Metal Energy Carriers (ReMECs), such as aluminum and iron, offer high energy density and up to 580 times lower storage volume, with aluminum potentially achieving the lowest Levelized Cost of X Storage (LCOXS) at a rate of 180 EUR/MWh of energy discharged. Underground TES and hydrogen caverns are cost-effective but face spatial/geological constraints. P2X alternatives have established infrastructure but have lower efficiency, whereas ReMECs show promise for large-scale storage. However, economic viability remains a challenge due to very few annual cycles, which require significant reductions of investment cost and annual cost of capital (CAPEX), as well as improvements in overall system efficiency to minimize losses. These findings highlight the trade-offs between cost, space requirements, and the feasibility of SES deployment in industry. Full article