Search Results (514)

Small ruminant production in Kosovo is predominantly extensive, and biosecurity practices remain poorly characterized. The emergence of Peste des Petits Ruminants (PPR) in Europe (beginning in 2024) and the first confirmed case in Kosovo (July 2025) highlight the urgent need for baseline biosecurity data to inform disease control. A cross-sectional pilot study was conducted on 63 small ruminant farms (53 meat-producing, 10 dairy-producing) across seven municipalities in Kosovo between September 2025 and February 2026. Biosecurity practices were assessed using the Biocheck.UGent™ questionnaire during direct on-farm visits. External (Ext) biosecurity scores (preventing pathogen introduction) were higher (p < 0.0001) than internal (Int) scores (limiting spread within farms). For external biosecurity, the highest scores were observed for purchase and reproduction (Ext A), intermediate scores existed for feed and water (Ext C) and visitors and farm workers (Ext D), and the lowest scores were found for transport and carcass removal (Ext B) and infrastructure (Ext E). For internal biosecurity, the highest scores were observed for lamb/kid management (Int H) and dairy management (Int I), followed by the management of adult animals (Int J); work organization (Int K) and reproduction management (Int G) formed an intermediate-low cluster, whereas disease management (Int F) scored the lowest. Benchmarking against the Biocheck.UGent™ worldwide database (predominantly intensive systems, thus not directly comparable) indicated that internal biosecurity and overall biosecurity levels were lower than the benchmark, while external biosecurity was comparable for some components. Given the convenience sample (36.4% response rate), findings are exploratory and are not directly generalizable. Larger herd size was positively correlated with external (ρ = 0.54, p < 0.0001), internal (ρ = 0.35, p = 0.005), and overall (ρ = 0.57, p < 0.0001) biosecurity scores. This first empirical biosecurity assessment of small ruminant farms in Kosovo reveals critical gaps in transport hygiene, disease management, and reproductive management pathways that enable PPR spread and perpetuate endemic zoonoses. The positive association between herd size and biosecurity may indicate structural barriers and/or knowledge gaps for small farms. Current biosecurity tools, designed for intensive systems, require adaptation for extensive production systems. These findings provide a baseline for targeted interventions, policy development, and validation of context-appropriate biosecurity instruments in Kosovo and similar extensive systems globally. Full article

The proposed methodology combines analytical control laws with adaptive mechanisms and machine-learning-assisted modules based on regression trees, random forests, and extreme gradient boosting (XGBoost). Machine learning models are employed to approximate unknown nonlinear dynamics, compensate disturbances, and adjust controller parameters, while the overall control structure is constrained by Lyapunov stability conditions. This ensures that the inclusion of data-driven components does not violate the fundamental requirement of system stability. The effectiveness of the proposed approach is evaluated through simulation experiments across three operating modes with varying degrees of nonlinearity and dynamic complexity. The results show that hybrid models incorporating ensemble machine learning methods improved performance compared with the analytical and adaptive baselines examined. XGBoost-based control achieves the lowest error values and the highest level of Lyapunov stability compliance (up to 99.3%). The main contribution of this study lies in the development of a unified synthesis framework in which machine learning is not used as a standalone control strategy but as a machine-learning-assisted support mechanism integrated into a theoretically grounded control architecture. The proposed approach provides a balance between adaptability, accuracy, and rigorous stability guarantees, suggesting potential applicability to simulation-based and offline-assisted control design tasks, while real-time embedded implementation requires additional computational optimization and validation. Full article

Equipment fault prediction in maglev train systems poses substantial challenges: fault events are inherently rare, class distributions are severely imbalanced, and individual equipment units are subject to complex spatial and functional couplings that single-device statistical approaches fundamentally cannot capture. To address these challenges, this study proposes a Knowledge Graph-driven Graph Neural Network (KG-GNN) framework. A fault knowledge graph encompassing equipment, fault, temporal, and environmental entities is constructed to unify multi-source maintenance data. Graph connectivity is established via three spatial relation types (co-location, co-zone, and co-level), with edge weights derived from Laplacian-smoothed Lift scores quantifying fault co-occurrence strength. A two-layer GATv2Conv-based graph attention network is designed: the first layer employs four-head attention with explicit edge-weight integration to capture heterogeneous neighborhood influences, while the second layer produces compact node embeddings via single-head attention. A Top-20 sparsification strategy suppresses weak-association noise, and training under severe class imbalance is stabilized through Focal Loss and F2-Score-guided early stopping. On the test set, the proposed method achieves an F2-Score of 0.5703, Recall of 0.6825, and AUC-ROC of 0.9329 (single-run evaluation); multi-seed evaluation (5 seeds) yields F2 = 0.5645 ± 0.0035, Recall = 0.6789 ± 0.0095, and AUC-ROC = 0.9298 ± 0.0026, outperforming the MLP baseline by 18.3% in F2-Score and substantially exceeding GCN (F2 = 0.1476 ± 0.0176) and GATConv (F2 = 0.4284 ± 0.0097). Ablation studies confirm the individual contributions of authentic graph topology, precise edge weighting, and graph sparsification to overall performance. Full article

Recent advancements in computer vision, particularly in detection, segmentation, and classification, have significantly impacted various domains. However, these advancements are still strongly tied to RGB-based systems, which are insufficient for applications in industries such as waste sorting, pharmaceuticals, and defence, where material characterization beyond shape or visible colour is necessary. Hyperspectral (HS) imaging captures spatial and spectral information for each pixel and therefore offers a promising route for material-level classification. This study evaluates the potential of combining HS imaging with deep learning for plastic material classification. The work includes: (i) the design of an experimental setup with a HS line-scan camera, conveyor, and controlled illumination; (ii) the construction of an object-disjoint dataset of HDPE, PET, PP, and PS samples with semi-automated mask generation and Raman spectroscopy-based labelling; and (iii) the development of P1CH, a lightweight pixel-wise 1D convolutional hyperspectral classifier. On object-disjoint test images, P1CH achieved 97.44% all-pixel accuracy. A boundary sensitivity analysis, reported separately because semi-automated labels are uncertain at material/background interfaces, yielded 99.94% accuracy after excluding a pre-defined two-pixel border band. Additional ablation, baseline, and robustness analyses show that the proposed pixel-wise spectral approach is effective for small fragments, visually similar plastics, and overlapping materials, while black or very dark plastics remain challenging under the present camera and illumination configuration. Full article

Metallurgical lifting equipment operates under prolonged heavy-load, high-impact, and complex working conditions. The resulting failure reports contain rich field knowledge applicable to fault diagnosis and predictive maintenance. Nevertheless, reliably extracting traceable, structured knowledge from procedural and implicit maintenance records remains a significant challenge. To address this, the paper proposes a generative information extraction method for large language models (LLMs) that integrates ontology schema with inference chain constraints, targeting knowledge extraction and knowledge graph construction from failure reports of metallurgical lifting equipment, named generative constrained information extraction for operations and maintenance (GCIE-OM). A domain ontology schema is first constructed, defining seven entity types and nine relation types to establish explicit knowledge boundaries for structured LLM generation. An inference chain-assisted structured parsing method, termed IC-ASP, is then designed to guide the model through a sequential extraction pipeline comprising scene identification, scope of entity boundary, inference of relation type, evidence traceability with localization, and triple output. This stepwise process strengthens the model’s capacity to comprehend equipment hierarchies, fault evolution chains, and maintenance action logic. Building on this, ChatGLM or LLaMA serves as the backbone model and is adapted to the target domain via LoRA fine-tuning. Entity alignment and character-level source localization mechanisms are further introduced to establish precise mappings between generated outputs and their textual evidence in the source documents. The extracted results are ultimately converted into standardized knowledge triples and stored in a Neo4j graph database. Based on this, a prototype system for generative information extraction is designed and implemented to demonstrate the practical effectiveness and adaptability of the proposed method. Experimental results show that the proposed method outperforms baseline methods across entity recognition, relation extraction, and structured output quality, providing robust knowledge support for fault tracing and predictive maintenance of metallurgical lifting equipment. Full article

Industrial robot after-sales question answering often depends on multimodal evidence, such as error screenshots, interface displays, and wiring diagrams, which are difficult for conventional text-based retrieval-augmented generation (RAG) systems to exploit effectively. To address this issue, we design a dual-channel multimodal RAG system that converts image content into retrievable textual knowledge through the collaboration of optical character recognition (OCR) and structured semantic description. In the proposed system, OCR is used to extract explicit textual cues, such as error codes, parameter fields, and interface prompts, while expert-authored semantic descriptions complement implicit visual evidence, including device parts, fault phenomena, and contextual scene information. The transformed knowledge is further integrated into a hybrid retrieval pipeline that combines dense retrieval and BM25, followed by Reciprocal Rank Fusion (RRF) and Maximal Marginal Relevance (MMR) reordering to improve both relevance and contextual diversity. Experiments on a real-world industrial robot after-sales dataset show that the proposed method achieves an overall question-answering accuracy of 87.9%, outperforming the LLM-only baseline by 35.6 percentage points. For image-related questions, accuracy improves from 46.7% to 83.3%. These results indicate that the proposed framework provides a deployment-friendly and interpretable system-level alternative to end-to-end multimodal model fine-tuning for industrial after-sales question answering. Full article

This study examined the instructional effects of integrating a game-based learning system into a programming course, focusing on how tool-supported practice influences students’ learning outcomes and learning experiences. A quasi-experimental design was employed, involving an experimental group that used a game-based learning system for programming practice and a control group that completed traditional programming assignments. Both groups were taught by the same instructor using identical instructional content over an eight-week period. Pre-tests and post-tests were administered to assess learning performance. Baseline-adjusted and conditional effect analyses were conducted to examine whether the instructional effect varied according to students’ prior programming knowledge. The results showed that students in the experimental group achieved higher post-test performance than those in the control group, and the Group × Pre-test interaction indicated that the learning effect was conditional on learners’ baseline programming competence. In addition, students in the experimental group completed questionnaires on system use perceptions and flow experience. The findings indicated generally positive perceptions of the game-based learning system and a significantly positive level of flow during programming practice. The findings suggest that the GBPLS can support programming practice when it is embedded within a coherent instructional design. However, the observed benefits should be interpreted as conditional rather than universal. The educational value of the system appears to depend on the alignment among programming tasks, feedback, game-based engagement, generative AI-supported question generation, and teacher guidance. Full article

Existing truck–drone collaborative routing models predominantly assume fixed flight speeds, overlooking the non-linear coupling among speed, payload, and energy consumption, which limits urban delivery efficiency. To bridge this gap, this paper proposes the multiple flying sidekick traveling salesman problem with variable drone speed (mFSTSP-VDS). Formulating drone cruising speed as a continuous variable under strict non-linear energy constraints, we design a hybrid algorithm (ALNS-SA-VND) to jointly optimize routing, task allocation, and speed. Empirical analysis of Wuhan’s road network demonstrates the VDS strategy’s robustness. Specifically, VDS reduces the system makespan by up to 17.5% compared to rigid maximum-speed strategies, with consistent stability across varying load scenarios. By adaptively trading permissible battery capacity for temporal synchronization, VDS effectively mitigates unnecessary truck waiting times at rendezvous nodes. This study quantitatively validates the impact of sortie-specific speed adaptation on time efficiency, providing an exploratory theoretical baseline for tactical-level planning in smart logistics networks. Full article

To address the challenges of strong signal noise, pronounced cross-modal asynchrony, high subjectivity in manually defined state labels, and insufficient model stability under extreme abnormal conditions in multi-source sensor systems, a low-noise system state prediction and anomaly detection method based on multimodal sensor signals and self-supervised representation learning is proposed. Environmental sensing data, device status data, network transmission data, operational behavior data, and event log data are uniformly modeled as system state perception signals. A temporal masking-based state structure modeling method, a state-oriented contrastive learning representation constraint mechanism, and a state representation and downstream prediction task alignment strategy are designed to learn stable, transferable, and interpretable system state features. Experimental results demonstrate that the proposed method achieves the best performance in multimodal sensor state prediction and anomaly detection tasks, with mean squared error (MSE), mean absolute error (MAE), and root mean square error (RMSE) values of $0.0167$, $0.0856$, and $0.1291$, respectively, outperforming baseline models such as GARCH, MLP, LSTM, TCN, and Transformer. Meanwhile, $IC$, $RankIC$, and $AUC$ reach $0.494$, $0.460$, and $0.815$, respectively, indicating stronger state-ranking capability and improved discrimination between high-abnormality and low-abnormality states. At the classification recognition level, superior accuracy, precision, recall, and $F1$-score are also achieved by the proposed method, suggesting that potential abnormal states can be identified more accurately. Ablation experiments verify the effectiveness of multimodal fusion, temporal masking modeling, self-supervised contrastive constraints, and task alignment strategies. Robustness experiments further show that lower prediction errors and higher $AUC$ can still be maintained under high-fluctuation and extreme-shock states, demonstrating strong noise resistance, stability, and practical application potential in complex sensor system scenarios. Full article

AI-enabled cyber–physical systems (CPSs) are increasingly deployed in public governance contexts where they sense human populations, infer classifications or risks, and trigger interventions that can shape liberty, equality, and access to essential services. In these deployments, governance failures often arise not only from model error but from systems-level interactions across data generation, model updates, organizational practices, and downstream actuation. This paper introduces a Risk–Rights–Rules (3R) architecture that treats fundamental rights and legal rules as enforceable constraints on the sensing–inference–actuation loop, rather than as external ethical aspirations. Building on established risk-management baselines and safety engineering practice, we specify a testable assurance object, a structured 3R assurance case, that links rights claims to explicit assumptions, measurable evidence, and accountable control points across the lifecycle. The approach is designed to reduce “legitimacy drift” in stochastic decision pipelines by making uncertainty, demographic error, contestability, and procurement leverage auditable at the system level. The result is a governance blueprint for high-consequence public-sector AI deployments for governance failures, which is both technically robust and institutionally defensible. Full article

Wind speed prediction is an essential spatiotemporal forecasting task in wind energy systems, yet it remains challenging due to the nonlinear and dynamic characteristics of atmospheric processes. The evolution of wind is governed by physical laws, which can be effectively described using partial differential equations (PDEs). To improve forecasting reliability and accuracy, this paper proposes a novel network model, termed DynWindNet, which integrates equation-based dynamics with data-driven dynamics within a unified framework. Specifically, an interactive dual-branch architecture is designed, where a Physics–Data Coupling Module (PDCM) enables adaptive information exchange between the two dynamics via attention-based gating mechanisms. In addition, a frequency-aware enhancement module (FAEM) is introduced to refine the representations of the data-driven branch by selectively emphasizing informative frequency components. Experimental results on the ERA5 dataset demonstrate that DynWindNet consistently outperforms representative baseline methods across atmospheric pressure levels. Overall, the proposed framework provides an effective approach for integrating physics-guided evolution modeling with deep spatiotemporal representation learning in wind field forecasting. Full article

This paper presents the design and experimental validation of a self-contained rotating Halbach array—based demonstrator for electrodynamic suspension (EDS) systems. The proposed platform was developed to bridge the gap between conventional externally powered laboratory testbeds and large-scale EDS vehicles by enabling investigation of levitation behavior under realistic onboard mass and subsystem integration constraints. The system integrates rotating circular Halbach arrays, onboard power supply, sensing, motor control, and structural support within a single levitated architecture. Experimental validation was conducted under a constrained one-degree-of-freedom configuration allowing vertical motion only. The system achieved stable levitation of a 35 kg platform and supported additional payloads approaching a 1:2 ratio relative to the baseline mass, while maintaining air-gap stability within approximately ±0.1 mm. The experimental results further reveal that the operational limit of the system is governed by actuation power and current constraints rather than electromagnetic levitation capability, highlighting a key distinction between self-contained and externally powered EDS systems. The proposed demonstrator provides a compact and practical experimental platform for the validation and performance evaluation of Halbach-array-based EDS systems. In addition, the study presents practical engineering insights regarding payload distribution, actuator saturation, structural integration, and system-level design constraints relevant to future self-contained EDS platforms and control-oriented levitation systems. Full article

In electric vehicle thermal management systems, direct measurement of the internal motor temperature is difficult. Therefore, the coolant pressure drop is an important indicator for estimating the motor thermal state. However, manufacturing and operating uncertainties in water-cooled interior permanent magnet synchronous motors (IPMSMs) can cause variability in cooling performance and pressure drop, requiring a reliability-based design approach. In this study, reliability-based design optimization (RBDO) is performed by considering manufacturing tolerances in the cooling channels and uncertainty in the inlet coolant flow rate. Based on coupled electromagnetic–thermal–fluid analysis and Kriging surrogate models, RBDO is applied to minimize the maximum temperature while satisfying the allowable pressure-drop limit at a target reliability level. The proposed RBDO improves the probability of satisfying the pressure-drop constraint from 54.1% in the baseline design to 99.9%, while increasing the mean maximum temperature by only 0.17 K. These results indicate that RBDO can improve the reliability of the pressure-drop constraint in IPMSM water-cooling systems under practical manufacturing and operating uncertainties, with only a limited change in thermal performance. Full article

Elevated concentrations of fine particulate matter ($P{M}_{2.5}$) are a critical threat to respiratory health worldwide. Therefore, there is an urgent need for precise urban forecasting systems for public health management. Technological advancements in the domains of continuous environmental monitoring and deep learning have enabled large-scale data acquisition, processing, and modeling. Existing predictive models typically depend on auxiliary meteorological inputs, which are frequently inaccessible within standard ground-level monitoring networks. Furthermore, conventional approaches often fail to adequately capture the complex spatio-temporal interactions of pollutants. To address these limitations, this study presents the Spatio-Temporal Endogenous Attention Network (STEA-Net), a forecasting framework designed to operate exclusively without weather variables. Validated on a comprehensive multi-year historical dataset (Jan 2015–Feb 2020) from diverse monitoring stations in India, STEA-Net employs a hybrid adjacency matrix that integrates physical geographical distances with functional clustering to accurately map pollutant transport pathways. Utilizing this structural map, a Graph Attention Network dynamically evaluates the spatial influence of neighboring nodes, while a Bidirectional LSTM processes the underlying temporal sequences. Experimental results demonstrate that STEA-Net substantially surpasses traditional machine learning algorithms and provides competitive performance against advanced deep learning baselines. The proposed model achieves a peak Coefficient of Determination ($R^2$) of 0.9294 (5-seed average: $0.9273\pm 0.0023$) and a peak RMSE of 14.38 µg/m³ (5-seed average: $14.59\pm 0.23$ µg/m³), effectively adapting to the dynamic volatility of urban pollution levels. The model exhibits architectural stability with a Monte Carlo dropout verified deviation of $\pm 2.22$ µg/m³. This research provides a forecasting architecture that retains competitive predictive performance under the strict operational constraint of meteorology-free deployment in resource-constrained urban monitoring environments. Full article

This paper presents Resilient Edge-IVA (Intelligent Video Analytics), an integrated framework designed to ensure real-time inference stability and high-speed embedding-based similarity search in resource-constrained edge computing environments. Conventional systems often face Quality of Experience (QoE) degradation caused by computational overhead and hardware-level bottlenecks. To address these challenges, this study proposes a “Whole-cycle” methodology employing a perception-driven, three-tier adaptive control algorithm. This algorithm dynamically modulates encoding parameters, such as resolution and bitrate, by utilizing real-time inference latency and CPU utilization as feedback signals. Furthermore, the framework incorporates an event-density-based Data Diet mechanism. This mechanism selectively adjusts video quality based on object detection results, preserving high-fidelity imagery for critical events while significantly reducing data volume during static intervals. The backend implements a hybrid storage architecture combining the Milvus vector database for CLIP-based high-dimensional visual embeddings with a PostgreSQL relational database for structured metadata. These systems are linked via a deterministic hash key to ensure data atomicity and facilitate high-speed, multi-dimensional embedding-based retrieval. Experimental evaluations conducted on a Raspberry Pi 5 and Hailo-8 NPU demonstrate that the proposed framework maintains a frame drop rate below 0.3% even under extreme workloads, providing a 13-fold improvement in operational stability over static configurations. The results also confirm a 54.2% reduction in total storage occupancy and a Hash Mapping Consistency (HMC) score of 0.89. These findings validate the framework’s effectiveness in reconciling real-time processing stability with storage efficiency. Building upon this baseline, future research will extend the framework to multi-class environments, targeting applications such as Intelligent Transport Systems (ITS). Full article