Search Results (1,119)

The classification of urban residential settlements through Machine Learning (ML) and Deep Learning (DL) remains a complex task due to the intrinsic heterogeneity of urban environments and the scarcity of large, accurately labeled training datasets. To overcome these limitations, this study introduces a novel GIS-based unsupervised classification framework that exploits Fuzzy C-Means (FCM) clustering for the detection and interpretation of urban morphologies. Compared to unsupervised classification approaches that rely on crisp-based clustering algorithms, the proposed FCM-based method more effectively captures heterogeneous urban fabrics where no clear predominance of specific building types exists. Specifically, the method applies fuzzy clustering to census units—considered the fundamental scale of urban analysis—based on construction techniques and building periods. By grouping census areas with similar structural features, the framework provides a flexible, data-driven approach to the characterization of urban settlements. The identification of cluster centroids’ dominant attributes enables a systematic interpretation of the spatial distribution of the built environment, while the subsequent mapping process assigns each cluster a descriptive label reflecting the prevailing building fabric. The generated thematic maps yield critical insights into urban morphology and facilitate evidence-based planning. The framework was validated across ten Italian cities selected for their diverse physical, morphological, and historical characteristics; comparisons with the results of urban zone classifications in these cities conducted by experts show that the proposed method provides accurate results, as the similarity to the classifications made by experts, measured by the use of the Adjusted Rand Index, is always higher than or equal to 0.93; furthermore, it is robust when applied in heterogeneous urban settlements. These results confirm the effectiveness of the method in delineating homogeneous urban areas, thereby offering decision makers a robust instrument to guide targeted interventions on existing building stocks. The proposed framework advances the capacity to analyze urban form, to strategically support renovation and urban regeneration policies, and demonstrates a strong potential for portability, as it can be applied to other cities for urban scale analyses. Full article

During UAV aerial photography tasks, influenced by flight altitude and imaging mechanisms, the target in images often exhibits characteristics such as small size, complex backgrounds, and small inter-class differences. Under single optical modality, the weak and less discriminative feature representation of targets in drone-captured images makes them easily overwhelmed by complex background noise, leading to low detection accuracy, high missed-detection and false-detection rates in current object detection networks. Moreover, such methods struggle to meet all-weather and all-scenario application requirements. To address these issues, this paper proposes DVIF-Net, a visible-infrared fusion network for small-target detection in UAV aerial images, which leverages the complementary characteristics of visible and infrared images to enhance detection capability in complex environments. Firstly, a dual-branch feature extraction structure is designed based on YOLO architecture to separately extract features from visible and infrared images. Secondly, a P4-level cross-modal fusion strategy is proposed to effectively integrate features from both modalities while reducing computational complexity. Meanwhile, we design a novel dual context-guided fusion module to capture complementary features through channel attention of visible and infrared images during fusion and enhance interaction between modalities via element-wise multiplication. Finally, an edge information enhancement module based on cross stage partial structure is developed to improve sensitivity to small-target edges. Experimental results on two cross-modal datasets, DroneVehicle and VEDAI, demonstrate that DVIF-Net achieves detection accuracies of 85.8% and 62%, respectively. Compared with YOLOv10n, it has improved by 21.7% and 10.5% in visible modality, and by 7.4% and 30.5% in infrared modality, while maintaining a model parameter count of only 2.49 M. Furthermore, compared with 15 other algorithms, the proposed DVIF-Net attains SOTA performance. These results indicate that the method significantly enhances the detection capability for small targets in UAV aerial images, offering a high-precision and lightweight solution for real-time applications in complex aerial scenarios. Full article

Educational data mining (EDM) plays a crucial role in developing intelligent early warning systems that enable timely interventions to improve student outcomes. This study presents a novel approach to student performance prediction by integrating metaheuristic hyperparameter optimization with explainable artificial intelligence for enhanced learning analytics. While Light Gradient Boosting Machine (LightGBM) demonstrates efficiency in educational prediction tasks, achieving optimal performance requires sophisticated hyperparameter tuning, particularly for complex educational datasets where accuracy, interpretability, and actionable insights are paramount. This research addressed these challenges by implementing and evaluating five nature-inspired metaheuristic algorithms: Fox Algorithm (FOX), Giant Trevally Optimizer (GTO), Particle Swarm Optimization (PSO), Sand Cat Swarm Optimization (SCSO), and Salp Swarm Algorithm (SSA) for automated hyperparameter optimization. Using rigorous experimental methodology with 5-fold cross-validation and 20 independent runs, we assessed predictive performance through comprehensive metrics including Coefficient of Determination (R²), Root Mean Squared Error (RMSE), Mean Squared Error (MSE), Relative Absolute Error (RAE), and Mean Error (ME). Results demonstrate that metaheuristic optimization significantly enhances educational prediction accuracy, with SCSO-LightGBM achieving superior performance with R² of 0.941. SHapley Additive exPlanations (SHAP) analysis provides crucial interpretability, identifying Attendance, Hours Studied, Previous Scores, and Parental Involvement as dominant predictive factors, offering evidence-based insights for educational stakeholders. The proposed SCSO-LightGBM framework establishes an intelligent, interpretable system that supports data-driven decision-making in educational environments, enabling proactive interventions to enhance student success. Full article

As the core refrigeration equipment in cooling systems, the operational state of chiller units is crucial for ship support, equipment cooling, and mission stability. However, because of their sensitivity and the complexity of operating environments, obtaining large volumes of complete, fault-labeled data is difficult in practical engineering appli-cations. This limitation makes it challenging for traditional data-driven approaches to deliver accurate fault diagnoses. Furthermore, data collected from different devices or under varying operating conditions often differ significantly in both feature dimensions and distributions, i.e., data heterogeneity, which further complicates model transfer. To address these challenges, this study proposes a deep transfer learning–based fault di-agnosis method designed to leverage abundant knowledge from the source domain while adaptively learning features of the target domain. Given the persistent difficulties in collecting sufficient high-quality labeled fault data, traditional data-driven models continue to face restricted diagnostic performance on target equipment. At the same time, data heterogeneity across devices or operating conditions intensifies the challenge of cross-domain knowledge transfer. To overcome these issues, this study develops a heterogeneous transfer learning method that integrates a dual-channel autoencoder, domain adversarial training, and pseudo-label self-training. This combination enables precise small-sample knowledge transfer from the source to the target domain. Specifi-cally, the dual-channel autoencoder is first applied to align heterogeneous feature di-mensions. Then, a Gradient Reversal Layer (GRL) and a domain discriminator are in-troduced to extract domain-invariant features. In parallel, high-confidence pseu-do-labeled samples from the target domain are incorporated into joint training to im-prove generalization and robustness. Experimental results confirm that the method achieves high fault diagnosis accuracy in typical industrial application scenarios, ena-bling effective identification of common faults in various types of chiller units under conventional operating conditions, the proposed method achieves higher accuracy and F1-scores in multi-class fault diagnosis tasks compared with both traditional approaches and existing transfer learning methods. These findings provide a novel perspective for advancing the intelligent operation and maintenance of chiller units. Full article

The accurate and efficient placement of traffic cones is a critical safety and logistical requirement in diverse industrial environments. This study introduces a novel dataset specifically designed for the near-overhead detection of traffic cones, containing both bounding box annotations and apex keypoints. Leveraging this dataset, we systematically evaluated whether classical object detection methods or keypoint-based detection methods are more effective for the task of cone apex localization. Several state-of-the-art YOLO-based architectures (YOLOv8, YOLOv11, YOLOv12) were trained and tested under identical conditions. The comparative experiments showed that both approaches can achieve high accuracy, but they differ in their trade-offs between robustness, computational cost, and suitability for real-time embedded deployment. These findings highlight the importance of dataset design for specialized viewpoints and confirm that lightweight YOLO models are particularly well-suited for resource-constrained robotic platforms. The key contributions of this work are the introduction of a new annotated dataset for overhead cone detection and a systematic comparison of object detection and keypoint detection paradigms for apex localization in real-world robotic applications. Full article

This paper introduces a hybrid learning framework that synergistically combines Reinforcement Learning (RL) and Supervised Learning (SL) to train autonomous cyber-defense agents capable of operating effectively in dynamic and adversarial environments. The proposed approach leverages RL for strategic exploration and policy development, while incorporating SL to distill high-reward trajectories into refined policy updates, enhancing sample efficiency, learning stability, and robustness. The framework first targets specialized agent training, where each agent is optimized against a specific adversarial behavior. Subsequently, it is extended to enable the training of a generalized agent that learns to counter multiple, diverse attack strategies through multi-task and curriculum learning techniques. Comprehensive experiments conducted in the CybORG simulation environment demonstrate that the hybrid RL–SL framework consistently outperforms pure RL baselines across both specialized and generalized settings, achieving higher cumulative rewards. Specifically, hybrid-trained agents achieve up to 23% higher cumulative rewards in specialized defense tasks and approximately 18% improvements in generalized defense scenarios compared to RL-only agents. Moreover, incorporating temporal context into the observation space yields a further 4–6% performance gain in policy robustness. Furthermore, we investigate the impact of augmenting the observation space with historical actions and rewards, revealing consistent, albeit incremental, gains in SL-based learning performance. Key contributions of this work include: $\left(i\right)$ a novel hybrid learning paradigm that integrates RL and SL for effective cyber-defense policy learning, $\left(ii\right)$ a scalable extension for training generalized agents across heterogeneous threat models, and $\left(iii\right)$ empirical analysis on the role of temporal context in agent observability and decision-making. Collectively, the results highlight the promise of hybrid learning strategies for building intelligent, resilient, and adaptable cyber-defense systems in evolving threat landscapes. Full article

The operational performance of robotic arms for multi-rotor flying robots (MFRs) has attracted growing attention in recent years. To explore new possibilities for aerial manipulation, this study investigates a novel parallel mechanism, the TriVariant, comprising one UP limb and two identical UPS limbs (2-UPS&UP). To evaluate its potential, we analyze its dimensional and kinematic characteristics and benchmark them against the widely adopted Delta robot, which is commonly integrated with unmanned aerial vehicles (UAVs). A prototype of the TriVariant is fabricated for experimental validation. Both analytical and experimental results reveal that, within a cylindrical task workspace characterized by a large diameter and moderate height, the TriVariant offers a more compact structure than the Delta robot, despite its slightly reduced dexterity. These findings highlight that the TriVariant is especially suitable for aerial manipulation in space-constrained environments where all limbs must be mounted beneath the UAV. Full article

The article addresses the challenges of beam position tracking in Free-Space Optical Communication (FSOC) systems. A review of available photodetector technologies is presented, highlighting their operating principles and applications in optical links. The analysis indicates that most current monitoring devices function with the visible and near- or short-infrared ranges. However, due to the propagation characteristics of radiation in terrestrial environments, the mid-wave infrared (MWIR) region offers particularly promising opportunities. To the end, the work introduces a novel detector module based on an MWIR quadrant detector capable of simultaneously performing two essential tasks: monitoring beam position and receiving transmitted data. Such an integrated approach has the potential to significantly simplify the design of mobile FSOC systems, especially those requiring accurate transceivers’ tracking. The concept was validated through laboratory experiments on an MWIR link model, where both the signal bandwidth and position transfer function of the quadrant detector were examined. Full article

High-precision angular positioning mechanisms are essential across diverse scientific and industrial applications, from optical instrumentation to automated mechanical systems. Conventional bronze–steel gear reduction units, while reliable, are often heavy, costly, and unsuitable for chemically aggressive or vacuum environments, limiting their use in advanced research setups. This work introduces a novel 1:360 gear reduction system manufactured by resin-based additive manufacturing, designed to overcome these limitations. The compact worm–gear assembly translates a single crank rotation into a precise one-degree indicator displacement, enabling fine and repeatable angular control. A primary application is the alignment of parabolic mirrors in schlieren systems, where accurate tilt adjustment is critical to correct optical alignment; however, the design is broadly adaptable to other precision positioning tasks in laboratory and industrial contexts. Compared with conventional assemblies, the resin-based reducer offers reduced weight, chemical and vacuum compatibility, and lower production cost. Its three-stage reduction design further enhances load-bearing capacity, achieving approximately double the theoretical torque transfer of equivalent commercial systems. These features establish the device as a robust, scalable, and automation-ready solution for high-accuracy angular adjustment, contributing both to specialized optical research and general-purpose precision engineering. Full article

Electrocardiogram (ECG) waveform delineation is fundamental to cardiac disease diagnosis. This task requires precise localization of key fiducial points, specifically the onset, peak, and offset positions of P-waves, QRS complexes, and T-waves. Current methods exhibit significant performance degradation in noisy clinical environments (baseline drift, electromyographic interference, powerline interference, etc.), compromising diagnostic reliability. To address this limitation, we introduce ECG-SCFNet: a novel dual-stream architecture employing selective context fusion. Our framework is further enhanced by a consistency training paradigm, enabling it to maintain robust waveform delineation accuracy under challenging noise conditions.The network employs a dual-stream architecture: (1) A temporal stream captures dynamic rhythmic features through sequential multi-branch convolution and temporal attention mechanisms; (2) A morphology stream combines parallel multi-scale convolution with feature pyramid integration to extract multi-scale waveform structural features through morphological attention; (3) The Selective Context Fusion (SCF) module adaptively integrates features from the temporal and morphology streams using a dual attention mechanism, which operates across both channel and spatial dimensions to selectively emphasize informative features from each stream, thereby enhancing the representation learning for accurate ECG segmentation. On the LUDB and QT datasets, ECG-SCFNet achieves high performance, with F1-scores of 97.83% and 97.80%, respectively. Crucially, it maintains robust performance under challenging noise conditions on these datasets, with 88.49% and 86.25% F1-scores, showing significantly improved noise robustness compared to other methods and demonstrating exceptional robustness and precise boundary localization for clinical ECG analysis. Full article

The Zebra Optimization Algorithm (ZOA) is a metaheuristic algorithm inspired by the collective behavior of zebras in the wild. Like many other swarm intelligence algorithms, the ZOA faces several limitations, including slow convergence, susceptibility to local optima, and an imbalance between exploration and exploitation. To address these challenges, this paper proposes an improved version of the ZOA, termed the Multi-strategy Improved Zebra Optimization Algorithm (MIZOA). First, a multi-population search strategy is introduced to replace the traditional single population structure, dividing the population into multiple subpopulations to enhance diversity and improve global convergence. Second, the mutation operation of genetic algorithm (GA) is integrated with the Metropolis criterion to boost exploration capability in the early stages while maintaining strong exploitation performance in the later stages. Third, a novel selective aggregation strategy is proposed, incorporating the hunting behavior of the Coati Optimization Algorithm (COA) and Lévy flight to further enhance global exploration and convergence accuracy during the defense phase. Experimental evaluations are conducted on 23 benchmark functions, comparing the MIZOA with eight existing swarm intelligence algorithms. The performance is assessed using non-parametric statistical tests, including the Wilcoxon rank-sum test and the Friedman test. The results demonstrate that the MIZOA achieves superior global convergence accuracy and optimization performance, confirming its robustness and effectiveness. The MIZOA was evaluated on real-world engineering problems against seven algorithms to validate its practical performance. Furthermore, when applied to path planning tasks for Automated Guided Vehicles (AGVs), the MIZOA consistently identifies paths closer to the global optimum in both simple and complex environments, thereby further validating the effectiveness of the proposed improvements. Full article

This study aimed to explore psychosocial factors in a sample of Peruvian workers, examine their convergence with the PROPSIT model, and identify the emergence of new or idiosyncratic psychosocial dimensions. At the same time, the quality and efficiency of the categorization process were evaluated. n = 48 workers were contacted by a non-probabilistic sampling method and asked to fill out a form with open-ended questions that explored negative stressors and positive engaging factors. Some strategies were used to assess the quality and efficiency of the categorization process. The results showed that the quality, speed, and reliability of the categorization procedure were satisfactory, and several categories were aligned with the PROPSIT model and other literature, both in their negative aspects (workload and rhythm, working hours, shifts, etc.) and positive aspects (rewarding tasks, atmosphere of unity, etc.). The emerging new categories were confined to aspects of teamwork and conflict climate, as well as topics such as order, cleanliness, and recreation. These findings underline the need to adapt existing models and instruments to capture idiosyncratic aspects of the Peruvian work environment. In conclusion, this study validated an efficient mixed approach for categorizing psychosocial work factors in Peru, revealing both PROPSIT-aligned and novel context-specific categories, and highlighting the need for culturally adapted tools and broader validation. Full article

Mobile crowd computing (MCdC) leverages the collective computational resources of nearby mobile devices to execute complex tasks without relying on remote cloud infrastructure. However, existing MCdC systems struggle with device heterogeneity and complex application dependencies, often leading to inefficient resource utilization and poor scalability. This paper presents Honeybee-Tx, a novel dependency-aware work stealing framework designed for heterogeneous mobile device clusters. The framework introduces three key contributions: (1) capability-aware job selection that matches computational tasks to device capabilities through lightweight profiling and dynamic scoring, (2) static dependency-aware work stealing that respects predefined task dependencies while maintaining decentralized execution, and (3) staged result transfers that minimize communication overhead by selectively transmitting intermediate results. We evaluate Honeybee-Tx using two applications: Human Activity Recognition (HAR) for sensor analytics and multi-camera video processing for compute-intensive workflows. The experimental results on five heterogeneous Android devices (OnePlus 5T, Pixel 6 Pro, and Pixel 7) demonstrate performance improvements over monolithic execution. For HAR workloads, Honeybee-Tx achieves up to 4.72× speed-up while reducing per-device energy consumption by 63% (from 1.5% to 0.56% battery usage). For video processing tasks, the framework delivers 2.06× speed-up compared to monolithic execution, with 51.4% energy reduction and 71.6% memory savings, while generating 42% less network traffic than non-dependency-aware approaches. These results demonstrate that Honeybee-Tx successfully addresses key challenges in heterogeneous MCdC environments, enabling efficient execution of dependency-aware applications across diverse mobile device capabilities. The framework provides a practical foundation for collaborative mobile computing applications in scenarios where cloud connectivity is limited or unavailable. Full article

Robot energy consumption is a prominent challenge in intelligent manufacturing and construction. Reducing energy consumption during robot trajectory execution is an urgent issue requiring immediate attention. In view of the shortcomings of traditional trajectory optimization methods, this paper proposes a multi-objective trajectory optimization method that combines energy consumption mapping with the NSGA-II, aiming to reduce robots’ trajectory energy consumption and optimize execution efficiency. By establishing a dynamic energy consumption model, energy consumption mapping is employed to constrain energy consumption within the robot’s workspace, thereby providing guidance for the optimization process. Simultaneously, with energy consumption minimization and time consumption as optimization objectives, the NSGA-II is utilized to obtain the Pareto-optimal solution set through non-dominated sorting and congestion distance calculation. Energy consumption mapping serves as a dynamic feedback mechanism during the optimization process, guiding the distribution of trajectory points towards low-energy-consumption regions, accelerating algorithm convergence, and enhancing the quality of the solution set. The experimental results demonstrate that the proposed method can significantly reduce robots’ trajectory energy consumption and achieve an effective balance between energy consumption and time consumption. Compared with the conventional NSGA-II normalized weighted function method in similar task scenarios, the robot can save 14.87% and 10.47% of its energy consumption, respectively. Compared with traditional methods, this method exhibits superior energy-saving performance and adaptability in complex task environments, providing a novel solution for the efficient trajectory planning of robots. Full article

Conventional projection systems typically require a fixed spatial configuration relative to the projection surface, with strict control over distance and angle. In contrast, UAV-mounted projectors overcome these constraints, enabling dynamic, large-scale projections onto non-planar and complex environments. However, such flexible scenarios introduce a key challenge: severe geometric distortions caused by intricate surface geometry and continuous camera–projector motion. To address this, we propose a novel image registration method based on global dense matching, which estimates the real-time optical flow field between the input projection image and the target surface. The estimated flow is used to pre-warp the image, ensuring that the projected content appears geometrically consistent across arbitrary, deformable surfaces. The core idea of our method lies in reformulating the geometric distortion correction task as a global feature matching problem, effectively reducing 3D spatial deformation into a 2D dense correspondence learning process. To support learning and evaluation, we construct a hybrid dataset that covers a wide range of projection scenarios, including diverse lighting conditions, object geometries, and projection contents. Extensive simulation and real-world experiments show that our method achieves superior accuracy and robustness in correcting geometric distortions in dynamic UAV projection, significantly enhancing visual fidelity in complex environments. This approach provides a practical solution for real-time, high-quality projection in UAV-based augmented reality, outdoor display, and aerial information delivery systems. Full article