Search Results (321)

Aiming at the challenges of class imbalance, tiny defect scales, and complex brushed background interference in the surface defect detection of electrical commutators, this paper proposes a high-precision and lightweight improved instance segmentation algorithm named WG-YOLOv11. Firstly, to overcome the barrier of highly imbalanced positive and negative samples in actual industrial data collection, a Balanced Defect Synthesis (BDS) data augmentation strategy is introduced to effectively enrich the morphological diversity of tiny defects. Secondly, a Wavelet Transform Convolution (WTConv) module is collaboratively integrated into the feature extraction network to expand the receptive field while preserving the high-frequency edge details of hairline cracks. Thirdly, a Group CBAM Enhancer (GCE) module is introduced to filter out high-reflection and brushed background noise through grouped attention and weight re-calibration mechanisms. Finally, addressing the difficulty of pixel-level alignment for tiny defects, an $\alpha$-IoU loss function is utilized to improve the high-precision segmentation and localization capabilities by dynamically adjusting the gradient distribution. Comprehensive evaluations are conducted on two real-world electrical commutator surface defect datasets: KolektorSDD2 and KolektorSDD. Experimental results show that on the KolektorSDD2 dataset, compared to the YOLOv11 baseline, the Mask mAP@50 of WG-YOLOv11 increases from 85.2% to 89.2%, and the stringent metric Mask mAP@50:95 improves from 52.7% to 56.9%. Additional computational analysis on the same dataset validates that the proposed method maintains high efficiency, matching the baseline computational cost without compromising real-time inference speed. Furthermore, evaluations on the public MSD dataset confirm the model’s cross-domain generalization capabilities. The proposed framework effectively achieves a balance between detection accuracy, anti-interference robustness, and a lightweight architecture. Full article

Breast cancer is a critical global health challenge, and deep learning shows transformative potential for medical image classification. However, privacy regulations such as HIPAA and GDPR create barriers to centralized data aggregation across institutions. This paper presents an empirical evaluation of federated learning (FL) for breast cancer classification in ultrasound images, systematically comparing seven deep learning architectures (ResNet-50, VGG16, VGG19, DenseNet-121, MobileNetV2, Vision Transformer, CoAtNet) across three FL algorithms (FedAvg, FedProx, FedOpt) with client-side differential privacy (DP). Using a simulated federation of eight institutions, we evaluate three clinically relevant classification scenarios. Federated models achieve performance comparable to centralized baselines—98.52% accuracy for normal/abnormal screening, 89.53% for three-class classification—with ViT-small and DenseNet-121 exceeding their centralized counterparts in several configurations. Under strong DP constraints (noise multiplier $\eta =2.0$, yielding conservative privacy budget estimates of $\epsilon <1.0$ with $\delta ={10}^{-5}$), screening accuracy remains above 82%, though diagnostic tasks incur substantial degradation (best 68.42%). Our findings provide empirical guidance on architecture selection, FL algorithm choice, and privacy-utility trade-offs for privacy-preserving breast cancer diagnosis, while identifying key challenges for clinical deployment. Full article

Modern turbine engines, when operating at high temperatures, can inhale calcium–magnesium–alumina–silicate particles (CaO-MgO-Al₂O₃-SiO₂, CMAS) from the air, which can erode the thermal barrier coatings on the blade surface, affecting the service life of the thermal barrier coatings and, in severe cases, leading to premature blade failure. Therefore, it is of great significance to effectively detect the thickness of CMAS deposited on the surface of the thermal barrier coatings at an early stage of CMAS erosion to ensure the high-temperature structural integrity of the hot-end components of aeroengines. Based on this, this study proposes a method combining terahertz time-domain spectroscopy technology and a hybrid machine learning algorithm for the quantitative detection of the thickness of CMAS on the surface of thermal barrier coatings. Firstly, the terahertz time-domain spectroscopy experimental data of CMAS were obtained using a terahertz experimental system, and the refractive index and absorption coefficient of CMAS in the terahertz frequency band were calculated. The FDTD method, Gaussian noise addition, and wavelet denoising processing were combined to further simulate the terahertz detection process of thermal barrier coatings with different thicknesses of CMAS attached to the surface under high-temperature conditions, and the terahertz simulation detection data were obtained. Principal component analysis (PCA) was used to reduce the dimensionality of the original experimental and simulation data, and a support vector machine (SVM) model integrating PCA and bacterial foraging optimization (BFO) algorithm was constructed. The research results show that the integrated model exhibits excellent performance in predicting the thickness of CMAS, with a correlation coefficient of 0.95, and the mean absolute error (MAE) and root mean square error (RMSE) are 0.13 μm and 0.46 μm, respectively. This study provides a new high-precision method for non-destructive detection of the thickness of CMAS on the surface of thermal barrier coatings, which has certain engineering application value for ensuring the service performance of thermal barrier coatings under harsh service conditions. Although the current method is based on simulated and experimental data under controlled conditions, it has the potential to be developed into an in situ monitoring strategy in the future, enabling real-time assessment of CMAS thickness on the coating surface during engine operation. Full article

Hydraulic engineering structures can threaten freshwater fish by entraining them into hazardous areas. Acoustic barriers have been proposed as a non-physical method to guide fish away from these zones. In this study, we investigated the behavioral responses of juvenile grass carp to different acoustic stimuli under semi-natural conditions using outdoor net cages. Four sound types were tested: a 1000 Hz pure tone and three broadband sounds, including Alligator sinensis hissing, pile-driving noise, and outboard motor noise. Behavioral responses were quantified using response frequency, total midline crossings, first-response time, maximum swimming speed, and average swimming speed. The results showed that Alligator sinensis hissing elicited the highest number of midline crossings, representing the strongest behavioral response among all tested sounds. In addition, both Alligator sinensis hissing and outboard motor noise induced significantly stronger avoidance responses than the pure tone or pile-driving noise, as indicated by higher response frequency and faster swimming speeds. Furthermore, manipulation of pulse repetition intervals in the most effective deterrent sounds generated a novel broadband sound, which altered fish distribution patterns and elicited avoidance behavior. These findings indicate that both sound type and temporal structure influence negative phonotaxis behavior in grass carp and provide experimental evidence for the optimization of acoustic barriers in fish management. Full article

Noise in industrial buildings affects workers’ productivity and can seriously impair their physical and mental health, yet existing studies often overlook workers’ subjective perceptions and rely on a single method. Therefore, this study recruited 263 workers from four industrial buildings in Beijing and adopted a mixed-methods approach. First, 30 semi-structured interviews were analyzed using grounded theory’s three-level coding procedure to construct a conceptual framework of a healthy acoustic environment and its influencing factors. Next, a 30-item subjective questionnaire was developed, and structural equation modeling was conducted on 256 valid responses. Finally, Spearman correlation analysis and multidimensional scaling were used to examine relationships between subjective evaluations and eight physical and psychoacoustic indicators. The results identified nine major dimensions, including Sound Source Localization, Physiological Effects at Work, and Regulatory Control, as well as 15 relational pathways. Compared with existing frameworks, Communication Barrier emerged as a more prominent dimension in industrial building contexts. Structural equation modeling confirmed that 12 pathways were statistically significant. Correlation analysis further showed that only a few objective–subjective associations were significant, indicating that objective acoustic indicators alone cannot explain workers’ multidimensional perceptions. In conclusion, this study developed an evaluation model for healthy acoustic environments in industrial buildings, highlighting the need to emphasize controllability, communication support, and integrated subjective–objective evaluation in acoustic design to better enhance workers’ well-being. Full article

Environmental noise is increasingly recognized as a major environmental and public health challenge, with road traffic identified as the dominant source of acoustic pollution across Europe. In this context, noise mitigation is directly linked to sustainable development goals related to human health and urban sustainability. Noise barriers are among the most widely implemented mitigation strategies; however, their spatial distribution and adequacy remain poorly documented, limiting their effectiveness for sustainable territorial planning. This study develops the first georeferenced database of highway noise barriers in Andalusia (Spain) and applies a reproducible, transdisciplinary geospatial workflow integrating field surveys, remote-sensing tools, and Geographic Information Systems (GIS). A total of 110 barriers were mapped, classified by material, geometry, and surrounding land use, and analyzed in relation to sensitive receptors, including dwellings, schools, and hospitals. Results show that only 1.6% of the Andalusian highway network is currently protected by noise barriers, with strong territorial disparities: over 50% of all structures are concentrated along coastal metropolitan corridors, while extensive inland areas remain unprotected. Misalignments were also detected between barrier placement and officially reported high-exposure segments, indicating limited correspondence between infrastructural deployment and planning-designated priority areas. Beyond generating a comprehensive regional dataset, the proposed methodology provides a scalable basis for national and European initiatives seeking to harmonize the mapping and assessment of noise-mitigation infrastructures. By offering an open-access, transferable framework, this work contributes to a more equitable distribution of environmental protection measures and supports policy professionals, environmental managers, and planners in advancing healthier and more sustainable urban and transport systems. Full article

Drone noise-induced human annoyance is emerging as one of the main barriers to socially acceptable large-scale urban air mobility (UAM) operations, which have the potential to revolutionize urban transportation systems in the next few decades. This paper investigates the state-of-the-art technology in the assessment of drone noise and its impact on individuals, focusing on measurement and evaluation methodologies, as well as subjective evaluations. Various acoustic metrics are reviewed to characterize drone noise, including sound pressure levels, spectral analysis, and psychoacoustic parameters such as loudness and annoyance. Preliminary experimental investigations to identify key frequencies and tonal components that significantly contribute to drone noise-induced public annoyance are also discussed. Interdisciplinary approaches integrating pure technical acoustics, human perception, and subjectivity emerge as promising solutions for a comprehensive understanding of drone noise effects. Finally, a preliminary framework for drone noise assessment towards noise-aware UAM operations is proposed. Full article

This article presents a systematic survey of six prominent quantum computing applications in finance, unified under the paradigm of optimization as the foundational use case from which derivative applications are constructed. We formalize the transition from the classical Markowitz portfolio optimization framework to a quantum implementation via the Quantum Approximate Optimization Algorithm (QAOA), including explicit mathematical derivations, theoretical performance bounds, and convergence guarantees. Beyond algorithmic formalism, we critically assess prevailing hardware limitations, focusing on noise thresholds and coherence constraints that currently preclude a demonstrable quantum advantage over classical counterparts. Furthermore, we address the underexplored institutional prerequisites for financial deployment, including regulatory compliance, model validation protocols, and structural barriers to adoption. We conclude that despite ongoing hardware maturation, proactive engagement with quantum algorithm development is imperative for financial institutions to preempt technological obsolescence upon the achievement of hardware parity. Full article

Unmanned aerial vehicles (UAVs) have become indispensable tools in precision agriculture and plant phenotyping, enabling the rapid, non-destructive assessment of crop traits across space and time. Equipped with RGB, multispectral, thermal, and other sensors, UAVs provide detailed information on canopy structure, physiology, and stress responses that can guide management decisions and accelerate breeding programs. Despite these advances, the downstream processing of UAV imagery remains technically demanding. Converting orthomosaics into standardized, biologically meaningful data often requires a combination of photogrammetry, geospatial analysis, and custom scripting, which can limit reproducibility and accessibility across research groups. We present drone2report, an open-source python-based software that processes orthomosaics from UAV flights to generate vegetation indices, summary statistics, derived subimages, and text (html) reports, supporting both research and applied crop breeding needs. Alongside the basic structure and functioning of drone2report, we also present five case studies that illustrate practical applications common in UAV-/drone-phenotyping of plants: (i) thresholding to remove background noise and highlight regions of interest; (ii) monitoring plant phenotypes over time; (iii) extracting information on plant height to detect events like lodging or the falling over of spikes; (iv) integrating multiple sensors (cameras) to construct and optimize new synthetic indices; (v) integrate a trained deep learning network to implement a classification task. These examples demonstrate the tool’s ability to automate analysis, integrate heterogeneous data and models, and support reproducible computation of agronomically relevant traits. drone2report streamlines orthorectified UAV-image processing for precision agriculture by linking orthomosaics to standardized, plot-level outputs. Its modular, configuration-driven design allows transparent workflows, easy customization, and integration of multiple sensors within a unified analytical framework. By facilitating reproducible, multi-modal image analysis, drone2report lowers technical barriers to UAV-based phenotyping and opens the way to robust, data-driven crop monitoring and breeding applications. Full article

Background/Objectives: Non-sedate magnetic resonance imaging (MRI) can be challenging for young children with neuromotor disabilities, often resulting in motion-degraded images that complicate interpretation in the context of underlying neuropathology. This study aimed to characterize tolerance factors and barriers related to awake MRI of the pediatric brain and to examine additional considerations in analyzing structural scans affected by motion and pathology. Methods: 10 children (mean age 5y9m; 5 girls; GMFCS level IV) with cerebral palsy (CP) underwent non-sedate 3T MRI of the brain. Tolerance factors and challenges were documented. MRI quality and automated structural preprocessing with Freesurfer (FS) v.8.0 were reviewed by a pediatric neuroradiologist and neurologist. To assess the impact of motion, automated basal ganglia segmentation was compared with manual segmentation. Segmentation accuracy was characterized using Dice Coefficient (D). Results: Five participants (50%) tolerated non-sedate structural MRI, although two of them were unable to remain still. Factors affecting MRI tolerance included sensitivity to scanner noise (n = 4), hyperkinetic movement (n = 2), difficulty with positioning/padding (n = 4), fear of clinical environment (n = 2) or confined scanner interior (n = 2), and earbud discomfort (n = 3). Automated structural preprocessing with FS yielded discrepancies in gray-white matter boundaries in motion-degraded scans, necessitating manual correction. Automated segmentation of motion-compromised scans closely agreed with manual delineation of the caudate (D ≥ 0.85) and putamen (D ≥ 0.78), while the pallidum was least reproducible (D = 0.58). Conclusions: Tailored acquisition and processing strategies are necessary to support non-sedate MRI in children with CP, preserve downstream neuroimaging analyses, and promote inclusion of underrepresented populations in research. Full article

The global push for sustainable energy has elevated wind power as a key renewable source; however, turbine noise remains a critical barrier to deployment near populated areas. This study investigates the optimization of symmetric and asymmetric trailing-edge profiles to minimize aeroacoustic emissions. The primary novelty lies in the comparative analysis of a novel Pressure-Side Intruding Divergent model against standard sinusoidal serrations. Employing finite volume analysis in ANSYS, the preliminary results revealed that these targeted modifications significantly reduced noise propagation by 51.1% to 75.4%. By altering vortex shedding patterns and turbulent boundary-layer interactions, these findings provide actionable guidelines for balancing aerodynamic efficiency with environmental noise standards. Full article

Urban freight transport generates significant negative externalities in the form of noise, congestion, and environmental impacts. Freight consolidation centres could be seen as a potential solution, offering benefits such as shorter delivery distances and fewer delivery routes. However, implementation of freight consolidation centers requires collaboration between actors with conflicting interests and goals. This study proposes a collaborative business model framework for freight consolidation centres. The novelty of the study lies in conceptualising collaboration as an outcome-based partnership and extending the Business Model Canvas with collaboration-specific components. This framework was empirically tested and refined through a pilot project in Gothenburg, applying the principles of engaged scholarship. The results indicate that last-mile consolidation can significantly improve operational efficiency and enable sustainability gains. At the same time, structural, economic, and organisational barriers need to be addressed to realise all benefits of the collaborative business model. The findings particularly highlight the need for deeper institutionalisation of collaborative practices, including the integration of new norms, procedures, and policies into the business models of the individual actors involved. Full article

Traditional vision-based vibration measurement is fundamentally constrained by the low sampling rates of area-scan cameras and the noise sensitivity of existing motion magnification algorithms. To overcome these spatiotemporal barriers, we propose a high-fidelity framework that integrates ultra-high-speed line-scan imaging with a 1D Complex Morlet Wavelet Phase-Based Video Magnification (CMW-PVM) algorithm. By extracting and manipulating the localized phase of 1D spatial signals, CMW-PVM effectively decouples structural dynamics from background noise while eliminating the computational redundancy associated with 2D spatial pyramid methods. Simulations demonstrate that CMW-PVM significantly extends the linear magnification range (up to $\alpha \approx 35$) while preserving exceptional structural fidelity (FSIM $>0.87$) under severe noise conditions (SNR = 10 dB). Experimental validation against a laser Doppler vibrometer (LDV) reveals near-perfect kinematic accuracy, with a relative amplitude error of only 1.65%. Furthermore, at a 100 Hz high-frequency excitation, the system successfully resolves microscopic displacements (≈10 μm) without temporal aliasing—enabled not by violating sampling theory but by leveraging the high physical line rate of the line-scan sensor. This establishes a robust, non-contact, and computationally efficient paradigm for broadband, micro-amplitude vibration monitoring in industrial environments. Full article

The rapid evolution of the Open Radio Access Network (O-RAN) architecture and the exponential growth in specification complexity create significant barriers for researchers translating 5G standards into practical implementations. Existing evaluation frameworks for large language models, such as ORAN-Bench-13K, focus predominantly on the theoretical comprehension of regulatory documents while neglecting the critical aspect of software execution. This disparity results in a profound semantic gap, defined here as the structural and conceptual misalignment between abstract normative requirements and their concrete realization in the source code of open platforms like srsRAN. To bridge this divide and enable advanced cognitive reasoning, this paper presents a Hybrid Retrieval-Augmented Generation (RAG) framework designed to unify two heterogeneous knowledge domains: the O-RAN/3GPP specification corpus and the srsRAN C++ codebase. The proposed architecture leverages a hierarchical Parent–Child Chunking strategy to preserve the structural integrity of complex code and normative protocols. Additionally, it introduces a probabilistic Semantic Query Routing mechanism that dynamically selects the relevant context domain based on query intent. This routing actively mitigates semantic interference—a phenomenon where merging conflicting cross-domain terminology introduces informational noise, which our baseline tests showed degrades response accuracy by 4.7%. Empirical evaluation demonstrates that the hybrid approach successfully overcomes this, achieving an overall accuracy of 76.70% and outperforming the standard RAG baseline of 72.00%. Furthermore, system performance analysis reveals that effective context filtering reduces the average response generation latency to 3.47 s, compared to 3.73 s for traditional RAG methods, rendering the framework highly suitable for real-time telecommunications engineering tasks. Full article