Search Results (1,164)

Automated surface defect detection in steel manufacturing is pivotal for ensuring product quality, yet it remains an open challenge owing to the extreme heterogeneity of defect morphologies—ranging from hairline cracks and microscopic pores to elongated scratches and shallow dents. Existing approaches, whether classical vision pipelines or recent deep-learning paradigms, struggle to simultaneously satisfy the stringent demands of industrial scenarios: high accuracy on sub-millimeter flaws, insensitivity to texture-rich backgrounds, and real-time throughput on resource-constrained hardware. Although contemporary detectors have narrowed the gap, they still exhibit pronounced sensitivity–robustness trade-offs, particularly in the presence of scale-varying defects and cluttered surfaces. To address these limitations, we introduce MBY (MBDNet-Attention-YOLO), a lightweight yet powerful framework that synergistically couples the MBDNet backbone with the YOLO detection head. Specifically, the backbone embeds three novel components: (1) HGStem, a hierarchical stem block that enriches low-level representations while suppressing redundant activations; (2) Dynamic Align Fusion (DAF), an adaptive cross-scale fusion mechanism that dynamically re-weights feature contributions according to defect saliency; and (3) C2f-DWR, a depth-wise residual variant that progressively expands receptive fields without incurring prohibitive computational costs. Building upon this enriched feature hierarchy, the neck employs our proposed MultiSEAM module—a cascaded squeeze-and-excitation attention mechanism operating at multiple granularities—to harmonize fine-grained and semantic cues, thereby amplifying weak defect signals against complex textures. Finally, we integrate the Inner-SIoU loss, which refines the geometric alignment between predicted and ground-truth boxes by jointly optimizing center distance, aspect ratio consistency, and IoU overlap, leading to faster convergence and tighter localization. Extensive experiments on two publicly available steel-defect benchmarks—NEU-DET and PVEL-AD—demonstrate the superiority of MBY. Without bells and whistles, our model achieves 85.8% mAP@0.5 on NEU-DET and 75.9% mAP@0.5 on PVEL-AD, surpassing the best-reported results by significant margins while maintaining real-time inference on an NVIDIA Jetson Xavier. Ablation studies corroborate the complementary roles of each component, underscoring MBY’s robustness across defect scales and surface conditions. These results suggest that MBY strikes an appealing balance between accuracy, efficiency, and deployability, offering a pragmatic solution for next-generation industrial quality-control systems. Full article

To improve the efficiency and stability of the system, this paper proposes a monolithic integrated optical path design for a cavity optomechanical accelerometer based on a 250 nm top silicon thickness silicon-on-insulator (SOI) wafer instead of readout through U-shape fiber coupling. Finite Element Analysis (FEA) and Finite-Difference Time-Domain (FDTD) methods are employed to systematically investigate the performance of key optical structures, including the resonant modes and bandgap characteristics of photonic crystal (PhC) microcavities, transmission loss of strip waveguides, coupling efficiency of tapered-lensed fiber-to-waveguide end-faces, coupling characteristics between strip waveguides and PhC waveguides, and the coupling mechanism between PhC waveguides and microcavities. Simulation results demonstrate that the designed PhC microcavity achieves a quality factor (Q-factor) of 2.26 × 10⁵ at a 1550 nm wavelength while the optimized strip waveguide exhibits a low loss of merely 0.2 dB over a 5000 μm transmission length. The strip waveguide to PhC waveguide coupling achieves 92% transmittance at the resonant frequency, corresponding to a loss below 0.4 dB. The optimized edge coupling structure exhibits a transmittance of 75.8% (loss < 1.2 dB), with a 30 μm coupling length scheme (60% transmittance, ~2.2 dB loss) ultimately selected based on process feasibility trade-offs. The total optical path system loss (input to output) is 5.4 dB. The paper confirms that the PhC waveguide–microcavity evanescent coupling method can effectively excite the target cavity mode, ensuring optomechanical coupling efficiency for the accelerometer. This research provides theoretical foundations and design guidelines for the fabrication of high-precision monolithic integrated cavity optomechanical accelerometers. Full article

Objectives: This study investigates whether scan time in the high-resolution magnetic resonance imaging (MRI) of human embryos can be reduced without compromising spatial resolution by applying zero-shot self-supervised learning (ZS-SSL), a deep-learning-based reconstruction method. Methods: Simulations using a numerical phantom were conducted to evaluate spatial resolution across various acceleration factors (AF = 2, 4, 6, and 8) and signal-to-noise ratio (SNR) levels. Resolution was quantified using a blur-based estimation method based on the Sparrow criterion. ZS-SSL was compared to conventional compressed sensing (CS). Experimental imaging of a human embryo at Carnegie stage 21 was performed at a spatial resolution of (30 μm)³ using both retrospective and prospective undersampling at AF = 4 and 8. Results: ZS-SSL preserved spatial resolution more effectively than CS at low SNRs. At AF = 4, image quality was comparable to that of fully sampled data, while noticeable degradation occurred at AF = 8. Experimental validation confirmed these findings, with clear visualization of anatomical structures—such as the accessory nerve—at AF = 4; there was reduced structural clarity at AF = 8. Conclusions: ZS-SSL enables significant scan time reduction in high-resolution MRI of human embryos while maintaining spatial resolution at AF = 4, assuming an SNR above approximately 15. This trade-off between acceleration and image quality is particularly beneficial in studies with limited imaging time or specimen availability. The method facilitates the efficient acquisition of ultra-high-resolution data and supports future efforts to construct detailed developmental atlases. Full article

Situated in the southern hilly-mountain belt of China’s “Three Zones and Four Belts Strategy”, Gannan region is a critical ecological shelter belt for the Ganjiang River. Decades of intensive mineral extraction and irrational agricultural development have rendered it into an ecologically fragile area. Consequently, multiple restoration initiatives have been implemented in the region over recent decades. However, it remains unclear how relationships among ecosystem services have evolved under these interventions and how future ecosystem management should be optimized based on these changes. Thus, in this study, we simulated and assessed the spatiotemporal dynamics of five key ESs in Gannan region from 1990 to 2020. Through integrated correlation, clustering, and redundancy analyses, we quantified ES interactions, tracked the evolution of ecosystem service bundles (ESBs), and identified their socio-ecological drivers. Despite a 31% decline in water yield, ecological restoration initiatives drove substantial improvements in key regulating services: carbon storage increased by 6.9 × 10¹² gC while soil conservation rose by 4.8 × 10⁸ t. Concurrently, regional habitat quality surged by 45% in mean scores, and food production increased by 2.1 × 10⁵ t. Critically, synergistic relationships between habitat quality, soil retention, and carbon storage were progressively strengthened, whereas trade-offs between food production and habitat quality intensified. Further analysis revealed that four distinct ESBs—the Agricultural Production Bundle (APB), Urban Development Bundle (UDB), Eco-Agriculture Transition Bundle (ETB), and Ecological Protection Bundle (EPB)—were shaped by slope, forest cover ratio, population density, and GDP. Notably, 38% of the ETB transformed into the EPB, with frequent spatial interactions observed between the APB and UDB. These findings underscore that future ecological restoration and conservation efforts should implement coordinated, multi-service management mechanisms. Full article

Many commercial wearable sensor systems typically rely on a single continuous cardiorespiratory sensing modality, photoplethysmography (PPG), which suffers from inherent biases (i.e., differences in skin tone) and noise (e.g., motion and pressure artifacts). In this research, we present a wearable device that provides robust estimates of cardiorespiratory variables by combining three physiological signals from the upper arm: multiwavelength PPG, single-sided electrocardiography (SS-ECG), and bioimpedance plethysmography (BioZ), along with an inertial measurement unit (IMU) providing 3-axis accelerometry and gyroscope information. We evaluated the multimodal device on 16 subjects by its ability to estimate heart rate (HR) and breathing rate (BR) in the presence of various static and dynamic noise sources (e.g., skin tone and motion). We proposed a hierarchical approach that considers the subject’s skin tone and signal quality to select the optimal sensing modality for estimating HR and BR. Our results indicate that, when estimating HR, there is a trade-off between accuracy and robustness, with SS-ECG providing the highest accuracy (low mean absolute error; MAE) but low reliability (higher rates of sensor failure), and PPG/BioZ having lower accuracy but higher reliability. When estimating BR, we find that fusing estimates from multiple modalities via ensemble bagged tree regression outperforms single-modality estimates. These results indicate that multimodal approaches to cardiorespiratory monitoring can overcome the accuracy–robustness trade-off that occurs when using single-modality approaches. Full article

Against the backdrop of rapid urbanization in western China, which has triggered remarkable land-use changes and habitat degradation, Chengdu, as a developed city in China, plays a demonstrative and leading role in the economic and social development of China during the transition period. Therefore, integrated modeling approaches are required to balance development and conservation. This study responds to this need by conducting a scenario-based assessment of urbanization-induced land-use changes and regional habitat quality dynamics in Chengdu (1990–2030), using the FLUS-InVEST model. By integrating remote sensing-derived land-use data from 1990, 1995, 2000, 2005, 2010, 2015, and 2020, we simulate future regional habitat quality under three policy scenarios: natural development, ecological priority, and cropland protection. Key findings include the following: (1) From 1990 to 2020, cropland decreased by 1917.78 km², while forestland and built-up areas increased by 509.91 km² and 1436.52 km², respectively. Under the 2030 natural development scenario, built-up expansion and cropland reduction are projected. Ecological priority policies would enhance forestland (+4.2%) but slightly reduce cropland. (2) Regional habitat quality declined overall (1990–2020), with the sharpest drop (ΔHQ = −0.063) occurring between 2000 and 2010 due to accelerated urbanization. (3) Scenario analysis reveals that the ecological priority strategy yields the highest regional habitat quality (HQ_mean = 0.499), while natural development results in the lowest (HQ_mean = 0.444). This study demonstrates how the FLUS-InVEST model can quantify the trade-offs between urbanization and regional habitat quality, offering a scientific framework for balancing development and ecological conservation in rapidly urbanizing regions. The findings highlight the effectiveness of ecological priority policies in mitigating habitat degradation, with implications for similar cities seeking sustainable land-use strategies that integrate farmland protection and forest restoration. Full article

Tocopherols, major lipid-soluble components of vitamin E, are essential natural products with significant nutritional and pharmacological value. Their structural diversity and uneven distribution across vegetable oils require accurate analytical strategies for compositional profiling, quality control, and authenticity verification, amid concerns over food fraud and regulatory demands. Analytical challenges, such as matrix effects in complex oils and the cost trade-offs of green extraction methods, complicate these processes. This review examines recent advances in tocopherol analysis, focusing on extraction and detection techniques. Green methods like supercritical fluid extraction and deep eutectic solvents offer selectivity and sustainability, though they are costlier than traditional approaches. On the analytical side, hyphenated techniques such as supercritical fluid chromatography-mass spectrometry (SFC-MS) achieve detection limits as low as 0.05 ng/mL, improving sensitivity in complex matrices. Liquid chromatography-tandem mass spectrometry (LC-MS/MS) provides robust analysis, while spectroscopic and electrochemical sensors offer rapid, cost-effective alternatives for high-throughput screening. The integration of chemometric tools and miniaturized systems supports scalable workflows. Looking ahead, the incorporation of Artificial Intelligence (AI) in oil authentication has the potential to enhance the accuracy and efficiency of future analyses. These innovations could improve our understanding of tocopherol compositions in vegetable oils, supporting more reliable assessments of nutritional value and product authenticity. Full article

This paper presents a novel approach employing localized annealing through Joule heating to enhance the performance of Thin-Film Piezoelectric-on-Silicon (TPoS) MEMS resonators that are crucial for applications in sensing, energy harvesting, frequency filtering, and timing control. Despite recent advancements, piezoelectric MEMS resonators still suffer from anchor-related energy losses and limited quality factors (Qs), posing significant challenges for high-performance applications. This study investigates interface modification to boost the quality factor (Q) and reduce the motional resistance, thus improving the electromechanical coupling coefficient and reducing insertion loss. To balance the trade-off between device miniaturization and performance, this work uniquely applies DC current-induced localized annealing to TPoS MEMS resonators, facilitating metal diffusion at the interface. This process results in the formation of platinum silicide, modifying the resonator’s stiffness and density, consequently enhancing the acoustic velocity and mitigating the side-supporting anchor-related energy dissipations. Experimental results demonstrate a Q-factor enhancement of over 300% (from 916 to 3632) and a reduction in insertion loss by more than 14 dB, underscoring the efficacy of this method for reducing anchor-related dissipations due to the highest annealing temperature at the anchors. The findings not only confirm the feasibility of Joule heating for interface modifications in MEMS resonators but also set a foundation for advancements of this post-fabrication thermal treatment technology. Full article

Urban agriculture (UA) is emerging as a promising strategy for sustainable food production in response to growing environmental pressures. Indoor vertical farming (IVF), combining Controlled Environment Agriculture (CEA) with Building-Integrated Agriculture (BIA), enables efficient resource use and year-round crop cultivation in urban settings. This study assesses the environmental performance of a prospective IVF system located on a university campus in Portugal, focusing on the integration of photovoltaic (PV) energy as an alternative to the conventional electricity grid (GM). A Life Cycle Assessment (LCA) was conducted using the Environmental Footprint (EF) method and the LANCA model to account for land use and soil-related impacts. The PV-powered system demonstrated lower overall environmental impacts, with notable reductions across most impact categories, but important trade-offs with decreased soil quality. The LANCA results highlighted cultivation and packaging as key contributors to land occupation and transformation, while also revealing trade-offs associated with upstream material demands. By combining EF and LANCA, the study shows that IVF systems that are not soil-based can still impact soil quality indirectly. These findings contribute to a broader understanding of sustainability in urban farming and underscore the importance of multi-dimensional assessment approaches when evaluating emerging agricultural technologies. Full article

Traffic crashes and congestion generate high social and economic costs, yet traditional traffic monitoring methods, such as police patrols, fixed cameras, and helicopters, are costly, labor-intensive, and limited in spatial coverage. This paper presents a novel Drone Routing and Scheduling with Flexible Multiple Visits (DRSFMV) framework, an optimization model for planning drone-based highway monitoring under realistic operational constraints, including battery limits, variable monitoring durations, recharging at a depot, and target-specific inter-visit time limits. A mixed-integer nonlinear programming (MINLP) model and a linearized version (MILP) are presented to solve the problem. Due to the NP-hard nature of the underlying problem structure, a heuristic solver, Hexaly, is also used. A case study using real traffic census data from three Southern California counties tests the models across various network sizes and configurations. The MILP solves small and medium instances efficiently, and Hexaly produces high-quality solutions for large-scale networks. Results show clear trade-offs between drone availability and time-slot flexibility, and demonstrate that stricter revisit constraints raise operational cost. Full article

In the process of CNC machining, reducing energy consumption, production costs, and improving machining quality are critical strategies for enhancing product competitiveness. Based on an analysis of machine tool processing mechanisms, calculation models for energy consumption, manufacturing cost, and quality (represented by surface roughness) in CNC lathes were established. These models were optimized using the Egret Swarm Optimization Algorithm (ESOA), which integrates three core strategies: waiting, random search, and bounding mechanisms. With the objectives of minimizing energy consumption, manufacturing cost, and maximizing quality, cutting parameters (e.g., cutting speed, feed rate, and depth of cut) were selected as optimization variables. A multi-objective ESOA (MOESOA) framework was applied to resolve trade-offs among conflicting objectives, and the effectiveness of the proposed method was validated through a case study. The simulation results show that the optimization of cutting parameters is beneficial to energy conservation during the machining process, although it may increase costs. Additionally, under the three-objective optimization, the improvement of surface roughness is relatively limited. The further two-objective (energy consumption and cost) optimization model demonstrates better convergence while ensuring that the surface roughness meets the basic requirements. This method provides an effective tool for optimizing cutting parameters. Full article

Recent advances in precision manufacturing and high-end equipment technologies have imposed ever more stringent requirements on the accuracy, real-time performance, and lightweight design of online steel strip surface defect detection systems. To reconcile the persistent trade-off between detection precision and inference efficiency in complex industrial environments, this study proposes StripSurface–YOLO, a novel real-time defect detection framework built upon YOLOv8n. The core architecture integrates an Efficient Cross-Stage Local Perception module (ResGSCSP), which synergistically combines GSConv lightweight convolutions with a one-shot aggregation strategy, thereby markedly reducing both model parameters and computational complexity. To further enhance multi-scale feature representation, this study introduces an Efficient Multi-Scale Attention (EMA) mechanism at the feature-fusion stage, enabling the network to more effectively attend to critical defect regions. Moreover, conventional nearest-neighbor upsampling is replaced by DySample, which produces deeper, high-resolution feature maps enriched with semantic content, improving both inference speed and fusion quality. To heighten sensitivity to small-scale and low-contrast defects, the model adopts Focal Loss, dynamically adjusting to sample difficulty. Extensive evaluations on the NEU-DET dataset demonstrate that StripSurface–YOLO reduces FLOPs by 11.6% and parameter count by 7.4% relative to the baseline YOLOv8n, while achieving respective improvements of 1.4%, 3.1%, 4.1%, and 3.0% in precision, recall, mAP₅₀, and mAP_50:95. Under adverse conditions—including contrast variations, brightness fluctuations, and Gaussian noise—SteelSurface-YOLO outperforms the baseline model, delivering improvements of 5.0% in mAP₅₀ and 4.7% in mAP_50:95, attesting to the model’s robust interference resistance. These findings underscore the potential of StripSurface–YOLO to meet the rigorous performance demands of real-time surface defect detection in the metal forging industry. Full article

Generative AI (genAI) has emerged as a powerful tool for synthesizing diverse and complex image data, offering new possibilities for scientific imaging applications. This review presents a comprehensive comparative analysis of leading generative architectures, ranging from Variational Autoencoders (VAEs) to Generative Adversarial Networks (GANs) on through to Diffusion Models, in the context of scientific image synthesis. We examine each model’s foundational principles, recent architectural advancements, and practical trade-offs. Our evaluation, conducted on domain-specific datasets including microCT scans of rocks and composite fibers, as well as high-resolution images of plant roots, integrates both quantitative metrics (SSIM, LPIPS, FID, CLIPScore) and expert-driven qualitative assessments. Results show that GANs, particularly StyleGAN, produce images with high perceptual quality and structural coherence. Diffusion-based models for inpainting and image variation, such as DALL-E 2, delivered high realism and semantic alignment but generally struggled in balancing visual fidelity with scientific accuracy. Importantly, our findings reveal limitations of standard quantitative metrics in capturing scientific relevance, underscoring the need for domain-expert validation. We conclude by discussing key challenges such as model interpretability, computational cost, and verification protocols, and discuss future directions where generative AI can drive innovation in data augmentation, simulation, and hypothesis generation in scientific research. Full article

Deep learning-based super-resolution (SR) frameworks are widely used in remote sensing applications. However, existing SR models still face limitations, particularly in recovering contours, fine features, and textures, as well as in effectively integrating channel information. To address these challenges, this study introduces a novel residual model named OARN (Optimized Attention Residual Network) specifically designed to enhance the visual quality of low-resolution images. The network operates on the Y channel of the YCbCr color space and integrates LKA (Large Kernel Attention) and OCM (Optimized Convolutional Module) blocks. These components can restore large-scale spatial relationships and refine textures and contours, improving feature reconstruction without significantly increasing computational complexity. The performance of OARN was evaluated using satellite images from WorldView-2, GaoFen-2, and Microsoft Virtual Earth. Evaluation was conducted using objective quality metrics, such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Edge Preservation Index (EPI), and Perceptual Image Patch Similarity (LPIPS), demonstrating superior results compared to state-of-the-art methods in both objective measurements and subjective visual perception. Moreover, OARN achieves this performance while maintaining computational efficiency, offering a balanced trade-off between processing time and reconstruction quality. Full article

The growing mismatch between ecosystem service (ES) supply and demand underscores the importance of thoroughly understanding their spatiotemporal patterns and key drivers to promote ecological civilization and sustainable development at the regional level in China. This study investigates six key ES indicators across mainland China—habitat quality (HQ), carbon sequestration (CS), water yield (WY), sediment delivery ratio (SDR), food production (FP), and nutrient delivery ratio (NDR)—by integrating a suite of analytical approaches. These include a spatiotemporal analysis of trade-offs and synergies in supply, demand, and their ratios; self-organizing maps (SOM) for bundle identification; and interpretable machine learning models. While prior research studies have typically examined ES at a single spatial scale, focusing on supply-side bundles or associated drivers, they have often overlooked demand dynamics and cross-scale interactions. In contrast, this study integrates SOM and SHAP-based machine learning into a dual-scale framework (grid and city levels), enabling more precise identification of scale-dependent drivers and a deeper understanding of the complex interrelationships between ES supply, demand, and their spatial mismatches. The results reveal pronounced spatiotemporal heterogeneity in ES supply and demand at both grid and city scales. Overall, the supply services display a spatial pattern of higher values in the east and south, and lower values in the west and north. High-value areas for multiple demand services are concentrated in the densely populated eastern regions. The grid scale better captures spatial clustering, enhancing the detection of trade-offs and synergies. For instance, the correlation between HQ and NDR supply increased from 0.62 (grid scale) to 0.92 (city scale), while the correlation between HQ and SDR demand decreased from −0.03 to −0.58, indicating that upscaling may highlight broader synergistic or conflicting trends missed at finer resolutions. In the spatiotemporal interaction network of supply–demand ratios, CS, WY, FP, and NDR persistently show low values (below −0.5) in western and northern regions, indicating ongoing mismatches and uneven development. Driver analysis demonstrates scale-dependent effects: at the grid scale, HQ and FP are predominantly influenced by socioeconomic factors, SDR and WY by ecological variables, and CS and NDR by climatic conditions. At the city level, socioeconomic drivers dominate most services. Based on these findings, nine distinct supply–demand bundles were identified at both scales. The largest bundle at the grid scale (B3) occupies 29.1% of the study area, while the largest city-scale bundle (B8) covers 26.5%. This study deepens the understanding of trade-offs, synergies, and driving mechanisms of ecosystem services across multiple spatial scales; reveals scale-sensitive patterns of spatial mismatch; and provides scientific support for tiered ecological compensation, integrated regional planning, and sustainable development strategies. Full article