Search Results (1,558)

Deep learning models have achieved high accuracy in forecasting problems, but at the cost of large computational energy demand. Brain-inspired spiking neural networks (SNNs) offer a promising, low-power alternative, yet their adoption for time-series forecasting has been limited by information loss from binary spikes and degraded performance in deeper networks. This paper proposes a fully spiking framework that bridges this gap by improving both the encoding and propagation of information in SNNs. The framework introduces a hybrid Delta-Rate encoding mechanism that captures both abrupt changes and gradual trends in time-series data, and a Mem-Spike mechanism that transmits analog membrane potential values to preserve fine-grained information between spiking layers. We further employ residual membrane connections to maintain signal flow in deep spiking networks. Using two public energy load datasets, our enhanced SNNs consistently outperform conventional spiking models, improving prediction accuracy by up to 61.6% and mitigating degradation in multi-layer networks. Notably, it narrows the gap to the selected deep learning baseline (LSTM), achieving comparable accuracy in some settings while requiring only about 10% of the estimated inference energy of that baseline under a common operation-level model. These results show that, within the empirical scope considered here, enhanced conventional SNNs can improve time-series forecasting accuracy while retaining favorable estimated efficiency. Full article

Citrus trees exhibit severe alternate bearing, resulting in significant annual yield fluctuations and posing substantial challenges to orchard management planning. Accurate citrus bud counting provides an effective solution by supplying essential data for tree-level and orchard-level yield prediction. However, citrus buds are extremely small (5–10 mm in diameter) and are frequently occluded by leaves during the flowering stage, which makes precise detection highly challenging in complex orchard environments. To address these challenges, this paper proposes a Contextual and Frequency-Aware Detector (CFADet) for robust citrus bud detection. Specifically, an Enhanced Feature Fusion (EFF) module is introduced in the neck to refine multi-scale feature aggregation and strengthen information flow for small targets. A Contextual Boundary Enhancement Module (CBEM) is designed to capture surrounding contextual cues and enhance boundary representation through dimensional interaction and max-pooling operations. To suppress background interference, a Frequency-Aware Module (FAM) is developed to adaptively recalibrate frequency components in the amplitude spectrum, thereby enhancing target features while reducing background noise. In addition, Spatial-to-Depth Convolution (SPDConv) is employed to reconstruct the backbone to preserve fine-grained bud features while reducing model parameters. Experimental results show that CFADet achieves 81.1% precision, 80.9% recall, 81.0% F1-score, and 87.8% mAP, with stable real-time performance on mobile devices in practical orchard scenarios. This study presents a preliminary investigation into robust citrus bud detection in real-world orchard environments and provides a promising technical foundation for intelligent orchard monitoring and early yield estimation, while further validation on larger and more diverse datasets is still required. Full article

Quantitative microstructure evaluation of sedimentary rock thin sections is essential for revealing reservoir flow mechanisms and assessing reservoir quality. However, traditional manual identification is inefficient and prone to subjectivity. Although current deep learning approaches have improved efficiency, most remain confined to single tasks and lack a pathway to translate image recognition into quantifiable geological parameters. Moreover, these methods struggle with cross-scale feature extraction and accurate grain boundary localization in complex textures. To overcome these limitations, this study proposes a three-stage automated analysis framework integrating intelligent lithology identification, sandstone grain segmentation, and quantitative analysis of fabric parameters. To address scale discrepancies in lithology discrimination, Rock-PLionNet integrates a Partial-to-Whole Context Fusion (PWC-Fusion) module and the Lion optimizer, which mitigates cross-scale feature inconsistencies and enables accurate screening of target sandstone samples. Subsequently, to correct boundary deviations caused by low contrast and grain adhesion, the PetroSAM-CRF strategy integrates polarization-aware enhancement with dense conditional random field (DenseCRF)-based probabilistic refinement to extract precise grain contours. Based on these outputs, the framework automatically calculates key fabric parameters, including grain size and roundness. Experiments on 3290 original multi-source thin-section images show that Rock-PLionNet achieves a classification accuracy of 96.57% on the test set. Furthermore, PetroSAM-CRF reduces segmentation bias observed in general-purpose models under complex texture conditions, enabling accurate parameter estimation with a roundness error of 2.83%. Overall, this study presents an intelligent workflow linking microscopic image recognition with quantitative analysis of geological fabric parameters, providing a practical pathway for digital petrographic evaluation in hydrocarbon exploration. Full article

Wire and arc additive manufacturing (WAAM) offers high deposition efficiency for large-scale aluminum components; however, layer-by-layer thermal cycling often induces microstructural anisotropy and spatial heterogeneity, which compromise structural reliability. In this study, an ultrasonic-based quantitative framework is proposed to evaluate and optimize anisotropy and heterogeneity in WAAM 2319 aluminum alloy. Nine blocks were fabricated using an orthogonal design with three key process parameters: torch travel speed, arc current, and shielding gas flow rate. Ultrasonic velocity and attenuation were employed to construct anisotropy and heterogeneity indicators. Results show that velocity-based anisotropy remains below 0.53%, indicating nearly isotropic elastic stiffness, whereas attenuation-based anisotropy reaches up to 76%, revealing pronounced direction-dependent microstructural and porosity features. Metallographic analysis confirms that grain morphology variation and interlayer porosity jointly govern attenuation responses. Response surface surrogate models were established to correlate ultrasonic indicators with process parameters, and both single- and multi-objective optimizations were performed within the feasible process window. The proposed framework provides a non-destructive, volumetric approach for microstructure-informed process parameter optimization in WAAM aluminum alloys. Full article

Friction stir welding (FSW) of dissimilar aluminium alloys often results in non-uniform microstructure and hardness distributions due to asymmetric temperature fields and material flow. The objective of this study is to establish a quantitative relationship between thermal history, microstructural evolution, and hardness distribution in dissimilar AA5052-H32/AA6061-T6 FSW joints by combining experimental characterisation with validated thermal modelling. AA5052-H32 and AA6061-T6 plates were welded under five different parameter sets. A thermal finite element model was developed in COMSOL Multiphysics to simulate temperature evolution during welding and was validated using embedded thermocouple measurements, with predicted peak temperatures ranging from 455 °C to 641 °C. Optical microscopy, scanning electron microscopy (SEM), and electron backscatter diffraction (EBSD) were employed to characterise grain structure and dynamic recrystallisation (DRX) behaviour, while Vickers microhardness mapping was used to evaluate the local mechanical response. The results show that DRX occurred in the nugget zone (NZ), leading to significant grain refinement, with a minimum grain diameter of 6.07 µm, representing an approximately eightfold reduction compared with the base material AA5052-H32. In contrast, the thermo-mechanically affected zone (TMAZ) experienced limited recrystallisation due to insufficient plastic deformation and temperature. The lowest hardness was observed in the TMAZ on the AA5052-H32 side, with the hardness reduction of 22% primarily caused by work hardening loss. Hardness was also reduced by 34% on the AA6061-T6 side due to decreased precipitation strengthening caused by high temperatures. This combined experimental–numerical study provides a systematic thermal–microstructure–hardness framework for understanding and predicting local property variations in dissimilar FSW joints. Full article

In this study, kefir production was investigated using both commercial kefir cultures and kefir grains, with milk treated at different UV-C doses and flow rates. The flow rate was set to 25 or 50 mL/min, and doses of 43.2 and 21.6 J/mL were applied at each flow rate, respectively. In all samples subjected to UV-C treatment, pH values decreased during storage, while % titratable acidity values increased. The kefir samples produced with UV-C-irradiated milk showed increased hardness and consistency, while cohesion and the index of viscosity decreased. The highest effect was observed in samples produced with kefir grain and at a flow rate of 50 mL/min. Lactic acid bacteria, Streptococcus/Lactococcus, and yeast counts in kefir samples produced from UV-C-treated milk increased. Flow rate affected the increase in microorganism counts. The physicochemical, textural, and microbiological changes during storage were more pronounced in kefir samples produced with kefir grains than with powdered cultures. The organic acid levels of kefir samples produced from milk treated with UV-C decreased compared to those of control samples. Furthermore, organic acid values increased during storage in all samples. As the flow rate increased, the amount of organic acids formed decreased (except for malic and formic acid levels). Full article

Cross-domain data exchange is an important technical approach for realizing the value of data assets. However, lacking a single trusted root CA across domains, cross-domain schemes often encounter difficulties in authentication, controlled data flow, and fine-grained authorization. We propose a cross-domain data sharing scheme that uses decentralized identifiers and threshold proxy re-encryption. This scheme adopts the intra-domain leader node to verify the user identity, and the inter-domain multi-agent nodes collaborate in a threshold manner to handle cross-domain registration requests and re-encryption requests. Through threshold cooperation, the problem of single point of failure is effectively solved. The hash value of cross-domain registration information is stored on the blockchain, leveraging the immutable and traceable characteristics of blockchain to achieve trusted cross-domain data sharing. In addition, we introduce a ciphertext version tag to enable fast updates of re-encryption keys and use zero-knowledge proofs to verify re-encrypted ciphertext correctness. The security analysis indicates that our scheme has IND-CCA2 security under the DBDH assumption and can effectively resist collusion attacks. Performance analysis shows that our scheme is efficient, and can better meet the needs of cross-domain data sharing. Full article

The performance of the pitcher is the cornerstone of baseball, often determining the flow and ultimate outcome of a game. Given this centrality, understanding the mechanics of an elite pitcher and decoding their strategies are paramount for both internal optimization and competitive scouting. This study proposes an end-to-end deep learning pipeline for automatically classifying five distinct pitch types from raw broadcast footage of MLB pitcher Max Scherzer between 2015 and 2020. By formulating pitch delivery as a time-series classification problem tailored to the unique biomechanics of an elite athlete, the proposed CNN–LSTM framework integrates per-frame spatial feature extraction using an advanced CNN backbone (YOLOv8s-cls) with a two-layer long short-term memory (LSTM) network to capture subtle biomechanical cues across a standardized 20-frame delivery sequence. While skeletal pose estimation primarily focuses on tracking major joints to analyze standard pitching mechanics, the proposed pixel-based method preserves fine-grained visual cues—such as finger grip and wrist rotation—that are critical for distinguishing pitch variations. The proposed framework achieved an accuracy of 91.8% under a standard Random Split and, importantly, 84.5% under a strict Chronological Split across different seasons, validating the feasibility of automated pitch “tell” detection from broadcast video. The resulting system provides coaches and analysts with an objective, data-driven tool for generating personalized scouting reports, identifying mechanical inconsistencies, and refining pitching strategies. Full article

This study establishes a facies-based framework for characterizing reservoir quality in the Upper Pannonian geothermal reservoirs of the Szentes field (Hungary). To evaluate vertical heterogeneity and optimize the selection of geothermal reinjection zones, an integrated core–log–statistical workflow was applied to data from boreholes SZT-1 and SZSZT-IX. The methodology combined petrophysical measurements, petrographic observations, and multivariate statistical analyses, including Hierarchical Cluster Analysis (HCA) and Linear Discriminant Analysis (LDA). The siliciclastic succession was classified into four distinct facies clusters representing a continuum of depositional energy regimes: Rolling, Graded Suspension with Rolling, fine-grained Suspension, and Uniform Suspension. The results demonstrate a dual control on reservoir quality: the primary pore framework is determined by depositional grain-size architecture and sediment transport processes, while mechanical compaction and diagenetic alteration subsequently modify pore connectivity and flow efficiency. Among the identified facies, deposits formed from Graded Suspension with Rolling represent the most favorable reservoir units, combining high porosity (up to 33%) with exceptionally high permeability (>1500 mD). In contrast, suspension-dominated facies deposited from Graded and Uniform Suspension exhibit significantly reduced permeability due to higher matrix content, cementation, and compaction. The results demonstrate that reservoir performance in the Szentes geothermal system is primarily controlled by facies-scale heterogeneity rather than by depth-based stratigraphic divisions alone. This integrated facies-based approach provides a predictive framework for extrapolating reservoir properties to uncored intervals and offers practical guidance for optimizing reinjection strategies and sustainable geothermal reservoir management. Full article

To address the issues of high impurity rates and grain loss during the wheat cleaning process, a coupled Computational Fluid Dynamics (CFD) and Discrete Element Method (DEM) approach was employed to investigate the internal airflow field and the fluid–solid coupling process of the wheat cleaning device. The numerical simulation of the three-dimensional internal flow field is carried out in the high-Reynolds-number turbulent region, and the transient double precision solver based on the pressure–velocity coupling algorithm is used. The effects of the air inlet velocity and angle on the airflow field distribution and air separation efficiency were analyzed through CFD simulation. Based on this, the structure of the cleaning device was optimized, and the movement characteristics of materials under various wind forces were compared through CFD-DEM coupling simulation. The results showed that the optimal air separation parameters were an air inlet velocity of 10 m/s and an air inlet angle of 20 degrees. Under these conditions, the airflow distribution in the air separation box was uniform, and the impurity separation efficiency reached the highest level. After optimizing the equipment by installing a high-pressure fan, the number of impurities in the wheat collection box under windy conditions was 265, a reduction of 53.8% compared to 573 under windless conditions. Finally, through repeated experiments on the entire machine, it was verified that the impurity rate of the optimized device was 1.722% and the loss rate was 0.622%, which were 0.23% and 0.12% lower than those of the existing equipment, respectively, consistent with the simulation results. This study provides theoretical basis and technical support for the optimization design of wheat cleaning equipment. Full article

High-velocity fluid flow in porous media frequently exhibits non-Darcy behavior, where inertial losses lead to nonlinear pressure gradient velocity behavior. Predicting the Forchheimer coefficient β remains challenging because β varies sensitively with pore geometry and is often not constrained by porosity and permeability alone. This study develops a structure-based method to estimate β using intrinsic descriptors obtained from the Darcy regime flow characterization and image-based geometry analysis. A set of two-dimensional granular porous media was generated with controlled variations in porosity, particle size distribution, and grain size variability. Single phase simulations are simulated with a body-force multiple-relaxation-time lattice Boltzmann method. The transition from Darcy flow to non-Darcy flow is identified from the velocity and pressure gradient response, and β is determined by fitting the inertial flow regime. Two tortuosity responses were observed. In uniform media, hydraulic tortuosity remained nearly constant in the Darcy regime and then gradually decreased. In disordered media, hydraulic tortuosity first increased with the onset of recirculation and then decreased as dominant flow paths became stable. Based on these results, a dimensionless inertial factor was correlated with porosity, intrinsic hydraulic tortuosity, and a pore structure index derived from specific surface area and hydraulic pore size. The resulting model predicts β from permeability and structural descriptors. The resulting correlation provides β estimates from Darcy permeability and geometry descriptors. Validation with quasi-two-dimensional microfluidic pillar array data showed that the model captured both the magnitude and relative ordering of β for the tested geometries. The proposed framework should be regarded as a proof of concept for idealized granular porous media and quasi-two-dimensional structured systems. Full article

Nanostructured metallic materials are widely applied in various fields due to their excellent comprehensive properties. Enhancing mechanical properties through microstructure design has emerged as a novel strengthening strategy. In this contribution, the microscopic mechanical behavior of coarse-grained and gradient-structured nanocrystalline NiCoAl alloys during tensile deformation was investigated via molecular dynamics simulations. Based on the investigation of compositional effects, the Ni₆₀Co₃₀Al₁₀ alloy composition was selected, exhibiting a yield strength of 4.92 GPa. The results indicate that increasing Al content reduces the material’s strength, Young’s modulus, and work hardening effect. Furthermore, by introducing a gradient structure with grain sizes gradually varying from 1.8 nm to 6.5 nm into the alloy, the yield strength reaches 1.8 GPa and the flow stress reaches 3.35 GPa, demonstrating a significant improvement compared to the uniform coarse-grained structure. Upon introducing the gradient structure into the alloy, it was observed that geometrically necessary dislocations (GNDs) nucleate in the coarse-grained region during deformation and gradually extend towards the fine-grained region. The increased grain boundary density effectively impedes dislocation motion and enhances dislocation pinning capability, thereby inducing continuous strain hardening and improving plasticity. By promoting the accumulation and interaction of grain boundary dislocations, the gradient structure achieves further strengthening and strain hardening in the alloy, providing a theoretical basis and simulation foundation for designing high-performance advanced alloys. Full article

Next Point-of-Interest (POI) recommendations are pivotal for enhancing location-based services; however, accurate prediction remains challenging due to the complex interplay between dynamic user preferences and spatiotemporal constraints. Existing graph-sequence hybrids often fail to unify these dimensions, typically treating temporal contexts as disjoint features or neglecting implicit collaborative signals within sparse user trajectories. This fragmentation limits the ability to capture high-order dependencies in user mobility. To address these challenges, we propose UPTRec, a unified framework that synergizes social, spatial, and temporal reasoning. UPTRec constructs a TF-IDF-weighted user similarity graph to recover latent social connections and a flow-based POI-transition graph to encode sequential mobility patterns. These structural priors are fused with fine-grained temporal-category embeddings (utilizing Time2Vec and periodic encoding) via a multi-layer Transformer encoder to comprehensively capture user behavior. Extensive experiments on three real-world datasets (NYC, TKY, and CA) demonstrate that UPTRec achieves state-of-the-art performance among the compared baselines under the same experimental settings. On the NYC dataset, UPTRec yields a Top-1 Accuracy of 25.76% and a Mean Reciprocal Rank (MRR) of 0.3879, representing a relative improvement of 5.8% and 7.1% over the strongest baseline (GETNext). These results validate the efficacy of jointly modeling collaborative and spatiotemporal dependencies. Full article

To study the influence of freckle defects on the hot deformation behavior and the inheritance of dynamic recrystallization (DRX) structure in GH4706 alloy, the microstructures of specimens with and without freckles and the evolution laws of hot-processing parameters were compared. Hot compression experiments were conducted on a thermal simulation testing machine at 950–1150 °C, strain rates of 0.001–1 s⁻¹, and 55% deformation. Freckle-containing specimens were tested under DRX critical conditions. The flow stresses of both specimens increase with strain rate or with decreasing temperature. The power dissipation coefficient (η) and instability value (ξ) follow complex laws. Electron back-scattering diffraction (EBSD) was used to analyze DRX microstructures and nucleation mechanisms. The DRX degree of freckle-containing specimens is lower, with a larger average grain size. The DRX mechanism initiates preferentially in freckle-containing specimens, and its volume fraction changes in a complex manner. Grain coarsening occurs in freckle-containing specimens at high temperatures and low strain rates. Freckle defects lead to significant differences in the DRX mechanism of GH4706 alloy. Freckle-containing specimens exhibit both discontinuous dynamic recrystallization (DDRX) and continuous dynamic recrystallization (CDRX), whereas freckle-free specimens primarily display DDRX and second-phase particle-stimulated nucleation (PSN). The presence of MC carbides and Laves phases within freckle defects provides nucleation sites, further supporting a typical second-phase particle-stimulated nucleation mechanism. Full article

The fractured lacustrine carbonate oil reservoir in the Lower submember of Member 4 (Qian-4) of the Qianjiang Formation in the Zhongshi area, Jianghan Basin, represents an important target for hydrocarbon exploration and exhibits substantial exploration and development potential. To clarify the mechanisms by which fractures control reservoir effectiveness, this study integrates core description, thin-section petrography, petrophysical measurements, and geophysical interpretation to systematically characterize matrix properties and fracture development. Results show that the reservoir matrix is dominated by micritic carbonate rocks and grain-dominated carbonate rocks, and overall exhibits low-porosity and ultra-low-permeability characteristics, with an average porosity of 5.19% and permeability generally below 5 mD. Fractures are well developed within the matrix, mainly comprising non-tectonic bedding-parallel fractures and tectonic high-angle fractures. Fracture-related porosity averages 8.42%, and permeability can reach 10–100 mD or higher. The fracture attributes and their spatial distribution are the key controls on hydrocarbon enrichment and deliverability; the occurrence of different fracture types across lithologies and sublayers can significantly enhance reservoir flow capacity. Moreover, natural-fracture characteristics provide critical geological constraints for hydraulic fracturing design and implementation. These findings offer a theoretical basis for fine-scale exploration and development of fractured lacustrine carbonate reservoirs. Full article