Search Results (674)

The identification of cotton diseases and pests is crucial for maintaining cotton yield and quality. However, conventional manual methods are inefficient and prone to high error rates, limiting their practicality in real-world agricultural scenarios. Furthermore, Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) models are insufficient in generating fine-grained and semantically rich image captions, particularly for complex disease and pest features. To overcome these challenges, we introduce CottonCapT6, a novel multi-task image captioning framework based on the Cross Vision Transformer (CrossViT-18-Dagger-408) and Text-to-Text Transfer Transformer (T5). We also construct a new dataset containing annotated images of seven common cotton diseases and pests to support this work. Experimental results demonstrate that CottonCapT6 achieves a Consensus-based Image Captioning Evaluation (CIDEr) score of 197.2% on the captioning task, demonstrating outstanding performance. Notably, the framework excels in providing more descriptive, coherent, and contextually accurate captions. This approach has strong potential to be deployed in cotton farms in the future, helping pest control personnel and farmers make precise judgments on cotton diseases and pests. However, its generalizability to other crops and environmental conditions remains an area for future exploration. Full article

In reconfigurable radio frequency (RF) microsystems, the interconnect structure critically affects high-frequency signal integrity, and the accuracy of electromagnetic (EM) modeling directly determines the overall system performance. Conventional neural network-based surrogate models mainly focus on minimizing numerical errors, while neglecting essential physical constraints, such as causality and passivity, thereby limiting their applicability in both time and frequency domains. This paper proposes a physics-constrained Neuro-Transfer surrogate model with a broadband output architecture to directly predict S-parameters over the 1–50 GHz range. Causality and passivity are enforced through dedicated regularization terms during training. Furthermore, a particle swarm optimization (PSO)-based multi-objective intelligent optimization framework is developed, incorporating fixed-weight normalization and a linearly decreasing inertia weight strategy to simultaneously optimize the S11, S21, and S22 performance of a quasi-coaxial TSV composite structure. Target values are set to −25 dB, −0.54 dB, and −24 dB, respectively. The optimized structural parameters yield prediction-to-simulation deviations below 1 dB, with an average prediction error of 2.11% on the test set. Full article

This study evaluates the forecast performance of four radiation parameterization schemes—the Rapid Radiative Transfer Model for General Circulation Models (RRTMG), its improved version RRTMG-K, the infrequently applied variant, RRTMG-K_60x, and the neural network emulator, RRTMG-K_NN, within a high-resolution numerical weather prediction (NWP) model. The evaluation uses satellite-derived observations of Outgoing Longwave Radiation (OLR) and Outgoing Shortwave Radiation (OSR) from the Clouds and the Earth’s Radiant Energy System (CERES) over the Korean Peninsula during 2020, including an extreme case study of Typhoon Haishen. Results show that RRTMG-K reduces RMSEs by 4.8% for OLR and 17.5% for OSR relative to RRTMG, primarily due to substantial bias reduction (42.3% for OLR, 60.4% for OSR). The RRTMG-K_NN scheme achieves approximately 60-fold computational speedup while maintaining similar or slightly better accuracy than RRTMG-K; specifically, it reduces OLR errors by 1.2% and OSR errors by 1.6% compared to the infrequently applied RRTMG-K_60x. In contrast, the infrequent application of RRTMG-K (RRTMG-K_60x) slightly increases errors, underscoring the trade-off between computational efficiency and accuracy. These findings demonstrate the value of integrating advanced satellite flux observations and machine learning techniques into the evaluation and optimization of radiation schemes, providing a robust framework for improving cloud–radiation interaction representation in NWP models. Full article

Nanotechnology has become a transformative field in modern science and engineering, offering innovative approaches to enhance conventional thermal and fluid systems. Heat and mass transfer phenomena, particularly fluid motion across various geometries, play a crucial role in industrial and engineering processes. The inclusion of nanoparticles in base fluids significantly improves thermal conductivity and enables advanced phase-change technologies. The current work examines Powell–Eyring nanofluid’s heat transmission properties on a stretched Riga plate, considering the effects of magnetic fields, porosity, Darcy–Forchheimer flow, thermal radiation, and activation energy. Using the proper similarity transformations, the pertinent governing boundary-layer equations are converted into a set of ordinary differential equations (ODEs), which are then solved using the boundary value problem fourth-order collocation (BVP4C) technique in the MATLAB program. Tables and graphs are used to display the outcomes. Due to their significance in the industrial domain, the Nusselt number and skin friction are also evaluated. The velocity of the nanofluid is shown to decline with a boost in the Hartmann number, porosity, and Darcy–Forchheimer parameter values. Moreover, its energy curves are increased by boosting the values of thermal radiation and the Biot number. A stronger Hartmann number M decelerates the flow (thickening the momentum boundary layer), whereas increasing the Riga forcing parameter Q can locally enhance the near-wall velocity due to wall-parallel Lorentz forcing. Visual comparisons and numerical simulations are used to validate the results, confirming the durability and reliability of the suggested approach. By using a systematic design technique that includes training, testing, and validation, the fluid dynamics problem is solved. The model’s performance and generalization across many circumstances are assessed. In this work, an artificial neural network (ANN) architecture comprising two hidden layers is employed. The model is trained with the Levenberg–Marquardt scheme on reliable numerical datasets, enabling enhanced prediction capability and computational efficiency. The ANN demonstrates exceptional accuracy, with regression coefficients $R\approx 1.0$ and the best validation mean squared errors of $8.52\times {10}^{-10}$, $7.91\times {10}^{-9}$, and $1.59\times {10}^{-8}$ for the Powell–Eyring, heat radiation, and thermophoresis models, respectively. The ANN-predicted velocity, temperature, and concentration profiles show good agreement with numerical findings, with only minor differences in insignificant areas, establishing the ANN as a credible surrogate for quick parametric assessment and refinement in magnetohydrodynamic (MHD) nanofluid heat transfer systems. Full article

Observing System Simulation Experiments (OSSEs) provide a framework in which to evaluate the impact of prospective ocean-observation networks on model forecasting performance prior to their actual deployment. This study presents the design and validation of an OSSE tailored for the operational coastal model of southern Portugal, SOMA. The system adopts the fraternal twins approach and a univariate data-assimilation scheme based on Ensemble Optimal Interpolation to update the model’s 3D temperature structure with SST. The methodology provides a flexible framework that preserves the statistical structure of real observation errors while remaining independent of SOMA. This allows straightforward transfer to other applications, thereby broadening its applicability and making it useful as a starting point in the design of observation networks beyond that presented in this case study. The OSSE experiments were compared against corresponding Observing System Experiments (OSEs) using real satellite SST products. Results show that the designed OSSE is internally consistent, sensitive to observation density, and capable of reproducing realistic correction patterns that closely match those obtained in the OSEs. These findings provide strong evidence that the SOMA OSSE system is a reliable tool for assessing the potential impact of future surface-observation strategies. Full article

Sea surface salinity (SSS) observations play a crucial role in the study of ocean circulation, climate variability, and marine ecosystems. However, current satellite SSS products suffer from systematic biases due to factors such as radio frequency interference (RFI) and land contamination, resulting in fundamental limitations to their application for SSS monitoring. To address this issue, we propose a physics-informed neural network (PINN) approach that directly integrates radiative transfer physical processes into the neural network architecture for SMAP L2 SSS bias correction. This method ensures oceanographically consistent corrections by embedding physical constraints into the forward propagation model. The results demonstrate that PINN achieved a root mean square error (RMSE) of 0.249 PSU, representing a 5.3% to 8.5% relative performance improvement compared to conventional methods—GBRT, ANN, and XGBoost. Further temporal stability analysis reveals that PINN exhibits significantly reduced RMSE variations over multi-year periods, demonstrating exceptional long-term correction stability. Meanwhile, this method achieves more uniform bias improvement in contaminated nearshore regions, showing distinct advantages over the inconsistent correction patterns of conventional methods. This study establishes a physics-constrained machine learning framework for satellite SSS data correction by integrating oceanographic domain knowledge, providing a novel technical pathway for reliable enhancement of Earth observation data. Full article

The thermal deformation of high-precision CNC machine tools has long been a significant barrier to improving machining accuracy. Accurately characterizing the thermal properties of the spindle, especially the convective heat transfer coefficients (CHTC), is essential for precise thermal analysis. However, due to the lack of dedicated instruments for directly measuring the CHTC, thermal analysis of the spindle faces substantial challenges. This study presents an innovative approach that combines multi-sensor data with intelligent optimization algorithms to address this issue. A distributed temperature monitoring network is constructed to capture real-time thermal field data across the spindle. At the same time, an improved Grey Wolf Optimization (IGWO) algorithm is employed to dynamically and accurately identify the CHTC. The proposed algorithm introduces an adaptive weight adjustment mechanism, which overcomes the limitations of traditional optimization methods in dynamic operating conditions. Experimental results show that the proposed method significantly outperforms conventional approaches in terms of temperature prediction accuracy across a broad operating range. This research provides a novel technical solution for machine tool thermal error compensation and establishes a scalable intelligent indirect measurement framework, even in the absence of specialized measurement instruments. Full article

The height of the center of gravity (Z_CG) is a critical parameter for evaluating vehicle safety and performance. Systematic errors arise in Z_CG measurement via the tilt-table test method due to unlocked suspension systems and variable sprung mass conditions, which compromise accuracy. To address this limitation, a CNN–LSTM–Attention model integrating convolutional neural networks (CNNs), long short-term memory networks (LSTMs), and an attention mechanism is proposed. The CNN extracts spatial correlations among vehicle load transfer, suspension stiffness, and tilt angles. The LSTM captures temporal dependencies in tilt angle sequences, while the attention mechanism amplifies critical load-transfer features near the 0° region. Simulations of vehicles with unlocked suspension and variable sprung mass were conducted in Adams using tilt-table protocols. The CNN–LSTM–Attention model was trained on simulation data and validated with real-world tilt-test data under identical suspension conditions. Results demonstrate that the CNN–LSTM–Attention model achieves at least a 6.9% improvement in computational speed and at least a 0.1% reduction in prediction error compared to CNN, CNN-LSTM, and Transformer baselines. The CNN–LSTM–Attention model demonstrates valid predictive capability for Z_CG at 0° tilt angle. This novel approach provides a robust solution for the tilt-table test method Z_CG measurement, enhancing practical accuracy in vehicle dynamics parameter quantification. Full article

Flow past bluff bodies (e.g., circular cylinders) forms a canonical context for teaching external flow separation, vortex shedding, and the coupling between surface pressure and hydrodynamic forces in offshore engineering. Conventional laboratory implementations, however, often fragment local and global measurements, delay data feedback, and omit intelligent modeling components, thereby limiting the development of higher-order cognitive skills and data literacy. We present a low-cost, modular, data-enabled instructional hydrodynamics platform that integrates a transparent recirculating water channel, multi-point synchronous circumferential pressure measurements, global force acquisition, and an artificial neural network (ANN) surrogate. Using feature vectors composed of Reynolds number, angle of attack, and submergence depth, we train a lightweight AI model for rapid prediction of drag and lift coefficients, closing a loop of measurement, prediction, deviation diagnosis, and feature refinement. In the subcritical Reynolds regime, the measured circumferential pressure distribution for a circular cylinder and the drag and lift coefficients for a rectangular cylinder agree with empirical correlations and published benchmarks. The ANN surrogate attains a mean absolute percentage error of approximately 4% for both drag and lift coefficients, indicating stable, physically interpretable performance under limited feature inputs. This platform will facilitate students’ cross-domain transfer spanning flow physics mechanisms, signal processing, feature engineering, and model evaluation, thereby enhancing inquiry-driven and critical analytical competencies. Key contributions include the following: (i) a synchronized local pressure and global force dataset architecture; (ii) embedding a physics-interpretable lightweight ANN surrogate in a foundational hydrodynamics experiment; and (iii) an error-tracking, iteration-oriented instructional workflow. The platform provides a replicable pathway for transitioning offshore hydrodynamics laboratories toward an integrated intelligence-plus-data literacy paradigm and establishes a foundation for future extensions to higher Reynolds numbers, multiple body geometries, and physics-constrained neural networks. Full article

This study presents an integrated experimental and computational investigation into the thermal and hydraulic performance of three oxide-based nanofluids: aluminum oxide (Al₂O₃), titanium dioxide (TiO₂), and copper oxide (CuO) for advanced engine cooling applications. A custom-built test rig was used to assess nanofluid behavior under varying flow rates, nanoparticle volume fractions, and temperature gradients, replicating realistic engine conditions. According to the results, at ideal concentrations, CuO nanofluids continuously demonstrate better heat transfer properties, outperforming TiO₂ by up to 15% and AlO₃ by 7%. However, performance plateaus beyond 1.5% volume fraction due to increased viscosity and pressure drop. A multilayer feedforward artificial neural network (ANN) model was developed to predict convective heat transfer coefficients and friction factors based on experimental inputs, achieving a mean absolute percentage error below 5% and a coefficient of determination (R²) exceeding 0.98. The ANN demonstrated robust generalization across varying operating conditions and nanoparticle types, confirming its utility for surrogate modeling and optimization. This work is distinguished by its dual focus on thermal efficiency and hydraulic stability, as well as its use of data-driven modeling validated by empirical results. The findings provide actionable insights for thermal management system design in internal combustion, hybrid, and electric vehicles, where efficient, compact, and reliable cooling solutions are increasingly vital. The study advances the practical application of nanofluids by offering a comparative, ANN-validated framework that bridges the gap between lab-scale performance and real-world automotive cooling demands. Full article

Unsafe behavior among air traffic controllers is a significant causal factor in civil aviation safety incidents. To explore the risks and pathways associated with controller-induced aviation accidents, this study develops an analytical model of controller unsafe behavior based on association rules and fault tree Bayesian networks. First, the Human Factors Analysis and Classification System (HFACS) was applied to identify and categorize aviation incident reports attributed to controller errors. Next, association rule algorithms were employed to uncover potential associations between controller unsafe behaviors and related risk factors, and a fault tree Bayesian network (FT-BN) model of controller unsafe behaviors was constructed based on these associations. The results revealed that the most likely unsafe behaviors were: improper allocation of aircraft spacing (30.5%), failure to take necessary intervention measures (28.4%), and improper transfer of control (27.8%). Backward analysis of the FT-BN indicated that improper allocation of aircraft spacing was most likely triggered by failure to provide adequate controller training, failure to take necessary intervention measures was most often caused by forgotten information, and improper transfer of control was most frequently associated with controller fatigue and failure to put risk management efforts in place. This study provides an important framework for the analysis and evaluation of controller behavior management and offers key insights for improving air traffic safety. Full article

The growing number of connected devices has strained traditional radio frequency wireless networks, driving interest in alternative technologies such as optical wireless communications (OWC). Among OWC solutions, optical camera communication (OCC) stands out as a cost-effective option because it leverages existing devices equipped with cameras, such as smartphones and security systems, without requiring specialized hardware. This paper proposes a novel deep learning-based detection and classification model designed to optimize the receiver’s performance in an OCC system utilizing color-shift keying (CSK) modulation. The receiver was experimentally validated using an $8\times 8$ LED matrix transmitter and a CMOS camera receiver, achieving reliable communication over distances ranging from 30 cm to 3 m under varying ambient conditions. The system employed CSK modulation to encode data into eight distinct color-based symbols transmitted at fixed frequencies. Captured image sequences of these transmissions were processed through a YOLOv8-based detection and classification framework, which achieved $98.4$% accuracy in symbol recognition. This high precision minimizes transmission errors, validating the robustness of the approach in real-world environments. The results highlight OCC’s potential for low-cost applications, where high-speed data transfer and long-range are unnecessary, such as Internet of Things connectivity and vehicle-to-vehicle communication. Future work will explore adaptive modulation and coding schemes as well as the integration of more advanced deep learning architectures to improve data rates and system scalability. Full article

As network infrastructure and Internet of Things (IoT) technologies continue to evolve, immersive systems such as virtual reality (VR) are becoming increasingly integrated into interconnected environments. These advancements allow real-time processing of multi-modal data, improving user experiences with rich visual and three-dimensional interactions. However, ensuring continuous user authentication in VR environments remains a significant challenge. To address this issue, an effective user monitoring system is required to track VR users in real time and trigger re-authentication when necessary. Based on this premise, we propose a multi-modal authentication framework that uses eye-tracking data for authentication, named MobileNetV3pro. The framework applies a transfer learning approach by adapting the MobileNetV3Large architecture (pretrained on ImageNet) as a feature extractor. Its pre-trained convolutional layers are used to obtain high-level image representations, while a custom fully connected classification is added to perform binary classification. Authentication performance is evaluated using Equal Error Rate (EER), accuracy, F1-score, model size, and inference time. Experimental results show that eye-based authentication with MobileNetV3pro achieves a lower EER (3.00%) than baseline models, demonstrating its effectiveness in VR environments. Full article

Accurate prediction of oil and gas reservoirs requires precise river morphology. However, geological sedimentary images are often degraded by scattered non-structural noise from data errors or printing, which distorts river structures and complicates reservoir interpretation. To address this challenge, we propose GD-PND, a generative framework that leverages pseudo-labeled non-matching datasets to enable geological denoising via information transfer. We first construct a non-matching dataset by deriving pseudo-noiseless images via automated contour delineation and region filling on geological images of varying morphologies, thereby reducing reliance on manual annotation. The proposed style transfer-based generative model for noiseless images employs cyclic training with dual generators and discriminators to transform geological images into outputs with well-preserved river structures. Within the generator, the excitation networks of global features integrated with multi-attention mechanisms can enhance the representation of overall river morphology, enabling preliminary denoising. Furthermore, we develop an iterative denoising enhancement module that performs comprehensive refinement through recursive multi-step pixel transformations and associated post-processing, operating independently of the model. Extensive visualizations confirm intact river courses, while quantitative evaluations show that GD-PND achieves slight improvements, with the chi-squared mean increasing by up to 466.0 (approximately 1.93%), significantly enhancing computational efficiency and demonstrating its superiority. Full article

This paper presents a physics-guided machine learning (PGML) approach to model the I–V characteristics of GaN current aperture vertical field effect transistors (CAVET). By adopting the method of transfer learning and the shortcut structure, a physically guided neural network model is established. The shallow neural network with $tanh$ as the basis function is combined with a hypernetwork that dynamically generates its weight parameters. The influence of transconductance is added to the loss function. This model can synchronously predict the output and transfer characteristics of the device. Under the condition of small samples, the prediction error is controlled within 5%, and the $R^2$ value reaches above 0.99. The proposed PGML approach outperforms conventional approaches, ensuring physically meaningful and robust predictions for device optimization and circuit-level simulations. Full article