Search Results (156)

Creating high-fidelity digital twins (DTs) for Industry 4.0 applications, it is fundamentally reliant on the accurate 3D modeling of physical assets, a task complicated by the inherent imperfections of real-world point cloud data. This paper addresses the challenge of reconstructing accurate, watertight, and topologically sound 3D meshes from sparse, noisy, and incomplete point clouds acquired in complex industrial environments. We introduce a robust two-stage completion-to-reconstruction framework, C2R3D-Net, that systematically tackles this problem. The methodology first employs a pretrained, self-supervised point cloud completion network to infer a dense and structurally coherent geometric representation from degraded inputs. Subsequently, a novel adaptive surface reconstruction network generates the final high-fidelity mesh. This network features a hybrid encoder (FKAConv-LSA-DC), which integrates fixed-kernel and deformable convolutions with local self-attention to robustly capture both coarse geometry and fine details, and a boundary-aware multi-head interpolation decoder, which explicitly models sharp edges and thin structures to preserve geometric fidelity. Comprehensive experiments on the large-scale synthetic ShapeNet benchmark demonstrate state-of-the-art performance across all standard metrics. Crucially, we validate the framework’s strong zero-shot generalization capability by deploying the model—trained exclusively on synthetic data—to reconstruct complex assets from a custom-collected industrial dataset without any additional fine-tuning. The results confirm the method’s suitability as a robust and scalable approach for 3D asset modeling, a critical enabling step for creating high-fidelity DTs in demanding, unseen industrial settings. Full article

This study presents an optimization approach for sizing photovoltaic (PV) and battery energy storage systems (BESSs) within a DC microgrid, aiming to enhance cost-effectiveness, energy reliability, and environmental sustainability. PV generation is modeled based on environmental parameters such as solar irradiance and ambient temperature, while battery charging and discharging operations are managed according to real-time demand. A simulation framework is developed in MATLAB 2021b to analyze PV output, battery state of charge (SOC), and grid energy exchange. For demand-side management, the Long Short-Term Memory (LSTM) deep learning model is employed to forecast future load profiles using historical consumption data. Moreover, a Multi-Layer Perceptron (MLP) neural network is designed for comparison purposes. The dynamic load prediction, provided by LSTM in particular, improves system responsiveness and efficiency compared to MLP. Simulation results indicate that optimal sizing of PV and storage units significantly reduces energy costs and dependency on the main grid for both forecasting methods; however, the LSTM-based approach consistently achieves higher annual savings, self-sufficiency, and Net Present Value (NPV) than the MLP-based approach. The proposed method supports the design of more resilient and sustainable DC microgrids through data-driven forecasting and system-level optimization, with LSTM-based forecasting offering the greatest benefits. Full article

Background/Objectives: The infraorbital canal (IOC) is a critical anatomical structure that passes through the anterior surface of the maxilla and opens at the infraorbital foramen, containing the infraorbital nerve, artery, and vein. Accurate localization of this canal in maxillofacial, dental implant, and orbital surgeries is of great importance to preventing nerve damage, reducing complications, and enabling successful surgical planning. The aim of this study is to perform automatic segmentation of the infraorbital canal in cone-beam computed tomography (CBCT) images using an artificial intelligence (AI)-based model. Methods: A total of 220 CBCT images of the IOC from 110 patients were labeled using the 3D Slicer software (version 4.10.2; MIT, Cambridge, MA, USA). The dataset was split into training, validation, and test sets at a ratio of 8:1:1. The nnU-Net v2 architecture was applied to the training and test datasets to predict and generate appropriate algorithm weight factors. The confusion matrix was used to check the accuracy and performance of the model. As a result of the test, the Dice Coefficient (DC), Intersection over the Union (IoU), F1-score, and 95% Hausdorff distance (95% HD) metrics were calculated. Results: By testing the model, the DC, IoU, F1-score, and 95% HD metric values were found to be 0.7792, 0.6402, 0.787, and 0.7661, respectively. According to the data obtained, the receiver operating characteristic (ROC) curve was drawn, and the AUC value under the curve was determined to be 0.91. Conclusions: Accurate identification and preservation of the IOC during surgical procedures are of critical importance to maintaining a patient’s functional and sensory integrity. The findings of this study demonstrated that the IOC can be detected with high precision and accuracy using an AI-based automatic segmentation method in CBCT images. This approach has significant potential to reduce surgical risks and to enhance the safety of critical anatomical structures. Full article

Building Integrated Photovoltaic (BIPV) systems have emerged as an option to design Net Zero Energy Buildings (NZEB), thus helping to meet sustainable development goals. Based on an exhaustive review of papers, this work identifies characteristics and solutions to address power management issues in BIPV systems through three key approaches: (1) configurations of photovoltaic arrays, (2) MPPT methods, and (3) granularity level of the MPPT action. The analysis also highlights the advantages of deploying DC buses alongside conventional AC infrastructure to reduce conversion losses. This work also provides information concerning the trends in design and performance of BIPV systems, which is useful as a background for researchers and designers. In addition, the cross-coupling phenomena occurring in distributed MPPT solutions for BIPV systems is explained and evaluated in order to propose a mitigation strategy. These findings offer practical guidelines for developing more efficient BIPV systems that effectively support the transition to sustainable buildings and cities. Full article

Real-time tumor-tracked radiotherapy with a linear accelerator-magnetic resonance (linac-MR) hybrid system requires accurate tumor delineation at a fast MR imaging rate. Various autocontouring methods have been previously evaluated against “gold standard” manual contours by experts. However, manually drawn contours have inherent intra- and inter-observer variations. We aim to quantify these variations and evaluate our tumor-autocontouring algorithm against the manual contours. Ten liver, ten prostate, and ten lung cancer patients were scanned using a 3 tesla (T) magnetic resonance imaging (MRI) scanner with a 2D balanced steady-state free precession (bSSFP) sequence at 4 frames/s. Three experts manually contoured the tumor in two sessions. For autocontouring, an in-house built U-Net-based autocontouring algorithm was used, whose hyperparameters were optimized for each patient, expert, and session (PES). For evaluation, (A) Automatic vs. Manual and (B) Manual vs. Manual contour comparisons were performed. For (A) and (B), three types of comparisons were performed: (a) same expert same session, (b) same expert different session, and (c) different experts, using Dice coefficient (DC), centroid displacement (CD), and the Hausdorff distance (HD). For (A), the algorithm was trained using one expert’s contours and its autocontours were compared to contours from (a)–(c). For Automatic vs. Manual evaluations (Aa–Ac), DC = 0.91, 0.86, 0.78, CD = 1.3, 1.8, 2.7 mm, and HD = 3.1, 4.6, 7.0 mm averaged over 30 patients were achieved, respectively. For Manual vs. Manual evaluations (Ba–Bc), DC = 1.00, 0.85, 0.77, CD = 0.0, 2.1, 2.8 mm, and HD = 0.0, 4.9, 7.2 mm were achieved, respectively. We have quantified the intra- and inter-observer variations in manual contouring of liver, prostate, and lung patients. Our PES-specific optimized algorithm generated autocontours with agreement levels comparable to these manual variations, but with high efficiency (54 ms/autocontour vs. 9 s/manual contour). Full article

Medical image segmentation is a critical task in image analysis and plays an essential role in computer-aided diagnosis. Despite the promising performance of hybrid models combining U-Net and transformer architectures, these approaches face challenges in extracting local features and optimizing attention mechanisms. To address these limitations, we propose the Depthwise Composite Transformer and Depthwise Polarized Attention Network (DC-TransDPANet), a novel framework designed for medical image segmentation. The proposed DC-TransDPANet introduces a Depthwise Composite Attention Module (DW-CAM), which integrates depthwise convolution, and a Composite Attention mechanism to enhance local feature extraction and fuse contextual information. Additionally, a Depthwise Polarized Attention (DPA) block is employed to improve global context representation while preserving high-resolution details, achieving a fine balance between local and global feature extraction. Extensive experiments on benchmark datasets demonstrate that DC-TransDPANet significantly outperforms existing methods in segmentation accuracy. Full article

The growing integration of DG enhances distribution network resilience, but existing centralized fault recovery strategies face critical limitations: excessive computational burdens on DCs and the insufficient utilization of local control capabilities, particularly with large-scale DG deployments. Current studies often fail to balance computational efficiency and dynamic recovery coordination between centralized and decentralized resources. To address the issue, a hierarchical control architecture is proposed that involves collaboration between the DC and LA energy gateways. By dynamically quantifying LA PSC through net power feasibility analysis, the framework optimizes network reconfiguration (DC level) and decentralized DG scheduling (gateway level). Validated on a modified IEEE 45-bus system, the strategy restored 7 MWh (4:00 fault) and 5 MWh (10:00 fault) of load, outperforming static methods by 26.9× in the mid-day case. While effective in urban grids, rural DG-sparse areas require future integration of mobile storage. The work balances centralized coordination and decentralized execution, offering a scalable resilience solution for modern networks. Full article

Linear accelerator–magnetic resonance (linac-MR) hybrid systems allow for real-time magnetic resonance imaging (MRI)-guided radiotherapy for more accurate dose delivery to the tumor and improved sparing of the adjacent healthy tissues. However, for real-time tumor detection, it is unfeasible for a human expert to manually contour (gold standard) the tumor at the fast imaging rate of a linac-MR. This study aims to develop a neural network-based tumor autocontouring algorithm with patient-specific hyperparameter optimization (HPO) and to validate its contouring accuracy using in vivo MR images of cancer patients. Two-dimensional (2D) intrafractional MR images were acquired at 4 frames/s using 3 tesla (T) MRI from 11 liver, 24 prostate, and 12 lung cancer patients. A U-Net architecture was applied for tumor autocontouring and was further enhanced by implementing HPO using the Covariance Matrix Adaptation Evolution Strategy. Six hyperparameters were optimized for each patient, for which intrafractional images and experts’ manual contours were input into the algorithm to find the optimal set of hyperparameters. For evaluation, Dice’s coefficient (DC), centroid displacement (CD), and Hausdorff distance (HD) were computed between the manual contours and autocontours. The performance of the algorithm was benchmarked against two standardized autosegmentation methods: non-optimized U-Net and nnU-Net. For the proposed algorithm, the mean (standard deviation) DC, CD, and HD of the 47 patients were 0.92 (0.04), 1.35 (1.03), and 3.63 (2.17) mm, respectively. Compared to the two benchmarking autosegmentation methods, the proposed algorithm achieved the best overall performance in terms of contouring accuracy and speed. This work presents the first tumor autocontouring algorithm applicable to the intrafractional MR images of liver and prostate cancer patients for real-time tumor-tracked radiotherapy. The proposed algorithm performs patient-specific HPO, enabling accurate tumor delineation comparable to that of experts. Full article

The world is increasingly turning to renewable energy sources (RES) to address climate change issues and achieve net-zero carbon emissions. Integrating RES into existing power grids is necessary for sustainability because the unpredictability and irregularity of the RES can affect grid stability and generate power quality issues, leading to equipment damage and increasing operational costs. As a result, the importance of RES is severely compromised. To tackle these challenges, traditional power systems (TPS) will have to become more innovative. Smart grids use advanced technology such as two-way communication between consumers and service providers, automated control, and real-time monitoring to manage power flow effectively. Inverters are effective tools for solving power quality problems in renewable-powered smart grids. However, their effectiveness depends on topology, control method and design. This review paper focuses on the role of multilevel inverters (MLIs) in mitigating power quality issues such as voltage sag, swell and total harmonics distortion (THD). The results shown here are through simulation studies using DC sources but can be extended to RES-integrated smart grids. The comprehensive review also examines the drawbacks of TPS to understand the importance and necessity of developing a smart power system. Finally, the paper discusses future trends in MLI control technology, addressing power quality problems in smart grid environments. Full article

Visual speech recognition is a technology that relies on visual information, offering unique advantages in noisy environments or when communicating with individuals with speech impairments. However, this technology still faces challenges, such as limited generalization ability due to different speech habits, high recognition error rates caused by confusable phonemes, and difficulties adapting to complex lighting conditions and facial occlusions. This paper proposes a lip reading data augmentation method—Partition-Time Masking (PTM)—to address these challenges and improve lip reading models’ performance and generalization ability. Applying nonlinear transformations to the training data enhances the model’s generalization ability when handling diverse speakers and environmental conditions. A lip-reading recognition model architecture, Swin Transformer and 3D Convolution (ST3D), was designed to overcome the limitations of traditional lip-reading models that use ResNet-based front-end feature extraction networks. By adopting a strategy that combines Swin Transformer and 3D convolution, the proposed model enhances performance. To validate the effectiveness of the Partition-Time Masking data augmentation method, experiments were conducted on the LRW video dataset using the DC-TCN model, achieving a peak accuracy of 92.15%. The ST3D model was validated on the LRW and LRW1000 video datasets, achieving a maximum accuracy of 56.1% on the LRW1000 dataset and 91.8% on the LRW dataset, outperforming current mainstream lip reading models and demonstrating superior performance on challenging easily confused samples. Full article

The tomato is among the crops with the most extensive cultivated area and greatest consumption in our nation; nonetheless, secondary salinization of facility soil significantly hinders the sustainable growth of facility agriculture. Melatonin (MT), as an innovative plant growth regulator, is essential in stress responses. This research used a hydroponic setup to replicate saline stress conditions. Different endogenous levels of melatonin (MT) were established by foliar spraying of 100 μmol·L⁻¹ MT, the MT synthesis inhibitor p-CPA (100 μmol·L⁻¹), and a combination of p-CPA and MT, to investigate the mechanism by which MT mitigates the effects of salt stress on the photosynthetic efficiency of tomato seedlings. Results indicated that after six days of salt stress, the endogenous MT content in tomato seedlings drastically decreased, with declines in the net photosynthetic rate and photosystem performance indices (PI_total and PI_abs). The OJIP fluorescence curve exhibited distortion, characterized by anomalous K-band and L-band manifestations. Exogenous MT dramatically enhanced the gene (TrpDC, T5H, SNAcT, and AcSNMT) expression of critical enzymes in MT synthesis, therefore boosting the level of endogenous MT. The application of MT enhanced the photosynthetic parameters. MT treatment decreased the fluorescence intensities of the J-phase and I-phase in the OJIP curve under salt stress, attenuated the irregularities in the K-band and L-band performance, and concurrently enhanced quantum yield and energy partitioning ratios. It specifically elevated φP_o, φE_o, and ψ_o, while decreasing φD_o. The therapy enhanced parameters of both the membrane model (ABS/RC, DI_o/RC, ET_o/RC, and TR_o/RC) and leaf model (ABS/CS_m, TR_o/CS_m, ET_o/CS_m, and DI_o/CS_m). Conversely, the injection of exogenous p-CPA exacerbated salt stress-related damage to the photosystem of tomato seedlings and diminished the beneficial effects of MT. The findings suggest that exogenous MT mitigates salt stress-induced photoinhibition by (1) modulating endogenous MT concentrations, (2) augmenting PSII reaction center functionality, (3) safeguarding the oxygen-evolving complex (OEC), (4) reinstating PSI redox potential, (5) facilitating photosynthetic electron transport, and (6) optimizing energy absorption and dissipation. As a result, MT markedly enhanced photochemical performance and facilitated development and salt stress resilience in tomato seedlings. Full article

Reconstructing high-resolution hyperspectral images (HR-HSIs) by fusing low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs) is a significant challenge in image processing. Traditional fusion methods focus on visual and statistical metrics, often neglecting the requirements of downstream tasks. To address this gap, we propose a novel three-stream fusion network, 3DCNet, designed to integrate spatial and spectral information from LR-HSIs and HR-MSIs. The framework includes two dedicated branches for extracting spatial and spectral features, alongside a hybrid spatial–spectral branch (HSSI). The spatial block (SpatB) and the spectral block (SpecB) are designed to extract spatial and spectral details. The training process employs the global loss, spatial edge loss, and spectral angle loss for fusion tasks, with an alternating training iteration strategy (ATIS) to enhance downstream classification by iteratively refining the fusion and classification networks. Fusion experiments on seven datasets demonstrate that 3DCNet outperforms existing methods in generating high-quality HR-HSIs. Superior performance in downstream classification tasks on four datasets proves the importance of the ATIS. Ablation studies validate the importance of each module and the ATIS process. The 3DCNet framework not only advances the fusion process by leveraging downstream knowledge but also sets a new benchmark for classification-oriented hyperspectral fusion. Full article

Proton exchange membrane fuel cell system (PEMFCS)-based battery-hybridized turboprop regional aircraft emerge as a promising solution to the urgency of reducing the environmental impact of such airplanes. The development of integrated simulation frameworks consisting of versatile and easily adaptable models and control strategies is deemed highly strategic to guarantee proper component sizing and in-flight, onboard energy management. This need is here addressed via a novel efficiency-driven PEMFCS model and a degradation-aware battery-PEMFCS unit specification-independent control algorithm. The proposed model simplifies stack voltage and current estimation while maintaining accuracy so as to support, in conjunction with the afore-introduced versatile control strategy, the development of architectures appropriate for subsequent fully integrated (i.e., at the entire aircraft design level) simulation frameworks. The model also allows assessing the balance of plant impact on the fuel cell system’s net power, as well as the heat generated by the stack and related cooling demand. Finally, the multi-stack configuration meeting the DC bus line 270 V constraint, as currently assumed by the aviation industry, is determined. Full article

Advancements in aviation technology have made intelligent navigation systems essential for improving flight safety and efficiency, particularly in low-visibility conditions. Radar and GPS systems face limitations in bad weather, making visible–infrared sensor fusion a promising alternative. This study proposes a salient object detection (SOD) method that integrates visible and infrared sensors for robust airport runway detection in complex environments. We introduce a large-scale visible–infrared runway dataset (RDD5000) and develop a SOD algorithm capable of detecting salient targets from unaligned visible and infrared images. To enable real-time processing, we design a lightweight dual-modal fusion network (DCFNet) with an independent–shared encoder and a cross-layer attention mechanism to enhance feature extraction and fusion. Experimental results show that the MobileNetV2-based lightweight version achieves 155 FPS on a single GPU, significantly outperforming previous methods such as DCNet (4.878 FPS) and SACNet (27 FPS), making it suitable for real-time deployment on airborne systems. This work offers a novel and efficient solution for intelligent navigation in aviation. Full article

Mapping the high-precision spatiotemporal dynamics of soil organic carbon (SOC) in croplands is crucial for enhancing soil fertility and carbon sequestration and ensuring food security. We conducted field surveys and collected 1121 soil samples from cropland in Changzhi, northern China, in 2010 and 2020. Random Forest (RF) models combined with 19 environmental covariates were used to map the topsoil (0–20 cm) SOC in 2010 and 2020, and uncertainty maps were used to calculate the dynamic changes in cropland SOC between 2010 and 2020. Finally, RF and Structural Equation Modeling (SEM) were employed to explore the effects of climate, vegetation, topography, soil properties, and agricultural management on SOC variation in croplands. Compared to the prediction model using only natural variables (RF_C), the model incorporating agricultural management (RF_A) significantly improved the simulation accuracy of SOC. The coefficient of determination (R²) increased from 0.77 to 0.85, while the Root Mean Square Error (RMSE) decreased from 1.74 to 1.53 g kg⁻¹, and the Mean Absolute Error (MAE) was reduced from 1.10 to 0.94 g kg⁻¹. The uncertainty in our predictions was low, with an average value of only 0.39–0.66 g kg⁻¹. From 2010 to 2020, SOC in the Changzhi croplands exhibited an overall increasing trend, with an average increase of 1.57 g kg⁻¹. Climate change, agricultural management, and soil properties strongly influence SOC variation. Mean annual precipitation (MAP), drainage condition (DC), and net primary productivity (NPP) were the primary drivers of SOC variability. Our findings highlight the effectiveness of agricultural management for predicting SOC in croplands. Overall, the study confirms that improved agricultural management has great potential to increase soil carbon stocks, which may contribute to sustainable agricultural development. Full article