Search Results (6,141)

Accurate multiphase flow measurement in horizontal wells is fundamentally challenged by the antagonistic electrical responses of water and gas: Electrical Resistance Tomography (ERT) loses sensitivity to thin liquid films, while Electrical Capacitance Tomography (ECT) suffers signal saturation in conductive water, preventing either modality from covering the full operating envelope alone. This study proposes a physics-guided hybrid modeling framework that integrates multi-modal ERT/ECT sensing to achieve high-precision flowrate inversion. The framework utilizes a corrected multi-modal fusion algorithm, achieving a liquid holdup MAPE of 2.5 ± 0.5% representing a nearly two-fold improvement over the best single-modality system (Direct ERT, 4.5%). For velocity estimation, an optimized cross-correlation method yields results with ± 3.0% error, incorporating multi-sensor and multi-sequence fusion. A key finding is that deep neural networks exhibit Architectural Phase Specialization: multi-branch architectures (MB-DNN) perform strongly on localized, heterogeneous liquid structures (2.0% liquid error), whereas fully-connected architectures (FC-DNN) excel at capturing the global patterns of the continuous gas core (1.2% gas error). By hybridizing a calibrated drift-flux physical model with these phase-specialized DNNs, the framework achieves overall averaged errors of 1.8% for gas and 1.5% for liquid across the full experimental envelope. The proposed framework was evaluated on 444,313 experimental samples and subsequently validated in a three-month industrial trial at the Puguang gas field under extreme conditions (26 MPa, 80 °C), where it maintained a prediction error of ± 2.3%. This work establishes a scalable, physically consistent paradigm for intelligent hydrocarbon production monitoring. Full article

Super high-rise buildings are increasingly equipped with structural monitoring systems to track deformation responses during construction and operation, thereby supporting structural condition assessment and engineering management. To address key monitoring challenges, including GNSS multipath interference, insufficient vertical accuracy, accelerometer integration drift, and high-frequency noise, this study proposes a GNSS/accelerometer fusion monitoring method based on whale optimization algorithm–optimized variational mode decomposition (WOA-VMD) and adaptive robust Kalman filtering (ARKF). Continuous three-hour GNSS and accelerometer observations collected from a super high-rise building under construction are used for fusion validation. The results show that WOA-VMD effectively separates noise from deformation-related signals and outperforms conventional EMD and standard VMD in denoising performance. Compared with the raw observations, the fused east, north, and vertical displacement RMSEs are reduced by 68.84%, 75.97%, and 60.22%, respectively; the SNRs increase to 22.03 dB, 21.38 dB, and 16.74 dB, respectively; the STDs decrease by 72.58%, 75.62%, and 68.39%, respectively; and the PSDs increase to 9.47 dB, 9.02 dB, and 8.31 dB, respectively. The proposed framework exhibits sub-centimeter-level displacement monitoring performance in the horizontal directions and significantly enhances the monitoring capability of the vertical component. The field validation results demonstrate the feasibility and effectiveness of the proposed framework for short-term deformation monitoring of super high-rise buildings under practical monitoring conditions and indicate its potential for structural health monitoring applications. Full article

Background: Advances in monitoring systems featuring wearable sensors, computer vision, and artificial intelligence (AI) have been increasingly used in sports science and rehabilitation practices as a means of movement pattern analysis, injury prevention, and training optimization. These technologies are becoming essential components of athlete-performance analysis and rehabilitation-monitoring systems designed to support biomechanical assessment, athlete development, and movement-quality evaluation. Athlete-performance analysis and rehabilitation monitoring increasingly rely on intelligent multimodal sensing systems capable of continuously evaluating movement quality, biomechanical patterns, training execution, and recovery progress. Human activity recognition (HAR) serves as a key enabling technology for these applications by providing automated assessment of human movement using wearable and vision-based sensing modalities. Therefore, the purpose of this study was to develop and evaluate an attention-based multimodal framework that integrates wearable inertial sensing and RGB video analysis for robust athlete-performance assessment and rehabilitation monitoring through accurate recognition of human movement patterns. Methods: Athlete-performance analysis and rehabilitation monitoring combining inertial sensor data and RGB-based visual information was introduced. Inertial signals were segmented with adaptive windowing, whereas silhouette refinement was performed to analyze motion structures from visual inputs in support of athlete-performance analysis and rehabilitation monitoring. Temporal, spatial, and motion features such as trajectory, orientation, and skeleton-based space-time representations were calculated from multimodal inputs. The proposed framework was designed to capture complex movement dynamics associated with rehabilitation exercises and sports-related motion patterns across heterogeneous sensing environments. Extracted features were then combined and optimized with a multimodal feature fusion approach, while the Ranger optimization algorithm was utilized during the process. An attention-based deep learning classifier was implemented to classify movement activities. Results: The results showed that the proposed framework reached accuracy scores of 88.40% and 87.96% on the VIDIMU dataset and the UTD-MHAD dataset respectively. Recognition performance across both inertial and vision-based modalities provided greater robustness than single-modality solutions. The integration of wearable sensing and computer vision modalities further improved the ability of the framework to analyze complex movement behaviors under varying execution conditions and environmental variations. Conclusion: The proposed multimodal framework provides a foundation for intelligent athlete-performance and rehabilitation-monitoring systems by integrating wearable sensing, computer vision, and attention-based artificial intelligence for robust movement analysis. The findings highlight its potential to support biomechanical assessment, movement-quality evaluation, training-performance monitoring, rehabilitation tracking, and injury-risk management in modern sports and healthcare environments. Full article

Conventional fire monitoring systems frequently exhibit high false alarm rates, delayed response times, and a lack of closed-loop control capabilities, which severely constrain their deployment in complex real-world environments. To address these issues, this paper proposes an embedded fire detection, tracking, and extinguishing system based on multimodal information fusion and a lightweight neural model. The system follows a “Perception–Decision–Execution–Feedback” closed-loop paradigm and is implemented on a heterogeneous cooperative computing architecture comprising OpenMV4 H7 Plus and STM32F103C8T6 microcontrollers. The perception layer implements a decision-level RGB-infrared fusion mechanism that incorporates a pruned, INT8-quantized lightweight FOMO model, enabling real-time fire detection with an inference latency of 210 ms and a model size of merely 1.8 MB under resource-constrained embedded conditions. The decision layer employs a Bayesian inference-based multimodal fusion framework that effectively suppresses spurious fire interference. The vision-only false detection rate is 15.3%. After infrared fusion verification, the system-level false alarm rate is reduced to 2.0% on the interference test set. In the execution layer, a sixth-degree polynomial jet trajectory model was established and combined with an improved PID–PI dual-loop controller to enable dynamic optimization of spray angle and flow rate in real time. Experimental results demonstrate that the proposed system achieves an average fire recognition accuracy of 95.6% with a false alarm rate as low as 1.4%. Furthermore, it realizes an extinguishing accuracy better than ±5 cm within an effective operating range of 10–60 cm and completes the entire perception-to-extinguishing cycle within 8.5 s under illumination conditions ranging from 50 to 100,000 lux. These results demonstrate the excellent real-time capability, robustness, and energy efficiency of the proposed system, providing a practical and scalable solution for autonomous embedded fire-fighting applications in household, industrial, and warehouse environments. Full article

As hen eggs are a primary source of high-quality dietary protein, egg freshness is fundamentally linked to biochemical alterations during storage, including moisture redistribution, protein degradation, and fluctuating chemical profiles. Accurate assessment of these internal changes is paramount for quality control; nonetheless, conventional analytical techniques remain predominantly destructive, rendering them impractical for high-throughput industrial monitoring. While existing literature has explored individual spectroscopic methods, the synergistic potential of multi-sensor integration and advanced artificial intelligence (AI) algorithms remains insufficiently synthesized. This review systematically evaluates recent breakthroughs in integrating AI with diverse spectroscopic modalities for non-destructive freshness quantification, including Visible-Near-Infrared (VIS-NIR), Raman, Fluorescence, and Hyperspectral Imaging (HSI). We elucidate the underlying mechanisms of spectral response to internal quality degradation and discuss the evolution of data-driven modeling from traditional chemometrics to sophisticated deep learning architectures. Furthermore, this work identifies critical bottlenecks in real-time industrial implementation and proposes future research trajectories toward intelligent multi-sensor fusion platforms. Full article

Compared with hardware-dependent methods, light field (LF) reconstruction algorithms enable a more economical and convenient acquisition of densely sampled LF (DSLF). Existing learning-based LF reconstruction methods suffer from limited flexibility, as they rely on fixed sampling patterns and predefined angular resolutions. In this paper, we propose a flexible deep learning framework, which can reconstruct DSLF with arbitrary angular resolution from randomly distributed sparse input views of an arbitrary quantity. The proposed framework consists of two core stages, namely the SAI Synthesis and the LF Refinement. The SAI Synthesis adopts Plane Sweep Volume (PSV) to cope with randomly sampled input views, and leverages the Multi-Scale Attention (MSA) module to compute per-view weights for adaptive feature fusion and support arbitrary numbers of input views. The LF Refinement stage integrates intermediate results and fully exploits LF parallax structures to further improve reconstruction quality. Experimental results demonstrate that our method achieves superior flexibility and reconstruction quality, and outperforms most state-of-the-art LF reconstruction methods. Full article

Unmanned aerial vehicles (UAVs) and deep learning (DL) have introduced a new framework for intelligent building façade defect detection, yet existing studies often focus on isolated technical components and lack a systematic evaluation of the entire pipeline. To address this gap, this paper conducts a systematic literature review of 135 peer-reviewed journal articles retrieved from the Web of Science database over the period 2021–2026. This review investigates four key domains: (1) UAV inspection path planning and data acquisition; (2) multi-modal data fusion; (3) DL-driven defect detection algorithms; and (4) 3D reconstruction and digital twin integration. Our analysis reveals the following main findings. Real-time perception-aware planning is central to UAV path planning, yet most studies lack robustness evaluations under real-world deployment conditions. Multi-modal data fusion improves detection across multiple defect types, yet edge deployment requires balancing lightweight design with recognition stability. Defect recognition algorithms increasingly adopt task-driven architectures, but limited edge-device resources demand joint optimization of efficiency and accuracy. In digital twins, systematic research is still lacking on semantically integrating recognition results into BIM for O&M decision-making, leaving the closed loop from defect detection to maintenance unresolved. This review aims to help researchers and practitioners advance UAV-based inspection from an auxiliary tool to a fully autonomous, reliable intelligent agent for refined management of the urban built environment. Full article

Pose estimation is an important task in the field of machine vision, being widely used in robot grasping, augmented reality, and other applications. Weakly textured objects pose severe challenges due to scarce texture and low-density features, becoming a bottleneck in robot grasping. This paper systematically reviews recent progress in weakly textured object pose estimation, classifying methods into traditional and deep learning categories, and further dividing deep learning methods into instance-level, category-level, and unseen object-level. This review further summarizes the core issues of generalization limitations, real-time contradictions, and data bottlenecks in existing research. Combined with the practical needs of weakly textured scenes, the review points out that multimodal fusion optimization, lightweight model design, and low-cost annotation technology development are the future core research directions. The research results can provide a reference for algorithm design, experimental verification, and engineering applications in the field of weakly textured object pose estimation. Full article

Drainage pipe defect detection is essential for maintaining the normal operation of urban infrastructure. In recent years, deep learning-based object detection methods have provided an effective technical solution for drainage pipe defect recognition. Among them, YOLO-series models have demonstrated strong potential in visual detection tasks due to their end-to-end architecture and high inference efficiency. However, directly applying baseline YOLO models may still face challenges such as limited detection accuracy, relatively high model complexity, and insufficient adaptability for lightweight deployment scenarios. To address these issues, this paper proposes a lightweight drainage pipe defect detection method based on an improved YOLO11 network. Rather than treating detection enhancement and model compression as two separate procedures, the proposed method integrates feature enhancement, adaptive pruning, and distillation-based recovery into a unified lightweight detection framework. Specifically, an improved SimAM attention mechanism is introduced into the backbone and integrated with the C3k2 module to construct the C3K2_SWS module, aiming to enhance the representation capability of critical defect features. In the neck network, a focused diffusion pyramid network with a dimension-aware selective fusion structure, termed FDPN-DASI, is designed to strengthen multi-scale feature interactions. In addition, an adaptive-threshold focal loss (ATFL) is introduced to improve the learning capability for hard samples. For efficient deployment, the LAMP pruning algorithm is further improved, and an entropy-guided entropy-adaptive magnitude-based pruning method (EA-LAMP) is proposed to enable adaptive allocation of pruning ratios across different network layers. Moreover, BCKD knowledge distillation is applied after pruning to mitigate the accuracy degradation caused by model compression. Experimental results indicate that the proposed lightweight YOLO11-SFA+EA+BCKD framework achieves a precision of 92.4%, a recall of 88.5%, and an mAP50 of 93.3%, while maintaining a compact model size of 1.6 M parameters and 4.5 G FLOPs. Compared with the baseline model, the proposed method improves precision, recall, and mAP50 by 5.9%, 5.0%, and 4.7%, respectively, while reducing the number of parameters, FLOPs, and model size by 1.0 M, 1.8 G, and 2.1 M, respectively. These results suggest that the proposed framework can improve detection performance while reducing model complexity under the current experimental setting, indicating its potential for lightweight drainage pipe defect detection tasks. Full article

The growth of Intelligent Transportation Systems (ITS) has made high-quality perception data from multi-sensor setups essential. Pairing millimeter-wave (mmW) radar with a monocular camera is a common way to recover three-dimensional information about the environment, but aligning the two is difficult because sparse radar point clouds and dense camera images differ sharply in how they sense a scene. The problem grows more severe in roadside infrastructure, where the high mounting elevation introduces perspective distortion that vehicle-mounted systems rarely face. This paper presents a systematic review, conducted under the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, of radar-camera extrinsic calibration for fixed roadside infrastructure, organizing existing work into a taxonomy that separates traditional two-stage pipelines from recent end-to-end learning frameworks. Because methods designed specifically for roadside units remain scarce, the review also covers vehicle- and robot-mounted methods whose static-sensor formulation carries over to fixed roadside deployment. For the two-stage pipeline, the analysis covers target-based and targetless correspondence registration along with the optimization techniques and algorithmic assumptions behind parameter estimation. The end-to-end learning literature shows a clear shift toward self-supervised and fusion-based models, some of which report real-time performance. The review also compares the metrics and procedures used to quantify calibration accuracy. Progress is evident, but robustness in cluttered urban environments remains an open challenge, and the paper closes by outlining future directions, arguing that standardized roadside benchmarks are needed before scalable, targetless calibration can mature. Full article

Autonomous ship maneuvering in harbor environments is increasingly supported by advances in model predictive control, reinforcement learning, digital twins, multi-sensor fusion, berth allocation, and multi-agent coordination. However, these developments are often studied as separate technological domains, while real harbor autonomy requires coordinated operation across vessels, port infrastructure, regulatory systems, cybersecurity mechanisms, and human supervisory processes. This study presents an architecture-oriented critical review of autonomous ship and harbor maneuvering research published between 2015 and May 2026. The review synthesizes literature from control engineering, maritime artificial intelligence, sensor fusion, digital twins, port logistics, cyber-physical systems, regulation, cybersecurity, and human–AI supervision. The analysis introduces two conceptual contributions: a layered cyber-physical taxonomy and an integration maturity model. The taxonomy organizes autonomous harbor maneuvering into seven interdependent layers: physical dynamics, perception and sensor fusion, prediction and state estimation, control, decision and coordination, digital twin federation, and regulatory–supervisory governance. The maturity model distinguishes isolated vessel autonomy, assisted coordination, shared digital synchronization, agent-based coordination, and fully federated maritime cyber-physical autonomy. The reviewed evidence shows substantial progress in individual layers, especially control, perception, digital twins, and berth allocation. However, major gaps remain in cross-layer synchronization, semantic interoperability, regulation-aware decision-making, cybersecurity integration, and validated ship–shore federation. To address these gaps, this study proposes a Federated Maritime Cyber-Physical Architecture for autonomous harbor maneuvering. The architecture integrates vessel autonomy cores, port intelligence cores, semantic federation middleware, agent-based negotiation, regulatory verification, cybersecurity safeguards, and human supervisory interfaces. This review argues that future progress in autonomous harbor operations depends not only on stronger algorithms, but on interoperable, explainable, regulation-aware, and cyber-resilient ship–shore ecosystems. Full article

Autonomous navigation of unmanned surface vehicles (USVs) in complex obstacle scenarios remains challenging due to redundant perception inputs, unstable value estimation, and inefficient policy convergence. To address these problems, this paper proposes LDA-D3QN, an improved deep reinforcement learning method for USV autonomous navigation. The proposed method constructs a compact navigation state representation by combining target-related information with local obstacle features, allowing the agent to retain key decision-making information while reducing unnecessary environmental redundancy. Based on this representation, an enhanced value-learning framework is developed to improve the stability of navigation decisions in cluttered environments. Moreover, a reward-guided and staged training strategy is introduced to help the agent gradually adapt to increasingly complex navigation tasks. The proposed method was evaluated on a Unity–ROS–MATLAB integrated simulation platform. Experimental results show that LDA-D3QN achieves superior overall navigation performance compared with several representative reinforcement learning algorithms. Specifically, the proposed method achieves a final training success rate of 91.4%, outperforming PPO (82.3%), Dueling DQN (78.5%), Double DQN (79.8%), and Rainbow DQN (86.5%). Additional tests in complex multi-obstacle and multi-target scenarios further demonstrate that the learned policy can generate safe, stable, and effective navigation behaviors. Preliminary validation using real-USV sensor data also confirms the feasibility of the LiDAR and GPS data processing procedures, providing a basis for future closed-loop autonomous navigation experiments and multi-sensor fusion deployment. Full article

Crack detection in mobile inspection scenarios is constrained by both the extremely slender geometry of crack targets and the real-time inference requirements on edge devices, which expose systematic limitations of general-purpose object detectors. This paper proposes YOLO-Crack, a closed-loop solution that couples geometry-statistics-driven module design with end-to-end edge deployment validation. On the algorithmic side, we first quantify crack geometric properties and then introduce (i) a crack-aware cross-dimensional fusion attention (CFCA) module to strengthen feature representations, (ii) a dual-path feature enhancement module (DFEM) to preserve fine details during upsampling, and (iii) an empirical smooth quality window adjustment with shape consistency regularization to stabilize bounding-box regression for slender cracks. Experiments on the Crack500 dataset show that YOLO-Crack achieves 78.8% precision, 51.4% recall, and 65.7% mAP@0.5, improving over the YOLOv11n baseline by 4.2, 1.7, and 2.9 percentage points, respectively. On the engineering side, we deploy YOLO-Crack on a Jetson Orin NX mobile robot platform and evaluate it in a real ROS pipeline; the measured end-to-end throughput reaches 25.5 FPS, meeting real-time video processing requirements. The proposed framework provides a practical reference workflow for edge vision tasks, from geometry analysis to engineering verification. Full article

To address the inherent limitations of the Dhole Optimization Algorithm (DOA)—limited exploration range, insufficient population diversity, and slow convergence—this paper proposes a Modified Dhole Optimization Algorithm (MDOA) integrating a Beta distribution-based opposition learning strategy, a DE/rand-to-best/1 differential mutation mechanism, and nonlinear parameter control. MDOA is evaluated on 41 CEC2017 and CEC2022 benchmark functions, outperforming 11 state-of-the-art algorithms in convergence speed, accuracy, and robustness. It is then applied to five engineering optimization problems: compression spring design, speed reducer weight minimization, rolling bearing optimization, tubular column design, and moisture content prediction of Dendrobium huoshanense using near-infrared spectroscopy with a BP neural network. The MDOA-BP model reduces MAE, RMSE, MSE, and MAPE by 27.5%, 27.8%, 47.6%, and 31.0%, respectively, while increasing $R^2$ from 0.8339 to 0.9130, achieving the best results among all comparison models. These results demonstrate that MDOA is a highly effective and robust optimizer for complex constrained engineering and high-dimensional optimization tasks. Full article

This study systematically investigates the hot deformation behavior of TC18 alloy under the conditions of deformation temperatures of 720–840 °C and strain rates of 0.001–1 s⁻¹. Based on the stress–strain data obtained under the aforementioned process parameters, a support vector regression (SVR) model was established and further optimized by using a Stacking algorithm to enhance predictive accuracy. Although SVR and Stacking techniques have been applied previously in material constitutive modeling, this paper presents a systematic optimization framework specifically for TC18, integrating comprehensive experimental data, kernel selection, hyperparameter tuning, and Stacking-based model fusion. The polynomial kernel function was identified as optimal, and hyperparameters were tuned via grid search combined with five-fold cross-validation, which is determined as {C = 1000, coef0 = 1, d = 5, ε = 1, γ = 1}. The Stacking-SVR model exhibits significantly improved fitting and generalization performance compared to Poly-SVR, Arrhenius, XGBoost and MLP, with RMSE, MAPE, and R² metrics of 2.7882, 0.0110, and 0.9973 on the training set, and 2.7956, 0.0169, and 0.9982 on the test set, respectively. Additionally, the proportion of samples with relative errors within 5% reaches 98.7% for the training set and 94.83% for the test set. These results indicate that the proposed framework not only possesses extremely high predictive accuracy, but also ensures strong generalization ability and interpretability in practical applications. Full article