Search Results (478)

With the continuous expansion of maritime trade scale, ports have put forward increasingly higher requirements for transshipment efficiency. Container twist lock disassembly is a key link in the loading and unloading process, and its automation level has a significant impact on the ship’s berthing time at the port. Aiming at the demand of automated disassembly for high-precision 3D vision, this paper proposes a multi-view point cloud local registration method for twist lock recognition. First, Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) is used to extract the keyhole region with the highest overlap in multi-view point clouds, reducing the interference from non-overlapping structures. Then, a two-stage strategy of “coarse registration + fine registration” is adopted: initial alignment is achieved through Random Sample Consensus (RANSAC), and the Iterative Closest Point (ICP) algorithm is improved by combining adaptive distance threshold and normal consistency constraint to complete fine registration. Experimental results show that the proposed method outperforms the global registration scheme in both accuracy and efficiency: the Root Mean Square Error (RMSE) is reduced to 2.15 mm, the Relative Mean Distance (RMD) is reduced to 1.81 mm, and the registration time is approximately 2.41 s. Compared with global registration, the efficiency is improved by 44.2%, which can meet the real-time requirements of continuous operation at automated terminals for the perception link and the time constraints for subsequent manipulator control. The research results preliminarily verify the application potential of this method in the scenario of automated twist lock disassembly. Full article

Three-dimensional (3D) reconstruction technology has found widespread applications across various domains, including intelligent driving and underwater exploration. But the existing imaging systems and methods still have deficiencies in terms of reconstruction accuracy, detection distance and system volume. Herein, this paper presents a three-dimensional detection and reconstruction method based on a compact Risley-prism 3D imaging system that achieves multi-viewpoint imaging by rotating the Risley prism to adjust the camera’s optical axis. A refractive camera model that integrates the pinhole camera model with the vector form of Snell’s law is established to precisely describe beam trajectory. A forward projection method suitable for refractive interfaces is developed based on Fermat’s principle, and the influence of systematic errors on the reconstruction is analyzed in detail through simulation. Furthermore, a new 3D reconstruction method combining error calibration based on the optimization iteration is introduced to avoid the influence of error and improve reconstruction quality. Experimental results demonstrate that the proposed approach markedly enhances 3D reconstruction accuracy, reducing the Normalized Root Mean Square Error (NRMSE) from 0.9076 to 0.0207. Full article

Wireless Sensor Networks (WSNs) commonly employ clustering to improve scalability and energy efficiency; however, cluster heads (CHs) located near the base station (BS) often suffer from excessive relay traffic, leading to rapid energy depletion and reduced network lifetime. This article proposes an Energy-Efficient Distance-Controlled Clustering (EEDC) scheme that adjusts CH density and transmission power according to each node’s distance from the BS. In EEDC, a higher number of CHs is deployed near the BS to balance forwarding loads, while fewer CHs are selected in distant regions to conserve energy. Additionally, CHs adapt their transmission power to enable distance-proportional communication. A mathematical model is developed to analyze the relationship between CH distribution, transmission power, and overall energy consumption. Performance evaluation is conducted through simulations and compared with LEACH, HEED, DEEC, SEP, and EECS. The results show that EEDC improves the stability period by up to 42%, extends network lifetime by 23%, increases average residual energy by 13–29%, enhances throughput by 16–44%, and achieves 23–61% higher packet delivery efficiency. Moreover, cumulative CH energy consumption is reduced by 5–21%, leading to more balanced energy distribution. These findings indicate that distance-controlled CH selection and adaptive transmission power effectively alleviate the BS energy bottleneck and enhance the energy efficiency and operational longevity of clustered WSNs. Full article

High-dimensional mixed data often lack a unified semantic representation for continuous and discrete attributes, which hinders mixed-attribute similarity modeling and can result in unstable reducts and overfitting in existing neighborhood rough set (NRS) methods. To address this issue, we propose IF-EMD-SPA, an attribute reduction method for NRS grounded in Information Flow theory. Unlike conventional NRS methods that rely on discretization or a single reduction criterion, IF-EMD-SPA first establishes a unified representation framework for heterogeneous attributes based on classifications and an Information Channel Core. It then integrates Earth Mover’s Distance (EMD) and Set Pair Analysis (SPA) to define a similarity metric for mixed attributes. In addition, a three-stage greedy reduction strategy is designed under the dual constraints of dependency preservation and structural error, consisting of dependency-driven forward selection, similarity-driven structure completion, and backward redundancy removal. Experiments on five UCI benchmark datasets and two high-dimensional gene expression datasets show that IF-EMD-SPA achieves average accuracies of 93.5% (k-Nearest Neighbors, KNN), 93.9% (Support Vector Machine, SVM), and 90.8% (Classification and Regression Trees, CART), with SVM achieving the best results on all seven datasets. Under CART, it reaches 100% accuracy on Wine and WPBC, improving performance by up to 37.5 percentage points over comparison methods. Full article

Achieving stable bipedal locomotion for humanoid robots remains a central challenge in reinforcement learning (RL), in which the design of reward functions is pivotal but non-trivial. This paper proposes a three-tier statistical reward shaping framework to optimize bipedal gait learning. First, training outcomes are diagnostically monitored using forward distance, fall rate, and posture score. Pearson correlation and regression analyses are then employed to identify trade-offs and isolate the direct effects of reward components. Finally, targeted parameter sweeps enable directionally guided optimization, substantially reducing heuristic parameter tuning while refining a reward function for the H1 robot in Isaac Lab. Experimental results demonstrate clear improvements over the baseline. The optimized policy reduces convergence time by 14% and increases forward distance by 186%. Stability is markedly enhanced, with fall rate decreasing from 75% to 2% and active locomotion efficiency nearly doubling (0.339 to 0.678). These results validate a reproducible, data-driven framework for reward design, highlighting the importance of principled statistical analysis in complex RL-based humanoid locomotion. Full article

Mobile ad hoc networks (MANETs) are highly vulnerable to denial-of-service (DoS) attacks because their decentralized operation, rapidly changing topology, and constrained node resources limit the use of heavyweight security mechanisms. This paper presents an Adaptive Clustering and Random-Forest-based Intrusion Detection System (ACRF-IDS), a lightweight intrusion detection framework that combines mobility-aware adaptive clustering with supervised learning to detect network-layer DoS behaviors. Cluster heads are elected using a multi-metric utility (residual energy, link stability, and mobility) to stabilize observations under node movement. Within fixed monitoring windows, cluster heads aggregate routing-, forwarding-, and energy-related features and classify nodes using a Random Forest model; a temporal voting scheme further suppresses transient mobility-induced alarms. Using ns-2.35 simulations with Ad hoc On-Demand Distance Vector (AODV) and both flooding and blackhole DoS scenarios, ACRF-IDS is compared with (i) a static clustering-based threshold IDS, (ii) a non-clustered Support Vector Machine (SVM)-based IDS, and (iii) AIFAODV, which specializes in flooding. Across the evaluated network sizes (4–50 nodes), the proposed method achieves a higher detection rate and F1-score while maintaining a lower false positive rate than the baseline techniques. We additionally quantify network-level impact using PDR, throughput, and routing overhead, showing that ACRF-IDS improves availability under DoS while adding bounded overhead. Future work will extend the evaluation to more diverse attack behaviors and validate the approach in real-world MANET testbeds. Full article

Vehicle networking is a new paradigm in wireless technology that facilitates communication between vehicles in close proximity and in-vehicle internet access. This technology paves the way for a variety of safety, convenience and entertainment applications, including safety message exchange, real-time traffic information sharing and public internet access. The overall goal of vehicular networks is to create an efficient, safe and convenient environment for vehicles on the road. This paper presents a Sensitive Node Election (SNE) algorithm adapted to routing protocols in certain opportunistic network environments. The algorithm focuses on selecting the best agent for communication using an innovative approach for message forwarding. Quality of Service (QoS) metrics targeted for optimization include network end-to-end throughput and packet delivery, with the aim of improving the overall performance of the network. Our algorithm includes a stochastic rebroadcasting scheme that takes into account parameters, such as vehicle density, distance between vehicles and transmission distance, and adapts to various network conditions. Furthermore, the SNE algorithm uses a metric based on transmission distance and can dynamically adapt to application requirements, such as prioritization. It provides high throughput and minimizes delay. The results demonstrate the effectiveness of this approach in improving QoS in various vehicular ad hoc network (VANET) simulations and influencing the neural network ensemble (NNE Algorithm). Full article

Remotely operated vehicles (ROVs) equipped with multibeam forward-looking sonar are widely used for underwater object search in environments where visibility is limited. Ensuring complete three-dimensional (3D) scan coverage within a bounded mission duration remains a challenging planning problem due to sonar beam geometry and vehicle motion constraints. This study presents a deterministic, geometry-driven framework for volumetric path planning of ROV-based forward-looking sonar scanning in predefined circular and rectangular underwater volumes. The proposed approach constructs layered planar scan trajectories by explicitly incorporating sonar detection range, horizontal and vertical beamwidths, and scan volume geometry. Mission duration is analytically estimated from path length and vehicle kinematic parameters, enabling systematic comparison among multiple planning strategies. To support qualitative interpretation of scan effectiveness, a distance-based target position certainty metric is introduced and combined with the active sonar equation to estimate likely target locations within the scanned volume. Simulation results under idealized sensing and motion assumptions demonstrate that the corrected zigzag pattern for rectangular scan areas, as well as the corrected zigzag-II and corrected arithmetic spiral-III patterns for circular scan areas, achieve complete volumetric coverage with bounded mission duration and consistent localization performance. The proposed framework provides a transparent analytical baseline for evaluating volumetric scan path planning strategies for forward-looking sonar–equipped ROVs. Full article

Capacitive Power Transfer (CPT) technology, as an emerging wireless power supply solution, exhibits great potential in areas such as electric vehicle charging, underwater equipment power supply, biomedical implants, and consumer electronics due to its advantages of low cost, light weight, insensitivity to metals, and potential high power density. However, the coupling capacitance is susceptible to the influence of transmission distance, misalignment, and changes in environmental media, leading to fluctuations in system output characteristics and becoming a key challenge restricting its application. This report aims to systematically review the key technological advancements proposed in recent years to achieve constant voltage/current/power output and enhance system robustness. Firstly, this study categorically reviews the CPT system topologies for constant voltage output, constant current output, and constant power output, analyzing the principles, advantages, and disadvantages of achieving load-independent or coupling-independent output. Secondly, it sorts out various active and passive control strategies, including frequency regulation, impedance matching, adaptive parameter switching, and pulse modulation, which are used to manage dynamic changes. Next, it summarizes innovative design and optimization methods for couplers tailored to specific application scenarios, such as large-gap electric vehicle charging, underwater, and rotating mechanisms. Finally, based on existing research, this review describes the challenges that CPT technology still faces in achieving efficient, high-power, and highly robust constant output, and looks forward to future research directions. Full article

This paper introduces RLFS-OR, a reinforcement learning-based opportunistic routing protocol designed for energy-constrained and duty-cycled wireless sensor networks (WSNs). Unlike traditional opportunistic routing, which either relies on static metrics or requires nodes to remain continuously active, RLFS-OR integrates a Deep Q-Network (DQN) to dynamically select the most energy-efficient forwarder based on residual energy, hop distance, wake-up timing, and link quality. A realistic Castalia-derived radio model is incorporated, accounting for transmission, reception, idle listening, and path loss-dependent energy consumption. Through coordinated learning and asynchronous duty-cycle integration, RLFS-OR minimizes overhearing and unnecessary wake-ups. Simulation results demonstrate that RLFS-OR significantly outperforms two established protocols—ORW and FCM-OR—achieving 10–30% lower energy consumption and 10–45% longer network lifetime under diverse network densities and traffic loads. RLFS-OR also provides smoother node-death dynamics and optimal performance at low duty cycles. The findings confirm RLFS-OR as an efficient and scalable solution for long-lived WSN deployments. Full article

Electrical Resistivity Tomography (ERT) has proven to be a highly sensitive geophysical method for characterizing the dynamics of seawater intrusion. This study uses tank experiments to simulate seawater intrusion, utilizing electrical resistivity tomography to monitor real-time changes in groundwater resistivity during the intrusion process. The objective is to quantitatively reveal the development and evolution mechanisms of seawater intrusion wedges in sandy aquifers, thereby establishing a real-time resistivity monitoring method for groundwater distribution and migration characteristics. This study improves resistivity imaging data processing methods, enhancing both efficiency and accuracy. The refined cross-hole ERT technique is applicable not only to meter-scale indoor experiments; its optimized forward and inverse algorithms can also be directly transferred to regional-scale field monitoring. Experimental results show that the average resistivity in the study area continuously decreases from 57 Ω·m in the initial freshwater state to 1.1 Ω·m at the intrusion stabilization point. Areas with resistivity values below 20 Ω·m corresponded exactly to the brine intrusion zone. The evolution of the freshwater-saltwater interface unfolded in three stages: Initially, the density difference (0.025 g/cm³) dominated, with the saltwater intrusion depth at the aquifer base reaching 0.45 m, significantly exceeding the 0.04 m penetration at the upper section. During the intermediate stage, the interface morphology differentiated into an “upper triangular, lower arc-shaped” configuration. The bottom intrusion distance increased to 1.65 m, and the thickness of the brackish-freshwater mixing zone expanded from 0.1 m to 0.3 m. In the final stage, the interface stabilized and began intruding toward the surface, establishing a new hydrodynamic equilibrium. In addition, the migration rate of saline water at the aquifer base gradually decreased from 6.25 × 10⁻⁴ cm/s initially to 1.16 × 10⁻⁵ cm/s at steady state. These results reflect the dynamic coupling process between seepage and dispersion and demonstrate that this method enables effective real-time monitoring of seawater intrusion development and conditions, as well as early warning capabilities. Full article

To address critical limitations in conventional forward collision warning (FCW) systems including inadequate road condition detection accuracy, significant warning area prediction errors, and poor environmental adaptability on wet/snow-covered roads, this study develops an adaptive collision warning framework based on real-time road slippery states recognition. An enhanced ED-ResNet50 model is proposed, incorporating grouped convolutions within the backbone network and embedding ECA attention mechanisms after the second/third residual blocks alongside DDS-DA modules after the fourth block, significantly improving discriminative capability for pavement texture analysis under adverse conditions. This vision-based recognition system synchronizes with YOLOv8 for preceding vehicle detection, enabling the construction of a friction-sensitive safety distance and the time-to-collision model that dynamically calibrates warning thresholds according to instantaneous vehicle velocity and road adhesion coefficients. Real-vehicle validation demonstrates an 8.76% improvement in overall warning accuracy and 7.29% reduction in lateral and early false alarm rates compared to static-threshold systems, confirming practical efficacy for safety assurance in inclement weather. Full article

Addressing the pressing need to extend the communication range of RF RFID tag antennas, this paper introduces a novel UHF RFID tag antenna technology based on resonant superstrate regulation using a Split-Ring Resonator (SRR). First, a finite element model of the UHF RFID folded dipole antenna was constructed based on the tag chip’s port impedance. Subsequently, a Two-element SRR resonant superstrate was employed to enhance the dipole antenna’s gain through “resonance and near-field coupling” technology. A folded dipole antenna gain-enhancing SRR resonant superstrate unit was designed, and a multi-parameter joint optimization method was adopted to obtain the optimal SRR resonant superstrate configuration for regulating the dipole antenna. Near-field coupling technology was used to design SRR resonant superstrate elements that enhance the folded dipole antenna’s gain. A multi-parameter joint optimization method was employed to obtain the optimal structural parameter set for the SRR resonant superstrate-controlled dipole antenna. Finally, simulations and experimental measurements of the RFID antenna performance revealed that: within the 920–925 MHz band, the maximum measured forward reading distance enhancement reached 62.1%. The research findings significantly enhance the practical performance of UHF RFID tags in complex environments, enabling more stable and efficient long-range identification in applications such as logistics tracking, asset management, and smart warehousing. Full article

Stress evolution during overburden stabilization in non-pillar mining with roof-cutting and roadway formation (NMRRF) in inclined coal seams is highly complex due to the combined influence of seam dip angle and mining method. This study investigates the spatial stress evolution and structural stability of the overburden through numerical simulation and theoretical analysis. Results indicate that along the strike direction, the peak abutment pressure ahead of the working face decreases from the lower to the upper sections. As mining advances, the peak in the lower section shifts significantly forward, whereas changes in the middle and upper sections remain minimal. After advancing 150 m, upward expansion of the pressure-relief zone ceases, with the relief height in the lower goaf being smaller than that in the upper region. Along the dip direction, a pressure-relief zone forms in the roof and floor after 30 m of advancement, while stress concentration zones develop in the coal on both sides. With continued mining, the highest point of the pressure-relief zone gradually deviates from the central axis toward the upper section and eventually stabilizes within deeper strata at a certain distance from the axis. By 150 m of advancement, the relief zone peaks in the upper-middle section of the working face, and the height of the caved zone in the upper goaf exceeds that in the middle and lower parts. An asymmetric “inverted J-shaped” stress shell forms along the working face centerline, evolving into an overall asymmetric stress shell with its apex located in the upper goaf. A mechanical model of the overburden structure is established, yielding an expression for the three-dimensional stress shell morphology. Based on the stability mechanism of overburden movement and the failure modes of key block structures, support strategies for the mining face are proposed. The findings provide theoretical insights for non-pillar mining under similar geological conditions. Full article

The growing interest in precision agriculture has led, in recent years, to an increase in the adoption of Internet of Things (IoT) technologies in the service of smart agriculture to optimize agricultural production processes through the monitoring of environmental conditions and prevent food loss. This work stems from research conducted as part of the Tech4You project, where the enabling digital technologies developed in Spoke 6 contribute to the advanced solutions envisaged by Spoke 3 to facilitate the transition to a sustainable agrifood system. In particular, we present the design and evaluation of a multi-hop Device-to-Device (D2D) communication architecture that leverages Long Range (LoRa) technology, specifically designed for monitoring vineyards in the context of passito wine production. The proposed framework addresses the challenge of monitoring mobile containers for grapes during the drying phase, a critical stage in which inadequate temperatures and humidity can promote the growth of fungi and the formation of mycotoxins. The integration of simulation-based performance evaluation with a multi-layer system architecture is presented in this work. The objective is to compare the performance of different routing strategies in choosing data forwarding paths to the gateway. The simulation results show that the proposed routing strategy, which is based on learning but also focuses on energy consumption, offers good performance. In particular, it achieves packet delivery rates of over $92\%$ and preserves over $95\%$ of active nodes after 2 h of operation. Energy-aware routing strategies also perform well compared to those that only consider the distance from the destination, but overall, the proposed strategy achieves a better trade-off on the metrics analyzed. Full article