Search Results (603)

Edge detection of space targets is vital in aerospace applications, such as satellite monitoring and analysis, yet it faces challenges due to diverse target shapes and complex backgrounds. While deep learning-based edge detection methods dominate due to their powerful feature representation capabilities, they often suffer from large parameter sizes and lack explicit geometric prior constraints for space targets. This paper proposes a novel edge detection method for satellite targets based on knowledge distillation, namely STED-KD. Firstly, a multi-stage distillation strategy is proposed to guide a lightweight, fully convolutional network with fewer parameters to learn key features and decision boundaries from a complex teacher model, achieving model efficiency. Next, a shape prior guidance module is integrated into the student branch, incorporating geometric shape information through shape prior model construction, similarity metric calculation, and feature reconstruction, enhancing adaptability to space targets and improving detection accuracy. Additionally, a curvature-guided edge loss function is designed to ensure continuous and complete edges, minimizing local discontinuities. Experimental results on the UESD space target dataset demonstrate superior performance, with ODS, OIS, and AP scores of 0.659, 0.715, and 0.596, respectively. On the BSDS500, STED-KD achieves ODS, OIS, and AP scores of 0.818, 0.829, and 0.850, respectively, demonstrating strong competitiveness and further confirming its stability. Full article

This work introduces a comprehensive vision-based framework for autonomous space debris removal using robotic manipulators. A real-time debris detection module is built upon the YOLOv8 architecture, ensuring reliable target localization under varying illumination and occlusion conditions. Following detection, object motion states are estimated through a calibrated binocular vision system coupled with a physics-based collision model. Smooth interception trajectories are generated via a particle swarm optimization strategy integrated with a 5–5–5 polynomial interpolation scheme, enabling continuous and time-optimal end-effector motions. To anticipate future arm movements, a Transformer-based sequence predictor is enhanced by replacing conventional multilayer perceptrons with Kolmogorov–Arnold networks (KANs), improving both parameter efficiency and interpretability. In practice, the Transformer+KAN model compensates the manipulator’s trajectory planner to adapt to more complex scenarios. Each component is then evaluated separately in simulation, demonstrating stable tracking performance, precise trajectory execution, and robust motion prediction for intelligent on-orbit servicing. Full article

Global navigation satellite systems (GNSSs) are an integral part of modern society and are used in various industries, providing users with positioning, navigation, and timing (PNT). However, their effectiveness is vulnerable to signal interference, since GNSSs are based on received satellite signals from space, and that can severely impact applications that rely on continuous and accurate data. Interference can pose significant risks to sectors dependent on GNSSs, including transportation, telecommunications, finance, geodesy, and others. For this reason, in parallel with the development of GNSSs, various interference protection techniques are being developed to enable users to receive GNSS signals without the risk of interference, which can cause various effects, such as reducing the accuracy of positioning, as well as completely blocking signal reception and making it impossible to obtain positioning. There are various sources and methods of interfering with GNSS signals, and the greatest consequences are caused by intentional interference, which includes jamming, spoofing, and meaconing. This study investigates the effects of jamming devices on static GNSS observations using high-accuracy devices through multiple controlled experiments using both single-frequency (SF) and multi-frequency (MF) jammers. The aim was to identify the distances within which signal interference devices disrupt GNSS signal reception and position accuracy. The research conducted herein was divided into several phases where zones within which the jammer completely blocked the reception of the GNSS signal were determined (blackout zones), as were zones within which it was possible to obtain the position (but the influence of the jammer was present) and the influence of the jammer from different directions/azimuths in relation to the GNSS receiver. Various statistical indicators of the jammer’s influence, such as DOP (dilution of precision), SNR (signal-to-noise-ratio), RMS (root mean square), and others, were obtained through research. The results of this study indicate that commercially available, low-cost jamming devices, when operated within manufacturer-specified distances, completely disrupt the reception of GNSS signals. Their impact is also evident at greater distances, where they significantly reduce SNR values, increase DOP, and decrease the number of visible satellites, leading to reduced measurement reliability and integrity. These results underline the necessity of developing effective protection mechanisms against GNSS interference and strategies to ensure reliable signal reception in GNSS-dependent applications, particularly as the use of jamming devices becomes more prevalent. Full article

High-dynamic airborne gravimetry faces critical challenges from platform-induced noise contamination. Conventional filtering methods exhibit inherent limitations in simultaneously achieving dynamic tracking capability and spectral fidelity. To overcome these constraints, this study proposes a Kalman–FIR fusion filtering (K-F) method, which is validated through engineering implementation on the GIPS-1A airborne gravimeter platform. The proposed framework employs a dual-stage strategy: (1) An adaptive state-space framework employing calibration coefficients (S_x, S_y, S_z) continuously estimates triaxial acceleration errors to compensate for gravity anomaly signals. This approach resolves aliasing artifacts induced by non-stationary noise while preserving low-frequency gravity components that are traditionally attenuated by conventional FIR filters. (2) A window-optimized FIR post-filter explicitly regulates cutoff frequencies to ensure spectral compatibility with downstream processing workflows, including terrain correction. Flight experiments demonstrate that the K-F method achieves a repeat-line internal consistency of 0.558 mGal at 0.01 Hz—a 65.3% accuracy improvement over standalone FIR filtering (1.606 mGal at 0.01 Hz). Concurrently, it enhances spatial resolution to 2.5 km (half-wavelength), enabling the recovery of data segments corrupted by airflow disturbances that were previously unusable. Implemented on the GIPS-1A system, K-F enables precision mineral exploration and establishes a noise-suppressed paradigm for extreme-dynamic gravimetry. Full article

The energy management strategy of Hybrid Electric Vehicles (HEVs) plays a key role in improving fuel economy and reducing battery energy consumption. This paper proposes a Deep Reinforcement Learning-based energy management strategy optimized by the experience pool (P-HER-DDPG), aimed at improving the fuel efficiency of HEVs while accelerating the training speed. The method integrates the mechanisms of Prioritized Experience Replay (PER) and Hindsight Experience Replay (HER) to address the reward sparsity and slow convergence issues faced by the traditional Deep Deterministic Policy Gradient (DDPG) algorithm when handling continuous action spaces. Under various standard driving cycles, the P-HER-DDPG strategy outperforms the traditional DDPG strategy, achieving an average fuel economy improvement of 5.85%, with a maximum increase of 8.69%. Compared to the DQN strategy, it achieves an average improvement of 12.84%. In terms of training convergence, the P-HER-DDPG strategy converges in 140 episodes, 17.65% faster than DDPG and 24.32% faster than DQN. Additionally, the strategy demonstrates more stable State of Charge (SOC) control, effectively mitigating the risks of battery overcharging and deep discharging. Simulation results show that P-HER-DDPG can enhance fuel economy and training efficiency, offering an extended solution in the field of energy management strategies. Full article

Against the backdrop of growing concerns over university students’ mental health worldwide, campus environments play a crucial role not only in shaping spatial experiences but also in influencing psychological well-being. However, the psychosocial mechanisms through which campus landscapes affect well-being remain insufficiently theorized. Drawing on survey data from 500 students across two Chinese universities, this study employs structural equation modeling (SEM) and interpretable machine learning techniques (XGBoost-SHAP) to systematically examine the interrelations among landscape perception, place attachment, perceived social acceptance, school belonging, and psychological well-being. The results reveal the following: (1) campus landscapes serve as the primary catalyst for fostering emotional identification (place attachment) and social connectedness (perceived social acceptance and school belonging), thereby indirectly influencing psychological well-being through these psychosocial pathways; (2) landscape perception emerges as the strongest predictor of well-being, followed by school belonging. Although behavioral variables such as the green space maintenance quality, visit frequency, and duration of stay contribute consistently, their predictive power remains comparatively limited; (3) significant nonlinear associations are observed between core variables and well-being. While the positive effects of landscape perception, place attachment, and school belonging exhibit diminishing returns beyond certain thresholds, high levels of perceived social acceptance continue to generate sustained improvements in well-being. This study advances environmental psychology by highlighting the central role of campus landscapes in promoting mental health and provides actionable strategies for campus planning. It advocates for the design of balanced, diverse, and socially engaging landscape environments to maximize psychological benefits. Full article

As electric vehicles (EVs) gain widespread adoption in industrial environments supported by Industrial Internet of Things (IIoT) smart grids technology, coordinated charging of multiple EVs has become vital for maintaining grid stability. In response to the scalability challenges faced by traditional algorithms in multi-device environments and the limitations of discrete action spaces in continuous control scenarios, this paper proposes a dynamic charging scheduling algorithm for EVs based on Multi-Agent Deep Deterministic Policy Gradient (MADDPG). The algorithm combines real-time electricity prices, battery status monitoring, and distributed sensor data to dynamically optimize charging and discharging strategies of multiple EVs in continuous action spaces. The goal is to reduce charging costs and balance grid load through coordinated multi-agent learning. Experimental results show that, compared with baseline methods, the proposed MADDPG algorithm achieves a 41.12% cost reduction over a 30-day evaluation period. Additionally, it effectively adapts to price fluctuations and user demand changes through Vehicle-to-Grid technology, optimizing charging time allocation and enhancing grid stability. Full article

Under the advancing urban–rural integration strategy, last-mile logistics, and their spatial accessibility, have become key indicators for measuring regional coordination. Focusing on Guangzhou as the case study area, this study constructs an urban–rural spatial accessibility assessment model integrating multimodal convolutional neural networks and Graph Neural Networks (GNN) to systematically examine the evolving accessibility patterns in last-mile logistics distribution across urban and rural spaces. The study finds that Guangzhou’s urban space continues to expand while rural space gradually decreases during this period, showing an overall development trend from centralized single-core to multi-polar networked patterns. The spatial accessibility of last-mile logistics in Guangzhou exhibits higher levels in urban core areas and lower levels in peripheral rural areas, but the overall accessibility is progressively expanding and improving in outlying regions. These accessibility changes not only reflect the optimization path of logistics infrastructure but also reveal the practical progress of urban–rural integration development. Through spatial distribution analysis and dynamic simulation of logistics networks, this study establishes a novel explanatory framework for understanding the spatial mechanisms of urban–rural integration. The findings provide decision-making support for optimizing last-mile logistics network layouts while offering both theoretical foundations and practical approaches for promoting co-construction and sharing of urban–rural infrastructure and achieving integrated regional spatial governance. Full article

Background: Traditional molecular optimization methods struggle with high data dependency and significant computational demands. Additionally, conventional genetic algorithms often produce solutions with high similarity, leading to potential local optima and reduced molecular diversity, thereby limiting the exploration of chemical space. Methods: In order to address the above issues, this paper proposes an improved genetic algorithm for multi-objective drug molecular optimization (MoGA-TA). It uses the Tanimoto similarity-based crowding distance calculation and a dynamic acceptance probability population update strategy. The study employs a decoupled crossover and mutation strategy within chemical space for molecular optimization. The proposed crowding distance calculation method better captures molecular structural differences, enhancing search space exploration, maintaining population diversity, and preventing premature convergence. The dynamic acceptance probability strategy balances exploration and exploitation during evolution. Optimization continues until a predefined stopping condition is met. To assess MoGA-TA’s effectiveness, the algorithm is evaluated using metrics like success rate, dominating hypervolume, geometric mean, and internal similarity. Results: Experimental results show that compared to the comparative method, MoGA-TA performs better in drug molecule optimization and significantly improves the efficiency and success rate. Conclusions: The method described in this paper has been proven to be an effective and reliable method for multi-objective molecular optimization tasks. Full article

In complex urban wireless environments, unmanned aerial vehicle–mobile edge computing (UAV-MEC) systems face challenges like link blockage and single-antenna eavesdropping threats. The traditional single reconfigurable intelligent surface (RIS), limited in collaboration, struggles to address these issues. This paper proposes a double-RIS cooperative UAV-MEC optimization scheme, leveraging their joint reflection to build multi-dimensional signal paths, boosting legitimate link gains while suppressing eavesdropping channels. It considers double-RIS phase shifts, ground user (GU) transmission power, UAV trajectories, resource allocation, and receiving beamforming, aiming to maximize secure energy efficiency (EE) while ensuring long-term stability of GU and UAV task queues. Given random task arrivals and high-dimensional variable coupling, a dynamic model integrating queue stability and secure transmission constraints is built using Lyapunov optimization, transforming long-term stochastic optimization into slot-by-slot deterministic decisions via the drift-plus-penalty method. To handle high-dimensional continuous spaces, an end-to-end proximal policy optimization (PPO) framework is designed for online learning of multi-dimensional resource allocation and direct acquisition of joint optimization strategies. Simulation results show that compared with benchmark schemes (e.g., single RIS, non-cooperative double RIS) and reinforcement learning algorithms (e.g., advantage actor–critic (A2C), deep deterministic policy gradient (DDPG), deep Q-network (DQN)), the proposed scheme achieves significant improvements in secure EE and queue stability, with faster convergence and better optimization effects, fully verifying its superiority and robustness in complex scenarios. Full article

This study explores the application of modular design in the regeneration of community public spaces within rapidly transforming urban environments, using Haikou as a case study. The objective is to improve spatial quality and community sustainability while preserving cultural identity and community engagement. Through a mixed-methods approach involving questionnaires, GIS-based spatial analysis, and case studies, the research identifies key challenges such as fragmented layouts, limited accessibility, and insufficient green space. In response, a “policy–design–community” integration mechanism is proposed to guide bottom-up and top-down coordination. A multidimensional evaluation framework is developed to assess the effectiveness of modular interventions across functional, spatial, and cultural dimensions. The findings suggest that modular design—owing to its standardization and flexibility—enhances spatial adaptability and construction efficiency, and strengthens cultural identity and community engagement. This research provides a replicable and data-informed strategy for the renewal of public spaces in Chinese urban environments. Full article

This paper introduces a novel strategy for the diagnosis and fault-tolerant control (FTC) of inter-turn short-circuit (ITSC) faults in the stator windings of Doubly Fed Induction Generator (DFIG)-based wind turbines. ITSC faults are among the most common electrical issues in rotating machines: early detection is therefore essential to reduce maintenance costs and prevent severe damage to the wind turbine system. To address this, a Fault Detection and Diagnosis (FDD) approach is proposed to identify and assess the severity of ITSC faults in the stator windings. A state-space model of the DFIG under ITSC fault conditions is first developed in the (d,q) reference frame. Based on this model, an Unknown Input Observer (UIO) structured using Takagi–Sugeno (T-S) fuzzy models is designed to estimate the fault level. To mitigate the impact of the fault and ensure continued operation under degraded conditions, a T-S fuzzy fault-tolerant controller is synthesized. This controller enables natural decoupling and optimal power extraction across a wide range of rotor speed variations. Since the effectiveness of the FTC relies on accurate fault information, a Proportional-Integral Observer (PIO) is employed to estimate the ITSC fault level. The proposed diagnosis and compensation strategy is validated through simulations performed on a 3 kW wind turbine system, demonstrating its efficiency and robustness. Full article

The recently proposed concept of “precursory fingerprint” is a logical consequence of the commonsense statement that seismic structures are unique and that their expected preshock behaviors, including precursory phenomena, are also unique. Our new prediction-related research strategy is conceptually based on the principles of (1) the uniqueness of seismogenic structures, (2) interconnected and interacting geospheres, and (3) non-equivalence of Earth’s surface spots in terms of precursory signal receptivity. The precursory fingerprint of a given seismic structure is a unique assemblage of precursory signals of various natures (seismic, physical, chemical, and biological), detectable in principle by using a system of proper monitoring equipment that consists of a matrix of n sensors placed on the ground at “sensitive” spots identified beforehand and on orbiting satellites. In principle, it is composed of a combination of signals that are emitted by the “responsive sensors”, in addition to the “non-responsive sensors”, coming from the sensor matrix, monitoring as many virtual precursory processes as possible by continuously measuring their relevant parameters. Each measured parameter has a pre-established (by experts) threshold value and an uncertainty interval, discriminating between background and anomalous values that are visualized similarly to traffic light signals (green, yellow, and red). The precursory fingerprint can thus be viewed as a particular configuration of “precursory signals” consisting of anomalous parameter values that are unique and characteristic to the targeted seismogenic structure. Presumably, it is a complex entity that consists of pattern, space, and time components. The “pattern component” is a particular arrangement of the responsive sensors on the master board of the monitoring system yielding anomalous parameter value signals, that can be re-arranged, after a series of experiments, in a spontaneously understandable new pattern. The “space component” is a map position configuration of the signal-detecting sensors, whereas the “time component” is a characteristic time sequence of the anomalous signals including the order, occurrence time before the event, transition time between yellow and red signals, etc. Artificial intelligence using pattern-recognition algorithms can be used to follow, evaluate, and validate the precursory signal assemblage and, finally, to judge, together with an expert board of human operators, its “precursory fingerprint” relevance. Signal interpretation limitations and uncertainties related to dependencies on sensor sensibility, focal depth, and magnitude can be established by completing all three phases (i.e., experimental, validation, and implementation) of the precursory fingerprint-based earthquake prediction research strategy. Full article

To improve path planning performance for mobile robots in complex environments, this study proposes a hybrid method combining an improved jump point search (JPS) algorithm with the dynamic window approach (DWA). In global planning, a quadrant pruning strategy guided by the target direction and a sine-enhanced heuristic function reduces the search space and accelerates planning. Natural jump points are retained for path continuity, and the path is smoothed using cubic B-spline curves. In local planning, DWA is enhanced by incorporating a target orientation factor, a safety distance penalty, and a normalization mechanism into the cost function. An adaptive weighting strategy dynamically balances goal-directed motion and obstacle avoidance. Simulation experiments in static and complex environments with unknown and dynamic obstacles demonstrate the method’s effectiveness. Compared to the standard approach, the improved JPS reduces search time by 36.7% and node expansions by 60.9%, with similar path lengths. When integrated with DWA, the robot adapts effectively to changing obstacles, ensuring safe and efficient navigation. The proposed method significantly enhances the real-time performance and safety of path planning in dynamic and uncertain environments. Full article

This study investigates the scheduling problem of return communication tasks for unmanned aerial vehicle (UAV) swarms, where disaster relief environmental global positioning is hampered. To characterize the utility of these tasks and optimize scheduling decisions, we developed a time window-constrained scheduling model that operates under constraints, including communication base station time windows, battery levels, and task uniqueness. To solve the above model, we propose an enhanced algorithm through integrating Dueling Deep Q-Network (Dueling DQN) into adaptive large neighborhood search (ALNS), referred to as Dueling DQN-ALNS. The Dueling DQN component develops a method to update strategy weights, while the action space defines the destruction and selection strategies for the ALNS scheduling solution across different time windows. Meanwhile, we design a two-stage algorithm framework consisting of centralized offline training and decentralized online scheduling. Compared to traditionally optimized search algorithms, the proposed algorithm could continuously and dynamically interact with the environment to acquire state information about the scheduling solution. The solution ability of Dueling DQN is 3.75% higher than that of the Ant Colony Optimization (ACO) algorithm, 5.9% higher than that of the basic ALNS algorithm, and 9.37% higher than that of the differential evolution algorithm (DE). This verified its efficiency and advantages in the scheduling problem of return communication tasks for UAVs. Full article