Search Results (17)

The maritime wireless communication network (MWCN) faces challenges such as limited coverage, inaccurate channel state information (CSI), and the sparse distribution of maritime vessel users. To overcome the above challenges, this paper proposes a low Earth orbit satellite (LEO) MWCN based on rate-splitting multiple access (RSMA) and reconfigurable intelligent surface (RIS). Common data streams transmit broadcast-shared information to all vessel users. Private data streams provide differentiated supplements. The primary optimization objective is to maximize the sum rate. The transmission time is also introduced as a supplementary performance indicator to assess the system’s transmission capability. To overcome the problems of imperfect CSI and the low efficiency of the weighted minimum mean square error (WMMSE) algorithm, a block coordinate descent (BCD) algorithm is proposed based on the deep unfolding method (DU) and momentum-accelerated projection gradient descent (PGD). Numerical results show that DU-WMMSE reduces the number of convergence iterations from 8 to 4, improves the sum rate by 11.06%, and achieves lower transmission time. In addition, active RIS mitigates severe fading more effectively in complex channels. The proposed scheme also exhibits excellent scalability. Full article

Water scarcity severely restricts the sustainable development of water-stressed regions like Hebei Province. A scientific assessment of water resource carrying capacity (WRCC) is essential. However, single-weighting methods often lead to biased results. To address this limitation, we propose a combined weighting model that integrates the Entropy Weight Method (EWM), Projection Pursuit (PP), and CRITIC. To support this model, we developed a multi-dimensional, long-term WRCC evaluation dataset covering 11 prefecture-level cities in Hebei Province over 24 years (2000–2023). This approach simultaneously considers data dispersion, inter-indicator conflict, and structural features. It ensures that a more balanced weighting scheme is obtained. The traditional TOPSIS model was further improved through Grey Relational Analysis (GRA), which enhanced the discriminatory power and stability of WRCC assessment. The findings were as follows: (1) From 2000 to 2023, the WRCC in Hebei Province showed a fluctuating upward trend and a “high-north, low-south” spatial gradient. (2) Obstacle analysis revealed a vicious cycle of “resource scarcity–structural conflict–ecological deficit”. This cycle is caused by excessive exploitation of groundwater and low efficiency of industrial water use. The combined weighting–GRA–TOPSIS model offers a reliable WRCC diagnostic tool. The results indicate the core barriers to water use in Hebei and provide targeted policy ideas for sustainable development. Full article

This study aims to address the challenge of balancing historical preservation and sustainable material selection in ancient building renovations, particularly in regions with unique climatic conditions like Hunan Province. The research proposes a hybrid model integrating Genetic Algorithm-optimized Extreme Gradient Boosting (GA-XGBoost) and Long Short-Term Memory (LSTM) networks. The GA-XGBoost component optimizes hyperparameters to predict material performance, while the LSTM network captures temporal dependencies in environmental and material degradation data. A multi-objective optimization framework is developed to simultaneously prioritize preservation integrity and green performance. The methodology is validated through a case study on an ancient architectural complex in Rucheng, Hunan Province. Key results demonstrate that the hybrid model achieves superior accuracy in material selection, with an 18–23% reduction in embodied energy (compared to conventional AHP-TOPSIS methods) and a 21.9% improvement in prediction accuracy (versus standalone XGBoost with default hyperparameters). A multi-objective optimization framework is developed to simultaneously prioritize preservation integrity and green performance, with Pareto-optimal solutions identifying material combinations that balance historical authenticity (achieving 92% substrate compatibility) with substantial sustainability gains (18–23% embodied energy reduction). The model also identifies optimal material combinations, such as lime-pozzolan mortars with rice husk ash additives, which enhance moisture buffering capacity by 28% (relative to traditional lime mortar benchmarks) while maintaining 92% compatibility with original substrates (based on ASTM C270 compatibility tests). The findings highlight the model’s effectiveness in bridging heritage conservation and modern sustainability requirements. The study contributes a scalable and interpretable framework for green material selection, offering practical implications for cultural heritage projects worldwide. Future research directions include expanding the model’s applicability to other climate zones and integrating circular economy principles for broader sustainability impact. Preliminary analysis indicates the framework’s adaptability to other climate zones through adjustment of key material property weightings. Full article

Recent studies report that gradient guidance extracted from a single-reference model can improve Limited-Sample regression. However, one reference model may not capture all relevant characteristics of the target function, which can restrict the capacity of the learner. To address this issue, we introduce the Multi-Gradient Guided Network (MGGN), an extension of single-gradient guidance that combines gradients from several reference models. The gradients are merged through an adaptive weighting scheme, and an orthogonal-projection step is applied to reduce potential conflicts between them. Experiments on sine regression are used to evaluate the method. The results indicate that MGGN achieves higher predictive accuracy and improved stability than existing single-gradient guidance and meta-learning baselines, benefiting from the complementary information provided by multiple reference models. Full article

Human pose estimation is an important downstream task in computer vision, with significant applications in action recognition and virtual reality. However, data collected in a decentralized manner often exhibit non-independent and identically distributed (non-IID) characteristics, and traditional federated learning aggregation strategies can lead to gradient conflicts that impair model convergence and accuracy. To address this, we propose the Federated Gradient Harmonization aggregation strategy (FedGH), which coordinates update directions by measuring client gradient discrepancies and integrating gradient-projection correction with a parameter-reconstruction mechanism. Experiments conducted on a self-constructed single-arm robotic dataset and the public Max Planck Institute for Informatics (MPII Human Pose Dataset) dataset demonstrate that FedGH achieves average Percentage of Correct Keypoints (PCK) of 47.14% and 66.31% across all keypoints, representing improvements of 1.82 and 0.36 percentage points over the Federated Adaptive Weighting (FedAW) method. On our self-constructed dataset, FedGH attains a PCK of 86.4% for shoulder detection, surpassing other traditional federated learning methods by 20–30%. Moreover, on the self-constructed dataset, FedGH reaches over 98% accuracy in the keypoint heatmap regression model within the first 10 rounds and remains stable between 98% and 100% thereafter. This method effectively mitigates gradient conflicts in non-IID environments, providing a more robust optimization solution for distributed human pose estimation. Full article

Gravity inversion plays a crucial role in mineral exploration and resource evaluation, yet conventional depth-weighting methods often impose uniform resolution across all depths and fail to effectively delineate anomaly boundaries. This study presents an innovative attentional depth-weighting matrix based on a regularized downward continuation (RDC) mechanism. First, the observed gravity data are projected to greater depths using RDC, which suppresses high-frequency noise amplification. Next, gradient extrema are extracted from each grid cell to identify anomaly boundaries, forming a constant weighting matrix that enhances the focus on target regions. This matrix is then integrated with traditional depth weighting and a minimum-support focusing factor to optimize the inversion process. The proposed method is validated through two synthetic models, demonstrating improved resolution of deeper targets and more accurate amplitude recovery compared to conventional approaches. Further application to the Dahongshan Copper–Iron Ore region in Yunnan, China, reveals a deep intrusive body at approximately 4–5 km depth, extending east–west with a distinct “U”-shaped geometry. These results, consistent with previous geological studies, highlight the method’s ability to enhance deep anomaly characterization while effectively suppressing shallow noise interference. By balancing noise reduction with improved resolution, this approach broadens the applicability of gravity inversion in geological, geothermal, and mineral resource exploration. Full article

The prerequisite for the fusion processing of heterogeneous SAR images lies in high-precision image matching, which can be widely applied in areas such as geometric localization, scene matching navigation, and target recognition. This study proposes a method for high-precision matching of heterogeneous SAR images based on the combination of the single-scale ratio of an exponentially weighted averages (ROEWA) operator and angle-weighted gradient (RAWG). The method consists of the following three main steps: feature point extraction, feature description, and feature matching. The algorithm utilizes the block-based SAR-Harris operator to extract feature points from the reference SAR image, effectively combating the interference of coherent speckle noise and improving the uniformity of feature point distribution. By employing the single-scale ROEWA operator in conjunction with angle-weighted gradient projection, the construction of a 3D dense feature descriptor is achieved, enhancing the consistency of gradient features in heterogeneous SAR images and smoothing the search surface. Through the optimal feature construction strategy and frequency domain SSD algorithm, fast template matching is realized. Experimental comparisons with other mainstream matching methods demonstrate that the Root Mean Square Error (RMSE) of our method is reduced by 47.5% compared with CFOG, and compared with HOPES, the error is reduced by 15.4% and the matching time is reduced by 34.3%. The proposed approach effectively addresses the nonlinear intensity differences, geometric disparities, and interference of coherent speckle noise in heterogeneous SAR images. It exhibits robustness, high precision, and efficiency as its prominent advantages. Full article

Surface gravity inversion attempts to recover the density contrast distribution in the 3D Earth model for geological interpretation. Since airborne gravity is characterized by large data volumes, large-scale 3D inversion exceeds the capacity of desktop computing resources, making it difficult to achieve the appropriate depth/lateral resolution for geological interpretation. In addition, gravity data are finite and noisy, and their inversion is ill posed. Especially in the absence of a priori geological information, regularization must be introduced to overcome the difficulty of the non-uniqueness of the solutions to recover the most geologically plausible ones. Because the use of Haar wavelet operators has an edge-preserving property and can preserve the sensitivity matrix structure at each level of the multilevel method to obtain faster solvers, we present a multilevel algorithm for large-scale gravity inversion solved by the re-weighted regularized conjugate gradient (RRCG) algorithm to reduce the inversion computational resources and improve the depth/lateral resolution of the inversion results. The RRCG-based multilevel inversion was then applied to synthetic cases and airborne gravity data from the Quest-South project in British Columbia, Canada. Results from synthetic models and field data show that the RRCG-based multilevel inversion is suitable for obtaining density contrast distributions with appropriate horizontal and vertical resolution, especially for large-scale gravity inversions compared to Occam’s inversion. Full article

Collision safety is an essential issue for dual-arm nursing-care robots. However, for coordinating operations, there is no suitable method to synchronously avoid collisions between two arms (self-collision) and collisions between an arm and the environment (environment-collision). Therefore, based on the self-motion characteristics of the dual-arm robot’s redundant arms, an improved motion controlling algorithm is proposed. This study introduces several key improvements to existing methods. Firstly, the volume of the robotic arms was modeled using a capsule-enveloping method to more accurately reflect their actual structure. Secondly, the gradient projection method was applied in the kinematic analysis to calculate the shortest distances between the left arm, right arm, and the environment, ensuring effective avoidance of the self-collision and environment-collision. Additionally, distance thresholds were introduced to evaluate collision risks, and a velocity weight was used to control the smooth coordinating arm motion. After that, experiments of coordinating obstacle avoidance showed that when the redundant dual-arm robot is holding an object, the coordinating operation was completed while avoiding self-collision and environment-collision. The collision-avoidance method could provide potential benefits for various scenarios, such as medical robots and rehabilitating robots. Full article

In recent years, high-quality surfaces with large areas and curvatures have been increasingly used in engineering, but the precision machining and inspection of such surfaces is a particular challenge. Surface machining equipment needs to have a large working space, high flexibility, and motion accuracy to meet the demands of micron-scale precision machining. However, meeting these requirements may result in extremely large equipment sizes. To solve this problem, an eight-degree-of-freedom redundant manipulator with one linear and seven rotational joints is designed to assist in the machining described in this paper. The configuration parameters of the manipulator are optimized by an improved multi-objective particle swarm optimization algorithm to ensure that the working space of the manipulator completely covers the working surface and that the size of the manipulator is small. In order to improve the smoothness and accuracy of manipulator motion on large surface areas, an improved trajectory planning strategy for a redundant manipulator is proposed. The idea of the improved strategy is to pre-process the motion path first and then use a combination of the clamping weighted least-norm method and the gradient projection method to plan the trajectory, while adding a reverse planning step to solve the singularity problem. The resulting trajectories are smoother than those planned by the general method. The feasibility and practicality of the trajectory planning strategy are verified through simulation. Full article

Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network’s prediction. Gradient-based methods are generally faster than other branches of vision interpretability and independent of human guidance. The performance of CAM-like studies depends on the governing model’s layer response and the influences of the gradients. Typical gradient-oriented CAM studies rely on weighted aggregation for saliency map estimation by projecting the gradient maps into single-weight values, which may lead to an over-generalized saliency map. To address this issue, we use a global guidance map to rectify the weighted aggregation operation during saliency estimation, where resultant interpretations are comparatively cleaner and instance-specific. We obtain the global guidance map by performing elementwise multiplication between the feature maps and their corresponding gradient maps. To validate our study, we compare the proposed study with nine different saliency visualizers. In addition, we use seven commonly used evaluation metrics for quantitative comparison. The proposed scheme achieves significant improvement over the test images from the ImageNet, MS-COCO 14, and PASCAL VOC 2012 datasets. Full article

In machine learning (ML), adversarial attack (targeted or untargeted) in the presence of noise disturbs the model prediction. This research suggests that adversarial perturbations on pictures lead to noise in the features constructed by any networks. As a result, adversarial assaults against image categorization systems may present obstacles and possibilities for studying convolutional neural networks (CNNs). According to this research, adversarial perturbations on pictures cause noise in the features created by neural networks. Motivated by adversarial perturbation on image pixel attacks observation, we developed a novel exploit feature map that describes adversarial attacks by performing individual object feature-map visual description. Specifically, a novel detection algorithm calculates each object’s class activation map weight and makes a combined activation map. When checked with different networks like VGGNet19 and ResNet50, in both white-box and black-box attack situations, the unique exploit feature-map significantly improves the state-of-the-art in adversarial resilience. Further, it will clearly exploit attacks on ImageNet under various algorithms like Fast Gradient Sign Method (FGSM), DeepFool, Projected Gradient Descent (PGD), and Backward Pass Differentiable Approximation (BPDA). Full article

Different from traditional redundant manipulators, the redundant manipulators used in the surgical environment require the end effector (EE) to have high pose (position and orientation) accuracy to ensure the smooth progress of the operation. When analyzing the inverse kinematics (IK) of traditional redundant manipulators, gradient-projection method (GPM) and weighted least-norm (WLN) method are commonly used methods to avoid joint position limits. However, for the traditional GPM and WLN method, when joints are close to their limits, they stop moving, which greatly reduces the accuracy of the IK solution. When robotic manipulators enter a singular region, although traditional damped least-squares (DLS) algorithms are used to handle singularities effectively, motion errors of the EE will be introduced. Furthermore, selecting singular region through trial and error may cause some joint velocities exceed their corresponding limits. More importantly, traditional DLS algorithms cannot guide robotic manipulators away from singular regions. Inspired by the merits of GPM, WLN, and DLS methods, an improved weighted gradient projection method (IWGPM) is proposed to solve the IK problem of redundant manipulators used in the surgical environment with avoiding joint position limits and singularities. The weighted matrix of the WLN method and the damping factor of the DLS algorithm have been improved, and a joint limit repulsive potential field function and singular repulsive potential field function belong to the null space are introduced to completely keep joints away from the damping interval and redundant manipulators away from the unsafe region. To verify the validity of the proposed IWGPM, simulations on a 7 degree of freedom (DOF) redundant manipulator used in laparoscopic surgery indicate that the proposed method can not only achieve higher accuracy IK solution but also avoid joint position limits and singularities effectively by comparing them with the results of the traditional GPM and WLN method, respectively. Furthermore, based on the proposed IWGPM, simulation tests in two cases show that joint position limits have a great impact on the orientation accuracy, and singular potential energy function has a great impact on the position accuracy. Full article

Sea surface temperature (SST) analysis systems such as the Operational Sea Surface Temperature and Ice Analysis (OSTIA) use statistical methods to combine observations together with a first guess field to create spatially complete maps of SST. These commonly assume that observation errors are uncorrelated, yet some errors (such as due to retrieval issues) can be correlated. Information about errors is used by the analysis system to determine the weighting to apply to the observations, hence this incorrect assumption could degrade the analysis. A common technique to mitigate for this is to inflate the observation uncertainties. Using information on observation error correlations provided with data produced by the European Space Agency (ESA) SST Climate Change Initiative (CCI) project, idealised tests were carried out to determine how this inflation technique can best be applied. These showed that applying inflation in situations where the observation errors are correlated over similar or larger distances to the errors in the background can cause unpredictable and sometimes negative results. However, in situations where the observation error correlation length scale is relatively small, inflation should improve the analysis. These findings were adapted to the OSTIA system and various configurations were tested. It was found that the inflation methods did not affect statistics of differences between the analyses and independent Argo reference data. However, the SST gradients were affected, particularly if some observation uncertainties were inflated but others were not. The results from both the idealised tests and the application to the real system therefore highlight that it is challenging to implement the inflation method in the case of an SST analysis system and show the need for assimilation schemes that can make full use of observation error correlation information. Full article

Sustainable Development Goals (SDGs) are a set of priorities the United Nations and World Bank have set for countries to reach in order to improve quality of life and environment globally by 2030. Free satellite images have been identified as a key resource that can be used to produce official statistics and analysis to measure progress towards SDGs, especially those that are concerned with the physical environment, such as forest, water, and crops. Satellite images can often be unusable due to missing data from cloud cover, particularly in tropical areas where the deforestation rates are high. There are existing methods for filling in image gaps; however, these are often computationally expensive in image classification or not effective at pixel scale. To address this, we use two machine learning methods—gradient boosted machine and random forest algorithms—to classify the observed and simulated ‘missing’ pixels in satellite images as either grassland or woodland. We also predict a continuous biophysical variable, Foliage Projective Cover (FPC), which was derived from satellite images, and perform accurate binary classification and prediction using only the latitude and longitude of the pixels. We compare the performance of these methods against each other and inverse distance weighted interpolation, which is a well-established spatial interpolation method. We find both of the machine learning methods, particularly random forest, perform fast and accurate classifications of both observed and missing pixels, with up to 0.90 accuracy for the binary classification of pixels as grassland or woodland. The results show that the random forest method is more accurate than inverse distance weighted interpolation and gradient boosted machine for prediction of FPC for observed and missing data. Based on the case study results from a sub-tropical site in Australia, we show that our approach provides an efficient alternative for interpolating images and performing land cover classifications. Full article