Search Results (263)

This study proposes a novel Deep Reinforcement Learning (DRL) policy network structure for portfolio management called PortRSMs. PortRSMs employs stacked State-Space Models (SSMs) for the modeling of multi-scale continuous regime shifts in financial time series, striking a balance between exploring consistent distribution properties over short periods and maintaining sensitivity to sudden shocks in price sequences. PortRSMs also performs cross-asset regime fusion through hypergraph attention mechanisms, providing a more comprehensive state space for describing changes in asset correlations and co-integration. Experiments conducted on two different trading frequencies in the stock markets of the United States and Hong Kong show the superiority of PortRSMs compared to other approaches in terms of profitability, risk–return balancing, robustness, and the ability to handle sudden market shocks. Specifically, PortRSMs achieves up to a 0.03 improvement in the annual Sharpe ratio in the U.S. market, and up to a 0.12 improvement for the Hong Kong market compared to baseline methods. Full article

Empty container depot (ECD) design significantly impacts maritime terminal efficiency, yet traditional evaluation approaches assess limited operational factors, constraining comprehensive performance optimization. This study develops an integrated discrete event simulation (DES) framework that simultaneously evaluates lifting equipment utilization, truck turnaround times, and potential collisions to support terminal decision-making. This study combines operational efficiency metrics with safety analytics for non-automated ECDs using Top Lifters and Reach Stackers. Additionally, a regression analysis examines efficiency metrics’ effect on safety risk. A case study at a Chilean multipurpose terminal reveals performance trade-offs between indicators under different operational scenarios, identifying substantial efficiency disparities between dry and refrigerated container operations. An analysis of four distinct collision zones with varying historical risk profiles showed the gate area had the highest potential collisions and a strong regression correlation with efficiency metrics. Similar models showed a poor fit in other conflict zones, evidencing the necessity for dedicated safety indicators complementing traditional measures. This integrated approach quantifies interdependencies between safety and efficiency metrics, helping terminal managers optimize layouts, expose traditional metric limitations, and reduce safety risks in space-constrained maritime terminals. Full article

Deep learning-based super-resolution (SR) frameworks are widely used in remote sensing applications. However, existing SR models still face limitations, particularly in recovering contours, fine features, and textures, as well as in effectively integrating channel information. To address these challenges, this study introduces a novel residual model named OARN (Optimized Attention Residual Network) specifically designed to enhance the visual quality of low-resolution images. The network operates on the Y channel of the YCbCr color space and integrates LKA (Large Kernel Attention) and OCM (Optimized Convolutional Module) blocks. These components can restore large-scale spatial relationships and refine textures and contours, improving feature reconstruction without significantly increasing computational complexity. The performance of OARN was evaluated using satellite images from WorldView-2, GaoFen-2, and Microsoft Virtual Earth. Evaluation was conducted using objective quality metrics, such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Edge Preservation Index (EPI), and Perceptual Image Patch Similarity (LPIPS), demonstrating superior results compared to state-of-the-art methods in both objective measurements and subjective visual perception. Moreover, OARN achieves this performance while maintaining computational efficiency, offering a balanced trade-off between processing time and reconstruction quality. Full article

This paper proposes a lightweight gaze-tracking architecture named GhostBlock-Augmented Look to Coordinate Space (L2CS), which integrates GhostNet-based modules and depthwise separable convolution to achieve a better trade-off between model accuracy and computational efficiency. Conventional lightweight gaze-tracking models often suffer from degraded accuracy due to aggressive parameter reduction. To address this issue, we introduce GhostBlocks, a custom-designed convolutional unit that combines intrinsic feature generation with ghost feature recomposition through depthwise operations. Our method enhances the original L2CS architecture by replacing each ResNet block with GhostBlocks, thereby significantly reducing the number of parameters and floating-point operations. The experimental results on the Gaze360 dataset demonstrate that the proposed model reduces FLOPs from 16.527 × 10⁸ to 8.610 × 10⁸ and parameter count from 2.387 × 10⁵ to 1.224 × 10⁵ while maintaining comparable gaze estimation accuracy, with MAE increasing only slightly from 10.70° to 10.87°. This work highlights the potential of GhostNet-augmented designs for real-time gaze tracking on edge devices, providing a practical solution for deployment in resource-constrained environments. Full article

Accurate Doppler frequency estimation for Low Earth Orbit (LEO)-based Signals of Opportunity (SoOP) positioning faces significant challenges from extreme dynamics (±40 kHz Doppler shift, 0.4 Hz/ms fluctuation) and severe SNR fluctuations induced by multi-beam switching. Empirical analysis reveals that phased-array beamforming generates three-tiered SNR fluctuation patterns during unpredictable beam handovers, rendering conventional single-algorithm solutions fundamentally inadequate. To address this limitation, we propose KDFE (KNN-Driven Fusion Estimator)—an adaptive framework integrating the Rife–Vincent algorithm and MLE via intelligent switching. Global FFT processing extracts real-time Doppler-SNR parameter pairs, while a KNN-based arbiter dynamically selects the optimal estimator by: (1) Projecting parameter pairs into historical performance space, (2) Identifying the accuracy-optimal algorithm for current beam conditions, and (3) Executing real-time switching to balance accuracy and robustness. This decision model overcomes the accuracy-robustness trade-off by matching algorithmic strengths to beam-specific dynamics, ensuring optimal performance during abrupt SNR transitions and high Doppler rates. Both simulations and field tests demonstrate KDFE’s dual superiority: Doppler estimation errors were reduced by 26.3% (vs. Rife–Vincent) and 67.9% (vs. MLE), and 3D positioning accuracy improved by 13.6% (vs. Rife–Vincent) and 49.7% (vs. MLE). The study establishes a pioneering framework for adaptive LEO-SoOP positioning, delivering a methodological breakthrough for LEO navigation. Full article

Ensuring food security necessitates a high level of coordinated development between agricultural trade and production. Based on China’s provincial panel data from 2010 to 2023, this study constructs an evaluation index system for agricultural trade and production, employing an entropy-weighted TOPSIS model to measure their development levels. On this basis, a coupling coordination degree model and Moran’s I indices are used to analyze the coordinated development level’s temporal changes and spatial effects. The research finds that the development levels of China’s agricultural trade and production show an upward trend but currently still exhibit the pattern of higher levels in Eastern China and lower levels in Western China. The coupling coordination level between them demonstrates an increasing trend, yet the overall level remains relatively low, with an average value of only 0.445, consistently staying in a marginal disorder “running-in stage” and spatially presenting a distinct “east-high–west-low” stepped distribution pattern. Furthermore, from a spatial perspective, the Global Moran’s index decreased from 0.293 to 0.280. The coupling coordination degree of agricultural trade and production in China generally exhibits a positive spatial autocorrelation, but this effect has been weakening over time. Most provinces show spatial clustering characteristics of high–high and low–low agglomeration in local space, and this feature is relatively stable. Building on these insights, this study proposes a refinement of the coordination mechanisms between agricultural trade and production, alongside the implementation of differentiated regional coordinated development strategies, to promote the coupled and coordinated advancement of agricultural trade and production. Full article

Container terminals are facing significant challenges in meeting the increasing demands for volume and throughput, with limited space often presenting as a critical constraint. Key areas of concern at the quayside include the berth allocation problem, the quay crane assignment, and the scheduling problem. Effectively managing these issues is essential for optimizing port operations; failure to do so can lead to substantial operational and economic ramifications, ultimately affecting competitiveness within the global shipping industry. Optimization models, encompassing both mathematical frameworks and metaheuristic approaches, offer promising solutions. Additionally, the application of machine learning and reinforcement learning enables real-time solutions, while robust optimization and stochastic models present effective strategies, particularly in scenarios involving uncertainties. This study expands upon earlier foundational analyses of berth allocation, quay crane assignment, and scheduling issues, which have laid the groundwork for port optimization. Recent developments in uncertainty management, automation, real-time decision-making approaches, and environmentally sustainable objectives have prompted this review of the literature from 2015 to 2024, exploring emerging challenges and opportunities in container terminal operations. Recent research has increasingly shifted toward integrated approaches and the utilization of continuous berthing for better wharf utilization. Additionally, emerging trends, such as sustainability and green infrastructure in port operations, and policy trade-offs are gaining traction. In this review, we critically analyze and discuss various aspects, including spatial and temporal attributes, crane handling, sustainability, model formulation, policy trade-offs, solution approaches, and model performance evaluation, drawing on a review of 94 papers published between 2015 and 2024. Full article

This paper proposes a novel sparse twin parametric insensitive support vector regression (STPISVR) model, designed to enhance sparsity and improve generalization performance. Similar to twin parametric insensitive support vector regression (TPISVR), STPISVR constructs a pair of nonparallel parametric insensitive bound functions to indirectly determine the regression function. The optimization problems are reformulated as two sparse linear programming problems (LPPs), rather than traditional quadratic programming problems (QPPs). The two LPPs are originally derived from initial L1-norm regularization terms imposed on their respective dual variables, which are simplified to constants via the Karush–Kuhn–Tucker (KKT) conditions and consequently disappear. This simplification reduces model complexity, while the constraints constructed through the KKT conditions— particularly their geometric properties—effectively ensure sparsity. Moreover, a two-stage hybrid tuning strategy—combining grid search for coarse parameter space exploration and Bayesian optimization for fine-grained convergence—is proposed to precisely select the optimal parameters, reducing tuning time and improving accuracy compared to a singlemethod strategy. Experimental results on synthetic and benchmark datasets demonstrate that STPISVR significantly reduces the number of support vectors (SVs), thereby improving prediction speed and achieving a favorable trade-off among prediction accuracy, sparsity, and computational efficiency. Overall, STPISVR enhances generalization ability, promotes sparsity, and improves prediction efficiency, making it a competitive tool for regression tasks, especially in handling complex data structures. Full article

This study aimed to evaluate how wearable hip exoskeleton assistance affects phase-dependent gait stability in healthy adults using a novel visualization technique known as gait tube analysis. Hip exoskeletons offer significant potential to enhance human locomotion through joint torque augmentation, yet their effects on gait stability across the gait cycle remain underexplored. This study introduces gait tube analysis, a novel method for visualizing center of mass velocity trajectories in three-dimensional state space, to quantify phase-dependent gait stability under hip exoskeleton assistance. We analyzed data from ten healthy adults walking under twelve conditions (ten powered with varying torque magnitude and timing, one passive, and one unassisted), assessing variability via covariance-based ellipsoid volumes. Powered conditions, notably HighLater and HighLatest, significantly increased vertical variability (VT) during early-to-mid stance (10–50% of the gait cycle), with HighLater showing the highest mean ellipsoid volume (99,937 mm³/s³; z = 2.3). Conversely, the passive PowerOff condition exhibited the lowest variability (47,285 mm³/s³; z = –1.7) but higher metabolic cost, highlighting a stability-efficiency trade-off. VT was elevated in 11 of 12 conditions (p ≤ 0.0059), and strong correlations (r ≥ 0.65) between ellipsoid volume and total variability validated the method’s robustness. These findings reveal phase-specific stability challenges and metabolic cost variations induced by exoskeleton assistance, providing a foundation for designing adaptive controllers to balance stability and efficiency in rehabilitation and performance enhancement contexts. Full article

As a fundamental technology in environmental perception, sound source localization (SSL) plays a critical role in public safety, marine exploration, and smart home systems. However, traditional methods such as beamforming and time-delay estimation rely on manually designed physical models and idealized assumptions, which struggle to meet practical demands in dynamic and complex scenarios. Recent advancements in deep learning have revolutionized SSL by leveraging its end-to-end feature adaptability, cross-scenario generalization capabilities, and data-driven modeling, significantly enhancing localization robustness and accuracy in challenging environments. This review systematically examines the progress of deep learning-based SSL across three critical domains: marine environments, indoor reverberant spaces, and unmanned aerial vehicle (UAV) monitoring. In marine scenarios, complex-valued convolutional networks combined with adversarial transfer learning mitigate environmental mismatch and multipath interference through phase information fusion and domain adaptation strategies. For indoor high-reverberation conditions, attention mechanisms and multimodal fusion architectures achieve precise localization under low signal-to-noise ratios by adaptively weighting critical acoustic features. In UAV surveillance, lightweight models integrated with spatiotemporal Transformers address dynamic modeling of non-stationary noise spectra and edge computing efficiency constraints. Despite these advancements, current approaches face three core challenges: the insufficient integration of physical principles, prohibitive data annotation costs, and the trade-off between real-time performance and accuracy. Future research should prioritize physics-informed modeling to embed acoustic propagation mechanisms, unsupervised domain adaptation to reduce reliance on labeled data, and sensor-algorithm co-design to optimize hardware-software synergy. These directions aim to propel SSL toward intelligent systems characterized by high precision, strong robustness, and low power consumption. This work provides both theoretical foundations and technical references for algorithm selection and practical implementation in complex real-world scenarios. Full article

As the world’s third-longest river supporting 40% of China’s population, the Yangtze River Basin exemplifies the critical challenges of balancing riparian development and ecological resilience for major fluvial systems globally. This study analyzed the spatiotemporal evolution, proximity dynamics to the Yangtze River, and driving mechanisms of the “three types of spaces” (urban, agricultural, and ecological) in 130 counties along the Yangtze River mainstem from 2000 to 2020, utilizing an integrated approach incorporating land use transfer matrices, centroid-based distance metrics and GeoDetector models. Key findings reveal: (1) Urban space exhibited significant irreversible expansion while agricultural space continued to shrink, with ecological space maintaining overall stability but showing high-frequency bidirectional conversion with agricultural areas in localized zones. (2) Spatial proximity analysis demonstrated contrasting patterns—eastern riparian counties showed urban spatial agglomeration towards the river, whereas most mid-western regions experienced urban expansion away from the watercourse, with marked regional disparities in agricultural and ecological spatial changes. (3) Driving mechanism analysis identified topography as the dominant natural factor influencing ecological space evolution, while socioeconomic factors exerted stronger impacts on proximity variations of agricultural and urban spaces, with natural–socioeconomic interactive effects showing the most significant explanatory power. These spatial dynamics reflect universal trade-offs between economic development and ecosystem conservation in large river basins worldwide. We advocate differentiated spatial governance strategies, including rigorous riparian ecological redlines, eco-agricultural models in agricultural retreat zones, and proximity-based real-time monitoring for ecological early warning. The integrated methodology and spatial governance framework offer transferable solutions for sustainable management of major fluvial systems under rapid urbanization pressure. These findings provide scientific evidence and implementable pathways for coordinating socioeconomic development with ecosystem resilience in the Yangtze River Economic Belt. Full article

Optimizing manufacturing processes to reduce scrap and enhance process stability presents significant challenges, particularly when multiple conflicting objectives must be addressed concurrently. As the number of objectives increases, the complexity of the optimization task escalates. This difficulty is further intensified in online optimization scenarios, where optimal parameter settings must be delivered in real time within active production environments. In this work, we propose a reinforcement learning-based framework for the multi-objective optimization of manufacturing parameters, demonstrated through a case study on pinion gear manufacturing. The framework utilizes the Multi-Objective Maximum a Posteriori Optimization (MO-MPO) algorithm to train a reinforcement learning agent. A high-fidelity simulation of the pinion manufacturing process is constructed in Simufact, serving both data generation and validation purposes. The agent’s performance is assessed using a hold-out test set along with additional simulations of the physical process. To ensure the generalizability of the approach, further validation is performed using open-source manufacturing datasets and synthetically generated data. The results demonstrate the feasibility of the proposed method for real-time industrial deployment. Moreover, Pareto-optimality is verified via half-space analysis, emphasizing the framework’s effectiveness in managing trade-offs among competing objectives. Full article

As industries come under growing pressure to minimize carbon emissions without compromising the efficiency of operations, the integration of energy-aware production scheduling with emerging energy markets, renewable energy, and policy mechanisms is critical. This paper identifies critical shortcomings in current academic and industrial approaches—namely, an excessive reliance on deterministic assumptions, a limited focus on dynamic operational realities, and the underutilization of regulatory mechanisms such as carbon trading. We advocate for a paradigm shift to more robust, adaptable, and policy-compliant scheduling systems that provide space for on-site renewable generation, battery energy storage systems (BESSs), demand-response measures, and real-time electricity pricing schemes like time-of-use (TOU) and real-time pricing (RTP). By integrating recent advances and their critical analysis of limitations, we map out a future research agenda for the integration of uncertainty modeling, machine learning, and multi-level optimization with policy compliance. In this paper, we propose the need for joint efforts from researchers, industries, and policymakers to collectively develop industrial scheduling systems that are both technically efficient and adherent to sustainability and regulatory requirements. Full article

The CORUS-XUAM project defined three two-way U-space corridors linking Frankfurt Airport’s Terminal 2 on the city outskirts with the city-center Trade Fair. These corridors avoid the approach cones of the northern and central runways and bypass hospital no-fly zones and large buildings. In our previous studies, we first used fast-time simulations to evaluate the U-space routing and its operating concept, based on historical air traffic data. Included were arriving and departing airplanes as well as police, and medical helicopters throughout the city. The focus was on the limitations of the airspace, avoiding conflicts with other airspace users and between the airtaxis using a different corridor or delaying the departure, as well as determining the throughput potential of such a corridor system. Building on our previous studies, this study incorporates higher-fidelity traffic simulation data and an updated demand analysis for the airtaxi shuttle service. Our new sizing analysis reveals that ground operations typically, not airspace capacity, constitute the primary bottleneck. Full article

This study addresses the persistent challenge of balancing interpretability and robustness in black-box deep learning models for automatic modulation recognition (AMR), a critical task in wireless communication systems. To bridge this gap, we propose a novel explainable AI (XAI) framework that integrates symbolic feature interaction concepts into communication signal analysis for the first time. The framework combines a modulation primitive decomposition architecture, which unifies Shapley interaction entropy with signal physics principles, and a dual-branch XAI mechanism (feature extraction + interaction analysis) validated on ResNet-based models. This approach explicitly maps signal periodicity to modulation order in high-dimensional feature spaces while mitigating feature coupling artifacts. Quantitative responsibility attribution metrics are introduced to evaluate component contributions through modular adversarial verification, establishing a certified benchmark for AMR systems. The experimental validation of the RML 2016.10a dataset has demonstrated the effectiveness of the framework. Under the dynamic signal-to-noise ratio condition of the benchmark ResNet with an accuracy of 94.88%, its occlusion sensitivity increased by 30% and stability decreased by 22% compared to the SHAP baseline. The work advances AMR research by systematically resolving the transparency–reliability trade-off, offering both theoretical and practical tools for deploying trustworthy AI in real-world wireless scenarios. Full article