Search Results (5,470)

This paper addresses an integrated production–transportation scheduling problem in assembly workshops, encompassing the processes of part machining, material handling via handling resources, and final synchronous assembly. The finite buffer capacities of production resources can cause blocking, thereby reducing efficiency. Material handling resources are subject to different service area restrictions, and some share safety zones with production resources, preventing simultaneous processing. To address this, a mixed-integer programming model is formulated with makespan and total empty travel time as bi-objective optimization targets. Since the mixed-integer linear programming (MILP) model faces difficulties in solving medium- and large-scale instances, an improved memetic NSGA-II algorithm (IMNSGA-II) is proposed. The algorithm adopts a three-segment chromosome encoding and incorporates a VNS-SA local search mechanism within the global evolutionary framework of NSGA-II. Small-scale computational experiments using Gurobi are first used to verify the correctness of the model. Decoupling experiments further demonstrate the necessity of integrated optimization: compared with phased baseline methods, IMNSGA-II reduces makespan and empty travel time by approximately 10.16% and 12.33%, respectively. In ablation and comparative experiments, results based on hypervolume (HV) and inverted generational distance (IGD) show that the proposed method achieves better convergence, diversity, and overall Pareto front quality than multiple baseline algorithms. These experiments confirm the effectiveness of the proposed model and algorithm. Full article

Origin–destination (OD) matrix forecasting is essential for urban railway operations because it enables simultaneous understanding of the direction and magnitude of passenger flows. However, OD matrices in large-scale subway networks are difficult to predict owing to their high dimensionality and sparsity, and existing approaches often rely on station-level predictions or complex structural designs. This study addresses the offline full-matrix OD forecasting problem, where complete historical OD sequences are available at prediction time, and proposes Metro-GATF, a spatiotemporal forecasting framework that jointly models railway topology and dynamic OD interactions. The model employs a GATv2-based spatial encoder to learn static inter-station relationships and encodes time-varying interactions using sparse OD graphs. A non-autoregressive transformer decoder generates future multi-step node representations in parallel, whereas origin–destination factorization and sparsity-aware gating are used to reconstruct the full OD matrix. Experiments on minute-level AFC-based OD data from a 637-station metropolitan subway network demonstrated that Metro-GATF achieved the lowest sMAPE among the compared full-matrix models. These results indicate that the proposed framework effectively captures complex spatiotemporal OD patterns and offers a practical end-to-end framework for forecasting urban railway demand. Full article

Rice bran is a nutrient-rich agricultural by-product, and most of the bioactive compounds in it are bound and thus have poor bioavailability. Research has demonstrated that targeted microbial fermentation is a high-efficiency bioprocess for the degradation and modification of complex macromolecules to release phenolic compounds, flavonoids, dietary fibre derivatives and other new biologically active substances. Fermentation can be used to increase the antioxidant, anti-inflammatory and metabolically regulatory effects of rice bran more efficiently by changing its structure and increasing the content of active components compared with the conventional extraction method. Although some studies have investigated how to obtain suitable microbial strains and substrates, optimisation of the processing conditions for improving metabolic and functional performance has not been achieved; otherwise, other problems will still arise in the event of industrial-scale application, such as fluctuations in raw material supply, process instability, and high production costs. In the future, the integration of process analytical technology (PAT), artificial intelligence and microbial engineering will build a large-scale intelligent and controllable fermentation system. Therefore, the specific route of fermentation for valorising rice bran into high-value functional ingredients has been identified, and the scientific foundation for developing sustainable foods and nutraceuticals has been established. Full article

Decoration waste, because of its complex composition and the presence of volatile toxic and hazardous substances, has always been a difficult point in the management of urban construction waste. And with the continuous expansion of the town scale, the volume of decoration waste is gradually expanding, which constitutes a major challenge to the sustainable development of the construction industry. In order to solve this difficult problem, this paper took Henan Province as an example, and realized the accurate control of decoration waste based on GF-2 remote sensing images and a BP neural network model. The results of GF-2 remote sensing image interpretation and analysis showed that the spatial distribution of construction waste in the study area was extracted through a combination of manual visual interpretation and machine learning recognition, and as of 2021, the construction waste pile occupied a large proportion of the land area, of which the proportion of decoration waste was about 10%. Based on the trained BP neural network, the goodness-of-fit result was R = 0.95463. Selecting the research data from 2010 to 2021, the error of the predicted annual generation of decoration waste in Henan Province compared with the actual value was less than 15%, which had a high prediction accuracy. Based on the arithmetic sum of the projected figures for each year from 2022 to 2030, it is estimated that by 2030, the cumulative volume of construction and renovation waste generated in Henan Province will reach 49,827,200 tons. Visualization of spatial and temporal distribution characteristics was realized through ArcGIS, and the high production area of decoration waste was distributed from the beginning to the end of the distribution of multi-points to show the characteristics of a concentrated large area distribution, centrally located in southwestern and southeastern Henan Province, with the key cities of Zhumadian City, Luoyang City, Zhoukou City, and Xinyang City, which had obvious regional characteristics. At the same time, as the provincial capital, Zhengzhou has long ranked first in the province in terms of absolute case numbers and is therefore also a key focus of control measures. Uncertainty analysis indicates that the 95% confidence interval for the long-term forecast values is approximately ±12%. It is recommended to use the upper limit of this interval for the redundancy design of the absorption facilities to enhance the robustness of the decision. This study provides a theoretical basis and technical support for the governmental supervision of decoration waste during the development of national urban agglomerations, effectively solves regional urban planning and construction management problems, and promotes the sustainable development of the construction industry. Full article

The rapid growth of maritime communication networks introduces significant challenges to routing optimization, arising from large-scale network topologies, highly dynamic node mobility, and stringent real-time communication requirements. Conventional routing algorithms often exhibit limited scalability and poor adaptability when facing frequent topology variations. The routing problem is modeled as a multi-agent distributed decision-making process, where each node acts as an autonomous agent. In this paper, we propose a graph-partitioned hierarchical graph representation learning framework (GP-HGRL) for scalable and continual routing optimization in dynamic maritime networks. By explicitly modeling the network as a time-evolving graph, GP-HGRL first partitions the global topology into topology-aware subgraphs, enabling distributed learning and inference with reduced computational complexity. A hierarchical graph neural network architecture is then developed to jointly capture intra-subgraph local structures and inter-subgraph global dependencies, producing topology-aware embeddings for routing decision-making. Based on the learned representations, a deep reinforcement learning policy is employed to perform distributed next-hop routing decisions. To effectively handle topology dynamics induced by node mobility and link variations, we further introduce a continual graph learning mechanism that selectively updates representations and routing policies only within affected subgraphs, thereby avoiding costly global retraining and preserving routing stability. Extensive simulations demonstrate that GP-HGRL consistently outperforms shortest-path routing and existing reinforcement learning-based approaches in terms of packet delivery ratio, retransmission rate, packet loss, and training efficiency under various network loads and dynamic conditions. Full article

Academic stress in higher education is strongly influenced by workload structure and scheduling decisions, yet academic planning sometimes remains static and does not incorporate behavioural or physiological indicators. While existing research focuses on stress measurement and prediction, these approaches are rarely integrated into decision-support mechanisms capable of restructuring academic schedules. This work introduces a Course Digital Twin (CDT) framework that integrates multimodal student data with simulation-based academic planning. The proposed system models course scheduling as a decision-support problem, where alternative configurations are evaluated using a structured stress model combining wearable-derived physiological signals, self-reported stress measures, and contextual academic workload indicators. The framework employs a hybrid approach in which machine learning is used for physiological stress estimation, while schedule adaptation is performed through transparent rule-based mechanisms. The system was implemented as an end-to-end platform including mobile sensing, course configuration interfaces, and instructor analytics dashboards, and was evaluated through a pilot deployment across multiple postgraduate courses. Preliminary results indicate that simulation-based schedule adjustments are associated with reductions in projected peak stress levels and improved workload distribution patterns. The findings demonstrate the feasibility of integrating multimodal stress modelling and Digital Twin simulation into academic planning workflows. The proposed framework provides a foundation for future stress-aware scheduling systems, although further large-scale validation is required to establish its effectiveness and generalizability. Full article

Securing IoT-enabled wireless sensor network links requires selecting a minimum-cost set of connected monitor nodes that observes every link while satisfying capacity constraints, a problem known as the minimum weighted connected capacitated vertex cover (MWCCVC). To the best of our knowledge, this work introduces the first learning-based framework for the MWCCVC through a three-stage pipeline that combines supervised graph neural networks, feasibility repair, and local search. We compare twelve graph neural network architectures, including graph convolutional network, graph attention network, GraphSAGE, Graph Isomorphism Network (GIN), and GraphTransformer, under unified features, loss functions, and hyperparameter tuning. Throughout the evaluation on 309 benchmark instances under a 5-fold cross-validation protocol, feasibility is guaranteed by the deterministic repair module instead of being learned by the network, resulting in 100% feasible covers across all evaluated instances. At the large scale, GIN, GraphSAGE, DeeperGIN, and EdgeAwareGIN reach parity with the state-of-the-art hybrid genetic algorithm (HGA), with GIN attaining a mean gap of $-0.37\%$ (a difference of less than one percentage point) while completing in seconds instead of HGA’s hours. Statistical tests across the full 309-instance benchmark confirm significant differences between the architectures, with Friedman ${\chi }^2=93.05$, $p<{10}^{-4}$. The best-performing architectures remain within about $2\%$ of HGA on small- and medium-scale instances, where HGA is near-optimal, and become the preferred choice at the large scale, mainly because their wall-clock time is much shorter than HGA’s at the same solution quality. Full article

Based on the large volume of observational data obtained from Argo and several satellites, an increasing number of datasets are being developed and applied to oceanographic research. However, there are still problems such as sparse subsurface observations, insufficient parameters, and weak pertinence. This study provides a basic framework for high-resolution data fusion that focuses on the multi-source observations in the Western North Pacific. Multi-source observations from satellites, Argo floats, and historical in situ profiles are fused using a statistical model and a gradient-dependent optimal interpolation method. A daily gridded dataset with a 0.25° horizontal resolution is developed, which includes temperature, salinity, and currents. The results show that the correlation coefficients between the observations and the inverted profiles of temperature and salinity are about 0.99 and 0.94, respectively, with mean root mean square errors of about 1.27 °C and 0.13, respectively. In the Northwest Pacific Ocean, the most suitable parameter settings are a search radius of 1.5° in longitude and latitude, correlation scale constant of 0.25°, and relative observation error of 2. Consequently, the average RMSEs of the fused temperature and salinity fields are 0.43°C and 0.056, respectively. Compared with other reanalysis datasets, the product constructed in this study retains more high-frequency ocean signals, and its temperature error relative to XBT observations is also the smallest. Furthermore, the dataset effectively depicts the characteristics of marine dynamic processes such as the Kuroshio paths and mesoscale eddies. Full article

The modern power system is characterized by large-scale networks, diverse types of sources and loads, and complex grid structures. Virtual Power Plants (VPPs) are proposed to address the operation problem after the integration of Distributed Energy Resources (DERs). Optimization problems in the VPP operation are predominantly mixed-integer programming (MIP) problems belonging to the class of NP-hard problems, motivating the application of quantum computers. Focusing on the VPP optimal dispatch problem under wind and solar uncertainty, we employ the Model Predictive Control (MPC) framework to conduct the VPP intraday rolling dispatch. The classical model and the Quadratic Unconstrained Binary Optimization (QUBO) model for the MPC-based intraday rolling dispatch problem are formulated, respectively. The QUBO formulation of the VPP dispatch problem renders it directly solvable by a specialized quantum computer based on dissipative optical systems: the Coherent Ising Machine (CIM). Compared with the benchmark classical solvers, the experimental results demonstrate the significant computational time reduction capability of CIM. Specifically, compared to Gurobi, Simulated Annealing and Tabu Search, the CIM achieves relative computational time reductions of $75.25\%$, $99.95\%$ and $99.96\%$, respectively, while maintaining competitive solution quality. Our work demonstrates the applicability of CIM and its acceleration potential in VPP intraday rolling dispatch, paving the way for the practical application of specialized photonic quantum computers in smart grids. Full article

Bridge structural health monitoring (SHM) systems often suffer from large-scale data missing due to sensor faults, communication interruptions and other reasons during long-term operation, which seriously restricts the reliability of structural state assessment and maintenance decision-making. Compared with conventional single-channel independent modeling strategies commonly used for data imputation, their inherent neglect of spatial correlations and cross-modal causal associations among multi-source heterogeneous monitoring data such as displacement, wind speed, and temperature constrain the imputation capability, particularly when the target channel suffers from long-term continuous data loss. To address the above problems, this paper proposes a collaborative imputation framework integrating a graph attention network (GAT), a modal-aware cross-attention (MACA) mechanism and temporal encoder–decoder architecture (ITimeGAN). Firstly, the sensor feature topological graph is constructed based on the Pearson correlation coefficient, and the spatial dependency among multi-source features is adaptively learned through GAT. Then, the MACA module is introduced, which takes the target displacement as Query and environmental loads as Key/Value, and dynamically aggregates cross-modal driving information through multi-head attention. Finally, a bidirectional LSTM encoder and a unidirectional LSTM decoder are adopted to capture long-range temporal dependencies, so as to realize the accurate reconstruction of missing displacement data. Validated on the 9-dimensional real-world monitoring data from the GeoSHM system of the Forth Road Bridge (UK) under both random missing (10–50%) and continuous long-term missing (1–10 days) scenarios, ITimeGAN achieves an R² of 0.9950 (MAE = 4.25 mm) for longitudinal displacement and 0.9759 (MAE = 6.70 mm) for vertical displacement even under 10 consecutive days of complete data absence. Ablation analysis further reveals that the incorporation of graph attention and cross-modal attention modules reduces the longitudinal displacement MAE by 57% over the baseline, with the imputation performance ranking across three displacement directions being fully consistent with the underlying physical correlation strengths, thereby confirming the effectiveness of the proposed cross-modal collaborative strategy. Full article

Concrete wall cavities are common hidden defects in construction engineering that seriously reduce structural safety, durability, and construction quality, especially in old buildings and projects without complete design documents. Traditional detection methods have obvious limitations: the manual tapping method relies heavily on subjective experience and lacks quantitative standards, while advanced non-destructive testing methods such as ultrasonic testing and infrared thermography are expensive, complex to operate, and difficult to apply on a large scale. At present, the quantitative correlation between acoustic signal characteristics and cavity defects has not been fully studied. To address these problems, this study combines literature analysis, controlled experiments, and acoustic signal processing to propose a quantitative identification method for concrete wall cavities based on autocorrelation analysis of sound signals. Tapping signals from normal and cavity walls are collected and processed using band-pass filtering and amplitude normalization. The autocorrelation function (ACF) is then used to extract characteristic parameters. The results show that the proposed method exhibits significantly improved accuracy and efficiency compared with traditional manual detection. Obvious differences in autocorrelation characteristics can be observed between normal and cavity walls. The method realizes the transformation from subjective auditory judgment to objective quantitative identification, with low cost, strong anti-interference ability, and high sensitivity to small defects. It provides a reliable technical tool for the rapid and quantitative non-destructive testing of concrete wall cavities in engineering practice. Full article

With the deepening integration of 5G-Advanced (5G-A) technology into smart manufacturing, the large-scale deployment of dynamic terminals—such as mobile robots and automated guided vehicles (AGVs)—within industrial private networks introduces complex, time-varying penetration and path losses. This significantly degrades the accuracy of conventional signal quality and capacity estimation methods, which were primarily designed for static terminal scenarios, thereby posing substantial challenges to coverage and deployment planning of industrial 5G access points, with downstream implications for power capacity dimensioning. To address this problem, this paper proposes a coverage-driven base station deployment optimization method formulated as a combinatorial optimization problem. The study constructs a signal strength assessment and network throughput calculation model tailored for dynamic industrial environments. This model captures the joint impact of terminal mobility and environmental obstacles on signal propagation, thereby enabling more reliable estimation of coverage performance and power consumption. Furthermore, by formulating the base station placement optimization as a combinatorial optimization problem, and by introducing mechanisms for equivalent transformation of the objective function and data preprocessing, the proposed method substantially reduces redundant computations during heuristic iterations. Simulation results verify that, compared with conventional static planning approaches, the proposed scheme enhances both the accuracy and computational efficiency of deployment planning while maintaining coverage quality. This work provides a theoretical foundation and a practical methodology for deploying reliable and energy-efficient industrial 5G-A private networks. Full article

Association rule mining is a fundamental data mining technique for uncovering latent relationships among variables in large-scale datasets. However, conventional approaches rely on single-metric filtering strategies, which are insufficient for capturing the inherent multi-criteria nature of rule quality. To address this limitation, this study formulates ARM as a many-objective optimization problem and proposes a hybrid algorithm, NSGA-II/DE-ARM, that simultaneously optimizes four rule-quality measures: support, confidence, lift, and NetConf. The proposed algorithm enhances the NSGA-II framework by integrating binary differential evolution operators, an adaptive operator selection mechanism, lift-weighted tournament selection, and a constraint-domination principle combined with a dynamic minimum support threshold. Its performance was evaluated using two datasets: a SIPRI–World Bank panel dataset consisting of defense industry and macroeconomic indicators covering 46 items over the 2002–2023 period, and the UCI Mushroom benchmark dataset consisting of 118 items. Across 30 independent runs on the SIPRI–World Bank dataset, NSGA-II/DE-ARM outperformed the Apriori baseline in all four metrics (mean lift = 4.748, confidence = 0.853, support = 0.146, NetConf = 0.789), with large effect sizes (Cohen’s d = 1.77–5.77, p < 0.001 in each case). On the Mushroom benchmark dataset, the proposed method also achieved substantial improvements, with Cohen’s d values ranging from 0.93 to 6.16. NSGA-II/DE-ARM generated 68 Pareto-optimal rules in a representative run and achieved the highest hypervolume values on both datasets, with HV = 3.231 for SIPRI–World Bank and HV = 6.262 for Mushroom. These results suggest that NSGA-II/DE-ARM offers decision-makers a broader and more balanced multi-criteria solution set than single-metric filtering approaches. Full article

With the large-scale deployment of distributed photovoltaics (PVs) on the user side, integrated PV-storage systems have become a critical means to reduce electricity costs and enhance energy flexibility. However, the volatility of PV output and the dynamic nature of time-of-use (TOU) pricing render the economic viability of such systems highly dependent on the coordinated optimization of capacity configuration and operational strategies. To address this, a bi-level optimization model is developed. The upper level maximizes the equivalent annual economic benefit by determining the installed capacities of PV and storage, explicitly incorporating power-sensitive operation and maintenance costs. The lower level, formulated as a mixed-integer programming problem, minimizes the daily net electricity cost by optimizing charging/discharging schedules and grid interaction. The model is solved through an iterative hierarchical approach combining the chaotic sparrow search algorithm (CSSA) and the CPLEX solver. A case study using actual data from an industrial park demonstrates that, compared with scenarios without PV-storage and with PV only, the joint PV-storage configuration reduces total electricity costs by 17.3% and 4.5%, respectively. Furthermore, the asymmetric impacts of PV forecast errors on operational economics are quantitatively analyzed: when PV output is underestimated, the failure to pre-reserve accommodation capacity leads to an increase in electricity procurement costs of RMB 1927.84 compared with the ideal scenario. To mitigate this, a risk-aware fault-tolerant scheduling strategy is proposed, which reserves a 5% accommodation margin through conservative biasing, reducing the additional cost caused by forecast errors by 20.14% and significantly enhancing the system’s economic robustness under forecast uncertainty. Full article

The rapid evolution of next-generation electronics urgently demands high-performance functional materials. Two-dimensional (2D) semiconductors, characterized by tunable bandgaps, magnetic properties, and excellent optical and electronic properties, hold significant potential for applications in nanoelectronic devices, magnetic storage, and optoelectronics. However, the high computational cost of traditional Density Functional Theory (DFT) severely restricts large-scale high-throughput screening. Meanwhile, problems such as insufficient datasets and non-uniform data quality remain prevalent. Against this background, machine learning (ML), which captures intricate nonlinear correlations and accelerates the discovery of novel materials, has emerged as an efficient technical approach. This review systematically summarizes recent advances in ML-driven property prediction for 2D semiconductors. It first elaborates the fundamental properties and classifications of 2D semiconductors, and then compares traditional computational simulations with ML algorithms, clarifying the distinct advantages of data-driven approaches. Subsequently, this work focuses on the latest progress in predicting critical properties, including bandgap, magnetism, and other physical characteristics. For bandgap prediction, classical algorithms such as random forests are compared with deep learning models represented by graph neural networks. The results demonstrate that deep learning performs much better in low-data regimes and complex material systems. For magnetic property prediction, the impact of feature engineering strategies on model accuracy and efficiency is systematically analyzed. In addition, the research progress of other physical property prediction tasks is briefly summarized. Finally, future research directions for machine learning, including standardized materials databases, physics-informed machine learning, multimodal modeling, and the integration of machine learning with experimental and theoretical methods, are outlined to address challenges in data quality, model interpretability, and cross-system generalization ability. This work aims to provide a systematic theoretical foundation and methodological guidance for research on two-dimensional semiconductor materials assisted by machine learning. Full article