Search Results (1,153)

Unattended scheduled appointments (“patient no-shows” henceforth) adversely affect healthcare providers and patients’ health, disrupting the continuity of care, operational efficiency, and allocation of medical resources. Therefore, accurate predictive modeling is needed to reduce the impact of patient no-shows. Although machine learning methods, such as logistic regression, random forests, and decision trees, are widely used to predict patient no-shows, they often rely on hard decision splits and static feature importance, limiting adaptability to complex patient behaviors. To address this limitation, we propose a hybrid multi-head attention soft random forest (MHASRF) model that integrates attention mechanisms into a random forest using probabilistic soft splitting. It assigns attention weights across the trees, enabling attention on specific patient behaviors. The MHASRF model exhibited an accuracy of 88.24%, specificity of 91.21%, precision of 81.60%, recall of 82.01%, F₁-score of 81.81%, and area under the receiver operating characteristic curve of 94.07%, demonstrating high and balanced performance across metrics. It could also identify key predictors of patient no-shows at two feature-importance levels (tree and attention mechanism), providing deeper insights into patient no-shows. Thus, the proposed MHASRF model is a robust, adaptable, and interpretable method for predicting patient no-shows that can help healthcare providers optimize resources. Full article

The efficient scheduling of airport logistics vehicles is crucial for ensuring timely and cost-effective ground operations, particularly under dynamic disturbances such as flight delays, cancellations, and new task arrivals. With the increasing deployment of Internet of Things (IoT) technologies in airport environments, real-time data from sensors and connected devices enables efficient and adaptive scheduling. This paper considers a dynamic Airport Logistics Vehicle Scheduling (ALVS) problem that aims to minimize both vehicle usage and total task waiting time while satisfying task precedence and time window constraints. To address this problem, we propose a hybrid optimization framework, termed Periodic and Event-Driven Rolling Horizon Optimization (PERHO), which integrates periodic updates with event-driven rescheduling to adapt to real-time task variations in airport ground operations. Within PERHO, an Order-aware Adaptive Strategy Selection (OASS) algorithm is developed to dynamically select the most appropriate task sequencing heuristic from a candidate set based on recent performance and order relationships. Extensive experiments across various instance scales and dynamic scenarios demonstrate the effectiveness of the proposed PERHO-OASS approach. In experiments considering dynamic events, PERHO-OASS reduces vehicle usage and task waiting time by an average of 23.55% and 61.95%, respectively, over fixed heuristic algorithms, and by an average of 3.77% and 17.30% over adaptive selection methods, demonstrating strong robustness under uncertainty. The proposed approach can support airport operators in improving the efficiency and reliability of ground logistics operations. Full article

This paper presents a Digital Twin (DT)-based framework for the control, monitoring, and intelligent optimization of an Assembly/Disassembly/Repair Mechatronic Production Line (A/D/R MPL), developed as a laboratory platform aligned with Industry/Education 4.0/5.0 paradigms. The A/D/R MPL is assisted by two complementary cyber–physical robotic systems: an Assembly/Disassembly/Replacement Cyber–Physical Robotic System (A/D/R CPRS), and a Mobile Cyber–Physical Robotic System (MCPRS), enabling both fixed and mobile intelligent operations. The CPRS is equipped with an industrial robotic manipulator (IRM) responsible for A/D/R tasks, while the A/D Mechatronic Line (A/D ML) consists of seven interconnected workstations (WS1–WS7) dedicated to storage, transport, quality control, and final product handling. MCPRS includes a wheeled mobile robot (WMR), carrying a robotic manipulator (RM) and Mobile Visual Servoing System (MVSS). Each workstation is connected to a local slave programmable logic controller (PLC), which communicates via PROFIBUS with a master PLC located at the CPRS level. Additional communication infrastructures include LAN PROFINET and LAN Ethernet for local integration, and WAN Ethernet connectivity enabled through open platform Communication-Unified Architecture (OPC-UA), ensuring interoperability, scalability, and remote accessibility. Also, MODBUS TCP as serial industrial communication is used between the master PLC and the MCPRS. Virtual environment supports task planning through Augmented Reality (AR) and real-time monitoring through Virtual Reality (VR). The system behaviour is modelled with synchronized hybrid Petri Nets (SHPNs) which describe the discrete and hybrid dynamics of A/D/R processes. Artificial intelligence (AI) techniques are integrated into the DT framework for optimal task scheduling and adaptive decision-making. As a laboratory-scale implementation, the proposed system provides a comprehensive platform for experimentation, validation, and education. It supports Education 4.0/5.0 objectives by facilitating hands-on learning, human–machine interaction, and the integration of emerging technologies such as AI, Digital Twins, AR/VR, and cyber–physical systems. At the same time, it embodies Industry 4.0/5.0 principles, including interoperability, decentralization, sustainability, robustness, and human-centric design. Full article

Identifying and optimizing core factor configurations for anchorage operational safety under typhoon scenarios is critical to enhancing anchorage operational resilience and sustainable port development. This study develops a complementary hybrid SEM–fsQCA framework: key factors are identified via literature review and expert interviews; SEM quantifies factor correlations and contribution weights and corrects expert-evaluated anchorage capacity; six core factors are extracted, three typhoon types (heavy-rainfall, strong-wind, complex-track) are defined, and a coupled anchorage–typhoon case dataset is constructed. Subsequently, fsQCA performs necessary condition analysis and identifies causal configurations driving safety effectiveness. Based on these configurations, we establish a dynamic three-tier risk classification framework for refined anchorage management. Validated using 36 coupled cases (12 anchorages × 3 typhoon types) from Huizhou Port, a core hub in the Guangdong–Hong Kong–Macao Greater Bay Area, this framework enables adaptive vessel traffic scheduling throughout the entire typhoon cycle through dynamic tiered management. The proposed “identification-intervention-feedback” closed-loop governance model delivers theoretical rigor and operational implementation ability for coastal port typhoon risk mitigation. Full article

Hydrogen energy, owing to its advantages of low-carbon cleanliness, long-term storage capacity, and multi-energy coupling potential, has emerged as a crucial medium for enhancing renewable energy accommodation within integrated energy systems. However, the pronounced heterogeneity in hydrogen load behaviors, temporal characteristics, and regulation capabilities poses significant challenges for unified modeling approaches, which struggle to accurately capture the multi-modal regulation potential of hydrogen demand, thereby limiting the precision of system operation optimization. To address this issue, this paper proposes a data-driven hydrogen load flexibility modeling method for integrated energy system (IES) operation optimization. A hybrid LSTM-ISODATA framework is designed to extract deep temporal dependencies and identify six representative hydrogen consumption patterns from typical load sequences. Each hydrogen load category is decomposed into shiftable, transferable, and reducible flexible forms, and a category-specific time-varying flexibility constraint matrix is established to characterize differentiated regulation capabilities. An electricity–heat–hydrogen integrated energy system operation optimization model embedded with classified flexible hydrogen loads is developed and solved via mathematical programming. Simulation results show that the proposed method reduces system operating costs by 10.3% compared with conventional unified modeling, while significantly promoting renewable energy utilization and system operational flexibility. The effectiveness and engineering applicability of the proposed model in IES optimal scheduling are fully validated. Full article

The integration of large-scale electric vehicle (EV) fleets into vehicle-to-grid (V2G) systems offers significant potential for enhancing the operation of renewable-based smart grids. However, stochastic uncertainties in photovoltaic (PV) generation, vehicle availability, and load demand—coupled with battery degradation and life-cycle assessment (LCA) carbon emissions—pose major challenges to optimal scheduling. This paper proposes a scenario-based multi-objective MILP framework for a 500-EV fleet aggregator. The model incorporates Monte Carlo simulations for multi-source uncertainty quantification (±25% PV forecast errors, ±40% availability), LCA penalties (45 kgCO₂eq/kWh), and ancillary service revenues (25 USD/MW-h). Long-term state-of-health (SOH) projections, including a 1-year fade to 96.5%, are also integrated. Comparative analysis of V2X scenarios shows that the V2G Hybrid strategy reduces daily costs by 34.6% (from ~11,000 USD in the uncontrolled case to 7741 USD when reserve revenues are included), achieves over 50% peak shaving, and maintains voltage stability within 0.994–1.008 pu. The stochastic Pareto frontier identifies knee-point solutions that lower normalized expected costs to 134.61 while achieving 1–2% lower expected emissions compared to deterministic baselines. These results demonstrate a comprehensive framework, uncertainty-aware framework that balances economic viability, grid resilience, and environmental sustainability, offering actionable insights for fleet aggregators and policymakers working toward net-zero energy systems. Full article

Islanded microgrids face considerable operational difficulties because of the inconsistency of renewable energy sources and ongoing dependence on diesel power. This study offers a comparative assessment of a traditional rule-based energy management system versus an AI-augmented energy management system for a hybrid island microgrid that includes photovoltaic generation, wind generation, battery energy storage, and diesel generator. The suggested AI-driven controller incorporates short-term predictions and heuristic scheduling to enhance dispatch choices. Simulations using MATLAB and Simulink Ver-sion 25.2.0.2998904 (R2025b) over a 24 h period show enhanced management of battery state-of-charge, decreased operation of the diesel generator, and greater use of renewable energy. The findings show a decrease in fuel usage and carbon dioxide emissions of around 63% in comparison to the baseline rule-based approach. Full article

Accurate precipitation forecasting is essential for water resource management, flood early-warning systems, and agriculture, but remains difficult because of the nonlinear and highly variable spatiotemporal nature of rainfall. This paper compares four deep learning architectures—a standalone LSTM, a standalone CNN, a hybrid CNN–LSTM, and a Transformer encoder—against three classical baselines (persistence, day-of-year climatology, and per-grid-point ARIMA) for daily precipitation forecasting over Washington State at lead times of one to four days. A 40-year ERA5 dataset (1985–2024) of near-surface air temperature, mean sea-level pressure, and total precipitation is split into training (1985–2012), validation (2013–2015), and test (2016–2024) periods, with the test years held out completely. Each (model, horizon) is trained with three random seeds and evaluated in physical units (mm/day). On the held-out test period, the hybrid CNN–LSTM achieves the lowest RMSE at every horizon $h\ge 2$, with $R^2=0.576\pm 0.007$ and RMSE $=15.08\pm 0.07$ mm/day at $h=4$. Diebold–Mariano tests, paired t-tests, and bootstrap 95% confidence intervals confirm that the CNN–LSTM advantage over the LSTM is statistically significant at horizons 2–4 (but not at $h=1$), while CNN–LSTM is significantly better than every classical baseline and the Transformer at every horizon. The headline result is reproduced under a rolling-origin temporal cross-validation across three non-overlapping splits ($R^2\in [0.576,0.590]$). Practically, the sub-millisecond inference cost of the CNN–LSTM makes it directly deployable in operational forecasting pipelines used for flood early-warning, irrigation scheduling, and reservoir management, where even modest improvements in 3–4-day-ahead RMSE translate into measurable risk reduction and improved decision lead time for water managers and emergency planners. Full article

Sustainable manufacturing requires schedules that balance environmental responsibility with delivery reliability. This paper studies the Carbon-Aware Flexible Job Shop Scheduling Problem with Tardiness Penalty (CAFJSP-T), where total carbon emissions and total tardiness penalty are the primary objectives. We propose a Policy-based Rough Optimization with a Large Neighborhood Search (Pro-LNS) framework integrating Proximal Policy Optimization (PPO) and adaptive Large Neighborhood Search (LNS). PPO constructs a feasible schedule by selecting operation-machine assignments from job-readiness, machine-availability, earliest-completion, and critical-path features. This policy-generated schedule provides a structurally informed incumbent, enabling LNS to avoid unguided search and focus destroy-and-repair refinement on high-impact operations. Both phases use the same normalized scalarized carbon-tardiness objective, which guides PPO rewards and LNS removal, reinsertion, and acceptance while preserving precedence, eligibility, and capacity constraints. Experiments on small, medium, and large workcenter benchmarks show strong due-date performance and controlled carbon emissions. Under equal objective weighting, Pro-LNS achieves a median optimality gap of 6.12% relative to the exact formulation, with all instances within 14%, while requiring 4.08 s on average and at most 10.51 s. Comparisons with PPO-only, Advantage Actor-Critic (A2C), Soft Actor-Critic (SAC), and Genetic Algorithm (GA) schedulers show that Pro-LNS attains the best weighted scalarized objective across representative instance-weight settings. Friedman and Holm-corrected Wilcoxon tests confirm significant improvements over all competitors, with average weighted-objective gains of 4.90%, 7.25%, 8.81%, and 9.51% over PPO-only, A2C, SAC, and GA, respectively. These results demonstrate that Pro-LNS is an effective and computationally practical hybrid approach for carbon-aware, tardiness-sensitive flexible job shop scheduling. Full article

Despite growing interest in modular integrated construction (MiC) for public housing, procurement decisions remain dominated by initial cost comparisons that overlook broader social benefits. Quantitative evidence on the conditions under which these benefits can offset cost premiums is currently absent. This study identifies break-even conditions for high-rise modular public housing using a probabilistic life cycle sustainability assessment (P-LCSA). Four non-market social benefits—carbon reduction, safety improvement, waste reduction, and early occupancy—are monetized and evaluated through 10,000 Monte Carlo simulations for 17-story and 25-story public housing scenarios in Dongducheon, South Korea. Deterministic incremental social benefit–cost ratios (IS-BCRs) of 0.353 (17-story) and 0.226 (25-story) indicate that monetized benefits offset only 23–35% of cost premiums. Early occupancy dominates total benefits (87%), while Monte Carlo simulation confirms P(IS-BCR ≥ 1.0) = 0.00% in both scenarios. The contribution lies not in reporting a negative result, but in quantifying the viability gap and identifying decision-relevant thresholds. Break-even analysis shows reducing cost premiums to 8–10% as the most plausible pathway, while a hybrid package combining cost reduction, carbon pricing, and schedule compression achieves IS-BCR above 1.0. The study contributes a probabilistic decision-support framework that reframes the question from whether MiC is viable to what conditions are required for social justification. Full article

Background: Evidence supports the effectiveness and safety of open-source automated insulin delivery (AID) in patients with type 1 diabetes. However, evidence regarding the clinical application of open-source AID in perioperative patients with type 2 diabetes remains limited. Methods: This was an open-label, single-center, exploratory pilot randomized controlled trial (RCT) with parallel groups. Patients with diabetes (excluding type 1 diabetes mellitus) scheduled for elective surgery were randomly assigned to the closed-loop group (open-source hybrid closed-loop AID system) or the control group (conventional insulin pump). The primary outcome was the percentage of time in the target glucose range (TIR, 3.9–10.0 mmol/L). Other efficacy and safety outcomes were also compared between the groups. Results: A total of 49 participants were included and randomized to the closed-loop group (n = 25) or the control group (n = 24). Participants underwent abdominal, orthopedic, thoracic surgery, or neurosurgery during hospitalization. Patients in the closed-loop group had significantly higher TIR than patients in the control group (76.4 ± 14.1% vs. 61.2 ± 20.0%, p = 0.005). Compared with the control group, the closed-loop group also exhibited a 15.6 percentage point reduction in time above range (TAR, >10 mmol/L) without increasing time below range (TBR, <3.9 mmol/L). There were no episodes of severe hypoglycemia (<2.2 mmol/L) or diabetic ketoacidosis in either group. Conclusions: This study demonstrates that in patients with diabetes undergoing elective surgery, the open-source hybrid closed-loop AID system provides better glycemic control than conventional insulin pump therapy. Full article

Three-phase induction motors account for nearly two-thirds of industrial electricity consumption, making accurate parameter identification essential for efficiency optimization, predictive maintenance, and digital twin calibration. This paper introduces the stochastic spheric navigator algorithm (SSNA) for estimating the equivalent circuit parameters (stator and rotor resistances, leakage reactances, and magnetizing reactance) of induction motors by minimizing the normalized squared error between manufacturer-provided torque characteristics (starting, peak, and full-load) and their analytical counterparts derived from the steady-state Thévenin model. The SSNA employs an adaptive spherical search mechanism with a decaying radius schedule that progressively narrows the exploration neighborhood, enabling a balanced transition from global exploration to local refinement. Validated on 5 hp and 25 hp motors against the genetic algorithm (GA), particle swarm optimizer (PSO), hybrid GA-PSO, and sine–cosine algorithm (SCA), the SSNA demonstrates distinct advantages. For the 5 hp motor, it achieves the lowest errors in maximum torque ($1.34\times {10}^{-4}\%$) and full-load torque ($5.08\times {10}^{-4}\%$). For the previously unreported 25 hp motor, the SSNA yields an objective function value of $4.68\times {10}^{-12}$—six orders of magnitude lower than the SCA—and reduces magnetizing reactance estimation error from 46.55% (SCA) to 16.18%. Statistical analysis over 100 independent runs reveals that the SSNA uniquely combines the lowest minimum (best) value, the lowest maximum (worst) value, and the lowest standard deviation, demonstrating superior accuracy, reliability, and consistency. These results position the SSNA as a highly competitive optimization framework for induction motor parameter identification, with particular suitability for applications demanding high precision and robust performance. Full article

In recent years, cascaded hydropower (CHP) has been extensively leveraged to enhance the grid-connected penetration of photovoltaic (PV) generation. However, the inherent stochasticity and volatility of high-penetration PV often lead to significant renewable curtailment. To address this challenge, this paper proposes a coordinated day-ahead and intra-day scheduling model that incorporates curtailment risk assessment. The proposed framework employs a two-stage optimization architecture: the day-ahead stage establishes a baseline dispatch schedule with the objective of maximizing total energy production, while the intra-day stage refines this plan through multi-scenario optimization that explicitly accounts for curtailment risk. This synergistic mechanism achieves the objective of “maximizing day-ahead economic benefits and ensuring intra-day renewable accommodation”. Case studies on a specific river basin demonstrate the effectiveness of the proposed model. Simulation results indicate that, compared to conventional energy-maximization approaches, the proposed model significantly reduces intra-day curtailment rates and substantially enhances the integrated accommodation capacity of the hydro–solar hybrid system. Full article

As the number of unmanned aerial vehicles (UAVs) and the volume of computational tasks increase in UAV ad hoc networks (UAVANET), the solution space for task allocation strategies grows exponentially. In practical emergency scenarios with concurrent multi-user access, multi-UAV systems equipped with mobile edge computing (MEC) devices face challenges such as limited computing resources and imbalanced task distribution during task offloading. To address these challenges, this paper proposes an adaptive task allocation algorithm named AUSTA-DQHO (Adaptive UAV Swarm Task Allocation using Deep Q-networks and Genetic Algorithms Hybrid Optimization), which combines Deep Q-Network (DQN) with Genetic Algorithm (GA), aiming to optimize computational task scheduling and minimize both the total task delay and the variance in task delays. First, we introduce a multi-UAV-assisted MEC application framework. In this framework, UAVs equipped with high-performance computing modules are deployed as airborne servers in the target area, providing data offloading and task computation support for IoT devices. Next, to tackle the optimization problem, we replace the random action selection process in DQN with a hybrid strategy that incorporates heuristic methods—specifically, GA and greedy algorithms—to perform global search and make more effective decisions for optimal task allocation for each offloading request. Furthermore, to accelerate the convergence of the AUSTA-DQHO policy while ensuring global optimality, we introduce a pre-clustering mechanism and a dynamic weighting factor for randomly generated task offloading requests in the target area. These mechanisms effectively reduce the solution space and ensure that optimal actions are learned at different stages of the training process. Experimental results demonstrate that the proposed algorithm achieves a task latency reduction of 18.72% and a load balancing improvement of 98.72%, surpassing the performance of the other algorithms. Additionally, we explore the optimal number of UAVs under given environmental conditions to minimize the waste of computing resources. Full article

This paper introduces the ETMS-RCPSP (Earliness–Tardiness Multi-Skill Resource-Constrained Scheduling Problem)—a novel problem derived from the MS-RCPSP by adding constraints on project completion time or actual production contracts. The goal of the new problem is to control the project completion time as closely as possible to reality—this differs from the original MS-RCPSP, which aimed to minimize project execution time. The objective of the problem is of greater practical significance in ensuring project completion on schedule while also addressing related issues, such as the ability to receive finished products on time as stipulated in the contract. The ETMS-RCPSP is an NP-hard problem whose result can be used for resource allocation in project execution or for resource arrangement in production lines to fulfill economic contracts. To address the ETMS-RCPSP, the paper proposes a new evolutionary algorithm, BDERL (Balanced Differential Evolution with Reinforcement Learning), that combines differential evolution with a problem-specific decoding mechanism and an adaptive parameter control strategy based on reinforcement learning (Q-learning). The proposed algorithm is evaluated on benchmark instances derived from the iMOPSE dataset and the TNG company dataset—a real-world dataset from manufacturing and contract-driven environments. Experimental results demonstrate that the approach consistently reduces total production costs compared to baseline heuristics while maintaining competitive computational efficiency. The findings underscore the efficacy of adaptive hybrid optimization techniques in solving intricate production scheduling problems characterized by limited resources and varied skill competencies. Full article