Search Results (12,593)

Urban intersection traffic signals play a crucial role in managing traffic flow and ensuring road safety. However, traditional actuated signal controllers make phase-switching decisions based on limited local traffic information, without leveraging network-wide context from navigation services. In this paper, we propose CATS, a Context-Aware Traffic Signal control system that jointly optimizes intersection signal control and road navigation for Connected and Automated Vehicles (CAVs). CATS integrates two key components: a Best-Combination CTR (BC-CTR) scheme and the Self-Adaptive Interactive Navigation Tool (SAINT). BC-CTR enhances the original Cumulative Travel-Time Responsive (CTR) scheme through a two-step selection procedure: it first identifies the phase with the highest cumulative travel time (CTT) and then selects the compatible phase combination with the greatest group CTT, providing an explicit improvement over the single-combination evaluation of the original CTR that allows for a more accurate response to real-time intersection demand. SAINT provides congestion-aware route guidance via a congestion-contribution step function, directing vehicles away from congested segments while signal timings simultaneously adapt to incoming traffic. Under a 100% CAV penetration setting, SUMO-based simulations across moderate-to-heavy traffic conditions (vehicle inter-arrival times of 5 to 9 s) show that CATS reduces the mean end-to-end travel time by up to 23.72% and improves the throughput by up to 93.19% over three baselines (fixed-time navigation with enhanced signal control, congestion-aware navigation with original signal control, and fixed-time navigation with original signal control), confirming that the co-design of navigation and signal control produces complementary benefits. Full article

Large infrastructure projects frequently experience schedule slippage and cost escalation; however, time–cost planning still relies on expert-assigned activity parameters that fail to reflect the variability induced by construction modes, resource supply, and on-site conditions. This study focuses on activity-level multi-mode time–cost trade-off planning and its dynamic correction during project execution. The proposed methodology is intended for project-level short-term operational scheduling and rolling re-scheduling within a finite project execution horizon, rather than long-term strategic or portfolio-level scheduling. A predict–optimize–update framework is proposed, where light gradient boosting machine (LightGBM) is employed to predict the duration and direct cost of activity–mode pairs using unified features extracted from BIM/IFC records, schedule-resource ledgers, and cost-settlement data, covering engineering quantities, mode and resource decisions, and contextual factors. These predicted parameters are then fed into a time-indexed bi-objective mixed-integer linear program (MILP), which minimizes both project makespan and total cost (including indirect cost) to generate an interpretable Pareto frontier via a weighted-sum approach. Meanwhile, real-time monitoring updates refresh the predictors and re-solve the remaining project network to ensure dynamic adaptability. Validated on a desensitized proprietary enterprise multi-source dataset comprising 25 completed infrastructure projects and 5258 activity–mode samples, the proposed method achieves a mean absolute error (MAE) of 2.7 days and a coefficient of determination (R²) of 0.89 for duration prediction, as well as an MAE of 7.4 × 10⁴ CNY and an R² of 0.91 for direct-cost prediction. The generated Pareto set exhibits a diminishing return trend: as the project duration is relaxed from 101 to 146 days, the total cost decreases from 45.10 to 40.27 million CNY. A weather-triggered update case demonstrates that the completion forecast is revised from 133 to 128 days, with the total cost reduced from 53.05 to 52.75 million CNY. This framework enables explainable schedule–cost co-control, thereby effectively aiding decision-making for the planning and control of large infrastructure projects. Full article

Remote sensing semantic segmentation is fundamental to applications such as land-cover mapping, urban analysis, and environmental monitoring. However, remote sensing scenes often exhibit pronounced scale variation, fragmented regions, dense small objects, and complex boundary transitions, making fine-grained prediction particularly challenging. Transformer-based architectures such as SegFormer have demonstrated a strong capability in modeling long-range context through hierarchical encoding, yet their lightweight decoders mainly rely on linear projection and feature fusion, providing limited capacity for local refinement after multi-scale aggregation. This limitation may reduce spatial precision in boundary-sensitive and small-object-rich regions. To address this issue, we propose the Post-fusion Enhanced Block (PFEB), a lightweight decoder-side refinement module inserted after multi-scale feature fusion and before pixel-wise classification. PFEB combines channel expansion, depthwise and pointwise convolutions, efficient channel attention (ECA), and residual learning to enhance local semantic refinement while largely preserving computational efficiency. Built upon SegFormer, the proposed method was evaluated on two widely used remote sensing benchmarks, i.e., LoveDA and ISPRS Vaihingen, under both Mix Transformer-B0 (MiT-B0) and Mix Transformer-B2 (MiT-B2) backbones. Experimental results show that PFEB consistently improves the SegFormer baseline across datasets and model scales. Under MiT-B2 backbone, our method achieves 53.82 ± 0.31 mean intersection over union (mIoU) on LoveDA and 74.84 ± 0.41 mIoU on ISPRS Vaihingen. Boundary- and size-aware evaluations further indicate that the gains are mainly reflected in improved semantic correctness near boundaries and in the recoverability of small objects. With only modest additional cost (approximately +0.53 M parameters and +8.7 G floating point operations (FLOPs)), PFEB provides a favorable accuracy–efficiency trade-off. These results suggest that PFEB is an effective and lightweight post-fusion refinement module for improving fine-grained remote sensing semantic segmentation. Full article

Agriculture in the Pacific is driven primarily by small-scale private farmers, many of whom do not have access to soil testing services or advice, nor the means to interpret analytical results into soil management and agronomic recommendations. Soil degradation through the process of acidification poses a significant risk to food and income security as it directly threatens crop productivity. The nutritional quality of food crops may also be affected through sub-optimal nutrient uptake by plants and nutrient imbalances. The dataset reported here provides a useful platform for the development of a decision-support tool (DST) that will assist Fiji farmers in understanding and managing soil pH and soil acidity. The DST will enable making informed decisions about liming to help correct soil pH. To support this development, historical soil pH data available from the Pacific Soils Portal were combined with updated analyses of agricultural soils from 17 locations in Viti Levu Island (Fiji) collected during a field campaign undertaken in August 2025. The soils were sampled at two depth intervals (0–15 and 15–30 cm) and analyzed for pH using a variety of methods. These methods included direct field measurements using a portable pH-meter as well as traditional laboratory determinations. Of the soils sampled, it was found that most soils exhibited pH levels below 7, which were observed for both depth intervals. Across all samples taken in 2025, it was found that 54.3% of them had soil pH < 5, 38.6% had soil pH between 5 and 6, and 7.1% had pH > 6 (based on soil pH_1:5 soil-to-water method). Depending upon specific land uses, climate and cropping intensity, it was recommended that routine liming be built into soil fertility management programs to help farmers overcome soil acidity-related constraints to production. Liming frequency, timing of application and application rate will need to be determined for specific soil and cropping situations; however, it was suggested that soil pH was not changed by more than 1 unit each time lime was applied. Such an approach should reduce the risk of soil organic matter loss through accelerated mineralization, which would be challenging to restore in that environment if soils remained under continuous cropping. The analytical information contained in this article expanded and updated the datasets available in the Pacific Soils Portal. Furthermore, this work provided an opportunity to build analytical expertise in aspects of soil chemistry at local organizations to support academic and extension activities as well as the ongoing development of the Pacific Soils Portal. Full article

Background: Doctors have made increasing use of artificial intelligence-based clinical decision support systems in recent years in eastern China, but far less so in poorer western China, where hospitals with less access to specialized expert services might be expected to make greater use of such aids. Methods: This study of the reasons for lower uptake in the western hospitals focused on a tertiary referral hospital in the capital city of the poorest province in China. Drawing on UTAUT (unified theory of acceptance and use of technology) theoretical literature and previous studies, seven variables most likely to explain the limited adoption of the technology were identified and tested by means of an explanatory sequential mixed-methods study. Results: Initial bivariate tests revealed no significant differences across variables; however, multivariate logistic regression identified social influence as the sole statistically significant predictor of adoption willingness. Follow-up structured interviews revealed a surprisingly low awareness of the technology by medical personnel, with very limited deployment. Conclusions: The failure to adopt AI diagnosis technology is attributable not to the variables usually cited as factors inhibiting technology adoption but rather the failure of hospital and medical faculty administrators to acquire the technology and train doctors and medical students. Full article

Recurring socio-temporal events, such as Ramadan in Middle Eastern cities, introduce pronounced non-stationarity in urban traffic demand. During these periods, daytime traffic volumes typically decline, while congestion becomes more severe in the evening around the Iftar (fast-breaking) period and persists into late-night hours, making conventional fixed-time signal plans less effective. An additional challenge is that demand is not only time-varying, but also unevenly distributed across competing movements: attempts to prioritize high-volume phases can inadvertently cause excessive delays—or even starvation—on lower-demand approaches. To address these issues, this study presents an adaptive, regime-aware traffic signal control framework that combines predictive modeling with constrained optimization. Short-term phase-level delays are forecast using Long Short-Term Memory (LSTM) models, and a Model Predictive Control (MPC) scheme then determines the green time allocation at each control cycle through a receding-horizon strategy. The optimization explicitly represents phase interactions by including constraints that prevent excessive delay in competing movements, thereby yielding a balanced and operationally realistic control policy. The approach is validated with one-minute-resolution TomTom delay data from a signalized intersection in Jeddah, Saudi Arabia, covering both Normal and Ramadan conditions. The LSTM models show stable predictive performance, achieving root mean square errors (RMSEs) of 19.8 s under Normal conditions and 17.1 s during Ramadan. In general, the results show that the proposed framework cuts total intersection delay by about 0.3% to 2.8% compared to standard control strategies. Even though these total-delay improvements are small, they come with big drops in delay for lower-demand phases (about 12–20%) and keep the delay increases for higher-demand phases under control. This shows that the method makes the whole process more efficient by fairly spreading out the delay instead of just making one phase better on its own. The results show that combining forecasting with constrained optimization is a strong and useful way to handle changing traffic demand. This is especially true during times of high demand when flexibility, stability, and fairness across movements are all important. Full article

Background/Objectives: This study addresses the need for scalable and predictive strategies linking mixing conditions to nanocarrier properties by developing and analyzing a coaxial jet antisolvent process for the continuous production of pharmaceutical nanocarriers. Methods: A single experimental platform was used to generate both curcumin-based nanoparticles and nanoliposomes, enabling direct comparison of how mixing regime and formulation variables influence product characteristics. Results: Fluid-dynamic behavior was first characterized using tracer and micromixing experiments, revealing a strong dependence of mixing time on flow conditions, with characteristic mixing times decreasing from >1000 ms under laminar conditions to approximately 10–30 ms in turbulent regimes. Nanoparticles and liposomes obtained under optimized conditions exhibited mean sizes in the range of 120–250 nm, with polydispersity indices typically below 0.2 under optimized turbulent conditions. To rationalize these observations, a computational framework was implemented, combining Reynolds-averaged computational fluid dynamics with a population balance formulation solved by the method of moments. The model provided spatially resolved insight into solvent exchange, supersaturation development, and nucleation–growth dynamics, showing good agreement with experimental trends and capturing the effect of mixing conditions on particle size across different regimes. Conclusions: Although simplified, the modeling approach establishes the basis for future extensions toward full population-balance distribution simulations capable of predicting complete particle size distributions, highlighting the ability of the coaxial jet mixer to control supersaturation and particle formation through tunable hydrodynamic conditions. This capability makes the system particularly attractive compared to conventional batch or less controllable mixing technologies, enabling a more rational and scalable design of pharmaceutical nanocarriers, with good encapsulation performance as discussed in the main text. Full article

Background: Saudi Arabia has made significant progress toward malaria elimination; however, imported cases continue to occur, particularly in the southwestern regions. This study aimed to describe the clinical characteristics and outcomes of patients with malaria in the Aseer Region, Saudi Arabia. Methods: A retrospective observational study was conducted at Khamis Mushait General Hospital, Aseer Region, Saudi Arabia, including all patients with malaria from January 2022 to December 2025. Demographic, clinical, laboratory, and outcome data were extracted from the electronic medical records. Severe malaria was defined according to the World Health Organization criteria. Multivariate logistic regression using Firth’s penalized maximum likelihood estimation was performed to identify independent predictors of severe malaria (≥1 WHO criterion). Statistical analysis was performed using R software (version 4.2.1). Results: A total of 311 patients were included, predominantly male (90.0%), with a mean age of 28.8 ± 11.3 years. Ethiopian nationals comprised nearly half the cases (48.2%), followed by Saudi (16.4%) and Yemeni (15.1%) nationals. Plasmodium vivax was the most common species (51.1%), followed by Plasmodium. falciparum (40.2%). Fever was the most frequent symptom (89.4%), followed by fatigue (50.8%), chills (46.9%), and vomiting (39.5%). Low parasitemia (<1%) was the most frequent finding (33.8%), followed by moderate (27.3%) and mild (18.3%) levels, while high (4.2%) and very high parasitemia (1.9%) were uncommon. Severe malaria (≥1 criterion) was diagnosed at 43.7%, with severe anemia (26.0%) and jaundice (23.2%) being the most frequent WHO severity criteria. Notably, 84% of the cases occurred during 2024–2025, indicating a recent outbreak, with a sharp peak of 43 cases in October 2024. Multivariate logistic regression identified two independent predictors of having at least one WHO severity criterion: higher parasitemia level (adjusted OR = 1.70 per 1% increase, 95% CI: 1.40–2.11, p < 0.001) and non-Saudi nationality (adjusted OR = 2.40, 95% CI: 1.10–5.62, p = 0.027). Conclusions: Malaria in the Aseer Region predominantly affects young adult male expatriates, suggesting its imported nature. The predominance of P. vivax represents a shift from historical patterns. Parasitemia level and being of non-Saudi nationality independently predict severe malaria and may therefore support risk stratification and clinical decision-making. The dramatic case surge in 2024–2025 highlights regional vulnerability to outbreaks despite control progress. These findings support enhanced screening for at-risk populations, maintenance of clinical capacity for severe malaria management, and robust surveillance systems for early outbreak detection. Full article

Due to advancements in thermal engineering and nanotechnology, nanofluids—base fluids containing dispersed nanoparticles (1–100 nm)—have emerged as promising high-performance coolants. Their enhanced thermal properties make them attractive for application in hybrid-electric aircraft, which require efficient Thermal Management Systems (TMS) to dissipate significant heat loads. This study employs a dynamic TMS model to assess the influence of key nanofluid features, including nanoparticle type, volume fraction, particle diameter, and base fluid. Metal nanoparticles provided the greatest thermal improvement (up to 19%). Increasing concentration enhanced cooling efficiency, with 0.5%, 1%, and 2% volume fractions reducing mean temperature by 14%, 19%, and 24%, respectively. Smaller particles performed better, as 20 nm nanoparticles achieved a 21.3% temperature reduction compared to 17.5% for 60 nm. Water-based nanofluids exhibited the best overall thermal behaviour, although they remain unsuitable for aeronautical applications. Full article

Timely monitoring of tourism demand is essential for destination management, yet official monthly arrival statistics are often released with delays and can be difficult to use for near-real-time decision-making, particularly under structural shocks such as coronavirus disease 2019 (COVID-19). This study develops a fully reproducible, open-data nowcasting pipeline for Ecuador’s international tourist arrivals using a Python workflow. The framework integrates (i) the official monthly arrivals series published by Ecuador’s Ministry of Tourism (MINTUR), (ii) open online attention proxies from Wikipedia pageviews retrieved via the Wikimedia REST application programming interface (API), and (iii) open climate covariates derived from the ERA5-Land land reanalysis. Multiple forecasting models are evaluated under a rolling-origin, one-step-ahead backtest, with a mandatory seasonal naïve benchmark and a regime-aware assessment that separates a stress-test window (2019–2021) from an operational post-COVID window (2022–2025). Forecast accuracy is summarized using root mean squared error (RMSE), mean absolute error (MAE), and symmetric mean absolute percentage error (sMAPE), and statistical significance of performance differences is assessed using the Diebold–Mariano (DM) test. Results show that a ridge-regularized autoregressive model (ridge_ar) achieves the best overall accuracy, reducing RMSE by approximately 79% relative to the seasonal naïve baseline over the full evaluation window. Windowed results confirm robust performance during the shock period and sustained improvements in the post-2022 operational regime, while the incremental benefit of broader exogenous signals is heterogeneous across windows, underscoring the importance of regularization and regime-aware reporting. The proposed approach provides a transparent, low-cost blueprint for reproducible tourism monitoring that is transferable to other destinations using open data and standard computational tools. Full article

To meet the high-fidelity testing environment requirements for autonomous driving system development, driving simulators are gradually evolving from tools that “only provide scenes and interaction interfaces” into integrated verification platforms for autonomous driving capabilities. These simulators, in particular, need to feature testable and scalable decision-making modules. However, the autonomous driving functions in existing driving simulators mostly rely on rule-based or simplified model approaches, which are inadequate for depicting the complex interactions in real-world traffic and fail to meet the personalized decision-making needs under various driving styles. To address these challenges, this paper designs and implements a trajectory data-driven personalized autonomous driving decision system, using drone aerial imagery as the core data source to provide realistic background traffic flow and human-like decision-making capabilities. The proposed system can be interpreted as an integrated decision–planning–control framework deployed within a high-fidelity driving simulation platform. It consists of a driving style classification module based on drone trajectory data, a personalized decision module integrating inverse reinforcement learning and dynamic game theory, and a planning and control module. First, a natural driving database is built using 4997 real vehicle trajectories, and prior features of different driving styles are extracted through trajectory feature engineering and an improved K-means++ method. Based on this, a personalized decision-making framework that combines dynamic game theory and maximum entropy inverse reinforcement learning is proposed, aiming to learn the preference weights of different driving styles in terms of safety, comfort, and efficiency. Furthermore, the Dueling Network Architecture (DuDQN) is used to generate human-like lane-changing strategies. Subsequently, a real-time closed-loop execution of personalized decisions in the simulation platform is achieved through fifth-order polynomial trajectory planning, lateral Linear Quadratic Regulator (LQR) control, and longitudinal cascade Proportional–Integral–Derivative (PID) control. Experimental results show that the personalized decision model trained with drone data can realistically reproduce vehicle decision-making behaviors in natural traffic flows within the simulation environment and generate autonomous driving strategies that are highly consistent with different driving styles. This significantly enhances the humanization and personalization capabilities of the autonomous driving module in the driving simulator. Full article

High renewable penetration reduces effective inertia and increases frequency variability in microgrids, thereby limiting the performance of purely reactive frequency regulation. This paper presents a two-timescale frequency-support strategy based on bidirectional electric vehicles. The main novelty lies in introducing a learning-assisted correction layer between forecast-based aggregate regulation and final EV-level dispatch. Rather than replacing the predictive controller with an end-to-end data-driven policy, this layer uses measured fleet-state information to correct the supervisory aggregate request online before a final feasibility-preserving dispatch stage converts it into executable vehicle-level commands under concurrent power, energy, plug-in, and departure constraints. A supervisory predictive layer determines the aggregate support action from forecasted photovoltaic and load disturbances, whereas a lower real-time dispatch layer redistributes that action across the available fleet. Feasibility is enforced through an explicit projection stage prior to actuation. The method is assessed in simulation using measured campus operating profiles of irradiance, temperature, demand, frequency, and electric-vehicle availability. Across four representative operating days, the proposed strategy reduced the mean cumulative frequency deviation by 30.3% relative to droop control and by 24.7% relative to predictive-only operation, while reducing the mean time outside the admissible frequency band by 22.2% and 20.0%, respectively. Zero post-projection constraint violations were observed in all evaluated cases. These gains were obtained at the expense of higher actuation usage, thereby making the regulation–usage trade-off explicit. Full article

Background: To explore the correlation between spatial dose distribution and post-implant urinary toxicity, aiming to assist decision making in low-dose-rate (LDR) treatment planning, thereby improving patient outcomes. Methods: Eighty-five prostate LDR patients with >12-month follow-up were included. Patient-reported urinary toxicity was collected prospectively using the International Prostate Symptom Score (IPSS) questionnaire, from before implant (baseline) to post-implant follow-up. Patients were then grouped into those whose symptom scores returned to ≤2 points above baseline by 12 months (no long-term toxicity) vs. those who did not (long-term toxicity). A total of 106 features were extracted for each patient, including principal components of dose-volume histograms (DVHs) from multiple prostate subzones, the whole prostate and urethra, along with baseline IPSS, implantation characteristics, and additional DVH indicators for the prostate and the urethra. A machine learning (ML) model incorporating backward feature selection algorithm was developed to predict long-term toxicity status, using a shuffle-and-split validation strategy for model evaluation during feature selection. A univariate statistical analysis was conducted on the model’s selected features. Results: Out of 85 patients, 41 (48%) had long-term urinary toxicity. Seven features were selected during model training, including baseline IPSS and six dosimetric features from several prostate subzones primarily located in the posterior prostate. The model achieved a high mean area under the receiver operating characteristic curve (AUC) of 0.81, with a balanced sensitivity and specificity of 0.78 by adjusting the probability threshold. In univariate analysis, only baseline IPSS and one selected dose feature were significantly correlated with long-term toxicity with AUC < 0.71. Conclusions: The proposed ML model, integrating baseline IPSS and spatial dosimetric features, effectively predicts long-term urinary toxicity after prostate LDR. This approach offers a practical method for risk stratification, allowing clinicians to identify patients at elevated risk and prioritize them for targeted preventative measures and closer follow-up. Full article

Objective: Cerebral cavernous malformations (CCMs) are usually occult but can present with a symptomatic hemorrhage. Treatment recommendations for CCMs are still controversially discussed, as all CCMs have signs of chronic hemorrhage. The distinction of acute hemorrhage can be difficult, especially when patients only present with mild symptoms. Because of emerging evidence supporting inflammatory burden as a main avenue in the disease pathogenesis of CCMs, the aim of the present study was to investigate routine inflammatory parameters to support decision-making in ambiguous cases. Methods: A total of 87 patients who underwent CCM resection at the authors’ institution between 2008 and 2021 were included in this study. Data were recorded retrospectively. Patients were dichotomized into two groups: those with acute hemorrhage and those without, as a control group (e.g., resection for seizure control). Inflammatory parameters included C-reactive Protein (CrP), White Blood Cell Count (WBC), Red Cell Distribution Width (RDW), and Mean Platelet Volume/Platelet Count Ratio (MPV/PC). Results: The receiver operating characteristic curve demonstrated moderate diagnostic accuracy for predicting acute hemorrhage from CCM based on WBC at admission (AUC: 0.74, 95%-CI: 0.63–0.84) with a cut-off of ≥6.595 G/L. The multivariable analysis confirmed that having a WBC > 6.595 G/L is an independent predictor for acute hemorrhage of CCM (adjusted odds ratio: 4.5, 95%-CI: 1.8–11.2, p < 0.001). Conclusions: A white blood cell count >6.595 G/L was significantly associated with acute hemorrhage in CCMs and appears to be a quick-to-use biomarker in controversial cases. Moreover, leukocytosis emphasizes the involvement of neuroinflammation in acute hemorrhage of CCM. Further investigations are needed to analyze the precise role of inflammation in CCM pathogenesis and its impact on treatment strategies. Full article

Addressing the lack of high-fidelity test cycles for fuel cell light-duty trucks, this paper proposes an automated driving cycle construction method that integrates unsupervised clustering and reinforcement learning. Firstly, based on large-sample real-world driving data, four libraries of typical driving pattern segments are extracted through dimensionality reduction via Principal Component Analysis (PCA) and K-means clustering. Subsequently, the cycle construction process is formulated as a sequential decision-making problem, and a framework based on the Proximal Policy Optimization (PPO) algorithm, incorporating an action masking mechanism, is designed. This framework innovatively injects macro-level time budget allocation as a hard constraint into the agent’s policy space via action masking, while utilizing micro-level Markov transition probabilities as a soft guide. This dual approach drives the agent to learn an optimal segment concatenation strategy, thereby simultaneously ensuring both the macro-level statistical representativeness and the micro-level driving logic coherence of the synthesized cycle. Validation results demonstrate that the cycle constructed by the proposed method achieves an average relative error of only 7.53% in key characteristic parameters, and its joint speed-acceleration distribution exhibits a similarity as high as 0.9886 with the original data, significantly outperforming traditional methods such as the clustering method, the Markov chain method, and standard driving cycles. This study provides an effective tool for generating high-fidelity driving cycles and testing energy management strategies for fuel cell commercial vehicles. Full article