Search Results (215)

Power systems continuously generate large-scale load time series data for forecasting, consumption analysis, and equipment health monitoring. However, real-world load measurements are often contaminated by anomalies caused by sensor faults, communication errors, and abnormal consumption behaviors, which may degrade data quality and affect operational decision-making. To address this issue, this paper proposes an integrated anomaly detection framework named PEL, which combines Prophet-based seasonal-trend decomposition, ensemble empirical mode decomposition (EEMD), and a multilayer long short-term memory (LSTM) network. Prophet is first employed to decompose the original series into trend, seasonal, holiday, and residual components. Sample entropy analysis and white noise tests are then adopted to evaluate whether the residual component still contains complex structured information requiring secondary decomposition. Next, EEMD is applied to the residual component to extract multi-scale intrinsic mode functions. Finally, all decomposed components are normalized and fed into a multilayer LSTM model for anomaly detection. Experiments on a real-world power load dataset demonstrate that the proposed PEL framework achieves an accuracy of 99.92%, a precision of 97.33%, a recall of 100%, an F1-score of 98.65%, and an AUC of 0.9996, outperforming or matching several baseline and hybrid models. Full article

Tetracycline-class antibiotics are persistent contaminants in aquatic environments and are difficult to remove by conventional treatment processes. In this study, a recoverable granular MIL-101(Fe)/γ-Al₂O₃ catalyst was prepared through ligand anchoring followed by secondary Fe-MOF growth on spherical γ-Al₂O₃ and applied to catalytic ozonation of tetracycline (TC) under ordinary-bubble and microbubble-assisted operation. Structural characterization supported the formation of Fe-containing MOF domains on the alumina support, accompanied by an increase in BET surface area from 164.28 to 210.05 m² g⁻¹ and enhanced Lewis-acid-related pyridine-IR signals. Under conventional bubbling ozonation, the optimized catalyst achieved 67.93% apparent UV–Vis-based TC removal during an overall 50 min run consisting of 30 min dark adsorption followed by 20 min ozonation. In a 12 L microbubble reactor, the catalyst-assisted system reached 93.74% apparent UV–Vis-based TC removal at pH 6 with 100 g catalyst and 6 mg min⁻¹ fed ozone, showing higher apparent removal than ordinary ozonation, microbubble ozonation, and ordinary-bubble catalytic ozonation under the tested configuration. Phosphate-blocking and radical-quenching experiments were consistent with the involvement of Lewis-acid-related sites, hydroxyl radicals, and superoxide-related pathways, but these tests are interpreted as indirect mechanistic evidence. LC-MS analysis suggested possible hydroxylation, demethylation, deamidation, ring opening, and low-molecular-weight product formation. The system also transformed chlortetracycline, oxytetracycline, and doxycycline and reduced COD and TOC in a simulated mixed-antibiotic matrix. Because parent-compound HPLC/LC-MS time-series quantification, ozone utilization/off-gas ozone measurement, bubble-size/kLa analysis, and ICP-based Fe loading/leaching data were not available, the present work is positioned as an apparent catalyst–reactor coupling study rather than a complete catalytic, hydrodynamic, or process-level demonstration. Full article

The aim of this study was to determine the effects of PM10 and PM2.5 particulate matter pollution from the coal mining sector in the three municipalities of Cesar, La Guajira, and El Magdalena on respiratory morbidity in children under 5 years of age and adults over 60 years of age residing in these municipalities. This descriptive time series study included three municipalities in three departments: Algarrobo, Albania, and La Jagua de Ibirico. The SEVCA (Seasonal Environmental Monitoring System) was used to collect PM10 and PM2.5 pollutants. Data on secondary source air quality (RIPS) were collected from the public health services (ESE) in each municipality. The daily average concentration of μg/m³ was used for the statistical analysis of the pollutants. A time series statistical model was applied to compare the temporal variations in exposure levels and the event itself. The air quality data databases were analyzed using descriptive statistics. A logistic regression model was used to assess the association between pollutants and air quality. To account for the effects of time lags in air quality data, moving averages with lags of 0 to 3 days were used. Statistical analyses were performed using R version 4.5.1. We found daily averages of ARI in children under 5 years of age and adults over 60 years of age in the three municipalities of (1.35) admissions per day. The average daily concentrations of μg/m3 for Algarrobo were (29.79 μg/m³) for PM10 and (12.68 μg/m³) for PM2.5, for Albania (33.49 μg/m³) for PM10 and (13.23 μg/m³) for PM2.5, and for La Jagua (41.42 μg/m³) for PM10 and (15.18 μg/m³) for PM2.5. Significant positive associations greater than 1 were obtained between ARI admissions and PM10 and PM2.5 pollutants, with an RR of 1.105, 1.106, 1.125, 1.124, 1.157, and 1.155 95% CI, when PM10 and PM2.5 increase by 10 μg/m³ and for delays of 1 and 1–3 days. In conclusion, we observed significant positive associations between hospital admissions for ARI in children under 5 years of age and adults over 60 years of age for the three municipalities and the pollutants PM10 and PM2.5, which leads us to conclude that there is an epidemiological association and that the change in μg/m³ levels represents a change in the risk of hospital admission for ARI for children under 5 years of age and older adults in this coal corridor of the Colombian Caribbean. Full article

Background and Objectives: The SARS-CoV-2 pandemic disrupted oral and maxillofacial surgery (OMS) services worldwide because of the high aerosol-generating nature of head-and-neck procedures, restricted access to elective dental care, and systemic reallocation of hospital resources. Continuous longitudinal multi-year data covering both the pandemic and the post-pandemic phases from regional Romanian (and more broadly central and southeastern European) emergency centers remain scarce. We aimed to quantify the impact of the pandemic on OMS activity in a large Romanian regional referral center and to evaluate post-pandemic resilience. Materials and Methods: We conducted a retrospective single-center study of all inpatient admissions to the OMS Clinic of a tertiary emergency hospital in western Romania between 1 January 2018 and 31 December 2024. Three periods were pre-specified: pre-pandemic (2018–2019), pandemic (2020–2022) and post-pandemic (2023–2024). A Newey–West segmented interrupted-time-series (ITS) regression and a negative-binomial monthly count model with Fourier seasonality were fitted; length of hospital stay was further analyzed with a multivariable gamma-log generalized linear model adjusted for age, sex, county, primary ICD-10 chapter and total ICD-10 codes. Variables analyzed included case volume, demographics, primary and secondary ICD-10 diagnoses, length of hospital stay (LOS), case complexity (total ICD-10 codes per admission) and in-hospital mortality. Results: A total of 11,628 inpatient admissions corresponding to 8084 unique patients (56.5% male; mean age 52.2 ± 19.2 years) were analyzed. Compared with the pre-pandemic baseline (mean 2037 admissions/year), annual volume dropped by 45.1% in 2020, 44.0% in 2021 and 32.3% in 2022, with a nadir of −76% during the first state of emergency (April 2020; n = 34 admissions). Recovery was rapid; 2024 exceeded the pre-pandemic baseline by +10.1% on raw counts and by +16.2% on admissions per 100,000 catchment population using year-specific INS denominators. The segmented ITS regression confirmed an immediate level drop of −114.2 admissions/month in March 2020 (95% CI −133.1 to −95.3; p < 0.001) and a positive post-intervention slope of +2.06 admissions/month (95% CI 1.23–2.88; p < 0.001), with observed monthly volume returning to the counterfactual projection by October 2023. The case mix shifted significantly (χ² = 406.9, p < 0.0001); elective benign neoplasm admissions were reduced from 7.2% to 2.0%, while neoplasms of uncertain behavior nearly doubled from 15.7% to 27.5%. Case complexity increased during the pandemic (mean ICD codes 4.08 ± 2.42 vs. 3.44 ± 2.30; p < 0.001); after exclusion of administrative codes (whole Z chapter and U07.x), the difference attenuated to 3.34 vs. 3.17 codes (still p < 0.001 by Kruskal–Wallis), indicating that the largest portion of the unadjusted increase was driven by the new mandatory pre-admission SARS-CoV-2 screening code Z11.5 rather than true clinical complexity. Notably, the clinically interpretable proxy R63.3 (feeding difficulty) independently rose from 41.5% to 53.1%. The crude median LOS did not differ between the pre-pandemic and pandemic periods (3.07 vs. 3.06 d; p = 0.19) and dropped significantly post-pandemic (2.22 d; p < 0.001); however, after multivariable adjustment for case mix, age, sex, county and code count, the LOS was 15.7% shorter during the pandemic (adjusted ratio 0.84, 95% CI 0.82–0.87; p < 0.001) and 22.8% shorter post-pandemic (adjusted ratio 0.77, 95% CI 0.75–0.80; p < 0.001) relative to baseline. Conclusions: The pandemic caused a severe but transient contraction of OMS activity accompanied by increased case complexity and a marked shift away from elective surgery. Inpatient volume returned to and exceeded the pre-pandemic baseline by 2024. These results support the value of standing pandemic-preparedness protocols, sustained access to preventive dental care, and integrated tele-triage pathways for future public-health crises. Full article

Surface deformation induced by underground coal mining shows a clear time-lag effect, with persistent residual deformation in old goafs under strip pillar mining conditions, drawing significant research attention. This study focuses on the Gucheng mining area, where 210 Sentinel-1A SAR images (May 2017–January 2025) were processed using SBAS-InSAR to derive 7.5 years of time-series surface deformation. Based on these results, five strip pillar mining panels with different cessation times were selected. Through comparative analysis, a time-progressive sequence was constructed to identify post-mining residual deformation and stage-wise stabilization characteristics, and to reveal long-term deformation responses occurring years after cessation, thereby reconstructing the long-term evolution of surface deformation in old goafs. Furthermore, a stacking ensemble prediction model was developed to predict subsidence trends at representative feature points. The results indicate that subsidence mainly ranges from −20 to −10 mm/a, with a maximum of approximately −64 mm/a and cumulative subsidence of about −515 mm. Surface deformation follows a stage-wise evolution pattern of “residual subsidence—stage-wise stabilization—secondary subsidence—deformation stabilization”, with durations of approximately 2, 2, and 14 years, respectively, and overall stabilization occurring after approximately 18 years. The predicted results from the stacking model are highly consistent with the SBAS-InSAR monitoring data and can reliably describe the evolution trend of surface subsidence. The findings provide important evidence for understanding long-term surface deformation in old goafs of strip pillar mining areas. Full article

With the advancement of carbon peaking and carbon neutrality goals, the increasing penetration of renewable energy sources such as wind and photovoltaic power poses severe challenges to the power supply reliability of AC/DC hybrid distribution networks due to their fluctuating, intermittent, and stochastic outputs. This paper proposes a reliability assessment method for AC/DC hybrid distribution networks under large-scale renewable energy integration based on clustering of typical operating scenarios. The net load duration curve is adopted as the feature variable to characterize typical operating scenarios. An improved t-distributed Stochastic Neighbor Embedding (t-SNE) nonlinear dimensionality reduction method with Kullback–Leibler (KL) divergence elbow correction is proposed for effective reduction of high-dimensional time-series data. An adaptive Density-Based Spatial Clustering of Applications with Noise (DBSCAN) parameter optimization method based on the k-nearest-neighbor curve and a secondary K-means clustering method based on entropy-weighted multi-objective optimization are further developed, forming a hybrid t-SNE-DBSCAN–K-means clustering algorithm. The power supply reliability is then assessed based on the clustered typical operating scenarios. A typical AC/DC hybrid distribution network is used as the test system. Results show that the DB index of the proposed clustering method improves by at least 22% compared with conventional methods, the maximum relative error between the typical-day-based and full time-series simulation results is less than 6%, and the computational efficiency improves by about 8.8 times, achieving a good balance between accuracy and efficiency. Full article

Mauritius, as a Small Island Developing State (SIDS), depends heavily on tourism and is therefore exposed to external shocks; this study examines how the sector’s performance and value capture evolved from 2010 to 2025, with particular attention to the COVID-19 disruption and subsequent recovery. The analysis uses only secondary data, combining arrivals and source-market breakdowns published by the Ministry of Tourism with the monthly series of gross tourism earnings released by the Bank of Mauritius. Trends and seasonality are described for both arrivals and earnings, and three indicators are derived to support interpretation: revenue per arrival (as a proxy for value capture), the intensity of seasonality, and the concentration of source markets. The results document the magnitude of the pandemic-related break, trace the timing of the rebound, and show how value capture and market concentration shifted between the pre- and post-COVID periods. The paper concludes by discussing the implications for resilience in island destinations, highlighting the need for diversification and higher-value positioning, and proposing a replicable monitoring approach that can be updated as new official data become available. Full article

This study investigates the relationship between energy indicators and human development in South Africa over the period 1980–2023, employing a quantitative research design. Using secondary annual time-series data, the study examines the effects of electricity generation, per capita energy consumption, Oil-related fiscal revenue share as a share of total government revenue, and total energy consumption on the Human Development Index. The Autoregressive Distributed Lag (ARDL) bounds testing approach is employed to assess long-run and short-run relationships, complemented by Error Correction Models (ECM) to capture dynamic adjustments. Unit root and stability tests, including CUSUM and CUSUMSQ, ensure the robustness of the estimations, while Granger causality tests explore predictive linkages among variables. The findings reveal a positive long-run relationship between electricity generation and total energy consumption with human development, highlighting the importance of reliable and broad-based energy utilisation for enhancing welfare outcomes. In contrast, per capita energy consumption and Oil-related fiscal revenue share exhibit negative long-run effects, suggesting inefficiencies in energy use and the fiscal risks associated with reliance on oil-related government revenue. Short-run dynamics indicate that temporary adjustments, such as infrastructure expansion and transitional fiscal spending, can produce immediate but contrasting effects on human development. Granger causality analysis identifies unidirectional predictive relationships from electricity generation and Oil-related fiscal revenue share to human development, while total energy consumption exhibits weak bidirectional causality. Diagnostic tests confirm the model’s reliability and parameter stability over the study period. The results imply that energy policies in South Africa should prioritise efficient and inclusive energy use, ensure effective allocation of energy-related fiscal resources, and complement energy system improvements with broader socio-economic interventions. This study contributes to the understanding of the energy–development nexus in emerging economies, offering evidence-based insights for policymakers seeking sustainable human development. Future research could extend the analysis to provincial or sectoral levels, consider emerging energy technologies, and explore alternative development proxies to capture more nuanced socio-economic dynamics. Full article

This study compares the predictive performance of traditional multivariate time series models and machine learning (ML) techniques in modelling perceived feelings of safety among South African residents. The analysis uses secondary data from the Governance, Public Safety, and Justice Survey conducted by Statistics South Africa, covering 2013/2014 to 2023/2024 and comprising 215,301 observations. Perceived safety while walking alone in the neighbourhood during the day and after dark served as the response variables, while socio-economic characteristics such as age, sex, province, and main source of income were included as predictors. A Vector Autoregressive Moving Average (VARMA) model was estimated alongside Random Forest (RF) and Light Gradient Boosting Machine (LightGBM) algorithms. VARMA (2,2) and VARMA (3,1) provided the best statistical fit for daytime and after-dark safety perceptions, respectively. However, ML models achieved higher predictive accuracy overall, with RF outperforming both LightGBM and VARMA in capturing nonlinear relationships and short-term dynamics. The findings underscore the value of integrating ML into public safety modelling to enhance evidence-based planning and socio-economic policy development in South Africa. Future research should consider integrating higher-frequency and alternative data sources, such as administrative crime statistics and real-time behavioural data to improve model sensitivity and forecasting accuracy. Full article

Objective: To describe the experience of use of laser photobiomodulation in the management of orofacial neurosensory alterations and its clinical outcomes in a series of cases at a public university clinic in Northeast Brazil. Methods: A retrospective case series study was conducted using secondary data from 125 patients treated at the Biophotonics Center of the Federal University of Bahia between 2003 and 2019, all with a confirmed diagnosis of orofacial neurosensory alterations and who were referred to the service by other primary healthcare units in the municipality. Data collection included sociodemographic characteristics, clinical and dental history, and the main patient complaint. The therapeutic protocol consisted of infrared diode laser application (λ 700–808 nm) in continuous mode, performed every 48 h, totaling 12 individualized sessions per treatment cycle. Sensory evolution was monitored using the inverted Visual Analog Scale (VAS). Patients quantified their perceived sensitivity and discomfort at each session, assigning values from 0 to 10, and monitored symptom progression and treatment response over time. Data were analyzed using descriptive and analytical approaches. The study was approved by the Research Ethics Committee of UFBA (protocol 60327516500005024). Results: Tooth extraction was the most frequently reported etiological factor (60%), with an average of three treatment cycles per patient. At the end of follow-up, 67% of individuals reported changes in symptoms, including partial or complete resolution. Cases associated with orthognathic surgery required more treatment cycles; however, no statistically significant association was observed between the number of cycles and the reported outcomes. Conclusions: Laser photobiomodulation has been employed as a therapeutic approach in the management of orofacial neurosensory alterations in this clinical setting. The findings describe patterns of use and the distribution of patient-reported outcomes. Given the observational design, the results do not allow for causal interpretation or inference regarding treatment effectiveness. Full article

Background/Objectives: The ROSA^® Partial Knee System (Zimmer Biomet, Warsaw, IN, USA) is an imageless robotic platform developed to improve the reproducibility of tibial resection and implant positioning in unicompartmental knee arthroplasty (UKA). Evidence on imageless ROSA-assisted medial UKA remains limited. This preliminary single-center study evaluated the early radiographic accuracy of the system in reproducing planned tibial coronal alignment and tibial slope during robotic-assisted medial UKA, while perioperative and short-term clinical findings were assessed as secondary exploratory observations. Methods: A retrospective analysis of a prospectively maintained database was performed on 23 consecutive patients who underwent robotic-assisted medial UKA using the ROSA^® Partial Knee System and Persona^® Partial Knee implant between December 2025 and March 2026. Planned and robot-validated values were compared with postoperative radiographic measurements, which were used as the achieved alignment reference. Deviations >2° and >3° from target were defined as outliers. Paired clinical analyses were restricted to patients with data available at both time points. Results: Mean age was 68.4 ± 8.5 years and mean BMI was 28.2 ± 4.1 kg/m². Preoperative HKA was 5.4 ± 3.4° varus, while final robot-validated and postoperative radiographic HKA values were 2.3 ± 0.7° and 2.6 ± 0.9° varus, respectively (p = 0.08). Robot-validated and postoperative radiographic MPTA values were 2.0 ± 0.5° and 2.1 ± 0.7°, respectively (p = 0.41). Planned, robot-validated, and postoperative radiographic tibial slope values were 4.5 ± 0.6°, 4.6 ± 0.6°, and 4.8 ± 0.8°, respectively (p = 0.27). Mean absolute postoperative deviation from target was 0.42 ± 0.38° for HKA, 0.34 ± 0.29° for MPTA, and 0.46 ± 0.39° for tibial slope. Within 2° of target, accuracy ranged from 91.3% to 95.7%, and all cases were within 3°. Short-term clinical outcomes improved in the available paired subsets (n = 14 for VAS and KSS, n = 12 for ROM, and n = 9 for UCLA activity score). Conclusions: In this preliminary single-center observational series, the ROSA^® Partial Knee System showed high early radiographic accuracy in reproducing planned tibial coronal alignment and tibial slope during robotic-assisted medial UKA, with low outlier rates. Short-term clinical findings were favorable in the available paired subsets but should be interpreted as exploratory. Larger comparative studies with longer follow-up are needed to determine the clinical relevance of this technical accuracy. Full article

Introduction: Type 2 diabetes mellitus predisposes patients to neuropathy, peripheral arterial disease, and diabetic foot ulcers, which may become infected and progress to osteomyelitis, increasing the risk of amputation. The growing prevalence of multidrug-resistant organisms complicates management. Photodynamic therapy (PDT), which combines a photosensitizer with light-emitting diode irradiation to generate reactive oxygen species, has emerged as a potential adjunctive antimicrobial strategy without inducing resistance. Objective: To describe clinical outcomes observed in patients with diabetic foot osteomyelitis treated with adjunctive photodynamic therapy (PDT), with emphasis on wound evolution, limb preservation, and healing time. Methods: This prospective case series included patients with osteomyelitis secondary to infected diabetic foot ulcers treated at a university hospital. Demographic and clinical data were collected from medical records. Serial photographic documentation was used to monitor wound progression and tissue response during therapy. Results: Sixteen patients with diabetic foot osteomyelitis were included. Complete healing was achieved in 13 patients (81.25%), while 2 patients (12.5%) remained under treatment with partial healing and 1 (6.25%) underwent major amputation. Among healed patients, healing time ranged from 19 to 546 days, with a median of 118 days. The number of photodynamic therapy sessions ranged from 2 to 12, depending on the clinical course of each case. Healing time varied among patients, and the hallux was the most frequent site of osteomyelitis. During follow-up, only one patient underwent major amputation, whereas the remaining patients either achieved complete healing or were still under treatment at the time of analysis. Healing time was comparable between insulin-dependent and non-insulin-dependent diabetes, although numerically shorter in the latter. Longer healing periods were associated with more treatment sessions. Conclusions: In this prospective uncontrolled case series, adjunctive PDT was associated with favorable clinical evolution in a subset of patients with diabetic foot osteomyelitis. However, because of the small sample size and the absence of a control group, these findings should be considered preliminary and hypothesis-generating. Full article

This study aimed to compare RNN algorithms and select the best-performing one between the GRU and LSTM for forecasting South African adjusted closing gold prices. The study used weekly secondary data sourced from Yahoo Finance and partitioned into three regimes, pre-COVID-19, COVID-19, and post-COVID-19, as well as the overall sample. The results indicated that the GRU algorithm consistently outperformed the LSTM algorithm across all evaluation periods based on the selected metrics, except during the COVID-19 period, where LSTM exhibited slightly better performance. Consequently, the GRU algorithm was identified as the best-performing algorithm for the South African adjusted closing gold price series. The relative effectiveness of GRU and LSTM algorithms in financial time series forecasting was clarified by the results. By integrating GRU-based forecasts into development finance frameworks, stakeholders can strengthen resilience against global shocks, improve financial planning, and foster more stable pathways for economic development. The authors recommended that future studies explore the performance of the GRU and LSTM with other advanced algorithms like Transformer architectures, hybrid algorithms, or traditional statistical methods to further enhance the forecasting robustness. Full article

Quercus pyrenaica (Willd.), a sub-Mediterranean oak, is expected to experience substantial distribution shifts under climate change, with some populations in Portugal at risk. Beyond climate-driven pressures, long-standing anthropogenic pressures have likely contributed to the species’ current vulnerability. This work aims to characterize the current status of closed-canopy Q. pyrenaica forests by providing a spatio-temporal assessment of forest fragmentation and its recent evolution. Using multispectral bands from Sentinel-2 time-series data, vegetation indices, embedding vectors generated by Google’s AlphaEarth foundational model, and topographic variables, we applied a machine learning Random Forest classifier to map Q. pyrenaica forests in 2019 and 2024 and to analyze their spatial configuration patterns. The findings indicate robust predictive performance (spatial cross-validation OA of 95.1%, Kappa of 83.7%, and F1 of 86.9%) and reveal the prominent role of AlphaEarth embedding features in the RF classifier, suggesting that these features are well-suited for classifying forest habitats of conservation importance. Quercus pyrenaica occurs predominantly at mid-elevations (~820 m a.s.l.), on gentle slopes (~9°), topographically neutral terrain, and northwestern-facing aspects, consistently across both years. Between 2019 and 2024, the Q. pyrenaica forest area showed an increasing signal. However, the results point to a landscape in an initial phase of forest recovery, constrained by land-use legacies, with cover increasing predominantly through the sprawl of small, geometrically complex, and poorly connected patches. Together, these results provide a baseline to track recent changes in Q. pyrenaica distribution and fragmentation, highlighting a contrast between apparent area expansion and declining overall structural integrity. In the future, patch connectivity and full recovery of secondary succession should be a priority for policymakers and forest owners. Full article

The dynamic response of the secondary circuit system in nuclear propulsion plants is critical to the power output, safety, and energy efficiency of nuclear-powered ships. High-fidelity thermo-hydraulic simulation models can accurately capture system transients but are computationally expensive and unsuitable for real-time applications. To address this limitation, this study proposes a reduced-order dynamic parameter prediction method that integrates high-fidelity simulation with deep learning. A multi-operating-condition simulation model of a typical nuclear-powered ship secondary circuit system is developed to generate time-series data covering load ramping and propulsion mode switching. Based on this dataset, a conventional recurrent neural network (RNN) and a multilayer long short-term memory (LSTM) network are constructed for multivariate autoregressive prediction of 17 key dynamic parameters, and their performances are systematically compared. Results show that the LSTM significantly outperforms the RNN in capturing long-term temporal dependencies, achieving average RMSE and MAPE values of 0.0228% and 0.365%, respectively. The proposed model completes 50-step-ahead prediction within 0.84 s, satisfying real-time requirements. The hybrid simulation-driven and data-driven framework provides a practical solution for intelligent monitoring and control optimization of nuclear-powered ship propulsion systems. Full article