Search Results (994)

The widening gap between life expectancy and healthy life years underscores the need for scalable, adaptive, and privacy-conscious healthcare solutions. In this study, we integrate the AMPER (Aim–Measure–Predict–Evaluate–Recommend) framework with Bidirectional Encoder Representations from Transformers (BERT), Automated Machine Learning (AutoML), and privacy-preserving Federated Learning (FL) to deliver personalized hypertension management. Building on sequential data modeling and privacy-preserving AI, we apply this framework to the MIMIC-III dataset, using key variables—gender, age, systolic blood pressure (SBP), and body mass index (BMI)—to forecast future SBP values. Experimental results show that combining BERT with Moving Average (MA) or AutoRegressive Integrated Moving Average (ARIMA) models improves predictive accuracy, and that personalized FL (Per-FedAvg) significantly outperforms local models while maintaining data confidentiality. However, FL performance remains lower than direct data sharing, revealing a trade-off between accuracy and privacy. These findings demonstrate the feasibility of integrating AutoML, advanced sequence modeling, and FL within a structured health management framework. We conclude by discussing theoretical, clinical, and ethical implications, and outline directions for enhancing personalization, multimodal integration, and cross-institutional scalability. Full article

The evolution of the winemaking industry towards intelligent and digitalized systems is crucial for precision winemaking and ensuring product safety. In this context, the Internet of Things (IoT) provides a key strategy for real-time monitoring and data management throughout the winemaking process. However, comprehensive multi-parameter IoT-based monitoring and time-series prediction of physicochemical parameters during storage are currently lacking, limiting the ability to assess storage conditions and provide early warning of quality deterioration. To address these gaps, a multi-parameter IoT monitoring system was designed and developed to track conductivity, dissolved oxygen, and temperature in real time. Data were transmitted via a 4th-generation (4G) mobile communication module to the TLINK cloud platform for storage and visualization. An 80-day storage experiment confirmed the system’s reliability for long-term monitoring, and analysis of parameter trends demonstrated its effectiveness in assessing storage conditions and wine quality evolution. Furthermore, Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Temporal Convolutional Network (TCN) models, and Autoregressive Integrated Moving Average (ARIMA) were implemented to predict physicochemical parameter trends. The TCN model achieved the highest predictive performance, with coefficients of determination (R²) of 0.955, 0.968, and 0.971 for conductivity, dissolved oxygen, and temperature, respectively, while LSTM and GRU showed comparable results. These results demonstrate that integrating IoT-based multi-parameter monitoring with deep learning time-series prediction enables real-time detection of abnormal storage and quality deterioration, providing a novel and practical framework for early warning throughout the wine storage process. Full article

The objective of this research is to understand the relationship between the tone of information released in government harvest reports, in extreme market conditions (rising and falling), and the behavior of agricultural commodity prices. In the period between January/2017 and February/2023, an autoregressive model of moving averages was used with a generalized autoregressive conditional heteroscedasticity approach. The evidence allows us to infer that investors can, on some occasions, use this information to direct their portfolios in order to balance risk and return. However, the full impact of the tone is not reflected immediately, possibly requiring time to be absorbed. Depending on the informational weight, the commodity, and the market context, there may or may not be an impact. This divergent empirical evidence indicates that there is a complex relationship between tone reading and asset pricing. Full article

China is one of the world’s largest tea-producing countries, and its fluctuations in production affect the international market and domestic economic stability. Existing research often uses limited predictive models at the local scale and lacks systematic national analysis. This study evaluated five models—autoregressive integrated moving average model (ARIMA), grey model (GM (1,1)), Markov chain grey model (Markov-GM (1,1)), particle swarm optimization Markov chain grey model (PSO-Markov-GM), and dynamic rolling update grey model (DRUGM (1,1))—using three stages of annual tea production data from China (2004–2023). The results indicate that DRUGM (1,1) has the lowest prediction error, demonstrating superior ability to capture production trends. The dynamic update mechanism of this model enhances its adaptability, providing an efficient and scalable framework for predicting the production level of tea and other crops. Accurate predictions are crucial for improving agricultural planning, optimizing resource allocation, and providing information for trade policy design. This study provides practical tools for sustainable agricultural decision-making, helping to strengthen rural economic stability and resilient food systems. Full article

Natural gas, a key low-emission energy source with significant strategic value in modern energy systems, necessitates accurate forecasting of its market price to ensure effective policy planning and economic stability. This paper proposes an ensemble framework to enhance natural gas price forecasting accuracy across multiple temporal scales (weekly and monthly) by constructing hybrid models and exploring diverse ensemble strategies, while balancing model complexity and computational efficiency. For weekly data, an Autoregressive Integrated Moving Average (ARIMA) model optimized via 5-fold cross-validation captures linear patterns, while the Long Short-Term Memory (LSTM) network captures nonlinear dependencies in the residual component after seasonal and trend decomposition based on LOESS (STL). For monthly data, the superior-performing model (ARIMA or SARIMA) is integrated with LSTM to address seasonality and trend characteristics. To further improve forecasting performance, three diverse ensemble techniques including stacking, bagging, and weighted averaging are individually implemented to synthesize the predictions of the two baseline models. The bagging ensemble method slightly outperforms other models on both weekly and monthly data, achieving MAPE, MAE, RMSE, and $R^2$ values of 9.60%, 0.3865, 0.5780, and 0.8287 for the weekly data, and 11.43%, 0.5302, 0.6944, and 0.7813 for the monthly data, respectively. The accurate forecasting of natural gas prices is critical for energy market stability and the realization of sustainable development goals. Full article

Background: The cerebral compliance (or compensatory reserve) index, RAP, is a critical yet underutilized physiological marker in the management of moderate-to-severe traumatic brain injury (TBI). While RAP offers promise as a continuous bedside metric, its broader cerebral physiological context remains partly understood. This study aims to characterize the burden of impaired RAP in relation to other key components of cerebral physiology. Methods: Archived data from 379 moderate-to-severe TBI patients were analyzed using descriptive and threshold-based methods across three RAP states (impaired, intact/transitional, and exhausted). Agglomerative hierarchical clustering, principal component analysis, and kernel-based clustering were applied to explore multivariate covariance structures. Then, high-frequency temporal analyses, including vector autoregressive integrated moving average impulse response functions (VARIMA IRF), cross-correlation, and Granger causality, were performed to assess dynamic coupling between RAP and other physiological signals. Results: Impaired and exhausted RAP states were associated with elevated intracranial pressure (p = 0.021). Regarding AMP, impaired RAP was associated with elevated levels, while exhausted RAP was associated with reduced pulse amplitude (p = 3.94 × 10⁻⁹). These two RAP states were also associated with compromised autoregulation and diminished perfusion. Clustering analyses consistently grouped RAP with its constituent signals (ICP and AMP), followed by brain oxygenation parameters (brain tissue oxygenation (PbtO₂) and regional cerebral oxygen saturation (rSO₂)). Cerebral autoregulation (CA) indices clustered more closely with RAP under impaired autoregulatory states. Temporal analyses revealed that RAP exhibited comparatively stronger responses to ICP and arterial blood pressure (ABP) at 1-min resolution. Moreover, when comparing ICP-derived and near-infrared spectroscopy (NIRS)-derived CA indices, they clustered more closely to RAP, and RAP demonstrated greater sensitivity to changes in these ICP-derived CA indices in high-frequency temporal analyses. These trends remained consistent at lower temporal resolutions as well. Conclusion: RAP relationships with other parameters remain consistent and differ meaningfully across compliance states. Integrating RAP into patient trajectory modelling and developing predictive frameworks based on these findings across different RAP states can map the evolution of cerebral physiology over time. This approach may improve prognostication and guide individualized interventions in TBI management. Therefore, these findings support RAP’s potential as a valuable metric for bedside monitoring and its prospective role in guiding patient trajectory modeling and interventional studies in TBI. Full article

Ground settlement caused by urban subway construction can significantly impact surrounding buildings and underground infrastructure, posing risks to structural safety and long-term performance. Accurate prediction of settlement trends is therefore essential for ensuring building integrity and supporting informed decision-making during construction. This study proposes a hierarchical prediction framework that incorporates waveform-based curve classification and machine learning to forecast ground settlement patterns. Monitoring data from the Urumqi Metro construction project are analyzed, and settlement curve types are identified using Fréchet distance, categorized into five distinct forms: inverse cotangent, exponential, multi-step, one-shaped, and oscillating. Each type is then matched with the most suitable predictive model, including the Autoregressive Integrated Moving Average (ARIMA), Attention Mechanism-enhanced Long Short-Term Memory (AM-LSTM), Genetic Algorithm-optimized Support Vector Regression (GA-SVR), and Particle Swarm Optimization-based Backpropagation neural network (PSO-BP). Results show that AM-LSTM achieves the best performance for inverse cotangent and large-sample exponential curves; ARIMA excels for small-sample exponential curves; PSO-BP is most effective for multi-step curves; and GA-SVR offers superior accuracy for one-shaped and oscillating curves. Validation on a newly excavated section of Urumqi Metro Line 2 confirms the model’s potential in enhancing the safety management of buildings and infrastructure in subway construction zones. Full article

This study investigates whether firm-specific narratives extracted from the news add predictive content to monthly stock return models. Using bidirectional encoder representations from transformer-based topic modeling (BERTopic), we processed Microsoft (MSFT) news and constructed monthly narrative activations (binary presence and decay weighting). These narrative activations are used in autoregressive moving-average models with exogenous regressors (ARIMA-X) to analyze MSFT monthly log returns alongside the U.S. Economic Policy Uncertainty (EPU) index from February 2021 to March 2025. Decay models using a similarity-distilled BERT embedding yielded three significant narratives: Media and Public Perception (MPP) (β = 0.0128, p = 0.002), Currency and Macro Environment (CME) (β = −0.0143, p < 0.001), and Tech and Semiconductor Ecosystem (TSE) (β = −0.0606, p = 0.014). Binary activation identifies reputational shocks: the Media and Public Perception (MPP) indicator predicts lower returns at one- and two-month lags (β = −0.0758, p = 0.043; β = −0.1048, p = 0.007). A likelihood-ratio test comparing ARIMA-X models with narrative regressors to a baseline ARIMA (no narratives) rejects the null hypothesis that narratives add no improvement in fit (p < 0.01). Firm-level narratives enhance monthly forecasts beyond conventional predictors; decay activation and similarity-distilled embeddings perform best. Demonstrated on Microsoft as a proof of concept, the ticker-agnostic design scales to multiple firms and sectors, contingent on sufficient firm-tagged news coverage for external validity. Full article

Addressing the problems of wind power’s anti-peak regulation characteristics, increasing system peak regulation difficulty, and wind power uncertainty causing frequency deviation leading to power imbalance, this paper considers the peak shaving and valley filling function and frequency regulation characteristics of energy storage, establishing a day-ahead and intraday coordinated two-stage optimization scheduling model for research. Stage 1 establishes a deterministic wind power prediction model based on time series Autoregressive Integrated Moving Average (ARIMA), adopts dynamic peak-valley identification method to divide energy storage operation periods, designs energy storage peak regulation working interval and reserves frequency regulation capacity, and establishes a day-ahead 24 h optimization model with minimum cost as the objective to determine the basic output of each power source and the charging and discharging plan of energy storage participating in peak regulation. Stage 2 still takes the minimum cost as the objective, based on the output of each power source determined in Stage 1, adopts Monte Carlo scenario generation and improved scenario reduction technology to model wind power uncertainty. On one hand, it considers how energy storage improves wind power system inertia support to ensure the initial rate of change of frequency meets requirements. On the other hand, considering energy storage reserve capacity responding to frequency deviation, it introduces dynamic power flow theory, where wind, thermal, load, and storage resources share unbalanced power proportionally based on their frequency characteristic coefficients, establishing an intraday real-time scheduling scheme that satisfies the initial rate of change of frequency and steady-state frequency deviation constraints. The study employs improved chaotic mapping and an adaptive weight Particle Swarm Optimization (PSO) algorithm to solve the two-stage optimization model and finally takes the improved IEEE 14-node system as an example to verify the proposed scheme through simulation. Results demonstrate that the proposed method improves the system net load peak-valley difference by 35.9%, controls frequency deviation within ±0.2 Hz range, and reduces generation cost by 7.2%. The proposed optimization scheduling model has high engineering application value. Full article

Clinical laboratories require accurate forecasting and efficient inventory management to balance service quality and cost under uncertain demand. In this study, we propose a hybrid forecasting–optimization framework tailored to hospital clinical determinations with highly irregular, zero-inflated, and asymmetric consumption patterns. Demand series for 34 items were modeled using Seasonal AutoRegressive Integrated Moving Average with eXogenous regressors (SARIMAX) structures combined with skew-normal (SN) and zero-inflated skew-normal (ZISN) residuals, with residual centering, truncation, and lambda regularization applied to ensure stable estimation. Model performance was benchmarked against Gaussian SARIMA and non-linear MLP forecasts. The SN/ZISN models achieved improved forecasting accuracy while preserving interpretability and explainability of residual behavior. Forecast outputs were integrated into a Particle Swarm Optimization (PSO) layer to determine cost-minimizing order quantities subject to packaging and budget constraints. The proposed end-to-end framework demonstrated a potential 89% reduction in inventory costs relative to the hospital’s historical policy while maintaining service levels above 85% for high-volume determinations. This hybrid approach provides a transparent, domain-adapted decision support system for supply chain governance in healthcare settings. Beyond the specific case of Chilean hospitals, the framework is adaptable to broader healthcare supply chains, supporting generalizable applications in diverse institutional contexts. Full article

Accurate water demand prediction is essential for optimizing the daily operations of water treatment plants and pumping stations. To achieve accurate prediction of water demand for university campuses, this study utilizes real hourly water consumption data collected over 380 observation days from a water treatment plant located on a university campus in Zhenjiang, Jiangsu Province. Based on periodicity analysis of the original data through Fast Fourier Transform (FFT) and autocorrelation coefficients, the data were preprocessed and aggregated into two-hour intervals. The processed water consumption data, along with temporal information (month, day of the week, date, and hour) and weather conditions (daily average wind speed, maximum and minimum temperature), were used as model inputs. The first 352 days of data were utilized to train the model, followed by 14 days serving as the validation set and the final two weeks as the test set. A hybrid forecasting model for campus water demand was developed by integrating a Back Propagation (BP) neural network with a Long Short-Term Memory (LSTM) neural network. The model’s performance was compared with standalone BP, LSTM, and Seasonal Autoregressive Integrated Moving Average (SARIMA) models. Simulation results demonstrate that, compared to other models, the proposed BP–LSTM hybrid model achieves a reduction in Mean Absolute Percentage Error (MAPE) ranging from 4.4% to 15.8%, and a decrease in Root Mean Squared Error (RMSE) between 2.5% and 16.8%. These findings indicate that the BP–LSTM model offers higher prediction accuracy and greater reliability compared to traditional single-model approaches. Full article

Air pollution represents a critical environmental challenge in stressed riverine cities, particularly in regions experiencing rapid urbanization and inadequate emission management infrastructure. This study investigates the spatio-temporal dynamics of atmospheric pollution in Baghdad, Iraq, during 2012–2023, analyzing seven key pollutants (CO, CO₂, SO₂, SO₄, O₃, CH₄, and AOD) using NASA’s Giovanni platform coupled with Google Earth Engine analytics. Monthly time-series data were processed through advanced statistical techniques, including Seasonal Autoregressive Integrated Moving Average (SARIMA) modeling and correlation analysis with meteorological parameters, to identify temporal trends, seasonal variations, and driving mechanisms. The analysis revealed three distinct pollutant trajectory categories reflecting complex emission–atmosphere interactions. Carbon monoxide exhibited dramatic decline (60–70% reduction from 2021), attributed to COVID-19 pandemic restrictions and demonstrating rapid responsiveness to activity modifications. Conversely, greenhouse gases showed persistent accumulation, with CO₂ increasing from 400.5 to 417.5 ppm and CH₄ rising 5.9% over the study period, indicating insufficient mitigation efforts. Sulfur compounds and ozone displayed stable concentrations with pronounced seasonal oscillations (winter peaks 2–3 times summer levels), while aerosol optical depth showed high temporal variability linked to dust storm events. Spatial analysis identified pronounced urban–rural concentration gradients, with central Baghdad CO levels exceeding 0.40 ppm compared to peripheral regions below 0.20 ppm. Linear concentration patterns along transportation corridors and industrial zones confirmed anthropogenic source dominance. Correlation analysis revealed strong relationships between meteorological factors and pollutant concentrations (atmospheric pressure: r = 0.62–0.70 with NO₂), providing insights for integrated climate–air quality management strategies. The study demonstrates substantial contributions to Sustainable Development Goals across four dimensions (Environmental Health 30%, Sustainable Cities and Climate Action 25%, Economic Development 25%, and Institutional Development 20%) while providing transferable methodological frameworks for evidence-based policy interventions and environmental monitoring in similar stressed urban environments globally. Full article

Accelerated digital transformations and the evolution of consumer behavior in recent years underscore the need for a systemic perspective in marketing analytics to better comprehend the complex interplay between technology, data, and the profound changes triggered by global events, such as the COVID-19 pandemic. The COVID-19 pandemic has catalyzed a massive shift toward digitalization and transformed e-commerce from an option to a necessity for both businesses and consumers. This paper analyzes the total store and non-store sales, as well as total e-commerce sales, of the US retail trade across six main business categories and nine subcategories from the first quarter of 2018 to the first quarter of 2024. The data was divided into three time spans, corresponding to pre-, during, and post-COVID-19 pandemic periods, to examine the changing behavior of US consumers over time for different business categories. The statistical and econometric methods employed are the partial autocorrelation function (PACF), autocorrelation function, autoregressive integrated moving average model, inferential statistics, and regression model. The results indicate that the pandemic significantly increased non-store retailer sales compared to the pre-pandemic period, underscoring the importance of e-commerce. When physical stores reopened, e-commerce sales did not decline to pre-pandemic levels. The PACF analysis showed seasonality and lagged correlations. Thus, the pandemic-induced buying behaviors of US consumers continue to influence current sales patterns. The pandemic was more than just a temporary disruption, which permanently changed the retail sector. Retailers that quickly adapted to online models gained a competitive edge, whereas US consumers became accustomed to the convenience and flexibility of e-commerce. The behavior of US consumers adapted not only in response to immediate needs during the pandemic but also led to longer-term shifts in spending patterns, with each category reacting uniquely based on product type and perceived necessity. The analysis of how the COVID-19 pandemic transformed consumer behavior in the US reveals several important implications for both consumers and trade policymakers. First, the long-lasting and structural shift toward e-commerce is confirmed, representing a fundamental change in the dynamics of demand and supply. For consumers, the convenience, flexibility, and accessibility of digital channels have moved beyond mere situational advantages to become a behavioral norm. This shift has empowered consumers by giving them greater access to price comparisons, more diverse options, and increased informational transparency. Additionally, the data shows the emergence of hybrid consumption models: essential goods are mainly purchased online, while purchases of branded clothing, electronics, furniture, luxury items, and similar products continue to favor the traditional retail experience. Full article

This study aimed to forecast the gross domestic product (GDP) of the South Caucasian nations (Armenia, Azerbaijan, and Georgia) by scrutinizing the accuracy of various econometric methodologies. This topic is noteworthy considering the significant economic development exhibited by these countries in the context of recovery post COVID-19. The seasonal autoregressive integrated moving average (SARIMA), exponential smoothing state space (ETS) model, neural network autoregressive (NNAR) model, and trigonometric exponential smoothing state space model with Box–Cox transformation, ARMA errors, and trend and seasonal components (TBATS), together with their feasible hybrid combinations, were employed. The empirical investigation utilized quarterly GDP data at market prices from 1Q-2010 to 2Q-2024. According to the results, the hybrid models significantly outperformed the corresponding single models, handling the linear and nonlinear components of the GDP time series more effectively. Rolling-window cross-validation showed that hybrid ETS-NNAR-TBATS for Armenia, hybrid ETS-NNAR-SARIMA for Azerbaijan, and hybrid ETS-SARIMA for Georgia were the best-performing models. The forecasts also suggest that Georgia is likely to record the strongest GDP growth over the projection horizon, followed by Armenia and Azerbaijan. These findings confirm that hybrid models constitute a reliable technique for forecasting GDP in the South Caucasian countries. This region is not only economically dynamic but also strategically important, with direct implications for policy and regional planning. Full article

This study proposes a four-module “decomposition–forecasting–ensemble–correction” framework to improve the accuracy of complex coal price forecasts. The framework combines Variational Mode Decomposition (VMD), adaptive Autoregressive Integrated Moving Average (ARIMA) and Gated Recurrent Unit (GRU)-Attention forecasting models, a data-driven weighted ensemble strategy, and an innovative error correction mechanism. Empirical analysis using the Bohai-Rim Steam–Coal Price Index (BSPI) shows that the framework significantly outperforms benchmark models, as validated by the Diebold–Mariano test. It reduces the Mean Absolute Percentage Error (MAPE) by 30.8% compared to a standalone GRU-Attention model, with the error correction module alone contributing a 25.1% MAPE reduction. This modular and transferable framework provides a promising approach for improving forecasting accuracy in complex and volatile economic time series. Full article