Search Results (36,998)

Mild cognitive impairment (MCI), a transitional stage between normal aging and Alzheimer’s disease (AD), comprises three potential trajectories: reversion, stability, or progression. Accurate prediction of these trajectories is crucial for disease modeling and early intervention. We propose a novel analytical framework that integrates a healthy control–AD difference template (HAD) with a large-scale Granger causality algorithm based on long short-term memory networks (LSTM-lsGC) to construct effective connectivity (EC) networks. By applying principal component analysis for dimensionality reduction, modeling dynamic sequences with LSTM, and estimating EC matrices through Granger causality, the framework captures both symmetrical and asymmetrical connectivity, providing a refined characterization of the network alterations underlying MCI progression and reversion. Leveraging graph-theoretical features, our method achieved an MCI subtype classification accuracy of 84.92% (AUC = 0.84) across three subgroups and 90.86% when distinguishing rMCI from pMCI. Moreover, key brain regions, including the precentral gyrus, hippocampus, and cerebellum, were identified as being associated with MCI progression. Overall, by developing a symmetry-aware effective connectivity framework that simultaneously investigates both MCI progression and reversion, this study bridges a critical gap and offers a promising tool for early detection and dynamic disease characterization. Full article

The global pursuit of sustainable development amplifies renewable energy’s strategic importance, positioning wind power as a vital modern grid component. Accurate wind forecasting is essential to counter inherent volatility, enabling robust grid operations, security protocols, and optimization strategies. Such predictive precision directly governs wind energy systems’ stability and sustainability. This research introduces a novel spatio-temporal hybrid model integrating convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM), and graph convolutional networks (GCN) to extract temporal patterns and meteorological dynamics (wind speed, direction, temperature) across 134 wind turbines. Building upon conventional methods, our architecture captures turbine spatio-temporal correlations while assimilating multivariate meteorological characteristics. Addressing data integrity compromises from equipment failures and extreme weather-which undermine data-driven models-we implement Wasserstein GAN (WGAN) for generative missing-value interpolation. Validation across severe data loss scenarios (30–90% missing values) demonstrates the model’s enhanced predictive capacity. Rigorous benchmarking confirms significant accuracy improvements and reduced forecasting errors. Full article

The global economy frequently experiences cycles of rapid growth followed by abrupt crashes, challenging economists and analysts in forecasting and risk management. Crashes like the dot-com bubble crash and the 2008 global financial crisis caused huge disruptions to the world economy. These crashes have been found to display somewhat similar characteristics, like rapid price inflation and speculation, followed by collapse. In search of these underlying patterns, the Log-Periodic Power-Law (LPPL) model has emerged as a promising framework, capable of capturing self-reinforcing dynamics and log-periodic oscillations. However, while log-periodic structures have been tested in developed and stable markets, they lack validation in volatile and developing markets. This study investigates the applicability of the LPPL framework for modeling financial crashes in the Brazilian stock market, which serves as a representative case of a volatile market, particularly through the Bovespa Index (IBOVESPA). In this study, daily data spanning 1993 to 2025 is analyzed to model pre-crash oscillations and speculative bubbles for five major market crashes. In addition to the traditional LPPL model, autoregressive residual analysis is incorporated to account for market noise and improve predictive accuracy. The results demonstrate that the enhanced LPPL model effectively captures pre-crash oscillations and critical transitions, with low error metrics. Eigenstructure analysis of the Hessian matrices highlights stiff and sloppy parameters, emphasizing the pivotal role of critical time and frequency parameters. Overall, these findings validate LPPL-based nonlinear modeling as an effective approach for anticipating speculative bubbles and crash dynamics in complex financial systems. Full article

This study validates numerical models for mixed polymer combustion in a B-707 aircraft cargo compartment against Federal Aviation Administration test data. A simplified approach using a predefined mass loss rate was compared with a detailed model coupling in-depth heat transfer and pyrolysis kinetics based on the assumption of negligible co-pyrolysis effects. Both approaches reliably captured smoke dynamics and light transmission. The detailed model predicted the mass loss rate with high accuracy, matching the experimental value of 0.11 g/s at 200 s after the ignition. However, it significantly overpredicted the heat release rate with a peak value of 8 kW versus 5 kW in the experiment. This discrepancy was examined through a sensitivity analysis of key parameters: the radiative fraction, heat of combustion, turbulence model, and pyrolysis kinetics. The Smagorinsky model best captures the growth pattern of the heat release and mass loss rates, despite its larger deviation from the experimental data compared to other models. The analysis revealed that the radiative fraction and the activation energy of high heat-of-combustion materials like high-density polyethylene are the most influential parameters. One possible solution to the overestimation is the calibration of the activation energy and heat of combustion values for high-energy materials like HDPE. The results confirm the detailed model’s physical realism for fire spread modeling and highlight a path for improving its heat release rate predictions. Further investigation is required across a wider range of computational cases with varying sample mass fractions, compositions, geometries, and boundary conditions to establish the broader applicability of this approach. Full article

It is widely recognized that benthic sediment plumes generated by deep-sea mining may pose significant potential risks to ecosystems, yet their dispersion behavior remains difficult to predict with accuracy. In this study, we combined laboratory experiments with three-dimensional numerical simulations using the Environmental Fluid Dynamics Code (EFDC) to investigate the dispersion of sediment plumes composed of particles of different sizes. Laboratory experiments were conducted with deep-sea clay samples from the western Pacific under varying conditions for plume dispersion. Experimental data were used to capture horizontal diffusion and vertical entrainment through a Gaussian plume model, and the results served for parameter calibration in large-scale plume simulations. The results show that ambient current velocity and discharge height are the primary factors regulating plume dispersion distance, particularly for fine particles, while discharge rate and sediment concentration mainly control plume duration and the extent of dispersion in the horizontal direction. Although the duration of a single-source release is short, continuous mining activities may sustain broad dispersion and result in thicker sediment deposits, thereby intensifying ecological risks. This study provides the first comprehensive numerical assessment of deep-sea mining plumes across a range of particle sizes with clay from the western Pacific. The findings establish a mechanistic framework for predicting plume behavior under different operational scenarios and contribute to defining threshold values for discharge-induced plumes based on scientific evidence. By integrating experimental, theoretical, and numerical approaches, this work offers quantitative thresholds that can inform environmentally responsible strategies for deep-sea resource exploitation. Full article

Background/Objectives: Sleep disturbances are recognized as a common feature of Long COVID but detailed investigation into the specific nature of these sleep symptoms remain limited. This study analyzes comprehensive sleep questionnaire data from a Long COVID clinic to better characterize the nature and prevalence of sleep complaints in this population. Methods: We conducted a cross-sectional analysis of 200 adults referred to the Stanford Long COVID Clinic. Patients completed an intake questionnaire including three sleep-related items (unrefreshing sleep, insomnia, daytime sleepiness) rated on a 0–5 Likert scale. Additionally, patients completed the Alliance Sleep Questionnaire (ASQ), incorporating the Insomnia Severity Index, Epworth Sleepiness Scale, reduced Morningness–Eveningness Questionnaire, and modules for parasomnia, restless legs, and breathing symptoms. We calculated the prevalence of six sleep symptom domains. Standardized symptom data were analyzed using principal component analysis (PCA) and K-means clustering (k = 2) to explore latent phenotypes and used logistic regression to assess associations between demographic and clinical variables and each sleep complaint. Results: Sleep-related breathing complaints affected 57.5% of participants, insomnia 42.5%, and excessive daytime sleepiness 28.5%. Parallel analysis supported a nine-factor structure explaining ~90% of variance, with varimax rotation yielding interpretable domains such as insomnia/unrefreshing sleep, fatigue/post-exertional malaise, parasomnias, and respiratory symptoms. Gaussian mixture modeling favored a two-cluster solution (n = 94 and n = 106); one cluster represented a higher-burden phenotype characterized by greater BMI, insomnia, daytime sleepiness, gastrointestinal symptoms, and parasomnias. Logistic models using factor scores predicted insomnia with high accuracy (AUC = 0.90), EDS moderately well (AUC = 0.81), but extreme chronotype poorly (AUC = 0.39). In adjusted models, hospitalization during acute COVID-19 was significantly associated with insomnia (OR 4.41; 95% CI 1.27–15.36). Participants identifying as multiracial had higher odds of insomnia (OR 3.22; 95% CI 1.00–10.34), though this narrowly missed statistical significance. No other predictors were significant. Conclusions: Sleep disturbances are frequent and diverse in Long COVID. Factor analysis showed overlapping domains, while clustering identified a higher-burden phenotype marked by more severe sleep and systemic complaints. Symptom-based screening may help target those at greatest risk. Full article

Cloudbursts and other extreme rainfall events are becoming more frequent and intense, making precise forecasts and disaster preparedness more challenging. Despite advances in meteorological monitoring, current models often lack the precision needed for hyperlocal extreme rainfall forecasts. This study addresses the research gap in spatial configuration-aware modeling by proposing a novel framework that combines geometry-based weather station selection with advanced deep learning architectures. The primary goal is to utilize real-time data from well-placed Automatic Weather Stations to enhance the precision and reliability of extreme rainfall predictions. Twelve unique datasets were generated using four different geometric topologies—linear, triangular, quadrilateral, and circular—centered around the target station Chinchwad in Pune, India, a site that has recorded diverse rainfall intensities, including a cloudburst event. Using common performance criteria, six deep learning models were trained and assessed across these topologies. The proposed Bi-GRU model under linear topology achieved the highest predictive accuracy (R² = 0.9548, RMSE = 2.2120), outperforming other configurations. These findings underscore the significance of geometric topology in rainfall prediction and provide practical guidance for refining AWS network design in data-sparse regions. In contrast, the Transformer model showed poor generalization with high MAPE values. These results highlight the critical role of spatial station configuration and model architecture in improving prediction accuracy. The proposed framework enables real-time, location-specific early warning systems capable of issuing alerts 2 h before extreme rainfall events. Timely and reliable predictions support disaster risk reduction, infrastructure resilience, and community preparedness, which are essential for safeguarding lives and property in vulnerable regions. Full article

Traditional empirical correlations for predicting saturated flow boiling heat transfer coefficients (HTC) often struggle with accuracy and generalizability, particularly across different refrigerants, heat exchanger geometries, and operating conditions. To address these limitations, this study investigates the application of machine learning for more robust HTC prediction. A comprehensive dataset was compiled, consisting of 22,608 data points from over 140 published studies, covering 18 pure refrigerants under diverse experimental setups. The primary goal was to evaluate the performance of different machine learning approaches—Wide Neural Network (WNN), Linear Regression (LR), and Support Vector Machine (SVM)—in predicting HTCs across varying tube types and heat exchanger configurations. The results indicate that the WNN model achieved the highest predictive accuracy, with a Root Mean Square Error (RMSE) of 1.97 and a coefficient of determination (R²) of 0.91, corresponding to less than 5% prediction error for all refrigerants. These outcomes confirm that machine learning models can effectively capture the complex thermofluid interactions involved in boiling heat transfer. This work demonstrates that data-driven methods provide a reliable and generalizable alternative to empirical correlations. Full article

In response to the growing safety challenges posed by large-scale and specialized freight transportation on China’s rapidly expanding highway network, this study investigates the operational characteristics of trucks in interchange diverging areas—a critical segment with elevated accident risks. Leveraging high-frequency trajectory data collected from 16 interchanges, we analyze speed profiles and acceleration behavior of heavy trucks across key sections: the diversion influence zone, preparation zone, transition segment, and deceleration lane. A key contribution of this work is the development of a continuous speed prediction model based on Partial Least Squares Regression, which integrates road geometric parameters and driving behavior features to estimate speeds at four critical cross-sections of the diverging process. Furthermore, we propose a comprehensive safety evaluation framework incorporating three novel indicators: longitudinal speed consistency, lateral stability, and deceleration comfort. The model demonstrates strong performance, with all mean absolute percentage errors below 10% during validation using data from four independent interchanges. Comparative analysis with existing safety standards confirms the practical applicability and accuracy of the proposed methodology. This research offers three major contributions: (1) a systematic approach for processing large-scale trajectory data and predicting truck speeds in diverging areas; (2) a safety assessment framework tailored for geometric design consistency evaluation; and (3) empirical support for optimizing traffic safety facilities in interchange design and operation. The findings address a significant gap in current highway design guidelines and provide actionable insights for enhancing safety in truck-dominated transportation environments. Full article

Water quality is an essential part of maintaining a healthy environment for fish farming. The quality of the water is related to a few of the chemical and biological characteristics of water. The conventional evaluation methods of the water quality are often time-consuming and may overlook complex interdependencies among multiple indicators. This study has proposed a robust machine learning framework for aquaculture water quality classification by integrating the Honey Badger Algorithm (HBA) with the XGBoost classifier. The framework enhances classification accuracy and incorporates explainability through SHAP and DiCE, thereby providing both predictive performance and transparency for practical water quality management. For reliability, the dataset has been randomly shuffled, and a custom 5-fold cross-validation strategy has been applied. Later, through the metaheuristic-based HBA, feature selections and hyperparameter tuning have been performed to improve and increase the prediction accuracy. The highest accuracy of 98.45% has been achieved by a particular fold, whereas the average accuracy is 98.05% across all folds, indicating the model’s stability. SHAP analysis reveals Ammonia, Nitrite, DO, Turbidity, BOD, Temperature, pH, and CO₂ as the topmost water quality indicators. Finally, the DiCE analysis has analyzed that Temperature, Turbidity, DO, BOD, CO₂, pH, Ammonia, and Nitrite are more influential parameters of water quality. Full article

Background: Operational cycle detection underpins a range of important tasks, such as predictive maintenance, energy consumption prediction, and energy management for mobile equipment in mining. Yet, no review has investigated the landscape of methods that segment mobile mining vehicle telemetry into discrete operating modes—a task termed operational cycle detection. Methods: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses, Scoping Review extension (PRISMA-ScR) framework, we searched The Lens database on 27 June 2025, for records published between 2000 and 2025 that apply cycle detection to mobile mining vehicles. After de-duplication and two-stage screening, 20 empirical studies met all criteria (19 diesel, 1 electric-drive). Due to the sparse research involving battery electric vehicles (BEVs) in mining, three articles performing cycle detection on heavy-duty vehicles in a similar operational context to mining are synthesized. Results: Early diesel work used single-sensor thresholds, often achieving >90% site-specific accuracy, while recent studies increasingly employ neural networks using multivariate datasets. While the cycle detection research on mining BEVs, even supplemented with additional heavy-duty BEV studies, is sparse, similar approaches are favored. Conclusions: Persisting gaps in the literature include the absence of public mining datasets, inconsistent evaluation metrics, and limited real-time validation. Full article

Fault prediction and diagnosis are critical for enhancing the maintenance and reliability of power system equipment, reducing operational costs, and preventing potential failures. In power transformers, periodic oil sampling and gas ratio analysis provide valuable insights for predictive maintenance and life-cycle assessment. Machine learning methods, such as XGBoost, have proven to deliver more accurate results, especially when historical data is limited. However, the performance of XGBoost is highly dependent on the optimization of its hyperparameters. To address this, this paper proposes an improved Particle Swarm Optimization (IPSO) method to optimize the hyperparameters of XGBoost for transformer fault diagnosis. The PSO algorithm is enhanced by introducing topology optimization, adaptively adjusting the acceleration factor, dividing the swarm into master–slave particle groups to strengthen search capability, and dynamically adjusting inertia weights using a linear adaptive strategy. IPSO is applied to optimize key hyperparameters of the XGBoost model, improving both its diagnostic accuracy and generalization ability. Experimental results confirm the effectiveness of the proposed model in enhancing fault prediction and diagnosis in power systems. Full article

Horizontal annular flow channels are widely applied in various fields, including thermal engineering, drilling engineering, and food engineering. Investigating their internal flow patterns is crucial for optimizing pipeline design, selecting appropriate equipment, and understanding the sedimentation and migration modes of multiphase flows within annular geometries. In practical engineering applications, the operational conditions of annular flow channels during gas drilling are the most complex, involving parameters such as eccentricity, rotation, surface roughness, and multiphase flow interactions. This study focuses on the flow characteristics of horizontal annular channels under real-world engineering conditions, examining variations in operational parameters. The pressure drop in annular pipelines is influenced by factors such as flow velocity, eccentricity, and rotational speed, exhibiting complex variation patterns. However, previous studies have not fully considered the impact of rough wellbore walls and the interactions among various factors. Employing experimental methods, this research analyzes the pressure drop characteristics within annular geometries. The results reveal that surface roughness significantly affects pressure drop, with the inner pipe’s roughness having a greater impact when the outer pipe surface is rough compared to when it is smooth. An increase in eccentricity substantially reduces pressure drop, with both positive and negative eccentricities demonstrating symmetric pressure drop patterns. Moreover, a significant positive correlation exists between the total rough area of the annular channel and pressure drop. Furthermore, this study establishes a predictive model through dimensional analysis. Unlike existing models, this new model incorporates the influences of both roughness and eccentricity, achieving a prediction accuracy of over 99%. This research confirms the critical role of roughness in annular flow systems and provides practical implications for selecting more reliable pump power equipment in engineering fields. Full article

Bone drilling is a widely encountered process in orthopedic surgeries and keyhole neuro surgeries. We are developing a sensor-integrated smart end-effector for drilling for robotic surgical applications. In manual surgeries, surgeons assess tool wear based on experience and force perception. In this work, we propose a machine-learning (ML)-based tool condition monitoring system based on multi-sensor data to preempt excessive tool wear during drilling in robotic surgery. Real-time data is acquired from the six-component force sensor of a collaborative arm along with the data from the temperature and multi-axis vibration sensor mounted on the bone specimen being drilled upon. Raw data from the sensors may have noises and outliers. Signal processing in the time- and frequency-domain are used for denoising as well as to obtain additional features to be derived from the raw sensory data. This paper addresses the challenging problem of identification of the most suitable ML algorithm and the most suitable features to be used as inputs to the algorithm. While dozens of features and innumerable machine learning and deep learning models are available, this paper addresses the problem of selecting the most relevant features, the most relevant AI models, and the optimal hyperparameters to be used in the AI model to provide accurate prediction on the tool condition. A unique framework is proposed for classifying tool wear that combines machine learning-based modeling with multi-sensor data. From the raw sensory data that contains only a handful of features, a number of additional features are derived using frequency-domain techniques and statistical measures. Using feature engineering, we arrived at a total of 60 features from time-domain, frequency-domain, and interaction-based metrics. Such additional features help in improving its predictive capabilities but make the training and prediction complicated and time-consuming. Using a sequence of techniques such as variance thresholding, correlation filtering, ANOVA F-test, and SHAP analysis, the number of features was reduced from 60 to the 4 features that will be most effective in real-time tool condition prediction. In contrast to previous studies that only examine a small number of machine learning models, our approach systematically evaluates a wide range of machine learning and deep learning architectures. The performances of 47 classical ML models and 6 deep learning (DL) architectures were analyzed using the set of the four features identified as most suitable. The Extra Trees Classifier (an ML model) and the one-dimensional Convolutional Neural Network (1D CNN) exhibited the best prediction accuracy among the models studied. Using real-time data, these models monitored the drilling tool condition in real-time to classify the tool wear into three categories of slight, moderate, and severe. Full article

Financial news has a significant impact on investor sentiment and short-term stock price trends. While many studies have applied natural language processing (NLP) techniques to financial forecasting, most have focused on single tasks or English corpora, with limited research in non-English language contexts such as Taiwan. This study develops a joint framework to perform sentiment classification and short-term stock price prediction using Chinese financial news from Taiwan’s top 50 listed companies. Five types of word embeddings—one-hot, TF-IDF, CBOW, skip-gram, and BERT—are systematically compared across 17 traditional, deep, and Transformer models, as well as a large language model (LLaMA3) fully fine-tuned on the Chinese financial texts. To ensure annotation quality, sentiment labels were manually assigned by annotators with finance backgrounds and validated through a double-checking process. Experimental results show that a CNN using skip-gram embeddings achieves the strongest performance among deep learning models, while LLaMA3 yields the highest overall F1-score for sentiment classification. For regression, LSTM consistently provides the most reliable predictive power across different volatility groups, with Bayesian Linear Regression remaining competitive for low-volatility firms. LLaMA3 is the only Transformer-based model to achieve a positive $R^2$ under high-volatility conditions. Furthermore, forecasting accuracy is higher for the five-day horizon than for the fifteen-day horizon, underscoring the increasing difficulty of medium-term forecasting. These findings confirm that financial news provides valuable predictive signals for emerging markets and that short-term sentiment-informed forecasts enhance real-time investment decisions. Full article