Search Results (21,386)

Flood damage assessment remains challenging, as conventional flood risk management mainly relies on hydraulic hazard maps that do not explicitly reproduce observed damage patterns. Recent advances in remote sensing and machine learning (ML) enable the integration of environmental and socio-economic data with historical impact information to improve flood damage modeling. This study proposes an explainable machine learning framework for flood damage susceptibility mapping, using observed institutional damage records from the 2011 and 2013 flood events combined with 17 geospatial flood risk factors (FRFs) representing hazard, exposure, and vulnerability. This approach enables the capture of non-linear relationships between flood damage and FRFs. For comparison purposes, the same framework was also applied using hydraulically modeled flood extents corresponding to return periods of 30, 200, and 500 years. The framework was tested along the Basilicata Ionian coast in southern Italy, a Mediterranean region characterized by complex geomorphology, intense rainfall events, and recurrent flood impacts. An eXtreme Gradient Boosting (XGBoost) model was trained using 17 FRFs related to hazard, exposure, and vulnerability at a spatial resolution of 20 m. The model achieved high performance with an accuracy of 0.988, an F1-score for the minority class of 0.860, and an ROC-AUC (test) of 0.996. High to very high flood damage probability was predicted in approximately 4.1% of the study area, mainly in low-lying floodplains near river corridors and infrastructure. SHAP-based explainability analysis revealed that damage susceptibility was predominantly driven by hazard and exposure factors: Drainage density (17.10%), Railway distance (16.33%), and Elevation (15.42%), extreme precipitation (Max rainfall, 10.66%) and Street distance (7.51%), with socio-economic vulnerability contributing less than 4%. The observed damage target exhibited clear threshold-like patterns (e.g., sharp risk increases below ~25/35 m elevation or within ~150/200 m of road infrastructure), contrasting with the smoother, continuous gradients produced by hydraulic scenarios. This analysis identified the most influential predictors and their response ranges. The proposed framework complements hydraulic hazard mapping by explicitly modeling observed flood damage, supporting flood risk assessment in flood-prone coastal regions. Full article

Accurate prediction of food consumption is essential for strengthening regional food security planning, particularly in areas experiencing increasing food demand and environmental uncertainty. This study aims to predict food consumption patterns in Sukabumi Regency, West Java, Indonesia, using an integrated artificial intelligence approach. The research combines the Adaptive Neuro-Fuzzy Inference System (ANFIS) for forecasting food consumption trends with three machine learning classification algorithms—Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR)—to classify food consumption levels. Historical rice consumption data from 2014 to 2024 were used to train the forecasting model and generate projections up to 2030. The ANFIS training process was conducted with 100 epochs and an error tolerance of 0, resulting in a training error value of 0.182, indicating strong model learning capability. The comparison between predicted and actual consumption values showed a prediction accuracy of 95.2%, demonstrating the reliability of the model in capturing consumption patterns. Furthermore, food consumption levels were classified into three categories: low, medium, and high. The classification results revealed that Random Forest achieved the most consistent performance across cross-validation folds, while SVM and Logistic Regression experienced misclassification in the medium consumption category. In several evaluation scenarios, machine learning models achieved accuracy levels up to 99.75%, precision 99.76%, recall 99.75%, and F1-score 99.75%. The integration of ANFIS forecasting and machine learning classification provides a robust analytical framework for understanding food consumption dynamics and supports data-driven policy formulation aimed at strengthening regional food security in Sukabumi Regency. Full article

Background/Objectives: The presented study aimed to understand the relationship between knowledge, attitudes, and practices, as well as consumers’ preferences for the consumption of Spirulina-enriched fruit and vegetable juices. Methods: A survey about the consumers’ attitudes towards consumption of algae in general and especially Spirulina was conducted to better understand the target groups and marketing strategies for this novel non-alcoholic beverage product. Knowledge–Attitude–Practice (KAP) model in combination with structural equation modelling (SEM) was applied to test the hypothesised relationships between the variables. Additionally, consumers’ preference test was done using a seven-point hedonic scale and ranking of the six juice samples: plain sour cherry juice (SC1), sour cherry juice with 0.8% (SC2) and 1.6% (SC3) of blue Spirulina powder; plain tomato juice (T1), tomato juice with 0.8% (T2) and 1.6% (T3) of blue Spirulina powder. Results: The SEM results showed that there is a limited direct impact of knowledge on social motivation, while personal behaviour strongly predicts social motivation. Namely, perceived nutritional value and health benefits were shown to be the main factors for consumers’ willingness to drink Spirulina-enriched juice. Conclusions: The result of the consumer preference evaluation exposed that the juices containing sour cherry and Spirulina achieved better sensory acceptance and ranking than those containing tomato, pointing out the importance of the product matrix for achieving consumer acceptance. Full article

Since 2007, the porosity–to–cement relationship has been widely used as a unified parameter to predict mechanical strength, durability, expansion, and stiffness of stabilized soils. In this formulation, the volumetric binder content is adjusted by an internal exponent x, typically ranging between 0 and 1, to balance the relative contributions of porosity and cementation. Traditionally, the parameters of this relationship have been obtained using manual regression procedures. This study proposes an automated calibration methodology for the porosity–binder index, where the parameters A, B, and x are determined through an iterative optimization framework based on minimization of the sum of absolute errors (SAE) combined with a Monte Carlo search algorithm. The methodology is applied to a cement-stabilized clay blended with ground glass (GG), recycled gypsum (GY), and limestone residues (CLW). The predictive capability of the calibrated model is evaluated using unconfined compressive strength (q_u) and initial shear stiffness (Go) datasets. Two calibration strategies are considered: Calibration Process No. 1, based on CLW mixtures and q_u values only, and Calibration Process No. 2, incorporating all mixtures (CLW, GG, and GY) and both q_u and Go responses. The results indicate that Calibration Process No. 2 provides a more robust and physically consistent parameter set, yielding coefficients of determination of 0.9318 and 0.9412 for q_u and Go, respectively. The proposed algorithm-driven calibration framework improves predictive capability and provides a systematic approach for determining the parameters of the porosity–binder relationship. Full article

Carbonate reservoirs exhibit complex combinations of pores, fractures, and vugs, and their strong heterogeneity makes pore-scale displacement mechanisms and recovery enhancement difficult to predict. In this study, six microfluidic glass-etched models representative of pore-type, vuggy, and fracture-pore carbonate reservoirs were designed from cast thin sections of the S oilfield. Experiments were conducted to investigate the effects of different factors on microscopic displacement behavior and residual-oil distribution. The results show that microscopic residual oil in carbonate reservoirs mainly occurs as film flow, droplet flow, columnar flow, multi-pore flow, and cluster flow, with cluster flow dominating the late stage of development in all model types. Under waterflooding, pore-type reservoirs exhibit the most uniform sweep and the highest recovery factor (44.26%), whereas vuggy reservoirs readily develop preferential flow channels and show the lowest recovery factor (41.58%). For fracture-pore reservoirs, injection perpendicular to the fracture provides the best performance, and wider or denser fractures improve displacement efficiency. Compared with gas flooding, waterflooding increases recovery by 10.48% in pore-type reservoirs and by 16.44% in fracture-type reservoirs. High-rate waterflooding and mid-stage flow diversion further improve recovery by 9.05–10.87% and 17.12–19.63%, respectively. These results provide pore-scale evidence for optimizing development strategies for carbonate reservoirs. Full article

Financial time series forecasting remains a persistent challenge due to the non-stationary nature, inherent noise, and multi-scale temporal dependencies present in market data. This paper presents MSTFNet, a multi-scale temporal fusion network that combines dilated causal convolutions with a frequency-enhanced sparse attention mechanism for improved financial prediction. The proposed architecture consists of three core components: a multi-scale dilated causal convolution module that extracts temporal patterns across different time horizons through parallel convolutional branches with varying dilation rates, a frequency-enhanced sparse attention mechanism that leverages Fast Fourier Transform to identify dominant periodic components and modulate attention weights accordingly, and an adaptive scale fusion gate that learns to dynamically combine representations from multiple temporal scales. Extensive experiments conducted on three public financial datasets (S&P 500, CSI 300, and NASDAQ Composite) spanning the period from January 2015 to December 2024 show two key results. First, consistent with near-efficient markets, the random-walk benchmark (${\widehat{y}}_{t+1}=y_t$) outperforms all the data-driven models on level-error metrics (MAE, RMSE, MAPE, and $R^2$), establishing the martingale as the binding lower bound on point-prediction error. Second, MSTFNet achieves the highest directional accuracy (DA) across all three indices—56.3% on the S&P 500 versus 50.0% for the martingale—representing a 6.3 percentage-point improvement that generates positive pre-cost returns in a trading strategy backtest. Among the eight data-driven baselines (LSTM, GRU, TCN, Transformer, Autoformer, FEDformer, PatchTST, and iTransformer), MSTFNet also achieves the lowest MAE, reducing it by 13.6% relative to the strongest data-driven baseline (iTransformer) on the S&P 500. These results confirm that integrating multi-scale temporal modeling with frequency-domain guidance extracts a real, if modest, directional signal from financial time series. Full article

Transcranial magnetic stimulation (TMS) combined with electroencephalography (EEG) provides a powerful framework to probe and modulate human cortical and corticospinal excitability. In recent years, brain state-dependent EEG–TMS paradigms have gained increasing interest by synchronizing stimulation to ongoing neural activity. However, traditional approaches relying on single oscillatory features or fixed thresholds have yielded heterogeneous and often inconsistent results, motivating the adoption of machine learning (ML) and artificial intelligence (AI) methods to model brain state in a multivariate, data-driven manner. This review synthesizes current ML and deep learning (DL) approaches aimed at predicting cortical and corticospinal excitability from pre-stimulus EEG. We contextualize these methods within brain state-dependent EEG–TMS frameworks based on oscillatory phase, power, and network-level features, and within evolving definitions of brain state that move beyond local biomarkers toward distributed, large-scale, and dynamically evolving neural representations. The reviewed studies span feature-engineered models, data-driven decoding approaches, and emerging adaptive closed-loop frameworks. Finally, we discuss key methodological challenges, translational barriers, and future directions toward personalized, interpretable, and fully closed-loop neuromodulation systems. Full article

Accurate estimation of lithium-ion battery State of Health (SoH) is critical for emerging applications such as reconfigurable battery systems. Although data-driven machine learning methods are promising, they often rely on costly, time-intensive aging experiments and extensive feature engineering. This work proposes a lightweight SoH-prediction framework validated on both physics-informed synthetic aging data and the NASA battery aging dataset. We evaluated Random Forest (RF) and Feedforward Neural Network (FNN) models that use only a limited number of samples from an early segment of the raw discharge voltage curve as input. Results show that RF consistently outperforms FNN across input sizes in deterministic or noise-free environments, achieving an RMSE of 0.07% SoH using just 5 voltage samples. In inherently stochastic experimental data, however, FNN can achieve an RMSE 50% lower than RF (1.28 vs. 2.87), but requires 37× more mathematical operations per inference. These findings emphasize the predictive value of the early-discharge-voltage region and demonstrate that compact, low-feature-complexity models can deliver accurate SoH estimates. Overall, the approach supports a goal of combining informed synthetic data with limited real measurements to build robust, scalable SoH predictors, reducing dependence on labor-intensive degradation testing and feature-heavy pipelines. Full article

Early diagnosis of ovarian cancer remains one of the most important unmet needs in gynecologic oncology because survival is strongly stage-dependent and most patients still present with disseminated disease. Conventional non-invasive tools, particularly CA-125, transvaginal ultrasound, and composite triage algorithms, remain clinically useful but are limited by suboptimal sensitivity for stage I disease and by reduced specificity in premenopausal women and in benign inflammatory or endometriosis-associated conditions. Circulating tumor DNA (ctDNA) has therefore emerged as a candidate biomarker capable of extending liquid biopsy beyond conventional serology. In ovarian cancer, however, ctDNA implementation is constrained by low tumor shedding in early-stage disease, marked biologic heterogeneity across histotypes, clonal hematopoiesis-related background noise, and major pre-analytical and analytical sources of variability. This narrative review, informed by structured searches of PubMed, Scopus, and Web of Science, examines the evolving evidence for ctDNA mutations, methylation-based assays, multi-omic platforms, and machine-learning models across three distinct clinical contexts: population screening, preoperative triage of adnexal masses, and post-treatment assessment of molecular residual disease. We also discuss positive predictive value, false-positive harms, health-economic implications, standardization initiatives, and ongoing prospective studies. Overall, current evidence suggests that the most plausible near-term role for liquid biopsy in ovarian cancer is not as a universal stand-alone screening test, but as an integrated component of risk stratification and disease-monitoring frameworks that combine molecular signals with clinicopathologic and imaging data. Full article

The load of the elastic tooth drum-type pepper harvester is a key parameter affecting harvesting efficiency and quality. Real-time analysis and prediction of drum load are crucial for stabilizing harvester operation and optimizing performance. Existing research focuses on either machine vision-based image analysis, which is difficult to collect in the field, or parameter-mapping methods, which suffer from time lag. This study proposes a GARCH-KPCA-ATLSTM method for load prediction, combining the generalized autoregressive conditional heteroskedasticity (GARCH) model, kernel principal component analysis (KPCA), and attention-enhanced long short-term memory (ATLSTM). EMD is first applied to denoise and reconstruct the load signal, removing mechanical vibration and other interferences. Conditional heteroskedasticity is confirmed, and the GARCH series (one symmetric and three asymmetric models) is introduced to extract fluctuation features. KPCA reduces dimensionality, removing redundant information and saving 2.91 s in computation while slightly improving accuracy. Additive attention in LSTM emphasizes critical information, enhancing learning of nonlinear relationships and further improving prediction. Comparative experiments demonstrate the model’s reliability. The method achieves RMSE = 0.911, MAE = 0.682, MBE = −0.025, MAPE = 1.147%, R² = 0.968, with a runtime of 2.023 s, confirming high accuracy and stability. This study provides a theoretical and technical foundation for real-time load prediction of pepper harvesters. Full article

Computer modeling has a strong potential to replace or supplement physical fire testing of building structures. A prepared and applicable model must be simple to prepare, capable of calculating and processing results in the shortest possible time without the need for complex computing technology, thus saving time, resources, and finances and becoming a profitable alternative. The aim of this article is to design a model that would suitably represent a non-standard fire test using the Ansys software package 2025/R2. The model was created by combining the Ansys Discovery, Ansys Mechanical and Ansys Fluent software, connected using Ansys Workbench. Several calculation settings were tested, including the proposed finite mesh. The results showed the suitability of the proposed procedure and the division of calculations in separate software. The Species Transport and Viscous Shear Stress Transport (SST) k-omega model best represented fluid flow in Ansys Fluent. Ansys Mechanical confirmed the accuracy of the model in Ansys Fluent, when the predicted temperatures matched the real medium-scale fire test with an average coefficient of determination R² = 0.93. Full article

Reliable short-term air traffic forecasts are important for operational planning in national airspace systems. This study develops a transparent forecasting framework for Türkiye’s monthly aircraft movements using publicly available data from the General Directorate of State Airports Authority (DHMİ) for 2018–2025. Because DHMİ releases may follow cumulative within-year reporting, month-specific increments are reconstructed through within-year differencing and checked through simple audit procedures. The empirical analysis compares seasonal naïve, ETS, and a constrained SARIMA family under leakage-free evaluation, combining a strict 2025 holdout with expanding-window rolling-origin validation. Forecast performance is assessed using standard accuracy metrics and complemented by Diebold–Mariano comparisons, which are interpreted cautiously, given the short holdout length. To examine instability around the pandemic period, this study also reports structural-break and stability diagnostics as supportive evidence rather than definitive identification. Uncertainty is evaluated through backtested 80% and 95% prediction intervals, comparing nominal SARIMA intervals, parametric bootstrap, split conformal prediction, and adaptive conformal inference (ACI). The results show that SARIMA provides the strongest point-forecast performance among the benchmarked models, while adaptive conformal calibration offers a useful balance between empirical coverage and interval width under changing conditions. Overall, this study provides a reproducible and operationally interpretable baseline for national air traffic forecasting in Türkiye and a clear benchmark for future multivariate extensions. Full article

Several prediction equations have been created, based on various dietary composition variables, to predict dairy cattle enteric methane emissions (EMEs). Inconsistencies in measuring EMEs have created difficulties comparing dairy cattle emissions between farms and inhibits certain in efforts to reduce emissions and work towards Net Zero. The aims of the current study were to gather existing EME prediction equations and evaluate the variability in their prediction results. An additional aim was to create a combined prediction equation, based on the dietary components with the highest predictive ability, representing the average prediction across existing equations, which accounted for the variation amongst existing equations. The 32 equations produced large variation in the prediction of EMEs for each of the 15 example diets, ranging from 12.49 to 34.27 g CH₄/kg DM. To create a combined EME prediction equation, twelve combinations of dietary variables were evaluated using a mixed-effects model. An equation based on metabolised energy (ME) and neutral detergent fibre (NDF) was chosen (methane (CH₄) = 0.33 × ME + 0.31 × NDF + 3.47), due to the significance of the predictor variables and low prediction error (RMSE = 1.47 g CH₄/kg DM), with a random-effects residual variance of 2.32. The combined equation may act as a suitable compromise to compare emissions between studies accounting for unexplained variation. Full article

Background/Objectives: This study aimed to investigate the impact of allergic diseases (AD) or obstructive sleep apnea (OSA) risk, as a host factor, on the development of severe Mycoplasma pneumoniae Pneumonia (SMPP) in children by analyzing the clinical data of pediatric patients with Mycoplasma pneumoniae Pneumonia (MPP). Methods: This retrospective study enrolled children hospitalized with Mycoplasma pneumoniae pneumonia (MPP) at Shanghai Ninth People’s Hospital from November 2024 to November 2025. Patients were classified into severe (SMPP) and mild (MMPP) groups. Demographic, clinical, laboratory, and questionnaire data were collected and compared between groups. Univariate and multivariate logistic regression analyses were performed to identify independent predictors of SMPP and construct a nomogram. The model was validated for discrimination, calibration, and clinical utility using ROC curves, calibration plots, and decision curve analysis, with internal validation by bootstrap resampling. Results: Among the 150 enrolled children with MPP, 35 (23.3%) were classified as severe (SMPP) and 115 (76.7%) as mild (MMPP). Patients with SMPP exhibited significantly higher frequencies of allergic diseases, prolonged fever and steroid use, elevated inflammatory markers (CRP, LDH, D-dimer, ferritin, ALT), and higher PSQ and RQLQ scores (all p < 0.05). Disease severity was positively correlated with these clinical, laboratory, and questionnaire-based parameters. Multivariate logistic regression identified allergic diseases, PSQ score, LDH, and ferritin as independent predictors of SMPP. A nomogram incorporating these four factors demonstrated good predictive performance, with an internally validated C-index of 0.827, satisfactory calibration (Hosmer–Lemeshow p = 0.116), and clinical utility within a 0–25% threshold probability range on decision curve analysis. Conclusions: Children with MPP and comorbid AD or OSA risk are more likely to develop SMPP. Among children aged 6–12 years, RQLQ score is positively correlated with the severity of MPP. AD, PSQ score, LDH, and ferritin are independent risk factors for SMPP. Clinicians should be alert to the development of SMPP when children with MPP present with a history of AD, PSQ score >3.5, LDH >327.50 U/L, or ferritin >120.05 ng/mL. The visual nomogram model constructed by combining these risk factors demonstrates improved predictive performance for SMPP, with high predictive efficacy and accuracy. It has great clinical value and can be used for individualized risk assessment and early intervention. However, our proposed nomogram requires external validation prior to broader implementation. Full article

Abnormal gait associated with neuromuscular and musculoskeletal disorders represents a growing clinical burden, particularly in aging populations. This study presents a modular, low-cost Smart Rehabilitation Walker (SRW) that integrates multimodal sensing and real-time haptic feedback to enable simultaneous gait monitoring and corrective intervention in both clinical and home environments. The system combines force-sensing resistors for bilateral load symmetry assessment, inertial measurement units for fall detection, and surface electromyography (sEMG) for neuromuscular activity monitoring within a closed-loop assistive feedback architecture. A 15-day pilot study involving ten individuals with rheumatoid arthritis and clinically observed neurological gait abnormalities demonstrated measurable improvements in gait biomechanics. The Force Symmetry Index (FSI), calculated using the Robinson symmetry metric, decreased from an average of 0.9691 to 0.2019, corresponding to a 79.26% average reduction in inter-limb load asymmetry. Concurrently, sEMG measurements showed a substantial increase in neuromuscular activation (ΔEMG = 4.28), with statistical analysis confirming a significant improvement across participants (paired t-test: t(9) = 13.58, p < 0.001). To model rehabilitation trajectories, a nonlinear predictive framework based on Gaussian Process Regression achieved high predictive accuracy (R² ≈ 0.9, with a mean RMSE of 0.0385), while providing uncertainty-aware trend estimation. Validation using an independent amyotrophic lateral sclerosis gait dataset further demonstrated the transferability of the analytical pipeline. These results highlight the potential of sensor-enabled assistive walkers as scalable platforms for quantitative gait rehabilitation, adaptive feedback, and long-term mobility monitoring. Full article