Search Results (496)

Background/Objectives: To develop a decision framework integrating computed tomography (CT) radiomics and clinical factors to guide the selection of transarterial chemoembolization (TACE) technique for optimizing treatment response in non-resectable hepatocellular carcinoma (HCC). Methods: A retrospective analysis was performed on 151 patients [33 conventional TACE (cTACE), 69 drug-eluting bead TACE (DEB-TACE), 49 degradable starch microsphere TACE (DSM-TACE)] who underwent TACE for HCC at a single tertiary center. Pre-TACE contrast-enhanced CT images were used to extract radiomic features of the TACE-treated liver tumor volume. Patient clinical and laboratory data were combined with radiomics-derived predictors in an elastic net regularized logistic regression model to identify independent factors associated with early response at 4–6 weeks post-TACE. Predicted response probabilities under each TACE technique were compared with the actual techniques performed. Results: Elastic net modeling identified three independent predictors of response: radiomic feature “Contrast” (OR = 5.80), BCLC stage B (OR = 0.92), and viral hepatitis etiology (OR = 0.74). Interaction models indicated that the relative benefit of each TACE technique depended on the identified patient-specific predictors. Model-based recommendations differed from the actual treatment selected in 66.2% of cases, suggesting potential for improved patient–technique matching. Conclusions: Integrating CT radiomics with clinical variables may help identify the optimal TACE technique for individual HCC patients. This approach holds promise for a more personalized therapy selection and improved response rates beyond standard clinical decision-making. Full article

Lung cancer is by far the leading cause of cancer death among both men and women, making up almost 25% of all cancer deaths Each year, more people die of lung cancer than colon, breast, and prostate cancer combined. The early detection of lung cancer is critical for improving patient outcomes, and automation through advanced image analysis techniques can significantly assist radiologists. This paper presents the development and evaluation of a computer-aided diagnostic system for lung cancer screening, focusing on pulmonary nodule segmentation in low-dose CT images, by employing HighRes3DNet. HighRes3DNet is a specialized 3D convolutional neural network (CNN) architecture based on ResNet principles which uses residual connections to efficiently learn complex spatial features from 3D volumetric data. To address the challenges of processing large CT volumes, an efficient patch-based extraction pipeline was developed. This method dynamically extracts 3D patches during training with a probabilistic approach, prioritizing patches likely to contain nodules while maintaining diversity. Data augmentation techniques, including random flips, affine transformations, elastic deformations, and swaps, were applied in the 3D space to enhance the robustness of the training process and mitigate overfitting. Using a public low-dose CT dataset, this approach achieved a Dice coefficient of 82.65% on the testing set for 3D nodule segmentation, demonstrating precise and reliable predictions. The findings highlight the potential of this system to enhance efficiency and accuracy in lung cancer screening, providing a valuable tool to support radiologists in clinical decision-making. Full article

Regularization methods such as LASSO, adaptive LASSO, Elastic-Net, and SCAD are widely employed for variable selection in statistical modeling. However, these methods primarily focus on variables with strong effects while often overlooking weaker signals, potentially leading to biased parameter estimates. To address this limitation, Gao, Ahmed, and Feng (2017) introduced a corrected shrinkage estimator that incorporates both weak and strong signals, though their results were confined to linear models. The applicability of such approaches to survival data remains unclear, despite the prevalence of survival regression involving both strong and weak effects in biomedical research. To bridge this gap, we propose a novel class of post-selection shrinkage estimators tailored to the Cox model framework. We establish the asymptotic properties of the proposed estimators and demonstrate their potential to enhance estimation and prediction accuracy through simulations that explicitly incorporate weak signals. Finally, we validate the practical utility of our approach by applying it to two real-world datasets, showcasing its advantages over existing methods. Full article

This paper focuses on the modeling of the performance of photovoltaic systems based on advanced techniques. This research leverages real-world data from the Shams Solar Facility at the German University of Technology in Oman to explore the application of Linear, Lasso, Ridge, and Elastic Net Regressions to predict and optimize the performance of photovoltaic systems. A comprehensive dataset of 36,851 observations of environmental and operational conditions forms the basis of the analysis. The research identifies the strengths and limitations of these modeling techniques for an accurate forecast of energy output under various scenarios. The comparative analysis highlights the precision and reliability of each regression method and offers actionable insights into their practical implementation. The findings highlight the importance of more sophisticated modeling approaches in increasing the knowledge of photovoltaic system dynamics and optimizing their performance. This research facilitates the advancement in solar energy systems and provides critical recommendations for the improvement in efficiency and reliability of photovoltaic installations under different geographic and climatic settings. Full article

Modulus of elasticity (MOE) and modulus of rupture (MOR) are crucial indicators for assessing the application value of wood. However, traditional physical testing methods for the mechanical properties of wood are typically destructive, costly, and time-consuming. To efficiently assess these properties, this study proposes a multi-input residual network (MIRN) model, which integrates microscopic images of wood with physical density data and leverages deep learning technology for rapid and accurate predictions. By using larger convolution kernels to enhance the receptive field, the model captures fine microstructural features in the images. Batch normalization layers were removed from the ResNet architecture to reduce the number of parameters and improve training stability. Shortcut connections were utilized to enable deeper network architectures and address the vanishing gradient problem. Two types of residual blocks, convolutional block and identity block, were defined based on input dimensional changes. The MIRN method, based on multi-input residual networks, is proposed for non-destructive testing of wood mechanical properties. The experimental results show that MIRN outperforms convolutional neural networks (CNNs) and ResNet-50 in predicting MOE and MOR, with an R² of 0.95 for MOE and RMSE reduced to 46.88, as well as an R² of 0.85 for MOR and an RMSE of 0.44. Thus, this method offers an efficient and cost-effective tool for wood processing and quality control. Full article

Background: Optimizing fluid therapy is critical for maintaining hemodynamic stability in elderly patients undergoing major surgeries. Dynamic arterial elastance (Eadyn), defined as the ratio of pulse pressure variation (PPV) to stroke volume variation (SVV), has been proposed as a predictor of fluid responsiveness, especially in challenging conditions like prone-positioned spine surgery under general anesthesia. Methods: Hemodynamic parameters were measured before and after fluid loading with 500 mL of crystalloid solution. Patients were classified as responders or non-responders based on a ≥15% increase in mean arterial pressure (MAP) post-fluid administration. Predictive performance of these parameters was assessed using receiver operating characteristic (ROC) analysis. Results: Of the 37 patients, 15 were classified as responders and 22 as non-responders. Eadyn demonstrated poor predictive performance (AUC = 0.508). In contrast, SVV (AUC = 0.808), PPV (AUC = 0.738), and C (AUC = 0.741) exhibited moderate to high predictive ability. Responders exhibited significantly higher baseline SVV, PPV, and net arterial compliance compared to non-responders. Conclusions: Dynamic arterial elastance (Eadyn) showed limited predictive ability for fluid responsiveness in elderly patients undergoing spine surgery in the prone position. In contrast, stroke volume variation (SVV), pulse pressure variation (PPV), and net arterial compliance (C) demonstrated superior reliability, with SVV emerging as the most accurate predictor. Full article

This study compares Artificial Neural Networks (ANN) and Elastic Net regression for predicting surface runoff in urban stormwater catchments. Both models were trained on a data set derived from the Stormwater Management Model that included parameters such as imperviousness, flow path width, slope, Manning coefficients, and depression storage. ANN exhibited greater predictive accuracy and stability, especially when modeling nonlinear hydrologic interactions, while Elastic Net offered faster inference and clearer interpretability, but showed reduced accuracy in low-flow conditions. Validation on real-world data revealed the sensitivity of the models to scenarios not fully represented during training. Despite higher computational demands, the ANN proved more adaptable, while the more resource-efficient Elastic Net remains suitable for time-critical or large-scale applications. These findings provide practical insights for urban water resource management, indicating when each approach can be most effectively used in flood risk assessment and stormwater infrastructure planning. Full article

Reliable inflation forecasts are essential for both business operations and macroeconomic policy making. This study explores the potential of using machine learning (ML) techniques to improve the accuracy of human forecasts of inflation. Specifically, we develop and examine ML-centered forecast adjustment procedures where advanced ML techniques are employed to predict and thus mitigate the errors of human forecasts, akin to how an AI-powered spell and grammar checker helps to prevent mistakes in human writing. Our empirical exercises demonstrate the benefits of several popular ML techniques, such as the elastic net, LASSO, and ridge regressions, and provide evidence of their ability to improve both our own benchmark inflation forecasts and those reported by the frequent participants in the US Survey of Professional Forecasters. The forecast adjustment procedures proposed in this paper are conceptually appealing, widely applicable, and empirically effective in reducing forecast bias and improving forecast accuracy. Full article

The development and maturation of TBM (tunnel boring machine) technology have significantly improved the accuracy and richness of excavation data, driving advancements in intelligent tunneling research. However, challenges remain in managing data noise and parameter coupling, limiting the interpretability of traditional machine learning models regarding TBM parameter relationships. This study proposes a cutterhead rotation speed prediction model based on dimensional analysis. By utilizing boxplot methods and low-pass filtering techniques, excavation data were preprocessed to select appropriate operational and mechanical parameters. A dimensionless model was established and integrated with elastic net regression to quantify parameters. Using TBM cluster data from a water diversion tunnel project in Xinjiang, the accuracy and generalizability of the model were validated. Results indicate that the proposed model achieves high prediction accuracy, effectively capturing trends in cutterhead rotation speed while demonstrating strong generalizability. Full article

The mechanical and hydrodynamic characteristics of single-piece nets are key to the design and optimization of offshore aquaculture net cages. A numerical approach for offshore submerged aquaculture net materials based on the Morison equations and finite element is proposed, simulating the hydrodynamic characteristics of single-piece nets under varying parameters such as wire diameter, mesh size, and flow velocity, and simulating the impact of marine organism attachment on nets by modifying the drag coefficient. The simulation results of nets made from materials such as Copper–Zinc Alloy (Cu-Zn), Zinc–Aluminum Alloy (Zn-Al), Semi-Rigid Polyethylene Terephthalate (PET), and Ultra-High Molecular Weight Polyethylene (UHMWPE) are compared, which provides a theoretical basis for optimizing design parameters and selecting materials for nets based on force conditions and hydrodynamic characteristics. The simulation results indicate that the current force on the net is positively correlated with flow velocity; the maximum displacement of the net is also positively correlated with the flow rate. Compared to other materials, the Cu-Zn net is subjected to the greatest water flow force, while the UHMWPE net experiences the greatest displacement; the larger the diameter of the netting twine, the greater the current force on the net; the mesh size is inversely related to the current force on the net. With increasing drag coefficient, both the maximum displacement of the net and the current force experiences increase, and UHMWPE material nets are more sensitive to increases in the drag coefficient, which indicates a greater impact from the attachment of marine organisms. The density and elastic modulus of the netting material affect the rate of increase in force on the net. The research results can provide a basis for further research on material selection and design of deep-sea aquaculture nets. Full article

Water scarcity, exacerbated by climate change and increasing agricultural water demands, highlights the necessity for efficient irrigation management. This study focused on estimating actual evapotranspiration (ETa) in watermelons under semi-arid Mediterranean conditions by integrating high-resolution satellite imagery and agro-meteorological data. Field experiments were conducted in Rutigliano, southern Italy, over a 2.80 ha area. ETa was measured with the eddy covariance (EC) technique and predicted using machine learning models. Multispectral reflectance data from Planet SuperDove satellites and local meteorological records were used as predictors. Partial least squares, the generalized linear model and three machine learning algorithms (Random Forest, Elastic Net, and Support Vector Machine) were evaluated. Random Forest yielded the highest predictive accuracy with an average R² of 0.74, RMSE of 0.577 mm, and MBE of 0.03 mm. Model interpretability was performed through permutation importance and SHAP, identifying the near-infrared and red spectral bands, average daily temperature, and relative humidity as key predictors. This integrated approach could provide a scalable, precise method for watermelon ETa estimation, supporting data-driven irrigation management and improving water use efficiency in Mediterranean horticultural systems. Full article

Predicting biomass gasification gases is crucial for energy production and environmental monitoring but poses challenges due to complex relationships and variability. Machine learning has emerged as a powerful tool for optimizing and managing these processes. This study uses Bayesian optimization to tune parameters for various machine learning methods, including Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient-Boosting Machine (LightGBM), Elastic Net, Adaptive Boosting (AdaBoost), Gradient-Boosting Regressor (GBR), K-nearest Neighbors (KNN), and Decision Tree (DT), aiming to identify the best model for predicting the compositions of CO, CO₂, H₂, and CH₄ under different conditions. Performance was evaluated using the correlation coefficient (R), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), Relative Absolute Error (RAE), and execution time, with comparisons visualized using a Taylor diagram. Hyperparameter optimization’s significance was assessed via t-test effect size and Cohen’s d. XGBoost outperformed other models, achieving high R values under optimal conditions (0.951 for CO, 0.954 for CO₂, 0.981 for H₂, and 0.933 for CH₄) and maintaining robust performance under suboptimal conditions (0.889 for CO, 0.858 for CO₂, 0.941 for H₂, and 0.856 for CH₄). In contrast, K-nearest Neighbors (KNN) and Elastic Net showed the poorest performance and stability. This study underscores the importance of hyperparameter optimization in enhancing model performance and demonstrates XGBoost’s superior accuracy and robustness, providing a valuable framework for applying machine learning to energy management and environmental monitoring. Full article

High-dimensional data have attracted considerable interest from researchers, especially in the area of variable selection. However, when dealing with time-to-event data in survival analysis, where censoring is a key consideration, progress in addressing this complex problem has remained somewhat limited. Moreover, in microarray research, it is common to identify groupings of genes involved in the same biological pathways. These gene groupings frequently collaborate and operate as a unified entity. Therefore, this study is motivated to adopt the idea of a penalized semi-parametric Bayesian Cox (PSBC) model through elastic-net and group lasso penalty functions (PSBC-EN and PSBC-GL) to incorporate the grouping structure of the covariates (genes) and optimally perform variable selection. The proposed methods assign a beta process prior to the cumulative baseline hazard function (PSBC-EN-B and PSBC-GL-B), instead of the gamma process prior used in existing methods (PSBC-EN-G and PSBC-GL-G). Three real-life datasets and simulation scenarios were considered to compare and validate the efficiency of the modified methods with existing techniques, using Bayesian information criteria (BIC). The results of the simulated studies provided empirical evidence that the proposed methods performed better than the existing methods across a wide range of data scenarios. Similarly, the results of the real-life study showed that the proposed methods revealed a substantial improvement over the existing techniques in terms of feature selection and grouping behavior. Full article

Background: The accurate staging of multiple myeloma (MM) is essential for optimizing treatment strategies, while predicting the progression of asymptomatic patients, also referred to as monoclonal gammopathy of undetermined significance (MGUS), to symptomatic MM remains a significant challenge due to limited data. This study aimed to develop machine learning models to enhance MM staging accuracy and stratify asymptomatic patients by their risk of progression. Methods: We utilized gene expression microarray datasets to develop machine learning models, combined with various data transformations. For multiple myeloma staging, models were trained on a single dataset and validated across five independent datasets, with performance evaluated using multiclass area under the curve (AUC) metrics. To predict progression in asymptomatic patients, we employed two approaches: (1) training models on a dataset comprising asymptomatic patients who either progressed or remained stable without progressing to multiple myeloma, and (2) training models on multiple datasets combining asymptomatic and multiple myeloma samples and then testing their ability to distinguish between asymptomatic and asymptomatic that progressed. We performed feature selection and enrichment analyses to identify key signaling pathways underlying disease stages and progression. Results: Multiple myeloma staging models demonstrated high efficacy, with ElasticNet achieving consistent multiclass AUC values of 0.9 across datasets and transformations, demonstrating robust generalizability. For asymptomatic progression, both modeling approaches yielded similar results, with AUC values exceeding 0.8 across datasets and algorithms (ElasticNet, Boosting, and Support Vector Machines), underscoring their potential in identifying progression risk. Enrichment analyses revealed key pathways, including PI3K-Akt, MAPK, Wnt, and mTOR, as central to MM pathogenesis. Conclusions: To the best of our knowledge, this is the first study to utilize gene expression datasets for classifying patients across different stages of multiple myeloma and to integrate multiple myeloma with asymptomatic cases to predict disease progression, offering a novel methodology with potential clinical applications in patient monitoring and early intervention. Full article

Shear wave velocity (V_s) is an important soil parameter to be known for earthquake-resistant structural design and an important parameter for determining the dynamic properties of soils such as modulus of elasticity and shear modulus. Different V_s measurement methods are available. However, these methods, which are costly and labor intensive, have led to the search for new methods for determining the V_s. This study aims to predict shear wave velocity (V_s (m/s)) using depth (m), cone resistance (q_c) (MPa), sleeve friction (f_s) (kPa), pore water pressure (u₂) (kPa), N, and unit weight (kN/m³). Since shear wave velocity varies with depth, regression studies were performed at depths up to 30 m in this study. The dataset used in this study is an open-source dataset, and the soil data are from the Taipei Basin. This dataset was extracted, and a 494-line dataset was created. In this study, using HyperNetExplorer 2024V1, V_s prediction based on depth (m), cone resistance (q_c) (MPa), shell friction (f_s), pore water pressure (u₂) (kPa), N, and unit weight (kN/m³) values could be performed with satisfactory results (R² = 0.78, MSE = 596.43). Satisfactory results were obtained in this study, in which Explainable Artificial Intelligence (XAI) models were also used. Full article