Search Results (140)

Background: Breast cancer remains a critical public health problem worldwide and is a leading cause of cancer-related mortality. Optimizing clinical outcomes is contingent upon the early and precise detection of malignancies. Advances in medical imaging and artificial intelligence (AI), particularly in the fields of radiomics and deep learning (DL), have contributed to improvements in early detection methodologies. Nonetheless, persistent challenges, including limited data availability, model overfitting, and restricted generalization, continue to hinder performance. Methods: This study aims to overcome existing challenges by improving model accuracy and robustness through enhanced data augmentation and the integration of radiomics and deep learning features from the CBIS-DDSM dataset. To mitigate overfitting and improve model generalization, data augmentation techniques were applied. The PyRadiomics library was used to extract radiomics features, while transfer learning models were employed to derive deep learning features from the augmented training dataset. For radiomics feature selection, we compared multiple supervised feature selection methods, including RFE with random forest and logistic regression, ANOVA F-test, LASSO, and mutual information. Embedded methods with XGBoost, LightGBM, and CatBoost for GPUs were also explored. Finally, we integrated radiomics and deep features to build a unified multimodal feature space for improved classification performance. Based on this integrated set of radiomics and deep learning features, 13 pre-trained transfer learning models were trained and evaluated, including various versions of ResNet (50, 50V2, 101, 101V2, 152, 152V2), DenseNet (121, 169, 201), InceptionV3, MobileNet, and VGG (16, 19). Results: Among the evaluated models, ResNet152 achieved the highest classification accuracy of 97%, demonstrating the potential of this approach to enhance diagnostic precision. Other models, including VGG19, ResNet101V2, and ResNet101, achieved 96% accuracy, emphasizing the importance of the selected feature set in achieving robust detection. Conclusions: Future research could build on this work by incorporating Vision Transformer (ViT) architectures and leveraging multimodal data (e.g., clinical data, genomic information, and patient history). This could improve predictive performance and make the model more robust and adaptable to diverse data types. Ultimately, this approach has the potential to transform breast cancer detection, making it more accurate and interpretable. Full article

Soil moisture serves as a critical factor in the hydrological cycle, affecting plant growth, ecosystem health, and groundwater reserves. Current methods for monitoring and predicting it fail to account for the complexities introduced by climatic variations and other influencing factors, such as the effects of atmospheric interference and data gaps, leading to reduced prediction accuracy. To address these challenges, this study introduces a novel soil moisture prediction model based on remote sensing and deep learning, utilizing the Adaptive Group Radial Lasso Regularized Basis Function Networks (AGRL-RBFN) optimized by the Hierarchical Correlated Spider Wasp Optimizer (HCSWO) and incremental learning (IL) techniques. The proposed method for monitoring soil moisture utilizes hyperspectral and soil moisture data from a 2017 campaign in Karlsruhe, encompassing variables such as datetime, soil moisture percentage, soil temperature, and remote sensing spectral bands. The proposed methodology begins with comprehensive preprocessing of historical remote sensing data to fill gaps, reduce noise, and correct atmospheric disturbances. It then employs a unique seasonal mapping and grouping technique, enhanced by the AdaK-MCC method, to analyze the impact of climatic changes on soil moisture patterns. The model’s innovative feature selection approach, using HCSWO, identifies the most significant predictors, ensuring optimal data input for the AGRL-RBFN model. The model achieves an impressive accuracy of 98.09%, a precision of 98.17%, a recall of 97.24%, and an F1-score of 98.95%, outperforming existing methods. Furthermore, it attains a mean absolute error (MAE) of 0.047 in gap filling and a Dunn Index of 4.897 for clustering. Although successful in many aspects, the study did not investigate the relationship between soil moisture levels and specific crops, which presents an opportunity for future research aimed at enhancing smart agricultural practices. Furthermore, the model can be refined by integrating a wider range of datasets and improving its resilience to extreme weather conditions, thereby providing a reliable tool for climate-responsive agricultural management and water conservation strategies. Full article

Penalized regression methods are widely used for variable selection. Non-negative garrote (NNG) was one of the earliest methods to combine variable selection with shrinkage of regression coefficients, followed by lasso. About a decade after the introduction of lasso, adaptive lasso (ALASSO) was proposed to address lasso’s limitations. ALASSO has two tuning parameters ($\lambda$ and $\gamma$), and its penalty resembles that of NNG when $\gamma =1$, though NNG imposes additional constraints. Given ALASSO’s greater flexibility, which may increase instability, this study investigates whether NNG provides any practical benefit or can be replaced by ALASSO. We conducted simulations in both low- and high-dimensional settings to compare selected variables, coefficient estimates, and prediction accuracy. Ordinary least squares and ridge estimates were used as initial estimates. NNG and ALASSO ($\gamma =1$) showed similar performance in low-dimensional settings with low correlation, large samples, and moderate to high $R^2$. However, under high correlation, small samples, and low $R^2$, their selected variables and estimates differed, though prediction accuracy remained comparable. When $\gamma \ne 1$, the differences between NNG and ALASSO became more pronounced, with ALASSO generally performing better. Assuming linear relationships between predictors and the outcome, the results suggest that NNG may offer no practical advantage over ALASSO. The $\gamma$ parameter in ALASSO allows for adaptability to model complexity, making ALASSO a more flexible and practical alternative to NNG. Full article

This study evaluates the competitiveness and sustainable development prospects of French-speaking African countries by constructing a comprehensive framework integrating the TOPSIS method and adaptive LASSO algorithm. Using multivariate data from sources such as the World Bank, 30 indicators covering core, basic, and auxiliary competitiveness were selected to quantitatively analyze the competitiveness of 26 French-speaking African countries. Results show that their comprehensive competitiveness exhibits spatial patterns of “high in the north and south, low in the east and west” and “high in coastal areas, low in inland areas”. Algeria, Morocco, and six other countries demonstrate high competitiveness, while Central African countries generally show low competitiveness. The adaptive LASSO algorithm identifies three key influencing factors, including the proportion of R&D expenditure to GDP, high-tech exports, and total reserves, as well as five secondary key factors, including the number of patent applications and total number of domestic listed companies, revealing that scientific and technological investment, financial strength, and innovation transformation capabilities are core constraints. Based on these findings, sustainable development strategies are proposed, such as strengthening scientific and technological research and development and innovation transformation, optimizing financial reserves and capital markets, and promoting China–Africa collaborative cooperation, providing decision-making references for competitiveness improvement and regional cooperation of French-speaking African countries under the background of the “Belt and Road Initiative”. Full article

Principal component analysis (PCA) is a widely applied multivariate statistical technique across scientific disciplines, with forestry being one of its most dynamic areas of use. Its primary strength lies in reducing data dimensionality and classifying parameters within complex ecological datasets. This study provides the first comprehensive bibliometric and literature review focused exclusively on PCA applications in forestry. A total of 96 articles published between 1993 and 2024 were analyzed using the Web of Science database and visualized using VOSviewer software, version 1.6.20. The bibliometric analysis revealed that the most active scientific fields were environmental sciences, forestry, and engineering, and the most frequently published journals were Forests and Sustainability. Contributions came from 198 authors across 44 countries, with China, Spain, and Brazil identified as leading contributors. PCA has been employed in a wide range of forestry applications, including species classification, biomass modeling, environmental impact assessment, and forest structure analysis. It is increasingly used to support decision-making in forest management, biodiversity conservation, and habitat evaluation. In recent years, emerging research has demonstrated innovative integrations of PCA with advanced technologies such as hyperspectral imaging, LiDAR, unmanned aerial vehicles (UAVs), and remote sensing platforms. These integrations have led to substantial improvements in forest fire detection, disease monitoring, and species discrimination. Furthermore, PCA has been combined with other analytical methods and machine learning models—including Lasso regression, support vector machines, and deep learning algorithms—resulting in enhanced data classification, feature extraction, and ecological modeling accuracy. These hybrid approaches underscore PCA’s adaptability and relevance in addressing contemporary challenges in forestry research. By systematically mapping the evolution, distribution, and methodological innovations associated with PCA, this study fills a critical gap in the literature. It offers a foundational reference for researchers and practitioners, highlighting both current trends and future directions for leveraging PCA in forest science and environmental monitoring. Full article

Partial Least Squares (PLS) regression has been widely used to model the relationship between predictors and responses. However, PLS may be limited in its capacity to handle complex spectral data contaminated with significant noise and interferences. In this paper, we propose a novel filter learning-based PLS (FPLS) model that integrates an adaptive filter into the PLS framework. The FPLS model is designed to maximize the covariance between the filtered spectral data and the response. This modification enables FPLS to dynamically adapt to the characteristics of the data, thereby enhancing its feature extraction and noise suppression capabilities. We have developed an efficient algorithm to solve the FPLS optimization problem and provided theoretical analyses regarding the convergence of the model, the prediction variance, and the relationships among the objective functions of FPLS, PLS, and the filter length. Furthermore, we have derived bounds for the Root Mean Squared Error of Prediction (RMSEP) and the Cosine Similarity (CS) to evaluate model performance. Experimental results using spectral datasets from Corn, Octane, Mango, and Soil Nitrogen show that the FPLS model outperforms PLS, OSCPLS, VCPLS, PoPLS, LoPLS, DOSC, OPLS, MSC, SNV, SGFilter, and Lasso in terms of prediction accuracy. The theoretical analyses align with the experimental results, emphasizing the effectiveness and robustness of the FPLS model in managing complex spectral data. Full article

Logistic regression is often used to solve classification problems. This article combines the advantages of Bayesian methods and spike-and-slab Lasso to select variables in high-dimensional logistic regression. The method of introducing a new hidden variable or approximating the lower bound is used to solve the problem of logistic functions without conjugate priors. The Laplace distribution in spike-and-slab Lasso is expressed as a hierarchical form of normal distribution and exponential distribution, so that all parameters in the model are posterior distributions that are easy to deal with. Considering the high time cost of parameter estimation and variable selection in high-dimensional models, we use the variational Bayesian algorithm to perform posterior inference on the parameters in the model. From the simulation results, it can be seen that it is an adaptive prior that can perform parameter estimation and variable selection well in high-dimensional logistic regression. From the perspective of algorithm running time, the method proposed in this article also has high computational efficiency in many cases. Full article

Information regarding the impact of polymetallic exposure on metabolic syndrome (MetS) among residents living near abandoned Pb-Zn mines is limited. Our objective was to investigate the impact of co-exposure to metal mixtures on the prevalence of MetS among residents. ICP-MS was used to measure the levels of 24 metals in the urine of 1744 participants, including 723 participants living near abandoned Pb-Zn mines, labeled as exposed area, and 1021 participants from other towns, labeled as reference area in the same city. Multivariable generalized linear regression, adaptive LASSO penalized regression, and BKMR were used to assess the associations between metals and MetS. The levels of eleven metals were higher, while those of nine metals were lower in the exposed area than those in the reference area. Mg, Cd, Ti, TI, Zn, Rb, and Pb were selected as important MetS predictors using LASSO regression. In exposed area, urinary Zn and TI were positively associated with MetS, whereas Mg was negatively associated with MetS. In the reference area, urinary Zn was positively associated with MetS, whereas Mg and Ti were negatively associated with MetS. The BKMR model indicates a statistically significant positive overall effect of the seven metal mixtures on MetS in the exposed area. Polymetallic exposure was positively associated with MetS risk in the abandoned Pb-Zn mining areas, suggesting that excessive Zn and TI may be associated with a higher MetS risk among residents living near abandoned Pb-Zn mines. Full article

Variable selection is important for developing accurate and interpretable prediction models. While classical and penalized methods are widely used, few simulation studies provide meaningful comparisons. This study compares their predictive performance and model complexity in low-dimensional data. Three classical methods (best subset selection, backward elimination, and forward selection) and four penalized methods (nonnegative garrote (NNG), lasso, adaptive lasso (ALASSO), and relaxed lasso (RLASSO)) were compared. Tuning parameters were selected using cross-validation (CV), Akaike information criterion (AIC), and Bayesian information criterion (BIC). Classical methods performed similarly and produced worse predictions than penalized methods in limited-information scenarios (small samples, high correlation, and low signal-to-noise ratio (SNR)), but performed comparably or better in sufficient-information scenarios (large samples, low correlation, and high SNR). Lasso was superior under limited information but was less effective in sufficient-information scenarios. NNG, ALASSO, and RLASSO outperformed lasso in sufficient-information scenarios, with no clear winner among them. AIC and CV produced similar results and outperformed BIC, except in sufficient-information settings, where BIC performed better. Our findings suggest that no single method consistently outperforms others, as performance depends on the amount of information in the data. Lasso is preferred in limited-information settings, whereas classical methods are more suitable in sufficient-information settings, as they also tend to select simpler models. Full article

Aiming at tackling the challenges of traditional classification methods, which are labor-intensive, time-consuming, and inefficient, a nitrogen-efficient wheat variety classification method using support vector machine-extreme gradient boosting (SVM-XGBoost) based on unmanned aerial vehicle (UAV) hyperspectral remote sensing was proposed in this study. First, eight agronomic indicators closely related to wheat nitrogen efficiency were analyzed using t-SNE dimensionality reduction and hierarchical clustering, enabling the classification of 12 wheat varieties into nitrogen-efficient and nitrogen-inefficient varieties under different nitrogen stress conditions. Second, a hyperspectral feature band selection method based on least absolute shrinkage and selection operator-competitive adaptive reweighted sampling (Lasso-CARS) was employed using hyperspectral canopy data collected during the wheat heading stage with an UAV to extract feature bands relevant to nitrogen-efficient wheat classification. This approach aimed to mitigate the impact of high collinearity and noise in high-dimensional hyperspectral data on model construction. Furthermore, the SVM-XGBoost method integrated the extracted feature bands with the support vectors and decision function outputs from the preliminary SVM classification. It then leveraged XGBoost to capture nonlinear relationships and construct the final classification model using gradient-boosted trees, achieving intelligent classification of nitrogen-efficient wheat varieties. The model also selected nitrogen fertilization strategies based on the characteristics of different wheat varieties. The results demonstrated robust performance under low, high, and no nitrogen stress, with average overall accuracies of 74%, 83%, and 70% (Kappa coefficients: 0.67, 0.80, and 0.48), respectively. This study provided an efficient and accurate UAV hyperspectral remote sensing-based method for nitrogen-efficient wheat variety classification, offering a technological foundation to accelerate precision breeding. Full article

Background: Prostate cancer (PCa) remains one of the most prevalent malignancies in men, with diagnostic challenges arising from the limited specificity of current biomarkers, like PSA. Improved stratification tools are essential to reduce overdiagnosis and guide personalized patient management. Objective: This study aimed to identify and validate clinical and hematological biomarkers capable of differentiating PCa from benign prostatic hyperplasia (BPH) and precancerous lesions (PL) using univariate and multivariate statistical methods. Methods: In a cohort of 514 patients with suspected PCa, we performed a univariate analysis (Kruskal–Wallis and ANOVA) with preprocessing via adaptive Box–Cox transformation and missing value imputation through probabilistic principal component analysis (PPCA). LASSO regression was used for variable selection and classification. An ROC curve analysis assessed diagnostic performance. Results: Five variables—age, PSA, Index %, hemoglobin (HGB), and the International Index of Erectile Function (IIEF)—were consistently significant across univariate and multivariate analyses. The LASSO regression achieved a classification accuracy of 70% and an AUC of 0.74. Biplot and post-hoc analyses confirmed partial separation between PCa and benign conditions. Conclusions: The integration of multivariate modeling with reconstructed clinical data enabled the identification of blood-based biomarkers with strong diagnostic potential. These routinely available, cost-effective indicators may support early PCa diagnosis and patient stratification, reducing unnecessary invasive procedures. Full article

Skeletal muscle health and function are closely linked to long-term aerobic exercise, particularly in enhancing muscle metabolism and regulating gene expression. Regular endurance training can significantly ameliorate metabolic dysfunction and prevent chronic diseases. However, the precise molecular mechanisms underlying skeletal muscle adaptations to long-term aerobic exercise require further clarification. To address this, we integrated transcriptomic and single-cell omics datasets from multiple long-term aerobic exercise models retrieved from the GEO database. After merging and batch correction, differential expression analysis identified 204 DEGs, including 110 upregulated and 94 downregulated genes. Key feature genes were screened using Lasso regression, SVM-RFE, and Random Forest machine learning algorithms, validated by RT-qPCR, and refined through PPI network analysis. Among them, Fos and Tnfrsf12a were significantly downregulated following long-term aerobic exercise. Notably, Fos exhibited a more pronounced decrease than Tnfrsf12a, and was strongly associated with inflammation and muscle regeneration. PPI network analysis indicated that Fos interacted with genes such as Casp3, Egr1, Aft3, Hspa5, Src, and Igf2. GO, KEGG, and GSEA enrichment analyses revealed that Fos is involved in skeletal muscle differentiation, tissue remodeling, and the NF-κB inflammatory pathway. ssGSEA analysis further showed that samples with low Fos expression had significantly elevated Th1/Th2 and Treg cell infiltration. Single-cell analysis confirmed preferential Fos expression in muscle fiber/adipocyte progenitors, satellite cells, and tenocytes, all critical for myogenesis. In summary, our findings suggest that long-term aerobic exercise downregulates Fos, potentially alleviating inflammation and enhancing satellite cell-mediated muscle regeneration. Fos may serve as a central regulator of skeletal muscle remodeling during long-term aerobic exercise. Full article

This paper presents a data-driven framework for optimizing energy-efficient locomotion in a bio-inspired soft inchworm robot. Leveraging a feedforward neural network, the proposed approach accurately models the nonlinear relationships between actuation parameters (pressure, frequency) and environmental conditions (surface friction). The neural network achieves superior velocity prediction performance, with a coefficient of determination (R²) of 0.9362 and a root mean squared error (RMSE) of 0.3898, surpassing previously reported models, including linear regression, LASSO, decision trees, and random forests. Particle Swarm Optimization (PSO) is integrated to maximize locomotion efficiency by optimizing the velocity-to-pressure ratio and adaptively minimizing input pressure for target velocities across diverse terrains. Experimental results demonstrate that the framework achieves an average 9.88% reduction in required pressure for efficient movement and a 6.45% reduction for stable locomotion, with the neural network enabling robust adaptation to varying surfaces. This dual optimization strategy ensures both energy savings and adaptive performance, advancing the deployment of soft robots in diverse environments. Full article

This study includes a comprehensive evaluation of six penalty estimation strategies for partially linear models (PLRMs), focusing on their performance in the presence of multicollinearity and their ability to handle both parametric and nonparametric components. The methods under consideration include Ridge regression, Lasso, Adaptive Lasso (aLasso), smoothly clipped absolute deviation (SCAD), ElasticNet, and minimax concave penalty (MCP). In addition to these established methods, we also incorporate Stein-type shrinkage estimation techniques that are standard and positive shrinkage and assess their effectiveness in this context. To estimate the PLRMs, we consider a kernel smoothing technique grounded in penalized least squares. Our investigation involves a theoretical analysis of the estimators’ asymptotic properties and a detailed simulation study designed to compare their performance under a variety of conditions, including different sample sizes, numbers of predictors, and levels of multicollinearity. The simulation results reveal that aLasso and shrinkage estimators, particularly the positive shrinkage estimator, consistently outperform the other methods in terms of Mean Squared Error (MSE) relative efficiencies (RE), especially when the sample size is small and multicollinearity is high. Furthermore, we present a real data analysis using the Hitters dataset to demonstrate the applicability of these methods in a practical setting. The results of the real data analysis align with the simulation findings, highlighting the superior predictive accuracy of aLasso and the shrinkage estimators in the presence of multicollinearity. The findings of this study offer valuable insights into the strengths and limitations of these penalty and shrinkage strategies, guiding their application in future research and practice involving semiparametric regression. Full article

(1) Background: Predicting hospitalization length for COVID-19 patients is crucial for optimizing resource allocation and patient management. Radiomics, combined with machine learning (ML), offers a promising approach by extracting quantitative imaging features from CT scans. The aim of the present study is to use and adapt machine learning (ML) architectures, exploiting CT radiomics information, and analyze algorithms’ capability to predict hospitalization at the time of patient admission. (2) Methods: The original CT lung images of 168 COVID-19 patients underwent two segmentations, isolating the ground glass area of the lung parenchyma. After an isotropic voxel resampling and wavelet and Laplacian of Gaussian filtering, 92 intensity and texture radiomics features were extracted. Feature reduction was conducted by applying a last absolute shrinkage and selection operator (LASSO) to the radiomic features set. Three ML classification algorithms, linear support vector machine (LSVM), medium neural network (MNN), and ensemble subspace discriminant (ESD), were trained and validated through a 5-fold cross-validation technique. Model performance was assessed using accuracy, sensitivity, specificity, precision, F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). (3) Results: The LSVM classifier achieved the highest predictive performance, with an accuracy of 86.0% and an AUC of 0.93. However, reliable outcomes are also registered when MNN and ESD architecture are used. (4) Conclusions: The study shows that radiomic features can be used to build a machine learning framework for predicting patient hospitalization duration. The findings suggest that radiomics-based ML models can accurately predict COVID-19 hospitalization length. Full article