Search Results (477)

Background/Objectives: Radiomics enables extraction of quantitative imaging features to support non-invasive classification of prostate cancer (PCa). Accurate detection of clinically significant PCa (csPCa; Gleason score ≥ 3 + 4) is crucial for guiding treatment decisions. However, many studies explore limited feature selection, classifier, and harmonization combinations, and lack external validation. We aimed to systematically benchmark modeling pipelines and evaluate whether combining radiomics with the lesion-to-normal ADC ratio improves classification robustness and generalizability in multicenter datasets. Methods: Radiomic features were extracted from ADC maps using IBSI-compliant pipelines. Over 100 model configurations were tested, combining eight feature selection methods, fifteen classifiers, and two harmonization strategies across two scenarios: (1) repeated cross-validation on a multicenter dataset and (2) nested cross-validation with external testing on the PROSTATEx dataset. The ADC ratio was defined as the mean lesion ADC divided by contralateral normal tissue ADC, by placing two identical ROIs in each side, enabling patient-specific normalization. Results: In Scenario 1, the best model combined radiomics, ADC ratio, LASSO, and Naïve Bayes (AUC-PR = 0.844 ± 0.040). In Scenario 2, the top-performing configuration used Recursive Feature Elimination (RFE) and Boosted GLM (a generalized linear model trained with boosting), generalizing well to the external set (AUC-PR = 0.722; F1 = 0.741). ComBat harmonization improved calibration but not external discrimination. Frequently selected features were texture-based (GLCM, GLSZM) from wavelet- and LoG-filtered ADC maps. Conclusions: Integrating radiomics with the ADC ratio improves csPCa classification and enhances generalizability, supporting its potential role as a robust, clinically interpretable imaging biomarker in multicenter MRI studies. Full article

Urban water distribution networks (WDNs) are increasingly vulnerable to diverse disruptions, including pipe leaks/bursts and cyber–physical failures. A critical step in a resilience-based approach against these disruptions is the rapid and reliable identification of failures and their types for the timely implementation of emergency or recovery actions. This study proposes a framework for sensor placement and multiple failure type classification in WDNs. It applies a wrapper-based feature selection (recursive feature elimination) with Random Forest (RF–RFE) to find the best sensor locations and employs an Autoencoder–Random Forest (AE–RF) framework for failure type identification. The framework was tested on the C-town WDN using the failure type scenarios of pipe leakage, cyberattacks, and physical attacks, which were generated using EPANET-CPA and WNTR models. The results showed a higher performance of the framework for single failure events, with accuracy of 0.99 for leakage, 0.98 for cyberattacks, and 0.95 for physical attacks, while the performance for multiple failure classification was lower, but still acceptable, with a performance accuracy of 0.90. The reduced performance was attributed to the model’s difficulty in distinguishing failure types when they produced hydraulically similar consequences. The proposed framework combining sensor placement and multiple failure identification will contribute to advance the existing data-driven approaches and to strengthen urban WDN resilience to conventional and cyber–physical disruptions. Full article

Wetland mapping plays a crucial role in monitoring wetland ecosystems, water resource management, and habitat suitability assessment. Wetland classification remains significantly challenging due to the diverse types, intricate spatial patterns, and highly dynamic nature. This study proposed a dynamic hybrid method that integrated feature selection and object-oriented ensemble model construction to improve wetland mapping using Sentinel-1 and Sentinel-2 data. The proposed feature selection approach integrates the ReliefF and recursive feature elimination (RFE) algorithms with a feature evaluation criterion based on Shapley additive explanations (SHAP) values, aiming to optimize the feature set composed of various variables. During the construction of ensemble models (i.e., RF, XGBoost, and LightGBM) with features selected by RFE, hyperparameter tuning is subsequently conducted using Bayesian optimization (BO), ensuring that the selected optimal features and hyperparameters significantly enhance the accuracy and performance of the classifiers. The accuracy assessment demonstrates that the BO-LightGBM model with ReliefF-RFE-SHAP-selected features achieves superior performance to the RF and XGBoost models, achieving the highest overall accuracy of 89.4% and a kappa coefficient of 0.875. The object-oriented classification maps accurately depict the spatial distribution patterns of different wetland types. Furthermore, SHAP values offer global and local interpretations of the model to better understand the contribution of various features to wetland classification. The proposed dynamic hybrid method offers an effective tool for wetland mapping and contributes to wetland environmental monitoring and management. Full article

Background/Objective: Predicting pharmacological response in cancer remains a key challenge in precision oncology due to intertumoral heterogeneity and the complexity of drug–gene interactions. While machine learning models using multi-omics data have shown promise in predicting pharmacological response, selecting the features with the highest predictive power critically affects model performance and biological interpretability. This study aims to compare computational and biologically informed gene selection strategies for predicting drug response in cancer cell lines and to propose a feature selection strategy that optimizes performance. Methods: Using gene expression and drug response data, we trained models on both data-driven and biologically informed gene sets based on the drug target pathways to predict IC₅₀ values for seven anticancer drugs. Several feature selection methods were tested on gene expression profiles of cancer cell lines, including Recursive Feature Elimination (RFE) with Support Vector Regression (SVR) against gene sets derived from drug-specific pathways in KEGG and CTD databases. The predictability was comparatively analyzed using both AUC and IC₅₀ values and further assessed on proteomics data. Results: RFE with SVR outperformed other computational methods, while pathway-based gene sets showed lower performance compared to data-driven methods. The integration of computational and biologically informed gene sets consistently improved prediction accuracy across several anticancer drugs, while the predictive value of the corresponding proteomic features was significantly lower compared with the mRNA profiles. Conclusions: Integrating biological knowledge into feature selection enhances both the accuracy and interpretability of drug response prediction models. Integrative approaches offer a more robust and generalizable framework with potential applications in biomarker discovery, drug repurposing, and personalized treatment strategies. Full article

The prediction of stock prices is challenging due to their volatility, irregular patterns, and complex time-series structure. Reliably forecasting stock market data plays a crucial role in minimizing financial risk and optimizing investment strategies. However, traditional models often struggle to capture temporal dependencies and extract relevant features from noisy inputs, which limits their predictive performance. To improve this, we developed an enhanced recursive feature elimination (RFE) method that blends the importance of impurity-based features from random forest and gradient boosting models with Kendall tau correlation analysis, and we applied SHapley Additive exPlanations (SHAP) analysis to externally validate the reliability of the selected features. This approach leads to more consistent and reliable feature selection for short-term stock prediction over 1-, 3-, and 7-day intervals. The proposed deep learning (DL) architecture integrates a temporal convolutional network (TCN) for long-term pattern recognition, a gated recurrent unit (GRU) for sequence capture, and multi-head attention (MHA) for focusing on critical information, thereby achieving superior predictive performance. We evaluate the proposed approach using daily stock price data from three leading companies—HDFC Bank, Tata Consultancy Services (TCS), and Tesla—and two major stock indices: Nifty 50 and S&P 500. The performance of our model is compared against five benchmark models: temporal convolutional network (TCN), long short-term memory (LSTM), GRU, Bidirectional GRU, and a hybrid TCN–GRU model. Our method consistently shows lower error rates and higher predictive accuracy across all datasets, as measured by four commonly used performance metrics. Full article

Garlic, as an important economic crop, plays a crucial role in the global agricultural production system. Accurate identification of garlic cultivation areas is of great significance for agricultural resource allocation and industrial development. Traditional crop identification methods face challenges of insufficient accuracy and spatial fragmentation in complex agricultural landscapes, limiting their effectiveness in precision agriculture applications. This study, focusing on Kaifeng City, Henan Province, developed an integrated technical framework for garlic identification that combines deep learning edge detection, multi-source feature optimization, and spatial constraint optimization. First, edge detection training samples were constructed using high-resolution Jilin-1 satellite data, and the DexiNed deep learning network was employed to achieve precise extraction of agricultural field boundaries. Second, Sentinel-1 SAR backscatter features, Sentinel-2 multispectral bands, and vegetation indices were integrated to construct a multi-dimensional feature space containing 28 candidate variables, with optimal feature subsets selected through random forest importance analysis combined with recursive feature elimination techniques. Finally, field boundaries were introduced as spatial constraints to optimize pixel-level classification results through majority voting, generating field-scale crop identification products. The results demonstrate that feature optimization improved overall accuracy from 0.91 to 0.93 and the Kappa coefficient from 0.8654 to 0.8857 by selecting 13 optimal features from 28 candidates. The DexiNed network achieved an F1-score of 94.16% for field boundary extraction. Spatial optimization using field constraints effectively eliminated salt-and-pepper noise, with successful validation in Kaifeng’s garlic. Full article

Abdominal fat is a key indicator of chicken meat quality. Excessive deposition not only reduces meat quality but also decreases feed conversion efficiency, making the breeding of low-abdominal-fat strains economically important. Genomic selection (GS) uses information from genome-wide association studies (GWASs) and high-throughput sequencing data. It estimates genomic breeding values (GEBVs) from genotypes, which enables early and precise selection. Given that abdominal fat is a polygenic trait controlled by numerous small-effect loci, this study combined population genetic analyses with machine learning (ML)-based feature selection. Relevant single-nucleotide polymorphisms (SNPs) were first identified using a combined GWAS and linkage disequilibrium (LD) approach, followed by a two-stage feature selection process—Lasso for dimensionality reduction and recursive feature elimination (RFE) for refinement—to generate the model input set. We evaluated multiple machine learning models for predicting genomic estimated breeding values (GEBVs). The results showed that linear models and certain nonlinear models achieved higher accuracy and were well suited as base learners for ensemble methods. Building on these findings, we developed a Dynamic Adaptive Weighted Stacking Ensemble Learning Framework (DAWSELF), which applies dynamic weighting and voting to heterogeneous base learners and integrates them layer by layer, with Ridge serving as the meta-learner. In three independent validation populations, DAWSELF consistently outperformed individual models and conventional stacking frameworks in prediction accuracy. This work establishes an efficient GEBV prediction framework for complex traits such as chicken abdominal fat and provides a reusable SNP feature selection strategy, offering practical value for enhancing the precision of poultry breeding and improving product quality. Full article

This study explores the concept of environmental responsibility and assesses the attitudes and perceptions of young adults towards environmental challenges. Applying a hybrid approach based on feature selection, machine learning methods (classification and regression trees (CART) and recursive feature elimination (RFE)) and statistical methods (chi-squared tests), we analyzed survey data from 500 students across three universities. The results reveal that 82% of students rate their climate knowledge as moderate or good, while 92% perceive climate change as a serious threat. Women are more likely than men to report engagement in pro-environmental initiatives. Students’ environmental orientation weakens in the middle years of study but re-emerges in the final year, possibly reflecting greater maturity and a stronger sense of responsibility before graduation. The willingness to establish sustainable enterprises does not always correspond to a high level of knowledge or daily environmental practices. While undergraduates report high levels of climate awareness, they often fail to translate this into concrete actions, indicating a gap between knowledge, motivation, and practice. The insights from the research can inform environmental education strategies, institutional practices, and youth engagement programs within higher education. Full article

Reliable tools for cultivar discrimination and ripening stage evaluation are critical to optimize harvest timing and support milling process focused on olive oil quality. This research examines the spectral properties of olive drupes throughout different maturation stages, ranging from green to full purple-black pigmentation, across 29 distinct cultivars. High-resolution spectrometric analysis was conducted within the 380–1080 nm wavelength range. Multiple analytical approaches were employed to optimize wavelength selection from hyperspectral reflectance data to obtain discriminating tools for olive classification. A Biologically Informed Wavelength Extraction method (BIWE) was developed, focusing on cultivar and ripening stages identification, and pivoted on biologically informed single wavelengths and Vegetation Indices (VIs) selection. The methodology integrated multi-scale spectral analysis with biochemically weighted scoring and a multi-criteria evaluation framework, employing a two-iteration refinement process to identify optimal spectral features with high discriminatory power and biological relevance. Analysis revealed spectral variations associated with maturation. A characteristic reflectance peak at approximately 550 nm observed during early ripening stages underwent a notable shift, developing into distinct spectral behavior within the 700–780 nm range in intermediate and advanced ripening stages and reaching a plateau for all the samples between 800 and 950 nm. The BIWE method achieved exceptional efficiency in olive classification, utilizing only 25 single wavelengths compared to 114 required by Principal Component Analysis (PCA) and 131 by Recursive Feature Elimination (RFE), representing 4.6-fold and 5.2-fold reductions, respectively. Despite this reduction, BIWE’s overall accuracy (0.5634) remained competitive compared to RFE (−10%) and PCA (−8%) alternative approaches requiring larger wavelengths dataset acquisition. The integration of biochemically relevant VIs enhanced accuracy across all methodologies, with BIWE demonstrating notable improvement (+19.2%). BIWE demonstrated effective olive identification capacity with a reduction in required wavelengths and VIs dataset, affecting the technological needs (spectrometer offset and real-time classification applications) for a tool oriented to olive cultivars and ripening stage discrimination. Full article

Microbial communities within human tissues are increasingly recognized as promising biomarkers for cancer detection. However, leveraging microbiome data for multiclass cancer classification remains challenging due to its compositional structure, high dimensionality, and lack of model interpretability. In this study, we address these challenges by introducing MicroAIbiome, a machine learning-based artificial intelligence (AI) pipeline designed to classify five cancer types such as esophageal carcinoma (ESCA), head and neck squamous cell carcinoma (HNSC), stomach adenocarcinoma (STAD), colon adenocarcinoma (COAD), and rectum adenocarcinoma (READ), using genus-level microbial relative abundances. Our pipeline incorporates zero-replacement, centered log-ratio (CLR) transformation, correlation filtering, and recursive feature elimination (RFE) to enable robust learning from compositional data. Among five evaluated classifiers, XGBoost achieved the highest accuracy of 78.23%, outperforming prior work. We further enhance interpretability using SHapley Additive exPlanations (SHAP)-based feature attribution to uncover class-specific microbial signatures, such as Corynebacterium in ESCA and Bacteroides in COAD. Our results highlight the importance of compositional preprocessing and explainable AI in advancing microbiome-based cancer diagnostics. Full article

Background: Pediatric sepsis is a life-threatening disease that is associated with the progression of acute lymphoblastic leukemia (ALL) and the recurrence of B-cell ALL (B-ALL). Although previous studies have reported a partial association between sepsis and ALL, there is limited research on the shared genes between pediatric sepsis and relapsed B-ALL. This study aims to further elucidate the more comprehensive and novel common genetic factors and molecular pathways between the two diseases. Methods: Gene expression datasets pertaining to pediatric sepsis (GSE13904, GSE80496) and relapsed B-ALL (GSE3910, GSE28460) were retrieved from the Gene Expression Omnibus database for this retrospective analysis. The initial analysis identified differentially expressed genes common to both pediatric sepsis and relapsed B-ALL. Subsequent investigations employed three complementary approaches: protein–protein interaction networks, molecular complex detection (MCODE) clustering functions, and support vector machine recursive feature elimination model to separately identify the diagnostic biomarkers for each condition. Importantly, key common genes were identified by overlapping the diagnostic genes for pediatric sepsis and relapsed B-ALL. Further characterization involved comprehensive functional analysis through the Metascape platform, construction of transcription factor (TF)-mRNA-microRNA (miRNA) networks, drug prediction, and molecular docking to explore their biological significance and potential therapeutic targets. Results: Comparative analysis of pediatric sepsis-related and relapsed B-ALL-related datasets revealed two shared genetic markers, lactotransferrin (LTF) and matrix metallopeptidase 9 (MMP9), exhibiting diagnostic significance and consistent upregulation in both disease groups. Transcriptional regulatory network analysis identified specificity protein 1 (SP1) as the principal transcription factor capable of coregulating LTF and MMP9 expression. In addition, molecular docking demonstrated high-affinity interactions between curcumin and MMP9 (−7.18 kcal/mol) as well as reserpine and LTF (−5.4 kcal/mol), suggesting their potential therapeutic utility for clinical evaluation. Conclusions: These findings elucidate the molecular pathogenesis involving LTF and MMP9 in pediatric sepsis and relapsed B-ALL, providing novel insights for clinical diagnosis and therapeutic development. Full article

The dynamics of cyanobacteria bloom in Lake Taihu, China, are subject to rapid fluctuations under the influence of various factors, with meteorological conditions being particularly influential. In this study, monitoring data on the surface area of cyanobacteria bloom in Lake Taihu and observational data from automatic meteorological stations around Lake Taihu from 2016 to 2022 were utilized. Meteorological sub-indices were constructed based on the probability density distributions of meteorological factors in different areas of cyanobacterial bloom. A stacked ensemble model utilizing various machine learning algorithms was developed. This model was designed to forecast the cyanobacterial bloom area index in Lake Taihu based on meteorological data. This model has been deployed with real-time gridded forecasts from the China Meteorological Administration (CMA) to predict changes in the cyanobacteria bloom area index in Lake Taihu over the next 7 days. The results demonstrate that utilizing meteorological sub-indices, rather than traditional meteorological elements, provides a more effective reflection of changes in cyanobacteria bloom area. Key meteorological sub-indices were identified through recursive feature elimination, with wind speed variance and wind direction variance highlighted as especially important factors. The real-time forecasting system operated over a 2.5-year period (2023 to July 2025). Results demonstrate that for cyanobacteria bloom areas exceeding 100 km², the 1-day lead-time forecast hit rate exceeded 72%, and the 3-day forecast hit rate remained above 65%. These findings significantly enhance forecasting capability for cyanobacterial blooms in Lake Taihu, offering critical support for sustainable water management practices in one of China’s most important freshwater systems. Full article

The Nitrogen Balance Index is a key indicator of crop nitrogen status, but conventional monitoring methods are invasive, costly, and unsuitable for large-scale application. This study targets early-season winter wheat in the Guanzhong Plain and proposes a framework that integrates Sentinel-2 imagery with Sen2Res super-resolution reconstruction, multi-feature optimization, and interpretable machine learning. Super-resolved imagery demonstrated improved spatial detail and enhanced correlations between reflectance, texture, and vegetation indices and the Nitrogen Balance Index compared to native imagery. A two-stage feature-selection strategy, combining correlation analysis and recursive feature elimination, identified a compact set of key variables. Among the tested algorithms, the random forest model achieved the highest accuracy, with R² = 0.77 and RMSE = 1.57, representing an improvement of about 20% over linear models. Shapley Additive Explanations revealed that red-edge and near-infrared features accounted for up to 75% of predictive contributions, highlighting their physiological relevance to nitrogen metabolism. Overall, this study contributes to the remote sensing of crop nitrogen status through three aspects: (1) integration of super-resolution with feature fusion to overcome coarse spatial resolution, (2) adoption of a two-stage feature optimization strategy to reduce redundancy, and (3) incorporation of interpretable modeling to improve transparency. The proposed framework supports regional-scale NBI monitoring and provides a scientific basis for precision fertilization. Full article

The environmental impact of industrial processes, especially regarding CO₂ emissions, requires innovative tools to monitor and optimize resource consumption. This study presents a data-driven approach for a carded nonwoven production line, aiming to support integration into the sustainability framework FOREST (Framework for Resource, Energy, Sustainability Treatment). Real process data from a pilot line were pre-processed, analysed, and used to train machine learning models to predict energy consumption across multiple production stages. Using techniques such as recursive feature elimination and SHAP value interpretation, the most influential parameters for each process step were identified. Extra Trees Regression proved to be the most accurate and explainable model across all scenarios. The results allow real-time estimation of the Product Carbon Footprint (PCF) based on process parameters and provide a foundation for energy optimization in nonwoven manufacturing. Full article

Mangroves are critical blue carbon ecosystems, yet accurately estimating their aboveground carbon (AGC) stocks remains challenging due to structural complexity and spectral saturation in dense canopies. This study aims to develop a scalable AGC estimation framework by integrating high-resolution canopy height (CH) data from UAV-LiDAR with multi-source satellite features from Sentinel-1, Sentinel-2, and ALOS PALSAR-2. Using the Maowei Sea mangrove zone in Guangxi, China, as a case study, we extracted structural, spectral, and textural features and applied Random Forest regression with Recursive Feature Elimination (RFE) to optimize feature combinations. Results show that incorporating UAV-derived CH significantly improves model accuracy (R² = 0.75, RMSE = 14.18 Mg C ha⁻¹), outperforming satellite-only approaches. CH was identified as the most important predictor, effectively mitigating saturation effects in high-biomass stands. The estimated total AGC in the study area was 88,363.73 Mg, with a mean density of 53.01 Mg C ha⁻¹. This study highlights the advantages of cross-scale UAV–satellite data fusion for accurate, regionally scalable AGC mapping, offering a practical tool for blue carbon monitoring and coastal ecosystem management under global change. Full article