Browse Articles
Discover research articles across all indexed journals
Cross-well machine learning prediction of sonic logs in Newfoundland and Labrador
Abstract Predicting compressional slowness (DTCO) from non-sonic logs can reduce acquisition cost, fill data gaps, and support field planning. We evaluate blind cross-well DTCO prediction on two offshore Newfoundland & Labrador wells using a strictly leakage-free, features-only strategy: causal lag windows are built from past non-sonic logs and all sonic/sonic-derived channels are excluded. The pipeline includes deterministic depth conditioning, relative-depth features, multi-scale depth derivatives, rank-aggregated feature selection, and time-aware validation on the training well. We compare three model families: Random Forest (RF), Extreme Gradient Boosting (XGBoost), and a BiLSTM. In this setting, tuned XGBoost with the top 20 predictors and a 10-sample lag attains blind cross-well performance of $$R^2=0.895$$ , MAE $$=11.38~\mu \mathrm {s/m}$$ , RMSE $$=15.12~\mu \mathrm {s/m}$$ when trained on Well 1 and tested on Well 2; the reverse direction is lower, indicating inter-well distribution shift. RF performs competitively in several configurations, whereas BiLSTM underperforms on these data. Overall, rigorous leakage control, depth-aware feature engineering, and principled feature selection are key drivers of performance, and tree-based ensembles provide strong, data-efficient baselines for cross-well pseudo-sonic prediction.
Correction: Benchmarking genome assemblers for four bacterial models based on contiguity, correctness, and completeness
Developing and examining a compact dual band circularly polarized ultra-wideband antenna covering C-band and X-band applications
Skin disease diagnostics through federated transfer learning on heterogeneous data
Abstract Skin diseases frequently cause mental and physical distress and are major global health concern. Because early detection is crucial to successful treatment, accurate diagnosis is challenge for dermatologists as well. Diagnostic accuracy could be significantly enhanced using methods like machine learning (ML) and deep learning (DL). However, substantial datasets are required for these models to make accurate predictions. The healthcare providers frequently encounter data shortages, and privacy regulations restrict data sharing. A privacy-preserving federated transfer learning for diagnosing skin diseases which incorporate four key strategies to enhance effectiveness. The transfer learning is used to train a model with dense neural network (DNN) for skin diseases detection. The feature extraction is performed using pre-trained architectures and DNN is used for classification. The federated learning (FL) replaces the transfer learning to train the model across distributed nodes with the DNN used to disease detection. The FL is combined with transfer learning to build a cohesive ecosystem where data privacy is maintained. The model performance was validated on both IID and non-IID database, with the proposed feature extraction with federated learning model achieving cross validation accuracy of 99.528% and 99.689% for IID and non-IID database, respectively. Results indicate that feature extraction with FL model can produce efficient, lightweight models—well-suited for resource-constrained devices—while ensemble learning enhances edge device performance, offering a powerful and privacy-preserving solution for skin disease diagnosis in modern healthcare.
Correction: Sero-surveillance of SARS-CoV-2 specific antibody (IgG) among garment workers in Bangladesh
Pediatric diabetes prediction using machine learning
Abstract Diabetes is a chronic condition that affects a substantial portion of the global population and is linked to elevated mortality rates and a range of severe health complications. Despite its clinical importance, progress in diabetes research is often constrained by the limited availability of comprehensive datasets and robust predictive models. To address these challenges, researchers are increasingly turning to big data analytics and machine learning (ML) methodologies. This study presents the development of an ML-based system aimed at predicting the likelihood of diabetes and classifying its various types. A novel dataset, termed Diabetes Types Dataset, was constructed by integrating four heterogeneous dataset sources: paediatrics data from the Mansoura University Children Hospital repository, the Pima Indian Diabetes (PIMA) dataset, the Pone dataset, and a Gestational Diabetes dataset. The classification of diabetes types was approached as a multiclass problem using a suite of supervised ML algorithms, including Artificial Neural Networks (ANN), Logistic Regression, Naive Bayes, Decision Trees, Adaptive Boosting, Random Forests, Gradient Boosting, Support Vector Machines, and K-Nearest Neighbors. Model performance was evaluated using several metrics: Accuracy, Precision, Mean Squared Error, and Area Under the Receiver Operating Characteristic Curve. Among the models tested, the ANN classifier demonstrated the highest accuracy, achieving a peak performance of 99.98%. Further validation was conducted using an external dataset referred to as diabetes_prediction, which confirmed the model’s robustness with consistent accuracy. Additionally, the proposed system was applied to a publicly available dataset, diabetes_Dataset, containing 34 features used to predict 12 distinct types of diabetes efficiently. The results suggest that this ML-driven approach can significantly enhance the ability of healthcare professionals to detect and classify diabetes types, thereby supporting early intervention and improved disease management.
Association of RAS mutational status with clinical outcomes in metastatic colorectal cancer treated with trifluridine/tipiracil or regorafenib
Synergistic nitrification inhibitors with best management practices can achieve higher yield and nitrogen use efficiency in semi-arid saline-alkali soils
Infrared land surface emissivity dynamics in the Taklimakan desert from 2001 to 2023
Assessment of low dietary inclusion of nutraceuticals derived from microalgae to enhance intestinal function in gilthead seabream (Sparus aurata) juveniles
Abstract Development of more sustainable aquaculture requires alternatives to traditional fishmeal and fish oil in aquafeeds. Among the options, microalgae have emerged as promising functional ingredient, with the potential to provide additional benefits in aquaculture animals. The objective of this piece of research was to assess the effect of the microalgal-based functional ingredients, LB-GUThealth and LB-GREENboost on the intestinal function in juvenile gilthead seabream. Digestive enzyme activities, intestinal mucosa structure and ultrastructure, expression of key intestinal genes, and parameters like transepithelial resistance and permeability were analyzed after administration of feeds supplemented with those algal-based ingredients at two dietary levels (0.5 and 1%) during 91 days. Results indicated improvements in feed utilization efficiency, reflected by an expansion of the absorptive surface of the intestinal mucosa, enlargement of the apical surface of enterocytes and extension of microvilli length, together with elevated activity levels of digestive enzymes involved in macronutrient digestion. Additionally, no alterations were observed in basal gene expression related to permeability or the immune system, nor in the bioelectrical parameters associated with the integrity of the intestinal barrier. Results obtained evidenced that the algal-based ingredients tested seem to be useful for improving the intestinal functionality in juvenile gilthead seabream.
Distribution of device-measured 24-h movement behaviors in older adults: cross-sectional findings from the HUNT4 study
Abstract Comprehensive mapping of key physical activity (PA) types, postures, and sleep among older adults is important for informing public health policies and interventions. This study aimed to describe the 24-h time distribution of key PA types, postures, and sleep in a population-based sample of community-dwelling older adults and explore whether age, sex, and educational level influenced this distribution. Participants 65 years and older from the fourth survey of the Trøndelag Health Study (HUNT4, 2017–19) with ≥ 1 day of complete accelerometer recording were included (n = 8,114). PA types (walking, running, cycling), postures (standing, sitting, lying (awake)), and sleep were derived from the accelerometer data using validated machine learning models. Survey-weighted regression models were applied to describe the 24-h time distribution of PA types, postures, and sleep by age, sex, and education. Participants spent 4.1 h standing ( SD 85.3 min), 82.8 min ( SD 40.3 min) walking, 0.2 min ( SD 1.7 min) running, 4.6 min ( SD 7.2 min) cycling, 9.2 h ( SD 115.5 min) sitting, 2.1 h ( SD 86.6 min) lying (awake), and 7.1 h ( SD 50.4 min) sleeping per day. Time spent standing and walking decreased, while time spent sitting, lying (awake), and sleeping increased with higher age. Women spent more time standing and sleeping, and less time walking, sitting, and lying (awake) than men. Higher education was associated with more time standing and walking and less time sitting. This study provides novel insights into the distribution of 24-h movement behaviors among older adults and can serve as a benchmark for future research on key PA types, postures, sleep, and their interactions.