ZivaHub2027 · dataset · restricted
Retrieval-Augmented Decoding for Improving Truthfulness in Open-Ended GenerationEnsuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial amount of annotated data and computational resources, limiting scalability. In contrast, decoding-time interventions offer lightweight alternatives without model re
NCL Data2026 · dataset
Code, split files, out-of-fold predictions and latency measurements for "Coil leakage, training variance and FLOP proxies in the evaluation of real-time steel surface defect detectors"<p dir="ltr">Supplementary material for the article "Coil leakage, training variance and FLOP proxies in the evaluation of real-time steel surface defect detectors" (submitted to the Journal of Real-Time Image Processing).</p><p dir="ltr">The study re-evaluates real-time steel surface defect detectors on NEU-DET and GC10-DET with five-fold cross-validation, coil-disjoint folds for GC10-DET, repeat
NCL Data2026 · dataset
<p>Balanced accuracy of the best machine learning models. The model architecture and statistical feature test are listed.</p><p>Balanced accuracy of the best machine learning models. The model architecture and statistical feature test are listed.</p>
NCL Data2026 · dataset
<p>Raw model performance results across feature selection methods and population groups.</p><p>This table contains the complete set of unfiltered machine-learning model outputs, including balanced accuracy (BA), average precision (AP), false positive rate (FPR), and false negative rate (FNR). Results are reported across multiple feature selection techniques, model types, random seeds, and population strata.</p> <p>(CSV)</p>
NCL Data2026 · dataset
In-Ride Alcohol-Impairment Detection in E-Scooterists with False-Alarm Control<p dir="ltr">Code and data to reproduce the results from "In-Ride Alcohol-Impairment Detection in E-Scooterists with False-Alarm Control"</p>
NCL Data2026 · dataset
<p>External validation performance across bacterial dominance boundaries.</p><p>This table reports balanced accuracy (BA) from validation analyses comparing pairwise bacterial dominance boundaries (e.g., non-Lactobacillus taxa versus Lactobacillus species and combined Lactobacillus groups). Results are presented for the total sample and stratified population groups, providing an external assessment of model generalizability across taxonomic contrasts and demographic strata
NCL Data2026 · dataset
Table 1_Development and internal validation of machine learning models for identifying suicidal behavior in inpatients with mood disorders.docxBackground<p>Suicidal behavior (SB) is a major concern in mood disorders. Models developed from retrospective records are vulnerable to ambiguous targets, data leakage, and inappropriate handling of class imbalance. We developed and internally validated a model to identify the risk of suicidal behavior in patients with mood disorders upon admission.</p>Methods<p>The dataset included 1, 099 inpatie
NCL Data2026 · dataset
<p>Key Bacteria Determined using Permutation Importance. The table shows the permutation importance score of bacteria for each group. The score represents the reduction in balanced accuracy due to shuffling of the values corresponding to that bacteria. A blank means the bacteria did not score as important for that group.</p><p>Key Bacteria Determined using Permutation Importance. The table shows the permutation importance score of bacteria for each group. The score represents the reduction in balanced accuracy due to shuffling of the values corresponding to that bacteria. A blank means the bacteria did not score as important for that group.</p>
NCL Data2026 · dataset
<p>Bacterial taxonomic harmonization and reference mapping.</p><p>This table provides a comprehensive mapping of bacterial taxa used in the analysis, including harmonization of genus- and species-level names across reference taxonomies. Original taxonomic labels are aligned to standardized nomenclature to ensure consistency across datasets and analytical steps.</p> <p>(XLSX)</p>
NCL Data2026 · dataset
<p>Model performance results stratified by training–testing data splits.</p><p>This table summarizes model performance metrics following repeated training–testing splits, enabling assessment of robustness and variability. Metrics are reported by feature selection method, model type, population group, and random state to support transparency and reproducibility.</p> <p>(CSV)</p>
NCL Data2026 · dataset
<b>An Explainable Deep Learning Framework for Heart Disease Prediction Using SMOA-Based Feature Selection and ACIO-Optimized Improved GRU</b><p dir="ltr">Heart disease is a serious disease with possibly fatal consequences. Finding high-risk factors for chronic CVD, such as smoking, cholesterol, obesity, and high blood pressure, could save several lives. Our work proposes an AI-enabled framework to help professionals and physicians identify high-risk indicators for heart disease.</p>
UP Research Data Repository2026 · dataset
College Students' Academic Performance<p dir="ltr">Multidimensional Exploration of Influencing Factors of College Students' Academic Performance: An Empirical Study Based on 18 Machine Learning Algorithms Students' Academic Performance</p>
Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Crystal structure
Data from: A pilot computer-vision model trained to identify slide-mounted scale insect pests from the family Rhizoecidae<p dir="ltr">Using root mealybugs (Hemiptera: Rhizoecidae) as a test case, this study gathered high-resolution extended depth of field images from slide-mounted museum specimens and trained a convolutional neural network (CNN) to identify and distinguish among 16 species that are encountered as agricultural pests in plant quarantine or greenhouses. A pretrained EfficientNetV2-M model was trained u
figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
Data Sheet 1_Outcome-specific value of longitudinal clinical information and model complexity for dynamic prediction of type 2 diabetes-related outcomes: a pooled landmarking study.pdfObjective<p>To evaluate the outcome-specific incremental value of longitudinal clinical history and model complexity for annual dynamic prediction of multiple type 2 diabetes-related outcomes using pooled landmarking.</p>Methods<p>We included 646 patients with complete annual records from baseline through year 3. Landmark times at years 1 and 2 were used to predict the first recorded occurrence of
figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
Supplementary file 1_Explainable AI for phishing URL detection: a Bayesian-optimized stacking ensemble framework with SHAP-guided feature learning.zipIntroduction<p>Phishing remains one of the most persistent and financially damaging threats facing modern organizations, with over 4.7 million incidents recorded in 2023 alone. Existing AI-based phishing detection frameworks are constrained by limited benchmarking scope, absent model interpretability, and insufficient statistical validation — three limitations that collectively restrict operationa
figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
Supplementary file 1_A nested case-control study on the relationship between gut microbiota and non-alcoholic fatty liver disease.docxBackground<p>The gut microbiota plays an important role in non-alcoholic fatty liver disease (NAFLD). This study aimed to explore gut microbiota-associated biomarkers for incident NAFLD and evaluate their predictive value, providing preliminary evidence for early risk identification.</p>Methods<p>From an initial cohort of 1,772 participants, 404 were included in the final analysis, comprising 101
Teesside University Research Data Repository2026 · dataset
CD-PINODE code and datasetThis repository contains the source code and synthetic dataset supporting the study "CD-PINODE: A Physics-Informed Neural Ordinary Differential Equation Framework for Joint Fault Classification and Remaining Useful Life Estimation in Turbofan Engines." Five prognostics models are implemented and benchmarked on NASA C-MAPSS synthetic sensor data across two co-dependent tasks: (1) binary fault class
figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
Table 1_An explainable machine learning model based on multidimensional task-state electroencephalography for identifying attention-deficit/hyperactivity disorder comorbid developmental dyslexia.docxBackground<p>Attention-deficit/hyperactivity disorder (ADHD) and developmental dyslexia (DD) are highly comorbid, yet objective differentiation from individual disorders remains challenging due to the lack of neurophysiological biomarkers. This study aimed to develop an interpretable machine learning model leveraging multidimensional task-state EEG features to distinguish ADHD–DD comorbidity from
figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
Supplementary file 1_New insights into tumor size in colorectal cancer: smaller size, higher risk?.docxBackground<p>In colorectal cancer, the AJCC T category is defined by the depth of bowel wall invasion rather than by the absolute size of the primary tumor. The clinical value of tumor size in assessing tumor aggressiveness, metastatic risk, and prognosis remains insufficiently investigated.</p>Aim<p>To evaluate the clinical value of tumor size in assessing potential metastatic risk and prognostic
Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Genome sequencing
MRSP WGS-AST boundary benchmark: reproducibility package (revision version)MRSP WGS-AST boundary benchmark: reproducibility package (revision version). Reproducibility package for the Microbial Genomics manuscript MGEN-D-26-00487 (de Souza and Santoro): Staphylococcus pseudintermedius whole-genome sequencing antimicrobial susceptibility boundary benchmark with a training-only-dictionary pangenome projection, restricted-shell model inputs, frozen prediction chains and out
Teesside University Research Data Repository2026 · dataset
Brinjal Leaf Disease and Fruit Condition Image Dataset: A Field-Collected Dataset from BangladeshThis dataset is a field-collected image resource for researchers and practitioners working in agriculture, machine learning, and computer vision. It contains images of brinjal (Solanum melongena) leaves and fruits collected under field conditions in Bangladesh. The dataset covers different disease symptoms, pest infestation, nutritional deficiency, and healthy leaf and fruit conditions. The datase
figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
Data: Identification of letters distorted by physiologically-inspired spatial scrambling<p dir="ltr">human data and trained CNN models </p>
figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Computed tomography
Supplementary file 1_Deep learning with interactive segmentation for risk stratification of cystic renal lesions on tri-phase CT: a multicenter study.pdfBackground<p>Accurate preoperative risk stratification of cystic renal lesions (CRLs) remains a clinical challenge, primarily due to morphological overlap which often leads to the overtreatment of indolent cysts. To address this, we developed and validated an integrated deep learning framework that combines interactive segmentation with tri-phase CT feature integration to refine malignancy predict
figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Astronomical catalogue
Table 1_Multiparametric MRI-based habitat and peritumoral radiomics integrating semi-automated segmentation for preoperative prediction of high-grade prostate cancer: a dual-center study.docxBackground<p>This study aimed to develop and validate an interpretable machine learning framework that combines semi-automated segmentation, intratumoral habitats derived from multiparametric MRI (mpMRI), and multiscale peritumoral radiomics to predict high-grade prostate cancer (HGPCa) before surgery.</p>Methods<p>This retrospective dual-center study involved 274 patients, comprising 208 from Cen
figshare + Loughborough Research Repository + GRANTS Data + UP Research Data Repository2026 · Computed tomography
Video 1_Deep learning with interactive segmentation for risk stratification of cystic renal lesions on tri-phase CT: a multicenter study.mp4Background<p>Accurate preoperative risk stratification of cystic renal lesions (CRLs) remains a clinical challenge, primarily due to morphological overlap which often leads to the overtreatment of indolent cysts. To address this, we developed and validated an integrated deep learning framework that combines interactive segmentation with tri-phase CT feature integration to refine malignancy predict