Results 51 to 60 of about 14,987 (241)

Assessment of Stable Slopes Through BPSO-Driven Ensemble Models

open access: yesSlovak Journal of Civil Engineering
This study explores a hybrid approach that combines BPSO with ensemble machine learning techniques to improve predictive accuracy in assessments of slope stability.
Anuragi Saurabh Kumar, Kishan D.
doaj   +1 more source

Short-term natural gas load forecasting enhanced by GHMM-derived historical state features

open access: yesYou-qi chuyun
ObjectiveDaily natural gas load is influenced by multiple factors, including historical inertia, meteorological conditions, date types, and latent load regimes.
Hangsong MO, Genqing BIAN
doaj   +1 more source

Examining LightGBM and CatBoost models for wadi flash flood susceptibility prediction

open access: yes, 2021
This study presents two machine learning models, namely, the light gradient boosting machine (LightGBM) and categorical boosting (CatBoost), for the first time for predicting flash flood susceptibility (FFS) in the Wadi System (Hurghada, Egypt).
Mawloud Guermoui   +8 more
core   +1 more source

PrOMet: Accurate and Robust Metal‐Binding Site and Type Prediction

open access: yesAdvanced Science, EarlyView.
PrOMet is a two‐stage deep learning framework for jointly predicting metal‐binding sites and ion identities from protein structures. Surface candidate sites are first pruned, followed by refinement of the most probable sites and metal types. This hierarchical strategy enables robust and accurate metal prediction for cryo‐EM and AlphaFold‐derived ...
Gangeun Park, Chaok Seok, Hahnbeom Park
wiley   +1 more source

Multi-label auxiliary decision-making model for pharmacotherapy of ischemic stroke based on BR-SA-LightGBM using real-world electronic medical records

open access: yesFrontiers in Medicine
BackgroundIschemic stroke poses a substantial global health burden owing to its high prevalence, recurrence, disability, and mortality rates. Pharmacotherapy for ischemic stroke is highly heterogeneous across patients, with complex polypharmacy regimens ...
Yueqi Chen   +5 more
doaj   +1 more source

Enhanced Botnet Detection and Neutralization through Machine Learning: A Synergistic Analysis of Host Activity, Network Patterns with Explainable Insights [PDF]

open access: yesComputer Science Journal of Moldova
Botnets continue to be one of the biggest cybersecurity risks since they provide a platform for a number of unlawful operations. The growing sophistication and stealth of contemporary botnet networks, which frequently elude conventional detection tools ...
B. Gomathy   +4 more
doaj   +1 more source

An Integrated Artificial Intelligence Framework for Nanomedicine Engineering

open access: yesAdvanced Science, EarlyView.
This review outlines a closed‐loop AI ecosystem for nanomedicine engineering. By synergizing multimodal data harmonization, objective‐driven AI architectures, and automated high‐throughput validation, this “Design‐Make‐Test‐Analyze” (DMTA) workflow transforms traditional heuristic formulation into a predictive, self‐optimizing paradigm, accelerating ...
Meichen Dong   +10 more
wiley   +1 more source

An Innovative Approach for Forecasting Hydroelectricity Generation by Benchmarking Tree-Based Machine Learning Models

open access: yesApplied Sciences
Hydroelectricity, one of the oldest and most potent forms of renewable energy, not only provides low-cost electricity for the grid but also preserves nature through flood control and irrigation support.
Bektaş Aykut Atalay, Kasım Zor
doaj   +1 more source

AutoEncoder and LightGBM for Credit Card Fraud Detection Problems

open access: yes, 2023
This paper proposes a method called autoencoder with probabilistic LightGBM (AED-LGB) for detecting credit card frauds. This deep learning-based AED-LGB algorithm first extracts low-dimensional feature data from high-dimensional bank credit card feature ...
Haichao Du   +3 more
core   +1 more source

Pre‐Refinement Prediction of Dopant Site Occupancy in M‐Type Hexaferrites via Hierarchical and Uncertainty‐Aware Machine‐Learning

open access: yesAdvanced Science, EarlyView.
Refined data are extracted from CIF files to construct a hierarchical machine‐learning framework integrating sublattice classification, Fe‐site occupancy prediction, and reliability assessment. External validation yields 96% accuracy for sublattice classification and a macro mean absolute error of 0.0584 for Fe‐site prediction.
Dan Liu   +9 more
wiley   +1 more source

Home - About - Disclaimer - Privacy