Results 121 to 130 of about 14,987 (241)

PEMETAAN DAN KLASIFIKASI WILAYAH RAWAN GEMPA DI INDONESIA DENGAN METODE K-MEANS DAN LIGHTGBM [PDF]

open access: yes
Penelitian ini bertujuan untuk memetakan dan mengklasifikasikan wilayah rawan gempa di Indonesia dengan memanfaatkan algoritma K-Means dan LightGBM. Data historis gempa diperoleh dari Badan Meteorologi, Klimatologi, dan Geofisika (BMKG) sebagai dasar ...
Yudhi Selvina
core   +1 more source

Early prediction of acute kidney injury in traumatic and non‐traumatic rhabdomyolysis using an interpretable machine learning model: A multicenter study with external validation

open access: yesJournal of Intelligent Medicine, EarlyView.
Abstract Acute kidney injury (AKI) is a common and severe complication of rhabdomyolysis (RM), and early risk stratification remains challenging because of its multifactorial and heterogeneous nature. We developed and externally validated an interpretable machine learning (ML) model for early prediction of AKI in RM across traumatic and non‐traumatic ...
Chunli Liu   +11 more
wiley   +1 more source

Intelligent diagnosis‐related group classification for 134,189 patients in eastern China using machine learning

open access: yesJournal of Intelligent Medicine, EarlyView.
Intelligent DRG Classification with ELGWO‐LightGBM. Abstract Diagnosis‐related group (DRG) classification is crucial for healthcare cost management and resource allocation, but traditional manual classification by physicians is inefficient and error‐prone, especially for large‐scale medical data.
Yanxi Zhang   +3 more
wiley   +1 more source

High‐Fidelity Synthetic Raman Spectra Generation for Sinter Basicity Prediction Using β$$ \beta $$‐Variational Autoencoders

open access: yesJournal of Raman Spectroscopy, EarlyView.
A β$$ \beta $$‐variational autoencoder with β$$ \beta $$ = 0.1 generates high‐fidelity synthetic Raman spectra of industrial sinter with a 16‐fold improvement in spectral fidelity over SMOTE‐based augmentation (KL divergence: 0.0075 vs. 0.121), enabling reliable basicity prediction (R2 = 0.83) from limited labeled datasets.
Marjorie Ariele Pereira   +4 more
wiley   +1 more source

Proteomics of Nitrotyrosine: Integrating Mass Spectrometry and Immunodetection in Redox‐Driven Pathology

open access: yesMass Spectrometry Reviews, EarlyView.
ABSTRACT Nitrooxidative stress, driven by excess reactive nitrogen species like peroxynitrite, contributes to the pathogenesis of many chronic diseases. Among its molecular footprints, 3‐nitrotyrosine (3NT) has emerged as a biologically relevant marker of protein nitration.
Brîndușa Alina Petre
wiley   +1 more source

Advancing Artificial Intelligence in Myopia Management: From Predicting Progression to Supporting Clinical Decisions

open access: yesMed Research, EarlyView.
The AI‐enabled multimodal framework for whole‐life myopia management. Graphical abstract illustrates the transition of myopia care from premyopia to myopia, high myopia, and pathologic myopia. Multimodal data, including demographic and refractive information, genetic, behavioral and environmental factors, ophthalmic imaging, and omics profiles, can be ...
Zewei Zhang   +6 more
wiley   +1 more source

Interpretable Ensemble-Based Intrusion Detection Using Feature Selection on the ToN_IoT Dataset

open access: yesJISA (Jurnal Informatika dan Sains)
With With the rapid growth of IoT, securing interconnected devices against cyber threats has become critical. IoT datasets such as ToN-IoT are often high-dimensional, which poses challenges for efficient and accurate intrusion detection.
Vaman Shakir Sulaiman   +1 more
doaj   +1 more source

Inverse Design of Copolyamides via Sequence‐Sensitive Multifidelity Hybrid Models and Teacher–Student Genetic Algorithm

open access: yesMaterials Genome Engineering Advances, EarlyView.
A sequence‐sensitive multi‐fidelity hybrid modeling framework combined with a teacher‐student genetic algorithm enables the inverse design of copolyamides. The hybrid model balances prediction accuracy, sequence‑sensitivity, and computational cost. A two‑tier genetic algorithm can efficiently identify the monomer structures and ratios of copolyamides ...
Sheng Chen   +8 more
wiley   +1 more source

Machine Learning‐Assisted Prediction and Analysis of Viscosity and Fusion Characteristics for Coal and Biomass Ash

open access: yesMaterials Genome Engineering Advances, EarlyView.
This study develops a machine learning framework for predicting the flow temperature and viscosity of coal and biomass ash with CatBoost and LightGBM as the optimal models. Feature analysis revealed composition‐property mechanisms, and symbolic regression was further applied to derive empirical formulas for rapid and accurate prediction.
Gangcheng Wang   +7 more
wiley   +1 more source

Lithology Identification of Sandstone-type Uranium Ore Beds in the Songliao Basin based on Interpretable Machine Learning Model

open access: yesDonghua Ligong Daxue Xuebao. Ziran Kexue Ban
[Objective] Traditional lithology identification methods suffer from low accuracy, slow recognition speed, and poor generalization performance, thus there is an urgent need for an efficient and accurate solution.
XIAO Kun   +10 more
doaj   +1 more source

Home - About - Disclaimer - Privacy