Results 91 to 100 of about 40,856 (264)

Prediction of Pipeline Defect Depth and Classification Based on CatBoost

Energy Science &Engineering, EarlyView.
Obtaining detection data using in‐line pipeline inspection, the synthetic minority oversampling technique (SMOTE) is applied to expand the sample set, thereby increasing the number of minority‐class samples. This approach effectively improves minority‐class detection and enhances pipeline safety assessment. ABSTRACT Magnetic flux leakage detection is a
Cong Chen, Rui Li, Guanwei Jia, Dongcun Qin   +3 more
wiley   +1 more source

Ensemble Deep Learning–Based Wind Power Forecasting With Self‐Adaptive Osprey Optimization Algorithm

Energy Science &Engineering, EarlyView.
Design of Self‐Adaptive Osprey (SAO) algorithm: The novel SAO algorithm is designed by integrating the exploration capability of the conventional Osprey algorithm by including the self‐adaptiveness for enhancing the convergence rate. Ensemble Deep Learning for wind power forecasting: The wind forecasting is employed using the proposed Ensemble learning
Johncy Bai Johnson, Sivarani Thankamony Saradha Devi, Kumar Chandrasekaran, Sourav Barua   +3 more
wiley   +1 more source

Analyzing Sentiment of SiCepat Express User Reviews

Journal of Applied Informatics and Computing
The development of e-commerce in Indonesia has led to an increase in the number of users of product delivery services to deliver their customers' orders to their destination.
Endra Maulia Wicaksana, Nova Rijati
doaj   +1 more source

Interpretable Tree‐Based Models for Predicting Short‐Term Rockburst Risk Considering Multiple Factors

Energy Science &Engineering, EarlyView.
Interpretable tree‐based models integrate microseismic, geological, and mining indicators to predict short‐term rockburst risk. SHAP analysis reveals the dominant role of energy‐related features and clarifies nonlinear factor interactions, enabling transparent and reliable early‐warning in deep coal mines.
Shuai Chen, Linming Dou, Atao Li, Wu Cai, Lei Zhang   +4 more
wiley   +1 more source

A “demand and supply” approach to monitoring habitat and population changes of migratory birds

Frontiers in Ecology and the Environment, EarlyView.
Habitat loss and degradation threaten thousands of migratory bird species worldwide. Yet, because the distributions of migratory birds change throughout the year, quantifying the impacts of threats and identifying key sites for conservation attention have proved challenging.
Tong Mu, Mo A Verhoeven, Micha V Jackson, Theunis Piersma, Richard A Fuller, David S Wilcove   +5 more
wiley   +1 more source

Strip Steel Defect Prediction Based on Improved Immune Particle Swarm Optimisation–Improved Synthetic Minority Oversampling Technique–Stacking

Applied Sciences
A model framework for the prediction of defects in strip steel is proposed with the objective of enhancing the accuracy of defect detection. Initially, the data are balanced through the utilisation of the Improved Synthetic Minority Oversampling ...
Zhi Fang, Fan Zhang, Su Yu, Bintao Wang
doaj   +1 more source

Model Optimasi SVM Dengan PSO-GA dan SMOTE Dalam Menangani High Dimensional dan Imbalance Data Banjir

Teknika
Banjir merupakan salah satu bencana alam yang sering terjadi di Indonesia, termasuk di Kota Samarinda dengan 18-33 titik desa terdampak dari tahun 2018-2021.
Raenald Syaputra, Taghfirul Azhima Yoga Siswa, Wawan Joko Pranoto   +2 more
doaj   +1 more source

Between Consistency and Adaptation: How Middle Managers Shape Compensation System Implementation

Human Resource Management, EarlyView.
ABSTRACT The success of a human resource management (HRM) system or subsystem, such as a compensation system, hinges on its implementation—yet the microfoundations of this process remain underexplored. To address this gap, we conducted two studies. Study 1 surveyed middle managers and employees in six organizations to examine their attributions of ...
Aino Tenhiälä, Sven Kepes, Saku Mantere, Johanna Maaniemi   +3 more
wiley   +1 more source

A Comparative Analysis of Combination of CNN-Based Models with Ensemble Learning on Imbalanced Data

JOIV: International Journal on Informatics Visualization
This study investigates the usefulness of the Synthetic Minority Oversampling Technique (SMOTE) in conjunction with convolutional neural network (CNN) models, which include both single and ensemble classifiers. The objective of this research is to handle
Xiaoling Gao, Nursuriati Jamil, Muhammad Izzad Ramli, Syed Mohd Zahid Syed Zainal Ariffin   +3 more
doaj   +1 more source

IMPLEMENTASI SMOTE-ENN DAN BORDERLINE SMOTE TERHADAP PERFORMA LIGHTGBM PADA IMBALANCED CLASS

Rabit : Jurnal Teknologi dan Sistem Informasi Univrab
Ketidakseimbangan kelas (imbalanced class) merupakan tantangan yang sering dihadapi dalam pengembangan model pembelajaran mesin, di mana distribusi data yang tidak merata antara kelas mayoritas dan kelas minoritas dapat menyebabkan bias prediksi terhadap kelas mayoritas.
Andi Jamiati Paramita, Furqan Zakiyabarsi, Yabes Dwi Nugroho H   +2 more
openaire   +1 more source