Results 61 to 70 of about 3,838 (180)

MEBoost: Mixing Estimators with Boosting for Imbalanced Data Classification

, 2017
Class imbalance problem has been a challenging research problem in the fields of machine learning and data mining as most real life datasets are imbalanced.
Ahmed, Sajid, Farid, Dewan Md., Jani, Md. Rafsan, Mahbub, Asif, Rahman, Chowdhury Mofizur, Rayhan, Farshid, Shatabda, Swakkhar   +6 more
core   +1 more source

A Machine Learning Framework for Detecting and Preventing Cyber‐Attacks in Industrial Cyber‐Physical Systems

Engineering Reports, Volume 8, Issue 1, January 2026.
Proposed cyber physical system security framework. ABSTRACT The increasing adoption of cyber‐physical systems (CPS) in Industry 4.0 has heightened vulnerability to cyber threats. This study proposes a machine learning–based intrusion detection framework, DBID‐Net, to effectively identify and prevent attacks in CPS environments. The framework integrates
Anurag Sinha, Rejuwan Shamim, Mihika Mahendra, Trupti Mohota, G. Madhukar Rao, Mohammad Nadeem Ahmed, Mohammad Rashid Hussain, Satyam Solanki, Tanish Ranjan, Bhaskar, Mini Kumari, Karan Dixit, Vyom Modi, Syed Immamul Ansarullah, Mohd Asif Shah   +14 more
wiley   +1 more source

Explainable AI With Imbalanced Learning Strategies for Blockchain Transaction Fraud Detection

Engineering Reports, Volume 8, Issue 1, January 2026.
Research methodology pipeline for blockchain fraud detection. ABSTRACT Blockchain networks now support billions of dollars in daily transactions, making reliable and transparent fraud detection essential for maintaining user trust and financial stability.
Ahmed Abbas Jasim Al‐Hchaimi, M. A. Khalifa, Walid El‐Shafai   +2 more
wiley   +1 more source

Pengukuran Kinerja Model Klasifikasi dengan Data Oversampling pada Algoritma Supervised Learning untuk Penyakit Jantung

Computer Science
Penyakit jantung tetap menjadi penyebab utama kematian di Indonesia dan dunia. Dalam data mining, ketidakseimbangan kelas antara sampel penyakit jantung dan normal dalam dataset adalah masalah serius.
Anis Masruriyah, Hilda Novita, Cici Sukmawati, Angga Ramadhan, Siti Arif, Budi Dermawan   +5 more
doaj   +1 more source

DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN

, 2018
Recently, the introduction of the generative adversarial network (GAN) and its variants has enabled the generation of realistic synthetic samples, which has been used for enlarging training sets.
Cheung, Ngai-Man, Elovici, Yuval, Lim, Swee Kiat, Loo, Yi, Roig, Gemma, Tran, Ngoc-Trung   +5 more
core   +1 more source

IntelliMetro‐Hybrid: A Machine Learning and Deep Learning Fusion Model for Economic Optimization in Smart Metro Systems

Transactions on Emerging Telecommunications Technologies, Volume 37, Issue 1, January 2026.
IntelliMetro‐Hybrid is an intelligent fusion framework that integrates machine learning (ML) and deep learning (DL) for real‐time anomaly detection and economic optimization in smart metro systems. The model combines tree‐based feature extraction (Random Forest, XG Boost) with a deep neural classifier to effectively handle imbalanced, heterogeneous ...
Sijin Peng, Yongchang Wei, Zhigang Sun, Yong Chen, Jiang Huang, Hao Chen, Liuyi Chen   +6 more
wiley   +1 more source

Predicting Employee Turnover Based on Improved ADASYN and GS-CatBoost

Mathematics
In corporate management practices, human resources are among the most active and critical elements, and frequent employee turnover can impose substantial losses on firms.
Shuigen Hu, Kai Dong
doaj   +1 more source

Metaheuristic‐Driven Feature Selection for Blockchain Fraud Detection: A Comparative Study on Machine and Deep Learning Models

IET Blockchain, Volume 6, Issue 1, January/December 2026.
We present a metaheuristic feature‐selection framework—Artificial Bee Colony, Aquila Optimiser and Fox Optimiser—for blockchain fraud detection, benchmarked across machine‐learning and deep‐learning models on large‐scale transaction data. The study evaluates predictive performance (PR‐AUC/ROC‐AUC), stability across seeds and parsimony under cost ...
Hibatou allah Boulsane, Karim Afdel
wiley   +1 more source

A Hybrid Approach for Malicious URL Detection Using Ensemble Models and Adaptive Synthetic Sampling

JOIV: International Journal on Informatics Visualization
Malicious URLs pose a significant cybersecurity threat, often leading to phishing attacks, malware infections, and data breaches. Early detection of these URLs is crucial for preventing security vulnerabilities and mitigating potential losses.
Khaled Mahmud Sujon, Rohayanti Hassan, Muhammad Edzuan Zainodin, Mohamad Aizi Salamat, Shahreen Kasim, Alde Alanda   +5 more
doaj   +1 more source

OpthaNet: Attention‐Integrated Architecture for High‐Precision Multi‐Class Ophthalmic Image Classification

Healthcare Technology Letters, Volume 13, Issue 1, January/December 2026.
Tailored modifications to the classification head and fine‐tuning strategies to improve model robustness and performance. A comprehensive comparative study leveraging transfer learning techniques for multi‐class eye disease classification, evaluating efficacy in diagnosing cataract, diabetic retinopathy and glaucoma.
Souhardo Rahman, Md. Nasif Safwan, Mahamodul Hasan Mahadi, Md. Iftekharul Mobin, Muhammad Firoz Mridha   +4 more
wiley   +1 more source