Results 71 to 80 of about 3,838 (180)

Potential Collision Severity Prediction Based on Data Distribution‐Preserving Resampling

IET Intelligent Transport Systems, Volume 20, Issue 1, January/December 2026.
In this paper, a potential accident severity prediction method is proposed, which solves two key problems: how to characterise the severity of potential accidents and how to deal with the class‐imbalanced dataset caused by the scarcity of severe accidents.
Lan Zhao, Yuanyuan Ren, Xuelian Zheng, Xiansheng Li, Jianfeng Xi, Lei Shi, Yanhui Fan   +6 more
wiley   +1 more source

Improving Breast Cancer Classification with Adaptive Synthetic Sampling, Feature Selection, and Hyperparameter Optimization

ARO-The Scientific Journal of Koya University
Breast cancer is a major global health concern, highlighting the need for accurate and efficient diagnostic solutions rather than persistent issues with detection accuracy.
Hayder N. Jasim, Wesam M. Jasim, Mohammed S. Ibrahim   +2 more
doaj   +1 more source

A Novel Hybrid Deep Learning Approach Using Convolutional Neural Network–Transformer With Cross‐Attention Mechanism for an Effective Minor Blade Fault Detection

International Journal of Rotating Machinery, Volume 2026, Issue 1, 2026.
Blade faults are widely regarded as one of the most frequent failures in gas turbines, and if left unchecked, they can result in catastrophic failure. To ensure the safe operation of these machines, it is essential to detect minor blade faults and monitor blade health regularly.
Syed Asad Imam, Meng Hee Lim, Ahmed Mohammed Abdelrhman, Iftikhar Ahmad, Mohd Salman Leong, Sohini Basu Roy   +5 more
wiley   +1 more source

Explainability‐Aligned Reliability‐Weighted Fuzzy Ensemble for Automated Cervical Cancer Classification

International Journal of Intelligent Systems, Volume 2026, Issue 1, 2026.
Abstract Cervical cancer remains a major global health concern, highlighting the need for computer‐aided diagnostic systems that are both reliable and interpretable. Despite advances in deep learning–based cytology image classification, a gap persists in aligning model predictions with biologically meaningful explanations. This study aims to develop an
Süheyla Demirtaş Alpsalaz, Emrah Aslan, Yıldırım Özüpak, Feyyaz Alpsalaz, Hasan Uzel, Ievgen Zaitsev, Richard Murray   +6 more
wiley   +1 more source

Predictive Analysis of Early Thyroid Disorders Using Integration of Data Mining and Ensemble Intelligence Approaches

International Journal of Intelligent Systems, Volume 2026, Issue 1, 2026.
This study proposes a novel machine learning (ML) approach for early detection of thyroid disorders using data mining and ensemble learning techniques. By leveraging a diverse dataset—including demographic details, medical history, symptoms, and diagnostic test results—a high‐precision model is developed to predict the risk of thyroid dysfunction.
Sa’ed Abed, Sherlin Saji, Mohammad H. Alshayeji, Richard Murray   +3 more
wiley   +1 more source

Prediction of surface roughness using deep learning and data augmentation [PDF]

Journal of Intelligent Manufacturing and Special Equipment
Purpose – Surface roughness has a serious impact on the fatigue strength, wear resistance and life of mechanical products. Realizing the evolution of surface quality through theoretical modeling takes a lot of effort.
Miaoxian Guo, Shouheng Wei, Chentong Han, Wanliang Xia, Chao Luo, Zhijian Lin   +5 more
doaj   +2 more sources

The Effect of Resampling Techniques on Model Performance Classification of Maternal Health Risks

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Indonesia's maternal mortality rate was the second highest in ASEAN, reflecting the problem of class imbalance in maternal health data. This research aimed to improve prediction accuracy in the classification of pregnant women's diseases through the ...
Nia Mauliza, Aisha Shakila Iedwan, Yoga Pristyanto, Anggit Dwi Hartanto, Arif Nur Rohman   +4 more
doaj   +1 more source

An empirical evaluation of imbalanced data strategies from a practitioner's point of view

, 2018
This research tested the following well known strategies to deal with binary imbalanced data on 82 different real life data sets (sampled to imbalance rates of 5%, 3%, 1%, and 0.1%): class weight, SMOTE, Underbagging, and a baseline (just the base ...
Franceschinell, Rodrigo A., Wainer, Jacques   +1 more
core  

Enhanced Multitask Learning with Attention Sparse Routing Mechanism for Intelligent Diabetes Prediction

Advanced Intelligent Systems, Volume 7, Issue 12, December 2025.
The model leverages patient time‐space information for pattern feature representations. Encoders extract first and second‐order features, aggregated with categorical embeddings and dense features. Task‐specific and shared experts use gated networks, with a dispatch layer routing information for diabetes risk evaluation and blood glucose prediction ...
Yingshuai Wang, Hongpu Hu, Liqin Xie, Qingkun Chen, Xingyun Lei, Panpan Qin, Yan Wang, Xing Gao, Yanli Wan   +8 more
wiley   +1 more source

APAROS: A Clustering-Based Hybrid Approach for Handling Overlapped Regions in Imbalanced Datasets

IEEE Access
In many real-world datasets, the class distribution is often highly imbalanced, and minority class samples are located within the majority regions, leading to significant overlap.
Annam Nandini, Tapas Kumar Mishra, Abinash Pujahari, Sanket Mishra   +3 more
doaj   +1 more source