Hybrid oversampling technique for imbalanced pattern recognition: Enhancing performance with Borderline Synthetic Minority oversampling and Generative Adversarial Networks

Class imbalance problems (CIP) are one of the potential challenges in developing unbiased Machine Learning models for predictions. CIP occurs when data samples are not equally distributed between two or multiple classes. Several synthetic oversampling techniques have been introduced to balance the i...

Full description

Saved in:
Bibliographic Details
Main Authors: Md Manjurul Ahsan, Shivakumar Raman, Yingtao Liu, Zahed Siddique
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Machine Learning with Applications
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666827025000209
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334748303851520
author Md Manjurul Ahsan
Shivakumar Raman
Yingtao Liu
Zahed Siddique
author_facet Md Manjurul Ahsan
Shivakumar Raman
Yingtao Liu
Zahed Siddique
author_sort Md Manjurul Ahsan
collection DOAJ
description Class imbalance problems (CIP) are one of the potential challenges in developing unbiased Machine Learning models for predictions. CIP occurs when data samples are not equally distributed between two or multiple classes. Several synthetic oversampling techniques have been introduced to balance the imbalanced data by oversampling the minor samples. One of the potential drawbacks of existing oversampling techniques is that they often fail to focus on the data samples that lie at the border point and give more attention to the extreme observations, ultimately limiting the creation of more diverse data after oversampling, and that is almost the scenario for most of the oversampling strategies. As an effect, marginalization occurs after oversampling. To address these issues, in this work, we propose a hybrid oversampling technique, named Borderline Synthetic Minority Oversampling and Generative Adversarial Network (BSGAN), by combining the strengths of Borderline-Synthetic Minority Oversampling Technique (SMOTE) and Generative Adversarial Networks (GANs). This approach aims to generate more diverse data that follow Gaussian distributions, marking a significant contribution to the field of Artificial Intelligence. We tested BSGAN on ten highly imbalanced datasets, demonstrating its application in engineering, where it outperformed existing oversampling techniques, creating a more diverse dataset that follows a normal distribution after oversampling.
format Article
id doaj-art-3df32b10c1f846e484a45a57f37bcbee
institution Kabale University
issn 2666-8270
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Machine Learning with Applications
spelling doaj-art-3df32b10c1f846e484a45a57f37bcbee2025-08-20T03:45:28ZengElsevierMachine Learning with Applications2666-82702025-06-012010063710.1016/j.mlwa.2025.100637Hybrid oversampling technique for imbalanced pattern recognition: Enhancing performance with Borderline Synthetic Minority oversampling and Generative Adversarial NetworksMd Manjurul Ahsan0Shivakumar Raman1Yingtao Liu2Zahed Siddique3Department of Industrial and Systems Engineering, University of Oklahoma, Norman, OK 73019, USA; Corresponding author.Department of Industrial and Systems Engineering, University of Oklahoma, Norman, OK 73019, USADepartment of Aerospace and Mechanical Engineering, University of Oklahoma, Norman, OK 73019, USADepartment of Aerospace and Mechanical Engineering, University of Oklahoma, Norman, OK 73019, USAClass imbalance problems (CIP) are one of the potential challenges in developing unbiased Machine Learning models for predictions. CIP occurs when data samples are not equally distributed between two or multiple classes. Several synthetic oversampling techniques have been introduced to balance the imbalanced data by oversampling the minor samples. One of the potential drawbacks of existing oversampling techniques is that they often fail to focus on the data samples that lie at the border point and give more attention to the extreme observations, ultimately limiting the creation of more diverse data after oversampling, and that is almost the scenario for most of the oversampling strategies. As an effect, marginalization occurs after oversampling. To address these issues, in this work, we propose a hybrid oversampling technique, named Borderline Synthetic Minority Oversampling and Generative Adversarial Network (BSGAN), by combining the strengths of Borderline-Synthetic Minority Oversampling Technique (SMOTE) and Generative Adversarial Networks (GANs). This approach aims to generate more diverse data that follow Gaussian distributions, marking a significant contribution to the field of Artificial Intelligence. We tested BSGAN on ten highly imbalanced datasets, demonstrating its application in engineering, where it outperformed existing oversampling techniques, creating a more diverse dataset that follows a normal distribution after oversampling.http://www.sciencedirect.com/science/article/pii/S2666827025000209Imbalanced classGenerative Adversarial NetworksSynthetic Minority Oversampling TechniqueBorderline Synthetic Minority oversamplingMachine learningOversampling
spellingShingle Md Manjurul Ahsan
Shivakumar Raman
Yingtao Liu
Zahed Siddique
Hybrid oversampling technique for imbalanced pattern recognition: Enhancing performance with Borderline Synthetic Minority oversampling and Generative Adversarial Networks
Machine Learning with Applications
Imbalanced class
Generative Adversarial Networks
Synthetic Minority Oversampling Technique
Borderline Synthetic Minority oversampling
Machine learning
Oversampling
title Hybrid oversampling technique for imbalanced pattern recognition: Enhancing performance with Borderline Synthetic Minority oversampling and Generative Adversarial Networks
title_full Hybrid oversampling technique for imbalanced pattern recognition: Enhancing performance with Borderline Synthetic Minority oversampling and Generative Adversarial Networks
title_fullStr Hybrid oversampling technique for imbalanced pattern recognition: Enhancing performance with Borderline Synthetic Minority oversampling and Generative Adversarial Networks
title_full_unstemmed Hybrid oversampling technique for imbalanced pattern recognition: Enhancing performance with Borderline Synthetic Minority oversampling and Generative Adversarial Networks
title_short Hybrid oversampling technique for imbalanced pattern recognition: Enhancing performance with Borderline Synthetic Minority oversampling and Generative Adversarial Networks
title_sort hybrid oversampling technique for imbalanced pattern recognition enhancing performance with borderline synthetic minority oversampling and generative adversarial networks
topic Imbalanced class
Generative Adversarial Networks
Synthetic Minority Oversampling Technique
Borderline Synthetic Minority oversampling
Machine learning
Oversampling
url http://www.sciencedirect.com/science/article/pii/S2666827025000209
work_keys_str_mv AT mdmanjurulahsan hybridoversamplingtechniqueforimbalancedpatternrecognitionenhancingperformancewithborderlinesyntheticminorityoversamplingandgenerativeadversarialnetworks
AT shivakumarraman hybridoversamplingtechniqueforimbalancedpatternrecognitionenhancingperformancewithborderlinesyntheticminorityoversamplingandgenerativeadversarialnetworks
AT yingtaoliu hybridoversamplingtechniqueforimbalancedpatternrecognitionenhancingperformancewithborderlinesyntheticminorityoversamplingandgenerativeadversarialnetworks
AT zahedsiddique hybridoversamplingtechniqueforimbalancedpatternrecognitionenhancingperformancewithborderlinesyntheticminorityoversamplingandgenerativeadversarialnetworks