iHHO-SMOTe: A Cleansed Approach for Handling Outliers and Reducing Noise to Improve Imbalanced Data Classification

• URL: http://arxiv.org/abs/2504.12850v1
• Date: Thu, 17 Apr 2025 11:17:53 GMT
• Title: iHHO-SMOTe: A Cleansed Approach for Handling Outliers and Reducing Noise to Improve Imbalanced Data Classification
• Authors: Khaled SH. Raslan, Almohammady S. Alsharkawy, K. R. Raslan,
• Abstract summary: Classifying imbalanced datasets remains a significant challenge in machine learning.<n>Synthetic Minority Over-sampling Technique (SMOTE) generates new instances for the under-represented minority class.<n>A proposed approach, iHHO-SMOTe, addresses the limitations of SMOTE by first cleansing the data from noise points.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Classifying imbalanced datasets remains a significant challenge in machine learning, particularly with big data where instances are unevenly distributed among classes, leading to class imbalance issues that impact classifier performance. While Synthetic Minority Over-sampling Technique (SMOTE) addresses this challenge by generating new instances for the under-represented minority class, it faces obstacles in the form of noise and outliers during the creation of new samples. In this paper, a proposed approach, iHHO-SMOTe, which addresses the limitations of SMOTE by first cleansing the data from noise points. This process involves employing feature selection using a random forest to identify the most valuable features, followed by applying the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to detect outliers based on the selected features. The identified outliers from the minority classes are then removed, creating a refined dataset for subsequent oversampling using the hybrid approach called iHHO-SMOTe. The comprehensive experiments across diverse datasets demonstrate the exceptional performance of the proposed model, with an AUC score exceeding 0.99, a high G-means score of 0.99 highlighting its robustness, and an outstanding F1-score consistently exceeding 0.967. These findings collectively establish Cleansed iHHO-SMOTe as a formidable contender in addressing imbalanced datasets, focusing on noise reduction and outlier handling for improved classification models.

Related papers

• Neighbor displacement-based enhanced synthetic oversampling for multiclass imbalanced data [0.0]
  Imbalanced multiclass datasets pose challenges for machine learning algorithms. Existing methods still suffer from sparse data and may not accurately represent the original data patterns. A hybrid method called Neighbor Displacement-based Enhanced Synthetic Oversampling (NDESO) is proposed in this paper.
  arXiv  Detail & Related papers  (2025-01-07T19:15:00Z)
• ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labels [7.897299759691143]
  This paper introduces the Adaptive Nearest Neighbors and Eigenvector-based (ANNE) sample selection methodology. ANNE integrates loss-based sampling with the feature-based sampling methods FINE and Adaptive KNN to optimize performance across a wide range of noise rate scenarios.
  arXiv  Detail & Related papers  (2024-11-03T15:51:38Z)
• A Bilevel Optimization Framework for Imbalanced Data Classification [1.6385815610837167]
  We propose a new undersampling approach that avoids the pitfalls of noise and overlap caused by synthetic data.<n>Instead of undersampling majority data randomly, our method undersamples datapoints based on their ability to improve model loss.<n>Using improved model loss as a proxy measurement for classification performance, our technique assesses a datapoint's impact on loss and rejects those unable to improve it.
  arXiv  Detail & Related papers  (2024-10-15T01:17:23Z)
• Robust Learning under Hybrid Noise [24.36707245704713]
  We propose a novel unified learning framework called "Feature and Label Recovery" (FLR) to combat the hybrid noise from the perspective of data recovery.
  arXiv  Detail & Related papers  (2024-07-04T16:13:25Z)
• Tackling Diverse Minorities in Imbalanced Classification [80.78227787608714]
  Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers. We propose generating synthetic samples iteratively by mixing data samples from both minority and majority classes. We demonstrate the effectiveness of our proposed framework through extensive experiments conducted on seven publicly available benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-28T18:48:34Z)
• MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection [76.97324120775475]
  Cross-domain keypoint detection methods always require accessing the source data during adaptation. This paper considers source-free domain adaptive keypoint detection, where only the well-trained source model is provided to the target domain.
  arXiv  Detail & Related papers  (2023-02-09T12:06:08Z)
• Neighborhood Collective Estimation for Noisy Label Identification and Correction [92.20697827784426]
  Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. Recent advances employ the predicted label distributions of individual samples to perform noise verification and noisy label correction, easily giving rise to confirmation bias. We propose Neighborhood Collective Estimation, in which the predictive reliability of a candidate sample is re-estimated by contrasting it against its feature-space nearest neighbors.
  arXiv  Detail & Related papers  (2022-08-05T14:47:22Z)
• UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning [89.56465237941013]
  We propose UNICON, a simple yet effective sample selection method which is robust to high label noise. We obtain an 11.4% improvement over the current state-of-the-art on CIFAR100 dataset with a 90% noise rate.
  arXiv  Detail & Related papers  (2022-03-28T07:36:36Z)
• Scale-Equivalent Distillation for Semi-Supervised Object Detection [57.59525453301374]
  Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. We analyze the challenges these methods meet with the empirical experiment results. We introduce a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
  arXiv  Detail & Related papers  (2022-03-23T07:33:37Z)
• S3: Supervised Self-supervised Learning under Label Noise [53.02249460567745]
  In this paper we address the problem of classification in the presence of label noise. In the heart of our method is a sample selection mechanism that relies on the consistency between the annotated label of a sample and the distribution of the labels in its neighborhood in the feature space. Our method significantly surpasses previous methods on both CIFARCIFAR100 with artificial noise and real-world noisy datasets such as WebVision and ANIMAL-10N.
  arXiv  Detail & Related papers  (2021-11-22T15:49:20Z)
• SMOTified-GAN for class imbalanced pattern classification problems [0.41998444721319217]
  We propose a novel two-phase oversampling approach that has the synergy of SMOTE and GAN. The experimental results prove the sample quality of minority class(es) has been improved in a variety of tested benchmark datasets.
  arXiv  Detail & Related papers  (2021-08-06T06:14:05Z)
• Noise-resistant Deep Metric Learning with Ranking-based Instance Selection [59.286567680389766]
  We propose a noise-resistant training technique for DML, which we name Probabilistic Ranking-based Instance Selection with Memory (PRISM) PRISM identifies noisy data in a minibatch using average similarity against image features extracted from several previous versions of the neural network. To alleviate the high computational cost brought by the memory bank, we introduce an acceleration method that replaces individual data points with the class centers.
  arXiv  Detail & Related papers  (2021-03-30T03:22:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.