Class Distribution Imbalance Research Articles

A Novel Ensemble Deep Learning Based Polyp Detection Using Colonoscopy Dataset

This work addresses the critical task of polyp detection and classification using the SUN colonoscopy video database, which consists of still images annotated with bounding boxes. These images categorize frames into polyp and non-polyp and encompass six distinct classes of polyps: Hyperplastic polyp, Sessile serrated lesion, Low-grade adenoma, Traditional serrated adenoma, High-grade adenoma, and Invasive carcinoma. The approach involves a two-stage classification process. Initially, MobileNetV2 is employed to distinguish between polyp and non-polyp frames. Subsequently, ResNet50 and GoogLeNet are utilized to classify the identified polyps into the six predefined categories. Data augmentation techniques are implemented to address the inherent imbalance in class distribution within the dataset, enhancing model performance and generalizability. The results highlight the effectiveness of GoogLeNet, which achieved an impressive accuracy of 98%, significantly outperforming ResNet50's accuracy of 76.16%. This substantial improvement underscores the potential of GoogLeNet in enhancing the accuracy of polyp classification. The significance of this work lies in its contribution to advancing automated polyp detection and cancer stage classification, crucial for early diagnosis and treatment. These findings provide a foundation for further research and development in this domain, with the potential to improve clinical outcomes through more accurate and timely identification of colorectal polyps.

Class-overlap detection based on heterogeneous clustering ensemble for multi-class imbalance problem

The class imbalance problem is one of the main challenges that hinders classifiers from identifying unknown instances. When class distribution imbalance and class overlap coexist in the same data set, the recognition of minority instances by traditional classifiers will be seriously affected. In the binary classification problem, the relationship between the majority class and the minority class is clear, and the overlap problem between classes can be well solved by removing the majority instances in the class-overlap area. However, for multi-class imbalance problems, the relationships between classes will become complex. Clustering techniques are effective methods for identifying overlapping instances; however, a single clustering method cannot effectively identify clusters of different shapes. Therefore, in this paper, a Heterogeneous Clustering Ensemble learning method for Multiple Class-overlap Detection (HCE-MCD) is proposed for multi-class imbalance problems. This method uses a genetic algorithm to select a combination of heterogeneous clustering techniques with the best fitness function from a pool of clustering algorithms and uses majority voting to fuse the results of the clustering algorithm. Furthermore, instances located near the decision boundary are more likely to be overlapping instances. Therefore, according to the clustering results of the heterogeneous clustering ensemble method, we can identify the overlapping instances existing in the data set, thereby eliminating the class overlap problem in the multi-class dataset. Experimental results on 19 open-access datasets show that our proposed method outperforms or partially outperforms state-of-the-art research protocols.

CLIP-Guided Federated Learning on Heterogeneity and Long-Tailed Data

Federated learning (FL) provides a decentralized machine learning paradigm where a server collaborates with a group of clients to learn a global model without accessing the clients' data. User heterogeneity is a significant challenge for FL, which together with the class-distribution imbalance further enhances the difficulty of FL. Great progress has been made in large vision-language models, such as Contrastive Language-Image Pre-training (CLIP), which paves a new way for image classification and object recognition. Inspired by the success of CLIP on few-shot and zero-shot learning, we use CLIP to optimize the federated learning between server and client models under its vision-language supervision. It is promising to mitigate the user heterogeneity and class-distribution balance due to the powerful cross-modality representation and rich open-vocabulary prior knowledge. In this paper, we propose the CLIP-guided FL (CLIP2FL) method on heterogeneous and long-tailed data. In CLIP2FL, the knowledge of the off-the-shelf CLIP model is transferred to the client-server models, and a bridge is built between the client and server. Specifically, for client-side learning, knowledge distillation is conducted between client models and CLIP to improve the ability of client-side feature representation. For server-side learning, in order to mitigate the heterogeneity and class-distribution imbalance, we generate federated features to retrain the server model. A prototype contrastive learning with the supervision of the text encoder of CLIP is introduced to generate federated features depending on the client-side gradients, and they are used to retrain a balanced server classifier. Extensive experimental results on several benchmarks demonstrate that CLIP2FL achieves impressive performance and effectively deals with data heterogeneity and long-tail distribution. The code is available at https://github.com/shijiangming1/CLIP2FL.

A novel method for detecting credit card fraud problems.

Credit card fraud is a significant problem that costs billions of dollars annually. Detecting fraudulent transactions is challenging due to the imbalance in class distribution, where the majority of transactions are legitimate. While pre-processing techniques such as oversampling of minority classes are commonly used to address this issue, they often generate unrealistic or overgeneralized samples. This paper proposes a method called autoencoder with probabilistic xgboost based on SMOTE and CGAN(AE-XGB-SMOTE-CGAN) for detecting credit card frauds.AE-XGB-SMOTE-CGAN is a novel method proposed for credit card fraud detection problems. The credit card fraud dataset comes from a real dataset anonymized by a bank and is highly imbalanced, with normal data far greater than fraud data. Autoencoder (AE) is used to extract relevant features from the dataset, enhancing the ability of feature representation learning, and are then fed into xgboost for classification according to the threshold. Additionally, in this study, we propose a novel approach that hybridizes Generative Adversarial Network (GAN) and Synthetic Minority Over-Sampling Technique (SMOTE) to tackle class imbalance problems. Our two-phase oversampling approach involves knowledge transfer and leverages the synergies of SMOTE and GAN. Specifically, GAN transforms the unrealistic or overgeneralized samples generated by SMOTE into realistic data distributions where there is not enough minority class data available for GAN to process effectively on its own. SMOTE is used to address class imbalance issues and CGAN is used to generate new, realistic data to supplement the original dataset. The AE-XGB-SMOTE-CGAN algorithm is also compared to other commonly used machine learning algorithms, such as KNN and Light GBM, and shows an overall improvement of 2% in terms of the ACC index compared to these algorithms. The AE-XGB-SMOTE-CGAN algorithm also outperforms KNN in terms of the MCC index by 30% when the threshold is set to 0.35. This indicates that the AE-XGB-SMOTE-CGAN algorithm has higher accuracy, true positive rate, true negative rate, and Matthew's correlation coefficient, making it a promising method for detecting credit card fraud.

Credit Card Fraud Detection and Identification using Machine Learning Techniques

Fraudulent internet transactions have caused considerable harm and losses for both people and organizations over time. The growth of cutting-edge technology and worldwide connectivity has exacerbated the rise in online fraud instances. To offset these losses, robust fraud detection systems must be developed. ML and statistical approaches are critical components in properly recognizing fraudulent transactions. However, implementing fraud detection models presents challenges such as limited data availability, data sensitivity, and imbalanced class distributions. The confidentiality of records adds complexity to drawing inferences and constructing improved models in this domain. This research explores multiple algorithms suitable for classifying transactions as either genuine or fraudulent using the Credit Card Fraud dataset. Given the extremely unbalanced nature of the dataset, the SMOTE approach was used for oversampling to alleviate the class distribution imbalance. In addition, feature selection was carried out, and the dataset was divided into training and test data. The experiments utilized NB, RF, and MLP algorithms, all of which demonstrated high accuracy in detecting credit card fraud. MLP method achieved 99.95% accuracy as compared to other methods.

Imbalanced class distribution and performance evaluation metrics: A systematic review of prediction accuracy for determining model performance in healthcare systems.

Focus on predictive algorithm and its performance evaluation is extensively covered in most research studies to determine best or appropriate predictive model with Optimum prediction solution indicated by prediction accuracy score, precision, recall, f1score etc. Prediction accuracy score from performance evaluation has been used extensively as the main determining metric for performance recommendation. It is one of the most widely used metric for identifying optimal prediction solution irrespective of dataset class distribution context or nature of dataset and output class distribution between the minority and majority variables. The key research question however is the impact of class inequality on prediction accuracy score in such datasets with output class distribution imbalance as compared to balanced accuracy score in the determination of model performance in healthcare and other real-world application systems. Answering this question requires an appraisal of current state of knowledge in both prediction accuracy score and balanced accuracy score use in real-world applications where there is unequal class distribution. Review of related works that highlight the use of imbalanced class distribution datasets with evaluation metrics will assist in contextualizing this systematic review.

Fraud Detection and Identification in Credit Card Based on Machine Learning Techniques

Fraudulent internet transactions have caused considerable harm and losses for both people and organizations over time. The growth of cutting-edge technology and worldwide connectivity has exacerbated the rise in online fraud instances. To offset these losses, robust fraud detection systems must be developed. ML and statistical approaches are critical components in properly recognizing fraudulent transactions. However, implementing fraud detection models presents challenges such as limited data availability, data sensitivity, and imbalanced class distributions. The confidentiality of records adds complexity to drawing inferences and constructing improved models in this domain. This research explores multiple algorithms suitable for classifying transactions as either genuine or fraudulent using the Credit Card Fraud dataset. Given the extremely unbalanced nature of the dataset, the SMOTE approach was used for oversampling to alleviate the class distribution imbalance. In addition, feature selection was carried out, and the dataset was divided into training and test data. The experiments utilized NB, RF, and MLP algorithms, all of which demonstrated high accuracy in detecting credit card fraud. MLP method achieved 99.95% accuracy as compared to other methods

Class-overlap undersampling based on Schur decomposition for Class-imbalance problems

The class-imbalance problem is an important area that plagues machine learning and data mining researchers. It is ubiquitous in all areas of the real world. At present, many methods have been developed to deal with the class-imbalance problem. For the class-imbalance problem, many researchers believe that the class distribution imbalance is not the main factor affecting the performance of the classification model. When the class distribution imbalance coexists with problems such as class overlap, small disjuncts, and noise, the model performance will be severely affected. For the problem of class-distribution imbalance and class-overlap, the existing methods mainly use nearest neighbors to obtain the local similarity of instances in the local domain, and find the overlapping domains in the data set. To the best of our knowledge, no researchers have considered global similarity. In this regard, to find the global similarity of datasets, a novel Schur decomposition class-overlap undersampling method (SDCU) is proposed. SDCU attempts to obtain potentially overlapping instances on global similarity, and is the first to use matrix decomposition to deal with the problem of class-overlap on class-imbalanced data. We conduct comparative experiments on 46 publicly available real datasets. The experimental results show that when using AUC as the performance evaluation metric, the performance of SDCU has obvious advantages compared with other state-of-the-art methods on three different types of classifiers: SVM, CART, and 3NN. In addition, the test results of Friedman ranking and Holm’s post-hoc test also confirmed the conclusions obtained by the experiments.

A Learning Framework for Medical Image-Based Intelligent Diagnosis from Imbalanced Datasets.

Medical image classification and diagnosis based on machine learning has made significant achievements and gradually penetrated the healthcare industry. However, medical data characteristics such as relatively small datasets for rare diseases or imbalance in class distribution for rare conditions significantly restrains their adoption and reuse. Imbalanced datasets lead to difficulties in learning and obtaining accurate predictive models. This paper follows the FAIR paradigm and proposes a technique for the alignment of class distribution, which enables improving image classification performance in imbalanced data and ensuring data reuse. The experiments on the acne disease dataset support that the proposed framework outperforms the baselines and enable to achieve up to 5% improvement in image classification.

Dynamically Weighted Balanced Loss: Class Imbalanced Learning and Confidence Calibration of Deep Neural Networks.

Imbalanced class distribution is an inherent problem in many real-world classification tasks where the minority class is the class of interest. Many conventional statistical and machine learning classification algorithms are subject to frequency bias, and learning discriminating boundaries between the minority and majority classes could be challenging. To address the class distribution imbalance in deep learning, we propose a class rebalancing strategy based on a class-balanced dynamically weighted loss function where weights are assigned based on the class frequency and predicted probability of ground-truth class. The ability of dynamic weighting scheme to self-adapt its weights depending on the prediction scores allows the model to adjust for instances with varying levels of difficulty resulting in gradient updates driven by hard minority class samples. We further show that the proposed loss function is classification calibrated. Experiments conducted on highly imbalanced data across different applications of cyber intrusion detection (CICIDS2017 data set) and medical imaging (ISIC2019 data set) show robust generalization. Theoretical results supported by superior empirical performance provide justification for the validity of the proposed dynamically weighted balanced (DWB) loss function.

Classification of the urinary metabolome using machine learning and potential applications to diagnosing interstitial cystitis.

With the advent of artificial intelligence (AI) in biostatistical analysis and modeling, machine learning can potentially be applied into developing diagnostic models for interstitial cystitis (IC). In the current clinical setting, urologists are dependent on cystoscopy and questionnaire-based decisions to diagnose IC. This is a result of a lack of objective diagnostic molecular biomarkers. The purpose of this study was to develop a machine learning-based method for diagnosing IC and assess its performance using metabolomics profiles obtained from a prior study. To develop the machine learning algorithm, two classification methods, support vector machine (SVM) and logistic regression (LR), set at various parameters, were applied to 43 IC patients and 16 healthy controls. There were 3 measures used in this study, accuracy, precision (positive predictive value), and recall (sensitivity). Individual precision and recall (PR) curves were drafted. Since the sample size was relatively small, complicated deep learning could not be done. We achieved a 76%–86% accuracy with leave-one-out cross validation depending on the method and parameters set. The highest accuracy achieved was 86.4% using SVM with a polynomial kernel degree set to 5, but a larger area under the curve (AUC) from the PR curve was achieved using LR with a l1-norm regularizer. The AUC was greater than 0.9 in its ability to discriminate IC patients from controls, suggesting that the algorithm works well in identifying IC, even when there is a class distribution imbalance between the IC and control samples. This finding provides further insight into utilizing previously identified urinary metabolic biomarkers in developing machine learning algorithms that can be applied in the clinical setting.

Classification of Imbalanced Datasets using One-Class SVM, k-Nearest Neighbors and CART Algorithm

In this paper a new algorithm, OKC classifier is proposed that is a hybrid of One-Class SVM, k-Nearest Neighbours and CART algorithms. The performance of most of the classification algorithms is significantly influenced by certain characteristics of datasets on which these are modeled such as imbalance in class distribution, class overlapping, lack of density, etc. The proposed algorithm can perform the classification task on imbalanced datasets without re-sampling. This algorithm is compared against a few well known classification algorithms and on datasets having varying degrees of class imbalance and class overlap. The experimental results demonstrate that the proposed algorithm has performed better than a number of standard classification algorithms.

Identify High-Impact Bug Reports by Combining the Data Reduction and Imbalanced Learning Strategies

As software systems become increasingly large, the logic becomes more complex, resulting in a large number of bug reports being submitted to the bug repository daily. Due to tight schedules and limited human resources, developers may not have enough time to inspect all the bugs. Thus, they often concentrate on the bugs that have large impacts. However, there are two main challenges limiting the automation technology that would help developers to become aware of high-impact bug reports early, namely, low quality and class distribution imbalance. To address these two challenges, we propose an approach to identify high-impact bug reports that combines the data reduction and imbalanced learning strategies. In the data reduction phase, we combine feature selection with the instance selection method to build a small-scale and high-quality set of bug reports by removing the bug reports and words that are redundant or noninformative; in the imbalanced learning strategies phase, we handle the imbalanced distributions of bug reports through four imbalanced learning strategies. We experimentally verified that the method of combining the data reduction and imbalanced learning strategies could effectively identify high-impact bug reports.

A Preliminary Study on Learning Challenges in Machine Learning-based Flight Delay Prediction

Machine learning based flight delay prediction is one of the numerous real-life application domains where the problem of imbalance in class distribution is reported to affect the performance of learning algorithms. However, the fact that learning algorithms have been reported to perform well on some class imbalance problems posits the possibility of other contributing factors. In this study, we visually explore air traffic data after dimensionality reduction with t-Distributed Stochastic Neighbour Embedding. Our initial findings suggest a high degree of overlapping between the delayed and on-time class instances which can be a greater problem for learning algorithms than class imbalance.

SDD-CNN: Small Data-Driven Convolution Neural Networks for Subtle Roller Defect Inspection

Roller bearings are some of the most critical and widely used components in rotating machinery. Appearance defect inspection plays a key role in bearing quality control. However, in real industries, bearing defects are usually extremely subtle and have a low probability of occurrence. This leads to distribution discrepancies between the number of positive and negative samples, which makes intelligent data-driven inspection methods difficult to develop and deploy. This paper presents a small data-driven convolution neural network (SDD-CNN) for roller subtle defect inspection via an ensemble method for small data preprocessing. First, label dilation (LD) is applied to solve the problem of an imbalance in class distribution. Second, a semi-supervised data augmentation (SSDA) method is proposed to extend the dataset in a more efficient and controlled way. In this method, a coarse CNN model is trained to generate ground truth class activation and guide the random cropping of images. Third, four variants of the CNN model, namely, SqueezeNet v1.1, Inception v3, VGG-16, and ResNet-18, are introduced and employed to inspect and classify the surface defects of rollers. Finally, a rich set of experiments and assessments is conducted, indicating that these SDD-CNN models, particularly the SDD-Inception v3 model, perform exceedingly well in the roller defect classification task with a top-1 accuracy reaching 99.56%. In addition, the convergence time and classification accuracy for an SDD-CNN model achieve significant improvement compared to that for the original CNN. Overall, using an SDD-CNN architecture, this paper provides a clear path toward a higher precision and efficiency for roller defect inspection in smart manufacturing.

Ensemble MultiBoost Based on RIPPER Classifier for Prediction of Imbalanced Software Defect Data

Identifying defective software entities is essential to ensure software quality during software development. However, the high dimensionality and class distribution imbalance of software defect data seriously affect software defect prediction performance. In order to solve this problem, this paper proposes an E nsemble M ultiBoost based on R IPPER classifier for prediction of imbalanced S oftware D efect data, called EMR_SD . Firstly, the algorithm uses principal component analysis (PCA) method to find out the most effective features from the original features of the data set, so as to achieve the purpose of dimensionality reduction and redundancy removal. Furthermore, the combined sampling method of adaptive synthetic sampling (ADASYN) and random sampling without replacement is performed to solve the problem of data class imbalance. This classifier establishes association rules based on attributes and classes, using MultiBoost to reduce deviation and variance, so as to achieve the purpose of reducing classification error. The proposed prediction model is evaluated experimentally on the NASA MDP public datasets and compared with existing similar algorithms. The results show that EMR_SD algorithm is superior to DNC, CEL and other defect prediction techniques in most evaluation indicators, which proves the effectiveness of the algorithm.

RHSBoost: Improving classification performance in imbalance data

Imbalance data are defined as a dataset whose proportion of classes is severely skewed. Classification performance of existing models tends to deteriorate due to class distribution imbalance. In addition, over-representation by majority classes prevents a classifier from paying attention to minority classes, which are generally more interesting. An effective ensemble classification method called RHSBoost has been proposed to address the imbalance classification problem. This classification rule uses random undersampling and ROSE sampling under a boosting scheme. According to the experimental results, RHSBoost appears to be an attractive classification model for imbalance data.

Distinctive characteristics of a metric using deviations from Poisson for feature selection

In the previous paper (Ogura, H., Amano, H., & Kondo, M. (2009). Feature selection with a measure of deviations from Poisson in text categorization. Expert Systems with Applications, 36, 6826–6832.), we proposed a new metric, χ P 2 , for selecting features in text classification which estimates term importance based on how largely the probability distribution of a considered term deviates from the standard Poisson distribution. In this study, to establish the validity and advantage of using χ P 2 , we conducted experiments of automatic text classification on 20 NewsGroups data collection with binary setting. In the experiments, other three metrics for feature selection, i.e., Gini index, χ 2 statistic and information gain, were also used for comparison. From the results, it was confirmed that χ P 2 and Gini index are much better than χ 2 statistic and information gain in terms of F 1 performance when they handle imbalanced data set. Furthermore, through another experiment in which the degree of imbalance in class distribution was explicitly controlled, we clarified that the origin of the superiority of χ P 2 and Gini index is their ability to pick up suitable negative features in imbalanced data set. The ability of these two metrics to select suitable negative features is explained based on the analysis of their limiting behaviors at some extreme cases.