Imbalance Problem Research Articles

Review of imbalanced fault diagnosis technology based on generative adversarial networks

Abstract In the field of industrial production, machine failures not only negatively affect productivity and product quality, but also lead to safety accidents, so it is crucial to accurately diagnose machine failures in time and take appropriate measures. However, machines cannot operate with faults for extended periods, and the diversity of fault modes results in limited data collection, posing challenges to building accurate fault prediction models. Despite recent advancements, intelligent fault diagnosis methods based on traditional sampling and machine learning have shown notable progress. Nonetheless, these methods heavily rely on human expertise, making it challenging to extract comprehensive feature information. To address these challenges, numerous imbalance fault diagnosis methods based on generative adversarial networks (GANs) have emerged, GANs can generate realistic samples that conform to the distribution of the original data, showing promising results in diagnosing imbalances in critical components such as bearings and gears, despite their great potential, GAN methods also face challenges, including difficulties in training and generating abnormal samples. However, whether it is GAN-based resampling technology or traditional sampling technology, there are fewer reviews on noise-containing imbalance, intra- and inter-class dual imbalance, multi-class imbalance, time series imbalance and other problems in small samples, and there is a lack of a more comprehensive summary of the solutions to the above imbalance problems. Therefore, the purpose of this paper is to deeply explore the imbalance problems under various failure modes, and review and analyze the research methods and results based on GANs on this basis. By suggesting future research directions, this paper aims to provide guidance and reference for research in the field of industrial production maintenance.

A new chiller fault diagnosis method under the imbalanced data environment via combining an improved generative adversarial network with an enhanced deep extreme learning machine

The existing chiller fault diagnosis approaches often ignore the problem of data imbalance of chiller, which leads to low accuracy in diagnosing minority class fault samples. To conquer this issue, this paper proposes an improved generative adversarial network (IGAN) with an enhanced deep extreme learning machine (EDELM) method. Firstly, to better learn the latent structure of chiller fault data, the multi-head attention (MHA) mechanism is integrated into the traditional generative adversarial network (GAN) method to generate new samples that are more in line with the distribution of minority class fault samples for the purpose of obtaining a rebalanced dataset. Secondly, to fully handle the nonlinear features hidden in the massive chiller data, the deep extreme learning machine (DELM) basic classifier is trained on the rebalanced dataset. To enhance more attention to the misclassified samples, the adaptive boosting (AdaBoost) ensemble strategy is employed to train multiple DELM basic classifiers by updating the sample weights following the classification results through the iterative rounds. The voting weight of the current DELM basic classifier is given according to its fault diagnosis accuracy. Finally, multiple DELM basic classifiers are ensembled according to their voting weights to obtain the final ensemble classifier. The pattern of the snapshot sample is determined through the weighted voting strategy. Detailed experimental results based on the research project 1043 (RP-1043) conducted by the American society of heating, refrigeration, and air conditioning engineers (ASHRAE) confirm the effectiveness of the proposed IGAN-EDELM approach under imbalanced data environments.

A grid self-adaptive exploration-based algorithm for multimodal multiobjective optimization

In multimodal multiobjective optimization, the key is to find as many equivalent Pareto optimal solutions as possible through broad exploration in the decision space. The grid search strategy can achieve quick convergence by guiding the evolution with historical information in each grid while enabling broad exploration. However, inaccurate utilization of information in grids may lead to losing numerous potential solutions, especially on imbalanced problems. In order to resolve this issue, a grid self-adaptive exploration-based algorithm (GSEA) is proposed in this paper. In GSEA, the historical information in the grid is accurately utilized through grid-based self-adaptive exploration and niche clearing methods, which retain a large number of solutions with potential and effectively handle multimodal multiobjective optimization problems (MMOPs). Experimental results show that the proposed algorithm outperforms seven other state-of-the-art multimodal multiobjective evolutionary algorithms (MMEAs) on two types of MMOPs, and the approach can effectively deal with the MMOPs with middle-scale decision variables as memory allows.

Class imbalanced data handling with cyberattack classification using Hybrid Salp Swarm Algorithm with deep learning approach

Cyberattack classification involves applying deep learning (DL) and machine learning (ML) models to categorize digital threats based on their features and behaviors. These models examine system logs, network traffic, or other associated data patterns to discriminate between standard activities and malicious actions. Efficient cyberattack classification is vital for on-time threat detection and response, permitting cybersecurity specialists to categorize and reduce potential risks to a system. Handling class-imbalanced data in cyberattack classification using DL is critical for achieving exact and robust models. In cybersecurity databases, instances of normal behavior frequently significantly outnumber instances of cyberattacks, foremost due to biased methods that may complete poorly on minority classes. To address this issue approaches such as oversampling the lesser class, undersampling the popular class, or using more advanced systems can be used. These plans defend that the DL technique is more complex when determining cyberattacks, so it increases complete performance and adapts the effect of the imbalance class on the classification results. This study presents a novel Hybrid Salp Swarm Algorithm with a DL Approach for Cyberattack Classification (HSSADL-CAC) technique. The HSSADL-CAC method intends to resolve class imbalance data handling with an optimum DL model for the recognition of cyberattacks. At first, the HSSADL-CAC method experiences data normalization as a pre-processing stage. The HSSADL-CAC technique uses the ADASYN approach to handle class imbalance problems. In addition, the HSSADL-CAC technique applies an HSSA-based feature selection approach. The HSSADL-CAC technique detects cyberattacks using a deep extreme learning machine (DELM) model. Finally, the hyperparameter tuning of the ELM model takes place by utilizing the beluga whale optimization (BWO) model. The performance analysis of the HSSADL-CAC technique employs a benchmark database. The comprehensive comparison research indicates the superior performance of the HSSADL-CAC technique in the cyberattack detection procedure.

Surface energy fluxes in a drip-irrigated agroecosystem: Unique advection effect of oasis

Surface energy fluxes, mainly encompassing the net radiation (Rn), latent heat flux (LE), sensible heat flux (Hs), and soil heat flux (Gs), play an important role in the land-atmosphere interactions. However, almost all sites face the problem of energy imbalance, and advection fluxes associated with large inhomogeneous surfaces have been ignored, especially in arid oasis areas. In this study, a three-year continuous measurement of energy fluxes with an eddy covariance system was conducted in a drip-irrigated oasis agroecosystem in Northwest China. Reanalysis data including air temperature (Ta), soil moisture (θ), and leaf area index (LAI) in our cropland and surrounding deserts were also collected. The results showed that multi-year mean turbulent fluxes (LE+Hs) accounted for 75 ± 8 % (mean ± standard deviation) of available energy (Rn–Gs). To be precise, LE took up 72 ± 10 % of available energy, and 7.8 ± 2.8 % of it was induced by higher sensible heat advection, proving a pronounced advection effect in this study. When advection was present, most likely during the heading stage, the threshold value for the Priestley–Taylor parameter α, an indicator to reflect the advection effect, fell in the range of 0.88–1.34. Additionally, after a significant irrigation event, α showed a good linear relationship with differences in air temperature (ΔTa), soil moisture (Δθ), and leaf area index (ΔLAI) between our cropland and surrounding deserts. It's worth mentioning that Δθ was the most significant factor, showing a negative correlation with the advection effect. This study has deepened our understanding of the energy balance in oasis agriculture, emphasizing that the advection effect should not be overlooked.

Sample selection bias in non-traditional lending: A copula-based approach for imbalanced data

Credit scoring models for non-traditional lending channels, such as peer-to-peer (P2P) lending platforms, are usually estimated only on the sample of accepted applicants. This may lead to biased estimates of the risk drivers. This issue can be addressed using a reject inference technique that includes the characteristics of rejected applicants in the model. Due to the low numbers of accepted applicants and default records, credit scoring models usually face a class imbalance problem. However, previous literature on sample selection models for credit scoring does not address the class imbalance issue. To fill this gap, we extend the Generalised Extreme Value (GEV) regression model for binary data to the sample selection framework. We consider the quantile function of the GEV distribution as a link function in both the selection and outcome equations. We use the copula function to model the dependence structure between the two equations for its flexibility. This proposal is called the Sample Selection Generalised Extreme Value (SSGEV) model and it is implemented in the R package BivGEV. We apply this model to a comprehensive dataset provided by Lending Club, and we show that parameter estimates obtained only on accepted P2P applicants are biased and coherently with the literature. The SSGEV model achieves a higher predictive accuracy than those obtained using univariate approaches or a sample selection probit model. Our proposal also provides more conservative estimates of the Value-at-Risk and the Expected Shortfall.

Research on Default Classification of Unbalanced Credit Data Based on PixelCNN-WGAN

Personal credit assessment plays a crucial role in the financial system, which not only relates to the financial activities of individuals but also affects the overall credit system and economic health of society. However, the current problem of data imbalance affecting classification results in the field of personal credit assessment has not been fully solved. In order to solve this problem better, we propose a data-enhanced classification algorithm based on a Pixel Convolutional Neural Network (PixelCNN) and a Generative Adversarial Network (Wasserstein GAN, WGAN). Firstly, the historical data containing borrowers’ borrowing information are transformed into grayscale maps; then, data enhancement of default images is performed using the improved PixelCNN-WGAN model; and finally, the expanded image dataset is inputted into the CNN, AlexNet, SqueezeNet, and MobileNetV2 for classification. The results on the real dataset LendingClub show that the data enhancement algorithm designed in this paper improves the accuracy of the four algorithms by 1.548–3.568% compared with the original dataset, which can effectively improve the classification effect of the credit data, and to a certain extent, it provides a new idea for the classification task in the field of personal credit assessment.

An Active Learning Semantic Segmentation Model Based on an Improved Double Deep Q-Network

Image semantic segmentation is essential in fields such as computer vision, autonomous driving, and human-computer interaction due to its ability to accurately identify and classify each pixel in an image. However, this task is fraught with challenges, including the difficulty of obtaining detailed pixel labels and the problem of class imbalance in segmentation datasets. These challenges can hinder the effectiveness and efficiency of segmentation models. To address these issues, we propose an active learning semantic segmentation model named CG_D3QN, which is designed and implemented based on an enhanced Double Deep Q-Network (D3QN). The proposed CG_D3QN model incorporates a hybrid network structure that combines a dueling network architecture with Gated Recurrent Units (GRUs). This novel approach improves policy evaluation accuracy and computational efficiency by mitigating a Q-value overestimation and making better use of historical state information. Our experiments, conducted on the CamVid and Cityscapes datasets, reveal that the CG_D3QN model significantly reduces the number of required sample annotations by 65.0% compared to traditional methods. Additionally, it enhances the mean Intersection over Union (IoU) for underrepresented categories by approximately 1% to 3%. These results highlight the model’s effectiveness in lowering annotation costs, addressing class imbalance, and its versatility across different segmentation networks.

UB-FineNet: Urban building fine-grained classification network for open-access satellite images

Fine classification of city-scale buildings using satellite imagery is a crucial research area with significant implications for urban planning, infrastructure development, and population distribution analysis. However, the task faces great challenges due to low-resolution overhead images acquired from high-altitude space-borne platforms and the long-tailed sample distribution of fine-grained urban building categories, leading to a severe class imbalance problem. To address these issues, we propose a deep network approach to the fine-grained classification of urban buildings using open-access satellite images. A Denoising Diffusion Probabilistic Model (DDPM) based super-resolution method is first introduced to enhance the spatial resolution of satellite images, which benefits from domain-adaptive knowledge distillation. Then, a new fine-grained classification network with Category Information Balancing Module (CIBM) and Contrastive Supervision (CS) technique is proposed to mitigate the problem of class imbalance and improve the classification robustness and accuracy. Experiments on Hong Kong data set with 11 distinct building types revealed promising classification results with a mean Top-1 accuracy of 60.45%, which is on par with street-view image based approaches. A comprehensive ablation study demonstrates that the CIBM and CS modules improve Top-1 accuracy by 2.6% and 3.5%, respectively, over the baseline approach. In addition, these modules can be easily integrated into other classification networks, achieving similar performance improvements. This research advances urban analysis by providing an effective solution for detailed classification of buildings in complex mega-city environments using only open-access satellite imagery. The proposed technique can serve as a valuable tool for urban planners, aiding in the understanding of economic, industrial, and population distribution within cities and regions, ultimately facilitating informed decision-making in urban development and infrastructure planning. Data and code will be publicly available at https://github.com/ZhiyiHe1997/UB-FineNet.

Facebook Addiction: Advanced Vogel's Approximation Method of Unbalanced Fuzzy Transportation Problems.

In this article, we discuss the Advanced Vogel's Approximation Method (AVAM), a revolutionary solution for an imbalanced fuzzy transportation problem that avoids making it balanced. Notably, Facebook is the social network that is most popular and well-known globally. Some have characterized it as an invaluable resource for leisure and cross-cultural communication. Conversely, excessive use and a lack of self-control lead to Facebook addiction, which negatively affects the daily lives of many users, mostly young people. Facebook use appears to be connected to the drive to fit in, affiliate with people, and present oneself. Excessive Facebook use and addiction may also be linked to reward and pleasure systems.

Multi-source domain adaptation using diffusion denoising for bearing fault diagnosis under variable working conditions

Transfer learning of multi-source domain adaptation seems a promising way for fault diagnosis of roller element bearings under variable working conditions. Data imbalance affects the performance of multi-source domain adaptation greatly and is expected to be solved by GAN. However, GAN-based transfer learning diagnosis models suffer pattern collapse and training instability, leading to unsatisfying diagnosis results in practical engineering. This paper proposes a denoising diffusion multi-source domain adaptation model (DDMDA). The proposed model uses diffusion denoising, which has better performance and is simpler to train than GAN, to generate shifted source domains for solving the data imbalance problem. A new noise prediction structure in diffusion denoising named Utrans-net, is constructed to restore the data distribution in the shifted source domain. Also, a multiple-domain discriminator structure is designed to extract features from multiple source domains to solve the issue of variable working conditions. Advanced models are used in this paper to compare with the proposed model for validation. Experimental demonstrations show that the proposed model is superior to the comparison models with satisfying performance.

Novel imbalanced fault diagnosis method based on generative adversarial networks with balancing serial CNN and Transformer (BCTGAN)

In industrial production engineering, machines cannot sustain faults for extended periods, resulting in limited fault data collection. This scarcity of data impedes the advancement of accurate fault diagnosis models, particularly in the context of small-sample, extremely imbalanced fault modeling, which poses a significant and challenging problem. In this paper, we introduce an innovative data augmentation approach for addressing the small-sample imbalanced problem: the balanced conditioning CNN (Convolutional Neural Networks)-Transformer architecture based Generative Adversarial Network (BCTGAN). Firstly, we employ a serial CNN and Transformer architecture as the foundation of the generator. Secondly, we introduce micro-enhancement and SMOTE (Synthetic Minority Oversampling Technique) enhancement of samples to facilitate model training. Micro-enhancement simply augments the sample size, while SMOTE enhancement enhances diversity. Together, these techniques balance the training process by introducing new loss function terms. Finally, outlier samples are mitigated through a designed multi-domain feature screening method. Despite the added time cost and computational complexity, results from three instances demonstrate that the proposed method holds superior diagnostic results with great potential compared to traditional and general GAN-based fault diagnosis methods. Our work provides theoretical and practical insights for modeling the field of small-sample blended disequilibrium fault diagnosis.

Assessing the impact on quality of prediction and inference from balancing in multilevel logistic regression

The primary goal of this research is to examine the impact of balancing data on the prediction quality and inference in multilevel logistic regression models. Logistic regression is a valuable approach for modeling binary outcomes expected in health applications. The class imbalance problem, where one of the two outcome categories occurs much more often than the other, is common in healthcare data, such as when modeling the risk factors for rare diseases. The issue is particularly relevant for medical data that contains individual measurements and other data sources measured at a geographic region level, such as environmental risk factors. For this work, both prediction and model interpretation are of interest. A simulation model is proposed to test the impact of balancing strategies on the logistic multilevel model's parameter estimation, inference, and predictive performance. The simulated information emulates characteristics of a Gestational Diabetes Mellitus (GDM) dataset from Indiana's Medicaid program. Several datasets were simulated with varying levels of complexity, involving the balance of the outcome variable and predictors. These datasets exhibited high- or low-frequency occurrences in specific intersections of variables, often called ‘cells.’ The impact of the balancing strategies on prediction and inference was assessed using different techniques, such as the Equivalence (TOST) Test, power analysis, and predictive measures. To the best of our knowledge, this is the first research that explores the impact of using balanced samples on coefficient estimation and prediction measures when using logistic multilevel modeling, finding evidence about the benefits of using balanced samples in this context.

Piston aero-engine fault cross-domain diagnosis based on unpaired generative transfer learning

As artificial intelligence (AI) and machine learning continue to advance, they have become key players in signal analysis and pattern recognition. However, challenges such as domain shift and a lack of labeled data hinder the application of machine learning to new, unfamiliar signals, particularly in the development of intelligent diagnostic methods for mechanical faults. In this study, we address these challenges by framing them as the extreme class imbalance problem. We introduce a novel generative transfer learning framework that leverages cycle-consistent adversarial networks with hard constraints (CycleGAN-HCs). This framework is designed to generate unpaired mechanical fault signals, which are then used to train classifiers that can operate across different domains. To enhance feature extraction capabilities for time series data, we developed a new generator model called U-Attention. Additionally, we refined the training loss function to better capture domain-specific and classification-specific features in mechanical vibration signals. The proposed method successfully facilitates feature transfer and data augmentation. Its effectiveness and reliability have been demonstrated through four cross-domain fault diagnosis tasks involving piston aero-engines. Comparative verification shows that the generative transfer learning diagnostic framework outperforms traditional methods, offering superior performance and better generalization in complex mechanical fault diagnosis scenarios.

A comparative analysis of machine learning algorithms with tree-structured parzen estimator for liver disease prediction

The liver is one of the most essential organs in the body, which helps with metabolism and keeping the body healthy. Successful treatments and better patient outcomes depend on early and correct Liver Disease (LD) diagnosis and identification. This study proposes a system for predicting the LD by combining the techniques of Machine Learning (ML) algorithms that include the Decision Tree, Random Forest, Extra Tree Classifier (ETC), LightGBM, and Adaboost, with the Tree-Structured Parzen Estimator (TPE) method for hyperparameter tuning. No previous literature research has utilized ML algorithms with TPE to predict LD. For this research, the Indian Liver Patients’ Dataset with 583 instances and 11 attributes was used. In the pre-processing of the data, techniques such as upsampling have been utilized to address the class imbalance problem. Normalization has been employed to scale the dataset, and feature selection has been applied to choose important features. The proposed model has been analyzed and compared using a 10-fold cross-validation process, with various evaluation metrics including accuracy, precision, recall, and F1-score. The model proposed in this study achieved the best level of accuracy while employing the ETC with the TPE approach, with a recorded accuracy of 95.8%.

Machine learning models for differential diagnosing HER2-low breast cancer: A radiomics approach.

To develop machine learning models based on preoperative dynamic enhanced magnetic resonance imaging (DCE-MRI) radiomics and to explore their potential prognostic value in the differential diagnosis of human epidermal growth factor receptor 2 (HER2)-low from HER2-positive breast cancer (BC). A total of 233 patients with pathologically confirmed invasive breast cancer admitted to our hospital between January 2018 and December 2022 were included in this retrospective analysis. Of these, 103 cases were diagnosed as HER2-positive and 130 cases were HER2 low-expression BC. The Synthetic Minority Oversampling Technique is employed to address the class imbalance problem. Patients were randomly split into a training set (163 cases) and a validation set (70 cases) in a 7:3 ratio. Radiomics features from DCE-MRI second-phase imaging were extracted. Z-score normalization was used to standardize the radiomics features, and Pearson's correlation coefficient and recursive feature elimination were used to explore the significant features. Prediction models were constructed using 6 machine learning algorithms: logistic regression, random forest, support vector machine, AdaBoost, decision tree, and auto-encoder. Receiver operating characteristic curves were constructed, and predictive models were evaluated according to the area under the curve (AUC), accuracy, sensitivity, and specificity. In the training set, the AUC, accuracy, sensitivity, and specificity of all models were 1.000. However, in the validation set, the auto-encoder model's AUC, accuracy, sensitivity, and specificity were 0.994, 0.976, 0.972, and 0.978, respectively. The remaining models' AUC, accuracy, sensitivity, and specificity were 1.000. The DeLong test showed no statistically significant differences between the machine learning models in the training and validation sets (Z = 0, P = 1). Our study investigated the feasibility of using DCE-MRI-based radiomics features to predict HER2-low BC. Certain radiomics features showed associations with HER2-low BC and may have predictive value. Machine learning prediction models developed using these radiomics features could be beneficial for distinguishing between HER2-low and HER2-positive BC. These noninvasive preoperative models have the potential to assist in clinical decision-making for HER2-low breast cancer, thereby advancing personalized clinical precision.

COVID-19 Complications in Patients Aged 20-80 with Pulmonary Involvement: A Study on the 1-Month and 3-Month Post-Infection and Recovery Periods, from August 2021 to November 2021

Background: In this study, our aim is to investigate the complications caused by COVID-19 disease in the period of 1 month and 3 months after infection and recovery in patients aged 20 to 80 admitted to the special care department of Shariati Hospital in Tehran. Methods: The information of the patients in this research was collected between 1 and 3 months after discharge non-randomly and from among the samples that are available (consecutive), through phone calls and a prospective questionnaire including questions about complications such as fatigue, body pain, joint pain, anorexia, disorders, sleep, headache, depression, dizziness, palpitations, chest pain, cough, diabetes, skin disease, obesity, imbalance, neuropathy, neurological and mental problems, and other cases are collected. Results: In this study, what was observed was those 4 complications of nausea and vomiting, diabetes, depression, and hypothyroidism were significantly related to hospitalization of COVID-19 patients in the hospital's special care department. The frequency of other complications was also investigated in this study. Conclusions: According to the conducted study as well as previous studies, what is clear is that the frequency of complications caused by COVID-19 in patients admitted to the intensive care unit after discharge is high, and more studies should be done in order to reduce these complications.

Imbalanced ensemble learning leveraging a novel data-level diversity metric

Ensemble learning is one of the best solutions for imbalanced classification problems. Diversity is a key factor that affects the performance of ensemble learning. Most existing diversity metrics such as Q-statistics measure diversity based on the outputs of the base classifiers, incurring high complexity on model training due to the need to re-train base classifiers to achieve satisfactory diversity. We propose a new diversity measure, named Instance Euclidean Distance metric (IED), to evaluate diversity directly based on the training data without training base classifiers, which can significantly cut down the time costs of diversity measuring. A new imbalanced ensemble learning algorithm named P-EUSBagging is proposed to reduce training complexity and improve learning performance by combining IED with population-based incremental learning to generate training datasets with the maximal data-level diversity. Experimental results demonstrate that the diversities measured by IED and three classifier-based diversity measures exhibit a mean absolute correlation coefficient of 0.94, and P-EUSBagging significantly reduces training time and improves learning performance on both Geometric Mean (G-Mean) and Area Under the Curve (AUC).

Adversarial Training Based Domain Adaptation of Skin Cancer Images.

Skin lesion datasets used in the research are highly imbalanced; Generative Adversarial Networks can generate synthetic skin lesion images to solve the class imbalance problem, but it can result in bias and domain shift. Domain shifts in skin lesion datasets can also occur if different instruments or imaging resolutions are used to capture skin lesion images. The deep learning models may not perform well in the presence of bias and domain shift in skin lesion datasets. This work presents a domain adaptation algorithm-based methodology for mitigating the effects of domain shift and bias in skin lesion datasets. Six experiments were performed using two different domain adaptation architectures. The domain adversarial neural network with two gradient reversal layers and VGG13 as a feature extractor achieved the highest accuracy and F1 score of 0.7567 and 0.75, respectively, representing an 18.47% improvement in accuracy over the baseline model.

Perception of customer satisfaction and complaints based on BERTopic and interpretable machine learning: evidence from hotels in Xi’an

ABSTRACT This study aims to investigate the topics of customer satisfaction and complaints and explore their role in review sentiment prediction by using deep learning and interpretable machine learning methods. Specifically, this study first uses a BERT-based method for topic clustering and embedding, a factor analysis for topic feature extraction and dimensionality reduction and an oversampling method for the imbalance problem. Further, five types of machine learning methods are utilised to forecast review sentiment. To improve the interpretability of the machine learning model, we employ an interpretable framework to explore the role of topic features in review sentiment prediction. The results indicate that customers’ satisfaction mainly focuses on perfect conference facilities and delicious Chinese cuisine, while customers mainly complain about the quality of service, the attitude of staff and the accessibility of the hotel. In addition, ‘air quality and traffic’ is the most important factor influencing the sentiment in reviews. These findings suggest that hotel managers should focus more on the accommodation experience of customers rather than the value-added experience.