In recent years, the challenge of imbalanced data has become increasingly prominent in machine learning, affecting the performance of classification algorithms. This study proposes a novel data-level oversampling method called Cluster-Based Reduced Noise SMOTE (CRN-SMOTE) to address this issue. CRN-SMOTE combines SMOTE for oversampling minority classes with a novel cluster-based noise reduction technique. In this cluster-based noise reduction approach, it is crucial that samples from each category form one or two clusters, a feature that conventional noise reduction methods do not achieve. The proposed method is evaluated on four imbalanced datasets (ILPD, QSAR, Blood, and Maternal Health Risk) using five metrics: Cohen’s kappa, Matthew’s correlation coefficient (MCC), F1-score, precision, and recall. Results demonstrate that CRN-SMOTE consistently outperformed the state-of-the-art Reduced Noise SMOTE (RN-SMOTE), SMOTE-Tomek Link, and SMOTE-ENN methods across all datasets, with particularly notable improvements observed in the QSAR and Maternal Health Risk datasets, indicating its effectiveness in enhancing imbalanced classification performance. Overall, the experimental findings indicate that CRN-SMOTE outperformed RN-SMOTE in 100% of the cases, achieving average improvements of 6.6% in Kappa, 4.01% in MCC, 1.87% in F1-score, 1.7% in precision, and 2.05% in recall, with setting SMOTE’s neighbors’ number to 5.

This record contains the underlying research data for the publication "High impact bug report identification with imbalanced learning strategies" and the full-text is available from: https://ink.library.smu.edu.sg/sis_research/3702In practice, some bugs have more impact than others and thus deserve more immediate attention. Due to tight schedule and limited human resources, developers may not have enough time to inspect all bugs. Thus, they often concentrate on bugs that are highly impactful. In the literature, high-impact bugs are used to refer to the bugs which appear at unexpected time or locations and bring more unexpected effects (i.e., surprise bugs), or break pre-existing functionalities and destroy the user experience (i.e., breakage bugs). Unfortunately, identifying high-impact bugs from thousands of bug reports in a bug tracking system is not an easy feat. Thus, an automated technique that can identify high-impact bug reports can help developers to be aware of them early, rectify them quickly, and minimize the damages they cause. Considering that only a small proportion of bugs are high-impact bugs, the identification of high-impact bug reports is a difficult task. In this paper, we propose an approach to identify high-impact bug reports by leveraging imbalanced learning strategies. We investigate the effectiveness of various variants, each of which combines one particular imbalanced learning strategy and one particular classification algorithm. In particular, we choose four widely used strategies for dealing with imbalanced data and four state-of-the-art text classification algorithms to conduct experiments on four datasets from four different open source projects. We mainly perform an analytical study on two types of high-impact bugs, i.e., surprise bugs and breakage bugs. The results show that different variants have different performances, and the best performing variants SMOTE (synthetic minority over-sampling technique) + KNN (K-nearest neighbours) for surprise bug identification and RUS (random under-sampling) + NB (naive Bayes) for breakage bug identification outperform the F1-scores of the two state-of-the-art approaches by Thung et al. and Garcia and Shihab.Supplementary code and data available from GitHub:

A comparison of the RN-SMOTE, SMOTE-Tomek Link, SMOTE-ENN, and the proposed 1CRN-SMOTE methods on the Blood and Health-risk datasets is presented, based on various classification metrics using the Random Forest classifier.

Summary table: Oversampling techniques using SMOTE, ADASYN, and weighted rare classes.

Performance of machine learning models using SMOTE-balanced dataset.

Background: Burnout is usually defined as a state of emotional, physical, and mental exhaustion that affects people in various professions (e.g. physicians, nurses, teachers). The consequences of burnout involve decreased motivation, productivity, and overall diminished well-being. The machine learning-based prediction of burnout has therefore become the focus of recent research. In this study, the aim was to detect burnout using machine learning and to identify its most important predictors in a sample of Hungarian high-school teachers. Methods: The final sample consisted of 1,576 high-school teachers (522 male), who completed a survey including various sociodemographic and health-related questions and psychological questionnaires. Specifically, depression, insomnia, internet habits (e.g. when and why one uses the internet) and problematic internet usage were among the most important predictors tested in this study. Supervised classification algorithms were trained to detect burnout assessed by two well-known burnout questionnaires. Feature selection was conducted using recursive feature elimination. Hyperparameters were tuned via grid search with 5-fold cross-validation. Due to class imbalance, class weights (i.e. cost-sensitive learning), downsampling and a hybrid method (SMOTE-ENN) were applied in separate analyses. The final model evaluation was carried out on a previously unseen holdout test sample. Results: Burnout was detected in 19.7% of the teachers included in the final dataset. The best predictive performance on the holdout test sample was achieved by random forest with class weigths (AUC = .811; balanced accuracy = .745, sensitivity = .765; specificity = .726). The best predictors of burnout were Beck’s Depression Inventory scores, Athen’s Insomnia Scale scores, subscales of the Problematic Internet Use Questionnaire and self-reported current health status. Conclusions: The performances of the algorithms were comparable with previous studies; however, it is important to note that we tested our models on previously unseen holdout samples suggesting higher levels of generalizability. Another remarkable finding is that besides depression and insomnia, other variables such as problematic internet use and time spent online also turned out to be important predictors of burnout.

Classification result classifiers using TF-IDF with SMOTE.

Increase in the number of new chemicals synthesized in past decades has resulted in constant growth in the development and application of computational models for prediction of activity as well as safety profiles of the chemicals. Most of the time, such computational models and its application must deal with imbalanced chemical data. It is indeed a challenge to construct a classifier using imbalanced data set. In this study, we analyzed and validated the importance of different sampling methods over non-sampling method, to achieve a well-balanced sensitivity and specificity of a machine learning model trained on imbalanced chemical data. Additionally, this study has achieved an accuracy of 93.00%, an AUC of 0.94, F1 measure of 0.90, sensitivity of 96.00% and specificity of 91.00% using SMOTE sampling and Random Forest classifier for the prediction of Drug Induced Liver Injury (DILI). Our results suggest that, irrespective of data set used, sampling methods can have major influence on reducing the gap between sensitivity and specificity of a model. This study demonstrates the efficacy of different sampling methods for class imbalanced problem using binary chemical data sets.

Recent studies have shown that predictive models can supplement or provide alternatives to E. coli-testing for assessing the potential presence of food safety hazards in water used for produce production. However, these studies used balanced training data and focused on enteric pathogens. As such, research is needed to determine 1) if predictive models can be used to assess Listeria contamination of agricultural water, and 2) how resampling (to deal with imbalanced data) affects performance of these models. To address these knowledge gaps, this study developed models that predict nonpathogenic Listeria spp. (excluding L. monocytogenes) and L. monocytogenes presence in agricultural water using various combinations of learner (e.g., random forest, regression), feature type, and resampling method (none, oversampling, SMOTE). Four feature types were used in model training: microbial, physicochemical, spatial, and weather. “Full models” were trained using all four feature types, while “nested models” used between one and three types. In total, 45 full (15 learners*3 resampling approaches) and 108 nested (5 learners*9 feature sets*3 resampling approaches) models were trained per outcome. Model performance was compared against baseline models where E. coli concentration was the sole predictor. Overall, the machine learning models outperformed the baseline E. coli models, with random forests outperforming models built using other learners (e.g., rule-based learners). Resampling produced more accurate models than not resampling, with SMOTE models outperforming, on average, oversampling models. Regardless of resampling method, spatial and physicochemical water quality features drove accurate predictions for the nonpathogenic Listeria spp. and L. monocytogenes models, respectively. Overall, these findings 1) illustrate the need for alternatives to existing E. coli-based monitoring programs for assessing agricultural water for the presence of potential food safety hazards, and 2) suggest that predictive models may be one such alternative. Moreover, these findings provide a conceptual framework for how such models can be developed in the future with the ultimate aim of developing models that can be integrated into on-farm risk management programs. For example, future studies should consider using random forest learners, SMOTE resampling, and spatial features to develop models to predict the presence of foodborne pathogens, such as L. monocytogenes, in agricultural water when the training data is imbalanced.

The average values of evaluation metrics on ILDP, QSAR, Blood and Health risk imbalanced datasets using RF classifiers and 10-fold cross validation methodology.

BackgroundPrognostic models can help to identify patients at risk for end-stage kidney disease (ESKD) at an earlier stage to provide preventive medical interventions. Previous studies mostly applied the Cox proportional hazards model. The aim of this study is to present a resampling method, which can deal with imbalanced data structure for the prognostic model and help to improve predictive performance.MethodsThe electronic health records of patients with chronic kidney disease (CKD) older than 50 years during 2005–2015 collected from primary care in Belgium were used (n = 11,645). Both the Cox proportional hazards model and the logistic regression analysis were applied as reference model. Then, the resampling method, the Synthetic Minority Over-Sampling Technique-Edited Nearest Neighbor (SMOTE-ENN), was applied as a preprocessing procedure followed by the logistic regression analysis. The performance was evaluated by accuracy, the area under the curve (AUC), confusion matrix, and F3 score.ResultsThe C statistics for the Cox proportional hazards model was 0.807, while the AUC for the logistic regression analysis was 0.700, both on a comparable level to previous studies. With the model trained on the resampled set, 86.3% of patients with ESKD were correctly identified, although it was at the cost of the high misclassification rate of negative cases. The F3 score was 0.245, much higher than 0.043 for the logistic regression analysis and 0.022 for the Cox proportional hazards model.ConclusionThis study pointed out the imbalanced data structure and its effects on prediction accuracy, which were not thoroughly discussed in previous studies. We were able to identify patients with high risk for ESKD better from a clinical perspective by using the resampling method. But, it has the limitation of the high misclassification of negative cases. The technique can be widely used in other clinical topics when imbalanced data structure should be considered.

Class imbalance is a common challenge that is often faced when dealing with classification tasks aiming to detect medical events that are particularly infrequent. Apnoea is an example of such events. This challenge can however be mitigated using class rebalancing algorithms. This work investigated 10 widely used data-level class imbalance mitigation methods aiming towards building a random forest (RF) model that attempts to detect apnoea events from photoplethysmography (PPG) signals acquired from the neck. Those methods are random undersampling (RandUS), random oversampling (RandOS), condensed nearest-neighbors (CNNUS), edited nearest-neighbors (ENNUS), Tomek’s links (TomekUS), synthetic minority oversampling technique (SMOTE), Borderline-SMOTE (BLSMOTE), adaptive synthetic oversampling (ADASYN), SMOTE with TomekUS (SMOTETomek) and SMOTE with ENNUS (SMOTEENN). Feature-space transformation using PCA and KernelPCA was also examined as a potential way of providing better representations of the data for the class rebalancing methods to operate. This work showed that RandUS is the best option for improving the sensitivity score (up to 11%). However, it could hinder the overall accuracy due to the reduced amount of training data. On the other hand, augmenting the data with new artificial data points was shown to be a non-trivial task that needs further development, especially in the presence of subject dependencies, as was the case in this work.

The diagnosis of human knee abnormalities using the surface electromyography (sEMG) signal obtained from lower limb muscles with machine learning is a major problem due to the noisy nature of the sEMG signal and the imbalance in data corresponding to healthy and knee abnormal subjects. To address this challenge, a combination of wavelet decomposition (WD) with ensemble empirical mode decomposition (EEMD) and the Synthetic Minority Oversampling Technique (S-WD-EEMD) is proposed. In this study, a hybrid WD-EEMD is considered for the minimization of noises produced in the sEMG signal during the collection, while the Synthetic Minority Oversampling Technique (SMOTE) is considered to balance the data by increasing the minority class samples during the training of machine learning techniques. The findings indicate that the hybrid WD-EEMD with SMOTE oversampling technique enhances the efficacy of the examined classifiers when employed on the imbalanced sEMG data. The F-Score of the Extra Tree Classifier, when utilizing WD-EEMD signal processing with SMOTE oversampling, is 98.4%, whereas, without the SMOTE oversampling technique, it is 95.1%.

Internet of things (IoT) facilitates a variety of heterogeneous devices to be enabled with network connectivity via various network architectures to gather and exchange real-time information. On the other hand, the rise of IoT creates Distributed Denial of Services (DDoS) like security threats. The recent advancement of Software Defined-Internet of Things (SDIoT) architecture can provide better security solutions compared to the conventional networking approaches. Moreover, limited computing resources and heterogeneous network protocols are major challenges in the SDIoT ecosystem. Given these circumstances, it is essential to design a low-cost DDoS attack classifier. The current study aims to employ an improved feature selection (FS) technique which determines the most relevant features that can improve the detection rate and reduce the training time. At first, to overcome the data imbalance problem, Edited Nearest Neighbor-based Synthetic Minority Oversampling (SMOTE-ENN) was exploited. The study proposes SFMI, an FS method that combines Sequential Feature Selection (SFE) and Mutual Information (MI) techniques. The top k common features were extracted from the nominated features based on SFE and MI. Further, Principal component analysis (PCA) is employed to address multicollinearity issues in the dataset. Comprehensive experiments have been conducted on two benchmark datasets such as the KDDCup99, CIC IoT-2023 datasets. For classification purposes, Decision Tree, K-Nearest Neighbor, Gaussian Naive Bayes, Random Forest (RF), and Multilayer Perceptron classifiers were employed. The experimental results quantitatively demonstrate that the proposed SMOTE-ENN+SFMI+PCA with RF classifier achieves 99.97% accuracy and 99.39% precision with 10 features.

Thyroid disease classification plays a crucial role in early diagnosis and effective treatment of thyroid disorders. Machine learning (ML) techniques have demonstrated remarkable potential in this domain, offering accurate and efficient diagnostic tools. Most of the real-life datasets have imbalanced characteristics that hamper the overall performance of the classifiers. Existing data balancing techniques process the whole dataset at a time that sometimes causes overfitting and underfitting. However, the complexity of some ML models, often referred to as “black boxes,” raises concerns about their interpretability and clinical applicability. This paper presents a comprehensive study focused on the analysis and interpretability of various ML models for classifying thyroid diseases. In our work, we first applied a new data-balancing mechanism using a clustering technique and then analyzed the performance of different ML algorithms. To address the interpretability challenge, we explored techniques for model explanation and feature importance analysis using eXplainable Artificial Intelligence (XAI) tools globally as well as locally. Finally, the XAI results are validated with the domain experts. Experimental results have shown that our proposed mechanism is efficient in diagnosing thyroid disease and can explain the models effectively. The findings can contribute to bridging the gap between adopting advanced ML techniques and the clinical requirements of transparency and accountability in diagnostic decision-making.

Classification result of classifiers models using TF without SMOTE.

Internet of things (IoT) facilitates a variety of heterogeneous devices to be enabled with network connectivity via various network architectures to gather and exchange real-time information. On the other hand, the rise of IoT creates Distributed Denial of Services (DDoS) like security threats. The recent advancement of Software Defined-Internet of Things (SDIoT) architecture can provide better security solutions compared to the conventional networking approaches. Moreover, limited computing resources and heterogeneous network protocols are major challenges in the SDIoT ecosystem. Given these circumstances, it is essential to design a low-cost DDoS attack classifier. The current study aims to employ an improved feature selection (FS) technique which determines the most relevant features that can improve the detection rate and reduce the training time. At first, to overcome the data imbalance problem, Edited Nearest Neighbor-based Synthetic Minority Oversampling (SMOTE-ENN) was exploited. The study proposes SFMI, an FS method that combines Sequential Feature Selection (SFE) and Mutual Information (MI) techniques. The top k common features were extracted from the nominated features based on SFE and MI. Further, Principal component analysis (PCA) is employed to address multicollinearity issues in the dataset. Comprehensive experiments have been conducted on two benchmark datasets such as the KDDCup99, CIC IoT-2023 datasets. For classification purposes, Decision Tree, K-Nearest Neighbor, Gaussian Naive Bayes, Random Forest (RF), and Multilayer Perceptron classifiers were employed. The experimental results quantitatively demonstrate that the proposed SMOTE-ENN+SFMI+PCA with RF classifier achieves 99.97% accuracy and 99.39% precision with 10 features.

BackgroundThe Department of Rehabilitation Medicine is key to improving patients’ quality of life. Driven by chronic diseases and an aging population, there is a need to enhance the efficiency and resource allocation of outpatient facilities. This study aims to analyze the treatment preferences of outpatient rehabilitation patients by using data and a grading tool to establish predictive models. The goal is to improve patient visit efficiency and optimize resource allocation through these predictive models.MethodsData were collected from 38 Chinese institutions, including 4,244 patients visiting outpatient rehabilitation clinics. Data processing was conducted using Python software. The pandas library was used for data cleaning and preprocessing, involving 68 categorical and 12 continuous variables. The steps included handling missing values, data normalization, and encoding conversion. The data were divided into 80% training and 20% test sets using the Scikit-learn library to ensure model independence and prevent overfitting. Performance comparisons among XGBoost, random forest, and logistic regression were conducted using metrics, including accuracy and receiver operating characteristic (ROC) curves. The imbalanced learning library’s SMOTE technique was used to address the sample imbalance during model training. The model was optimized using a confusion matrix and feature importance analysis, and partial dependence plots (PDP) were used to analyze the key influencing factors.ResultsXGBoost achieved the highest overall accuracy of 80.21% with high precision and recall in Category 1. random forest showed a similar overall accuracy. Logistic Regression had a significantly lower accuracy, indicating difficulties with nonlinear data. The key influencing factors identified include distance to medical institutions, arrival time, length of hospital stay, and specific diseases, such as cardiovascular, pulmonary, oncological, and orthopedic conditions. The tiered diagnosis and treatment tool effectively helped doctors assess patients’ conditions and recommend suitable medical institutions based on rehabilitation grading.ConclusionThis study confirmed that ensemble learning methods, particularly XGBoost, outperform single models in classification tasks involving complex datasets. Addressing class imbalance and enhancing feature engineering can further improve model performance. Understanding patient preferences and the factors influencing medical institution selection can guide healthcare policies to optimize resource allocation, improve service quality, and enhance patient satisfaction. Tiered diagnosis and treatment tools play a crucial role in helping doctors evaluate patient conditions and make informed recommendations for appropriate medical care.

Performance measure of our scheme using K-means+SMOTE+KNN.

Predicting student performance automatically is of utmost importance, due to the substantial volume of data within educational databases. Educational data mining (EDM) devises techniques to uncover insights from data originating in educational settings. Artificial intelligence (AI) can mine educational data to predict student performance and provide measures to help students avoid failing and learn better. Learning platforms complement traditional learning settings by analyzing student performance, which can help reduce the chance of student failure. Existing methods for student performance prediction in educational data mining faced challenges such as limited accuracy, imbalanced data, and difficulties in feature engineering. These issues hindered effective adaptability and generalization across diverse educational contexts. This study proposes a machine learning-based system with deep convoluted features for the prediction of students’ academic performance. The proposed framework is employed to predict student academic performance using balanced as well as, imbalanced datasets using the synthetic minority oversampling technique (SMOTE). In addition, the performance is also evaluated using the original and deep convoluted features. Experimental results indicate that the use of deep convoluted features provides improved prediction accuracy compared to original features. Results obtained using the extra tree classifier with convoluted features show the highest classification accuracy of 99.9%. In comparison with the state-of-the-art approaches, the proposed approach achieved higher performance. This research introduces a powerful AI-driven system for student performance prediction, offering substantial advancements in accuracy compared to existing approaches.