Synthetic Minority Oversampling Technique Research Articles

Detection of COVID-19 Anti-Vaccination from Twitter Data Using Deep Learning and Feature Selection Approaches

The COVID-19 pandemic has evolved into a crisis significantly impacting health, the economy, and social life worldwide. During this crisis, anti-vaccination sentiment poses a considerable obstacle to controlling the epidemic and the effectiveness of vaccination campaigns. This study aimed to detect COVID-19 anti-vaccination sentiment from Twitter data using a combination of deep learning and feature selection approaches. The proposed method integrates a deep learning model with feature selection techniques to identify anti-vaccination sentiment by pinpointing important features in text data. Hybrid TF-IDF and N-gram methods were utilized for feature extraction, followed by Chi-square feature selection. The dataset comprises Twitter text data and two labels. The Synthetic Minority Oversampling Technique (SMOTE) was applied to balance the labels. Long Short-Term Memory (LSTM), a deep learning architecture, was employed for the classification process. The experimental results, obtained by leveraging the proposed feature extraction, feature selection, and LSTM methods, achieved the highest accuracy value of 99.23%. These findings demonstrate the proposed methods' success in effectively detecting COVID-19 anti-vaccination sentiment in text data. The study's results can offer valuable insights for developing health policies and public information strategies, presenting a new and powerful tool for detecting anti-vaccine sentiment in planning vaccination campaigns and public health interventions.

Dual-input robust diagnostics for railway point machines via audio signals

ABSTRACT Railway Point Machine (RPM) is a fundamental component of railway infrastructure and plays a crucial role in ensuring the safe operation of trains. Its primary function is to divert trains from one track to another, enabling connections between different lines and facilitating route selection. By judiciously deploying turnouts, railway systems can provide efficient transportation services while ensuring the safety of passengers and cargo. As signal processing technologies develop rapidly, taking the easy acquisition advantages of audio signals, a fault diagnosis method for RPMs is proposed by considering noise and multi-channel signals. The proposed method consists of several stages. Initially, the signal is subjected to pre-processing steps, including cropping and channel separation. Subsequently, the signal undergoes noise addition using the Random Length and Dynamic Position Noises Superposition (RDS) module, followed by conversion to a greyscale image. To enhance the data, Synthetic Minority Oversampling Technique (SMOTE) module is applied. Finally, the training data is fed into a Dual-input Attention Convolutional Neural Network (DIACNN). By employing various experimental techniques and designing diverse datasets, our proposed method demonstrates excellent robustness and achieves an outstanding classification accuracy of 99.73%.

A failure risk assessment method for lithium-ion batteries based on big data of after-sales vehicles

Accurate prediction of battery failure has always been a challenge in the field of electric vehicles. In existing prediction methods, battery current, voltage and temperature of a single vehicle sample are often analyzed as the main characteristic parameters, however, the independent analysis of these parameters can hardly achieve the early warning of battery failure. This paper proposes a failure risk assessment method based on big data analysis, which can evaluate the failure risk level of the battery pack in advance. Specifically, the characteristic parameters strongly related to battery failure are extracted through the correlation analysis of after-sales data. Then, the synthetic minority oversampling technique is employed to expand the number of failure samples for model training. Finally, the vehicle risk coefficient prediction model is established by the random forest algorithm. According to the prediction results of field data of extensive vehicles, the model can successfully pick out the high-risk vehicles before battery failure, occupying roughly 7% of all vehicles, which is of great value for engineering application. In practical application, these vehicles with high-risk coefficient can be paid more attention by companies, so as to further ensure the driving safety of vehicle users.

Harnessing Machine Learning and Data Fusion for Accurate Undocumented Well Identification in Satellite Images

This study utilizes satellite data to detect undocumented oil and gas wells, which pose significant environmental concerns, including greenhouse gas emissions. Three key findings emerge from the study. Firstly, the problem of imbalanced data is addressed by recommending oversampling techniques like Rotation–GaussianBlur–Solarization data augmentation (RGS), the Synthetic Minority Over-Sampling Technique (SMOTE), or ADASYN (an extension of SMOTE) over undersampling techniques. The performance of borderline SMOTE is less effective than that of the rest of the oversampling techniques, as its performance relies heavily on the quality and distribution of data near the decision boundary. Secondly, incorporating pre-trained models trained on large-scale datasets enhances the models’ generalization ability, with models trained on one county’s dataset demonstrating high overall accuracy, recall, and F1 scores that can be extended to other areas. This transferability of models allows for wider application. Lastly, including persistent homology (PH) as an additional input improves performance for in-distribution testing but may affect the model’s generalization for out-of-distribution testing. A careful consideration of PH’s impact on overall performance and generalizability is recommended. Overall, this study provides a robust approach to identifying undocumented oil and gas wells, contributing to the acceleration of a net-zero economy and supporting environmental sustainability efforts.

Comparison of Chi-Square Automatic Interaction Detector (CHAID) and Random Forest Methods in the Classification of Household Poverty Status in Central Java

Central Java was in second position as the province with the highest number of poor people in Indonesia in March 2020. Poverty alleviation efforts have been carried out, but many are still not yet on target. The purpose of this study was to model the classification of household poverty status in Central Java using CHAID and random forest methods and compare the two methods. The data used in this study is data from the 2020 National Socioeconomic Survey (SUSENAS) conducted by the Central Bureau of Statistics (BPS) for Central Java. The number of poor households is much less than non-poor households. Therefore, Synthetic Minority Oversampling Technique (SMOTE) was performed to handle unbalanced data. The random forest method produced better classification performance than the CHAID method with accuracy, sensitivity, specificity, and AUC of 93,95%, 98,43%, 89,92%, and 0,9417, respectively. The important variables that build the random forest model are the floor area of the house, the age of the head of the household, cooking fuel, the place for the final disposal of feces, and ownership of the place to defecate.

Prediction of cervix cancer stage and grade from diffusion weighted imaging using EfficientNet

Purpose. This study aims to introduce an innovative noninvasive method that leverages a single image for both grading and staging prediction. The grade and the stage of cervix cancer (CC) are determined from diffusion-weighted imaging (DWI) in particular apparent diffusion coefficient (ADC) maps using deep convolutional neural networks (DCNN). Methods. datasets composed of 85 patients having annotated tumor stage (I, II, III, and IV), out of this, 66 were with grade (II and III) and the remaining patients with no reported grade were retrospectively collected. The study was IRB approved. For each patient, sagittal and axial slices containing the gross tumor volume (GTV) were extracted from ADC maps. These were computed using the mono exponential model from diffusion weighted images (b-values = 0, 100, 1000) that were acquired prior to radiotherapy treatment. Balanced training sets were created using the Synthetic Minority Oversampling Technique (SMOTE) and fed to the DCNN. EfficientNetB0 and EfficientNetB3 were transferred from the ImageNet application to binary and four-class classification tasks. Five-fold stratified cross validation was performed for the assessment of the networks. Multiple evaluation metrics were computed including the area under the receiver operating characteristic curve (AUC). Comparisons with Resnet50, Xception, and radiomic analysis were performed. Results. for grade prediction, EfficientNetB3 gave the best performance with AUC = 0.924. For stage prediction, EfficientNetB0 was the best with AUC = 0.931. The difference between both models was, however, small and not statistically significant EfficientNetB0-B3 outperformed ResNet50 (AUC = 0.71) and Xception (AUC = 0.89) in stage prediction, and demonstrated comparable results in grade classification, where AUCs of 0.89 and 0.90 were achieved by ResNet50 and Xception, respectively. DCNN outperformed radiomic analysis that gave AUC = 0.67 (grade) and AUC = 0.66 (stage). Conclusion. the prediction of CC grade and stage from ADC maps is feasible by adapting EfficientNet approaches to the medical context.

A Machine Learning-Based Framework with Enhanced Feature Selection and Resampling for Improved Intrusion Detection

Intrusion Detection Systems (IDSs) play a crucial role in safeguarding network infrastructures from cyber threats and ensuring the integrity of highly sensitive data. Conventional IDS technologies, although successful in achieving high levels of accuracy, frequently encounter substantial model bias. This bias is primarily caused by imbalances in the data and the lack of relevance of certain features. This study aims to tackle these challenges by proposing an advanced machine learning (ML) based IDS that minimizes misclassification errors and corrects model bias. As a result, the predictive accuracy and generalizability of the IDS are significantly improved. The proposed system employs advanced feature selection techniques, such as Recursive Feature Elimination (RFE), sequential feature selection (SFS), and statistical feature selection, to refine the input feature set and minimize the impact of non-predictive attributes. In addition, this work incorporates data resampling methods such as Synthetic Minority Oversampling Technique and Edited Nearest Neighbor (SMOTE_ENN), Adaptive Synthetic Sampling (ADASYN), and Synthetic Minority Oversampling Technique–Tomek Links (SMOTE_Tomek) to address class imbalance and improve the accuracy of the model. The experimental results indicate that our proposed model, especially when utilizing the random forest (RF) algorithm, surpasses existing models regarding accuracy, precision, recall, and F Score across different data resampling methods. Using the ADASYN resampling method, the RF model achieves an accuracy of 99.9985% for botnet attacks and 99.9777% for Man-in-the-Middle (MITM) attacks, demonstrating the effectiveness of our approach in dealing with imbalanced data distributions. This research not only improves the abilities of IDS to identify botnet and MITM attacks but also provides a scalable and efficient solution that can be used in other areas where data imbalance is a recurring problem. This work has implications beyond IDS, offering valuable insights into using ML techniques in complex real-world scenarios.

B-HPD: Bagging-based hybrid approach for the early diagnosis of Parkinson’s disease1

Parkinson’s disease (PD) is a neurodegenerative condition that affects the neurological, behavioral, and physiological systems of the brain. According to the most recent WHO data, 0.51 percent of all fatalities in India are caused by PD. It is a widely recognized fact that about one million people in the United States suffer from PD, relative to nearly five million people worldwide. Approximately 90% of Parkinson’s patients have speech difficulties. As a result, it is crucial to identify PD early on so that appropriate treatment may be determined. For the early diagnosis of PD, we propose a Bagging-based hybrid (B-HPD) approach in this study. Seven classifiers such as Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), Naïve Bayes (NB), K nearest neighbor (KNN), Random Under-sampling Boost (RUSBoost) and Support Vector Machine (SVM) are considered as base estimators for Bagging ensemble method and three oversampling techniques such as Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic (ADASYN) and SVMSmote are implemented under this research work. Feature Selection (FS) is also used for data preprocessing and further performance enhancement. We obtain the Parkinson’s Disease classification dataset (imbalanced) from the Kaggle repository. Finally, using two performance measures: Accuracy and Area under the curve (AUC), we compare the performance of the model with ALL features and with selected features. Our study suggests bagging with a base classifier: RF is showing the best performance in all the cases (with ALL features: 754, with FS: 500, with three Oversampling techniques) and may be used for PD diagnosis in the healthcare industry.

Automated Sensor Node Malicious Activity Detection with Explainability Analysis.

Cybersecurity has become a major concern in the modern world due to our heavy reliance on cyber systems. Advanced automated systems utilize many sensors for intelligent decision-making, and any malicious activity of these sensors could potentially lead to a system-wide collapse. To ensure safety and security, it is essential to have a reliable system that can automatically detect and prevent any malicious activity, and modern detection systems are created based on machine learning (ML) models. Most often, the dataset generated from the sensor node for detecting malicious activity is highly imbalanced because the Malicious class is significantly fewer than the Non-Malicious class. To address these issues, we proposed a hybrid data balancing technique in combination with a Cluster-based Under Sampling and Synthetic Minority Oversampling Technique (SMOTE). We have also proposed an ensemble machine learning model that outperforms other standard ML models, achieving 99.7% accuracy. Additionally, we have identified the critical features that pose security risks to the sensor nodes with extensive explainability analysis of our proposed machine learning model. In brief, we have explored a hybrid data balancing method, developed a robust ensemble machine learning model for detecting malicious sensor nodes, and conducted a thorough analysis of the model's explainability.

Analysis of the Correspondence of the Degree of Fragility with the Way to Exercise the Force of the Hand

BackgroundFrailty is a geriatric syndrome characterized by increased individual vulnerability with an increase in both dependence and mortality when exposed to external stressors. The use of Frailty Indices in routine clinical practice is limited by several factors, such as the cognitive status of the patient, times of consultation, or lack of prior information from the patient.ObjectivesIn this study, we propose the generation of an objective measure of frailty, based on the signal from hand grip strength (HGS).Design and MeasurementsThis signal was recorded with a modified Deyard dynamometer and processed using machine learning strategies based on supervised learning methods to train classifiers. A database was generated from a cohort of 138 older adults in a transverse pilot study that combined classical geriatric questionnaires with physiological data.ParticipantsParticipants were patients selected by geriatricians of medical services provided by collaborating entities.Setting and ResultsTo process the generated information 20 selected significant features of the HGS dataset were filtered, cleaned, and extracted. A technique based on a combination of the Synthetic Minority Oversampling Technique (SMOTE) to generate new samples from the smallest group and ENN (technique based on K-nearest neighbors) to remove noisy samples provided the best results as a well-balanced distribution of data.ConclusionA Random Forest Classifier was trained to predict the frailty label with 92.9% of accuracy, achieving sensitivities higher than 90%.

Synthetic Minority Oversampling Technique (SMOTE) for Boosting the Accuracy of C4.5 Algorithm Model

The low accuracy of the classification model may be caused by dataset imbalance. In reality, low-accuracy models are unacceptable. The purpose of this research is to address data imbalances in an employee performance dataset identified using the C4.5 method. SMOTE is the approach for addressing data imbalance. SMOTE is utilized to generate a large amount of data in the majority or minority class, which has an initial classification accuracy of just 17%. The C4.5 algorithm classifies the new dataset created by SMOTE, which consists of 11 attributes divided three times between training and testing data. The research found that with a 60:40 data split, the classification model had a 69% accuracy. Model accuracy climbed to 76% at 70:30 data splitting, and 86% at the final splitting, which was 80:20. The model's output matches the evaluation findings obtained using the confusion matrix. The research findings indicate that SMOTE may improve classification model accuracy by boosting data in imbalanced classes.

Feature group partitioning: an approach for depression severity prediction with class balancing using machine learning algorithms

In contemporary society, depression has emerged as a prominent mental disorder that exhibits exponential growth and exerts a substantial influence on premature mortality. Although numerous research applied machine learning methods to forecast signs of depression. Nevertheless, only a limited number of research have taken into account the severity level as a multiclass variable. Besides, maintaining the equality of data distribution among all the classes rarely happens in practical communities. So, the inevitable class imbalance for multiple variables is considered a substantial challenge in this domain. Furthermore, this research emphasizes the significance of addressing class imbalance issues in the context of multiple classes. We introduced a new approach Feature group partitioning (FGP) in the data preprocessing phase which effectively reduces the dimensionality of features to a minimum. This study utilized synthetic oversampling techniques, specifically Synthetic Minority Over-sampling Technique (SMOTE) and Adaptive Synthetic (ADASYN), for class balancing. The dataset used in this research was collected from university students by administering the Burn Depression Checklist (BDC). For methodological modifications, we implemented heterogeneous ensemble learning stacking, homogeneous ensemble bagging, and five distinct supervised machine learning algorithms. The issue of overfitting was mitigated by evaluating the accuracy of the training, validation, and testing datasets. To justify the effectiveness of the prediction models, balanced accuracy, sensitivity, specificity, precision, and f1-score indices are used. Overall, comprehensive analysis demonstrates the discrimination between the Conventional Depression Screening (CDS) and FGP approach. In summary, the results show that the stacking classifier for FGP with SMOTE approach yields the highest balanced accuracy, with a rate of 92.81%. The empirical evidence has demonstrated that the FGP approach, when combined with the SMOTE, able to produce better performance in predicting the severity of depression. Most importantly the optimization of the training time of the FGP approach for all of the classifiers is a significant achievement of this research.

Dealing imbalance dataset problem in sentiment analysis of recession in Indonesia

<span lang="EN-US">Global recession news dominates social media, particularly in Indonesia, with social news platforms on Twitter generating public responses and <br /> re-tweetings on the issue. Mining these opinions from Twitter using a sentiment analysis approach yields invaluable insights. The research stages included data collection, pre-processing, data labeling using the <br /> lexical-based method like valence aware dictionary and sentiment reasoner (VADER) and TextBlob, sampling techniques using synthetic minority oversampling technique (SMOTE) and random over sampling (ROS) before and after splitting data, and modeling using machine learning such as support vector machines (SVM), k-nearest neighbour (KNN), naive Bayes, and model evaluation. The problem is that almost 300,000 data collected from NodeXL are unbalanced. The findings show that models with balanced datasets show better model evaluation results. The sampling technique was carried out before and after splitting the data. The model evaluation results show that the Bernoulli-naive Bayes algorithm, with the VADER labeling technique, and the SMOTE sampling technique after splitting data, obtains the best accuracy of 84%, and using the ROS technique obtains an accuracy of 81%. On the other hand, with the SMOTE and ROS technique before splitting data on the SVM algorithm, it gets the best accuracy of 93% from before if only using SVM only reached 84%.</span>

HGDO: An oversampling technique based on hypergraph recognition and Gaussian distribution

The synthetic minority oversampling technique (SMOTE) is the most prevalent solution in class imbalance learning. While SMOTE and its variant methods handle imbalanced data well in most cases, they fail to take full advantage of the structural information in the overall data, which leads to the propagation of noise. Some existing SMOTE variants remove noisy samples by adding an undersampling process. However, due to the complexity of the data distribution, it is difficult to accurately identify real noise samples, leading to lower modeling quality. To this end, we propose an oversampling technique based on hypergraph identification and Gaussian distribution (HGDO). First, neighborhood reconstruction is performed for each sample depending on the sparse representation to build a hypergraph model, and outlier and noisy samples are filtered according to this model. Then, the weight of each retained minority class sample is determined through the distribution relationship of hyperedges and vertices. Finally, new samples are generated based on the Laplacian matrix and Gaussian distribution to balance the dataset. The comprehensive experimental analysis demonstrates the superiority of HGDO over some popular SMOTE variants.

Analyzing Preprocessing Impact on Machine Learning Classifiers for Cryotherapy and Immunotherapy Dataset

In the clinical treatment of skin diseases and cancer, cryotherapy and immunotherapy offer effective and minimally invasive alternatives. However, the complexity of patient response demands more sophisticated analytical strategies for accurate outcome prediction. This research focuses on analyzing the effect of preprocessing in various machine learning models on the prediction performance of cryotherapy and immunotherapy. The preprocessing techniques analyzed are advanced feature engineering and Synthetic Minority Over-sampling Technique (SMOTE) and Tomek links as resampling techniques and their combination. Various classifiers, including support vector machine (SVM), Naive Bayes (NB), Decision Tree (DT), Random Forest (RF), XGBoost, and Bidirectional Gated Recurrent Unit (BiGRU), were tested. The findings of this study show that preprocessing methods can significantly improve model performance, especially in the XGBoost model. Random Forest also gets the same results as XGBoost, but it can also work better without significant preprocessing. The best results were 0.8889, 0.8889, 0.6000, 0.9037, and 0.8790, respectively, for accuracy, recall, specificity, precision, and f1 on the Immunotherapy dataset, while on the Cryotherapy dataset, respectively, they were 0.8889, 0.8889, 0.6000, 0.9037, and 0.8790. This study confirms the potential of customized preprocessing and machine learning models to provide deep insights into treatment dynamics, ultimately improving the quality of diagnosis.

Analyzing Quantum Feature Engineering and Balancing Strategies Effect on Liver Disease Classification

This research aims to improve the accuracy of liver disease classification using Quantum Feature Engineering (QFE) and the Synthetic Minority Over-sampling Tech-nique and Tomek Links (SMOTE-Tomek) data balancing technique. Four machine learning models were compared in this research, namely eXtreme Gradient Boosting (XGB), Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR) on the Indian Liver Patient Dataset (ILPD) dataset. QFE is applied to capture correlations and complex patterns in the data, while SMOTE-Tomek is used to address data imbalances. The results showed that QFE significantly improved LR performance in terms of recall and specificity up to 99%, which is very important in medical diagnosis. The combination of QFE and SMOTE-Tomek gives the best results for the XGB method with an accuracy of 81%, recall of 90%, and f1-score of 83%. This study concludes that the use of QFE and data balancing techniques can improve liver disease classification performance in general.

An Enhanced Lung Cancer Identification and Classification Based on Advanced Deep Learning and Convolutional Neural Network

In this research, a fast, accurate, and stable system of lung cancer detection based on novel deep learning techniques is proposed. Lung cancer continues to be one of the most monumental global health concerns, which is why there is an urgent need for low-cost and non-invasive screening. Though the diagnostic methods that are most commonly in use include CTscan, X-ray etc. The interpretation by the human eye varies and errors are bound to occur. In response to this challenge, we outline a more automated approach that is based on deep learning models and can be used to classify lung pictures with high levels of accuracy. This research makes use of a large data set of lung scans categorised as normal, malignant, and benign. The first look what the data had in store threw up some correlation with picture size and what seemed to be category differences. Realizing that live feed requires constant input, each picture underwent grayscale conversion and dimensionality reduction. In order to effectively deal with the unbalanced nature of the dataset that was discovered in the study, the Synthetic Minority Oversampling Technique (SMOTE) was applied as a technique. In this presentation, three new designs were introduced: Model I, Model 2, and Model 3. Additionally, one architecture was developed with the purpose of merging the predictions of all three models. Furthermore, out of all the models created, the best model emerged as model 1 with approximately an accuracy of 84%. 7%. But the ensemble strategy which was intended to make the best of each of the models, produced an astounding 82. 5% accuracy. The specific advantages and misclassification behaviors of Model 2 and 3, although less accurate than Model 1 but are currently under evaluation for future Model ensemble improvements. The technique developed using deep learning addresses the challenges at a faster, efficient, and contactless approach to lung cancer analysis. The fact that it is capable of operating in tandem with others diagnostic instruments may help reduce diagnostic errors and enhance patient care. We have addressed this issue so that the various practitioners would be able to read this paper and we can go to the next generation of diagnostic technologies.

Factor analysis influencing Mobile JKN user experience using sentiment analysis

<span lang="EN-US">Social security administration for health or Badan Penyelenggara Jaminan Sosial Kesehatan (BPJS Kesehatan), as a public legal entity, has a critical role in the health of the Indonesian population. BPJS Kesehatan introduced the Mobile national health insurance or </span><em><span lang="EN-US">jaminan kesehatan nasional</span></em><span lang="EN-US"> (JKN) application to enhance its services, enabling Indonesians to access it directly. Nevertheless, the rating of the Mobile JKN application on the Google Play Store has shown a gradual decline over time. Therefore, this study was conducted to analyze the factors influencing the user experience of the Mobile JKN application, utilizing the review data obtained from the Google Play Store. Sentiment analysis using the Naïve Bayes (NB) classification model and support vector machine (SVM) combined with synthetic minority oversampling technique (SMOTE) and slang word replacement. The results obtained an accuracy value of 93.33%, precision of 93.76%, recall of 93.33%, and F1-score of 93.43%. A further analysis was conducted using online service quality factors to obtain the main factors influencing the experience of Mobile JKN application users. The evaluation findings revealed that factors of security, ease of use, and timeliness are three fundamental aspects that should be given immediate attention by BPJS Kesehatan while improving the Mobile JKN application in the future.</span>

Predictive Modeling of Diabetes Mellitus Utilizing Machine Learning Techniques

Diabetes mellitus represents a persistent metabolic condition distinguished by elevated levels of blood sugar, which results from the inadequacy of the body to secrete and respond to insulin, leading to health risks and frequent hospitalizations. Accurate predictive models are vital for targeted interventions to reduce readmissions and improve healthcare quality and cost. Early prediction can mitigate its impact, aid in control, and potentially save lives. Machine learning algorithms show promise in medical applications, including diabetes prediction and diagnosis. Limited data quality hinders accurate diabetes prediction due to missing values and inconsistencies. This paper investigates machine learning's potential for predicting and diagnosing diabetes, aiming to enhance accuracy and efficiency in disease management. Feature engineering techniques are applied to preprocess the data and extract relevant features for model development. To address class imbalance, SMOTE (Synthetic Minority Oversampling Technique) is employed. Various machine learning algorithms, including logistic regression, Naïve Bayes, random forests, support vector machines (SVM), K-Nearest Neighbors (KNN), and eXtreme Gradient Boosting (XGBoost), are utilized to build predictive models. The performance evaluation employs standard metrics such as accuracy, recall, precision, and F1-Score. Notably, Random Forest achieves an accuracy of 82% followed by XGBoost(80%) , surpassing other ML algorithms utilized. Index Terms: Diabetes mellitus, Machine learning, Prediction, SVM, logistic regression, Accuracy.

CPS-3WS: A critical pattern supported three-way sampling method for classifying class-overlapped imbalanced data

Class-imbalance problem widely exists in real applications ranging from medial diagnosis to economic fraud detection, etc. As one of the mainstream techniques in dealing with imbalanced data, SMOTE (Synthetic Minority Over-sampling TEchnique) and its extensions mainly rebalance the datasets via generation of observations in specific regions with various adapted strategies. Many of them do not consider the cost of role assignment of samples, and the intractable data complexity (overlap, small disjuncts, etc.) poses additional challenges to them. This paper proposes a critical pattern supported three-way sampling method (CPS-3WS) for classifying class-overlapped imbalanced data, introducing the philosophy of thinking in threes to effective classification in imbalanced learning. Specifically, CPS-3WS uses a three-way sample partition strategy with the Bayes posterior probability by dividing majority and minority classes into three disjoint subsets: risky, critical and safe patterns. CPS-3WS conducts a three-way hybrid sampling through (i) evaluating the risky majority pattern to be eliminated and (ii) selecting critical minority pattern to synthesize new samples under local information constraint. Extensive experiments on 42 UCI benchmark datasets demonstrate the superiority of the proposed CPS-3WS compared with 11 data-level methods. The source code of CPS-3WS is available at https://github.com/ytyancp/CPS-3WS.