Synthetic Minority Oversampling Technique Research Articles

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.

An efficient synthetic minority oversampling technique-based ensemble learning model to detect COVID-19 severity

The COVID-19 pandemic has highlighted the importance of accurately predicting disease severity to ensure timely intervention and effective allocation of healthcare resources, which can ultimately improve patient outcomes. This study aims to develop an efficient machine learning (ML) model based on patient demographic and clinical data. It utilizes advanced feature engineering techniques to reduce the dimensionality of dataset and address the issue of highly imbalanced data using synthetic minority oversampling technique (SMOTE). The study employs several ensemble learning models, including XGBoost, Random Forest, AdaBoost, voting ensemble, enhanced-weighted voting ensemble, and stack-based ensembles with support vector machine (SVM) and Gaussian Naïve Bayes as meta-learners, to develop the proposed model. The results indicate that the proposed model outperformed the top-performing models reported in previous studies. It achieved an accuracy of 0.978, sensitivity of 1.0, precision of 0.875, F1-score of 0.934, and receiver operating characteristic area under the curve (ROC-AUC) of 0.965. The study identified several features that significantly correlated with COVID-19 severity, which included respiratory rate (breaths per minute), c-reactive proteins, age, and total leukocyte count (TLC) count. The proposed approach presents a promising method for accurate COVID-19 severity prediction, which may prove valuable in assisting healthcare providers in making informed decisions about patient care.

Analysis of Factors Influencing Online Learning Using the Decision Tree Method

Objective: With the continuous development of online learning, the analysis of students' online learning has become increasingly important. Understanding which factors can influence students' engagement in online learning plays a crucial role in improving their learning performance. Methods: By utilizing web crawling techniques, students' online learning behavior data was collected from the Chinese University’s massive open online courses (MOOC) platform. To address the imbalance in the dataset, a synthetic minority oversampling technique (SMOTE) was used. Course progress was used to reflect students' online learning status, which was categorized into interruptions and completions. Furthermore, to tackle the issue of low computational efficiency in the C4.5 decision tree algorithm, its calculation formula was improved to develop an improved version of C4.5. Findings: Of the several factors analyzed, the number of course chapters had the greatest impact on students' online learning, followed by the number of course evaluations and overall course scores. The classification of students’ online learning situations based on an improved C4.5 algorithm revealed that the improved method achieved the highest accuracy rate of 0.942 and the shortest classification time of 0.165 s compared to methods such as the naive Bayesian and random forest algorithms. Novelty: This study designed an improved version of C4.5 to analyze the influencing factors in online learning, and its reliability was demonstrated through experiments, providing a new effective method for data analysis in online learning. Doi: 10.28991/HIJ-2024-05-02-018 Full Text: PDF

Predictive analysis on the factors associated with birth Outcomes: A machine learning perspective

BackgroundRecent studies reveal that around 1.9 million stillbirths occur annually worldwide, with Sub-Saharan Africa having among the highest cases. Some Sub-Saharan African countries, including Ghana, failed to meet Millennium Development Goal 5 (MDG5) by 2015 and may struggle to meet Sustainable Development Goal 3 (SDG3) despite maternal healthcare interventions. Concerns arise about Ghana’s ability to achieve the World Health Organization’s neonatal mortality goal of 12 per 1000 live births by 2030. This study aims to identify key factors influencing childbirth outcomes and create a predictive method for high-risk pregnancies. MethodsWe compared four machine learning classifiers (Extreme Gradient Boosting, Random Forest, Logistic Regression, and Artificial Neural Network) in predicting childbirth outcomes using data from a tertiary health facility in Ghana. To address class imbalance, we employed the Synthetic Minority Over-sampling Technique (SMOTE). ResultsOur findings show that fetal heartbeat, gestation age at birth are the most influential factors on birth outcome (stillbirth or live birth), while there is no significant association with maternal age, number of babies, and type of delivery method. Among the machine learning models considered, Random Forest emerged as the optimal model achieving an accuracy, F1-score, and AUC values of approximately 0.98, 0.99, and 0.90 respectively. ConclusionOur study identifies key factors affecting childbirth outcomes and highlights the potential of machine learning for early high-risk pregnancy detection in clinical settings. These findings are crucial for Ghana and other Sub-Saharan African countries striving to meet maternal and neonatal healthcare goals. Further research and policy initiatives can use these results to improve healthcare in the region and work toward the World Health Organization’s objectives by 2030.

Predictors of receiving targeted treatment among eligible patients with metastatic colorectal cancer.

e15594 Background: Colorectal cancer is among the most frequently diagnosed cancers and ranks as the third leading cause of cancer-related mortality globally with increasing prevalence among younger patients and high mortality. While targeted therapies have revolutionized treatment and tripled the median survival over the past two decades, many eligible patients fail to receive them. This study sought to identify factors associated with receiving targeted treatment among eligible patients. Methods: We identified a cohort of patients with metastatic colorectal cancer diagnosed between 2007 and 2023 (n = 521,074) in Optum’s clinicogenomic database. Eligible patients were identified based on clinical and treatment history, broad-panel next-gen sequencing (NGS) results and the drug indications for targeted treatments available at time of diagnosis (n = 8,533), including MSI/MMR status, RAS WT status, presence of BRAF V600E, and other biomarkers. In total, we considered tucatinib, encorafenib, pembrolizumab, nivolumab, ipilimumab, panitumumab, cetuximab, and regorafenib. Most patients did not receive targeted treatment; we applied a synthetic minority oversampling technique to correct this class imbalance. We assessed how factors including sex, race, and receipt of genetic counseling services influenced the likelihood of receiving targeted treatment using logistic regression. Results: In the fully adjusted multivariable logistic regression analysis, all variables were significant with p < 0.05. Notably, patients receiving genetic counseling had 68% greater odds of receiving targeted treatment (OR, 1.68 [95% CI, 1.20-2.36]). African American (OR, 0.37 [95% CI, 0.27-0.50]) and Asian patients (OR, 0.10 [95% CI, 0.04-0.24]) had lower odds of receiving targeted treatment compared to Whites. Similarly, patients treated in community settings had 86% lower odds compared to patients in academic settings (OR, 0.14, [95% CI, 0.11-0.18]) as did male patients (OR, 0.39, [95% CI, 0.33-0.44]). Conclusions: This study underscores the challenges in receiving targeted treatments despite clinical eligibility. Our findings highlight the significance of genetic counseling in facilitating access to targeted therapies, and the stark gap in uptake among minority patients. These results can inform strategies to increase access to these treatments. Future research will attempt to better understand the mechanisms underlying receipt of targeted treatment.

Machine Learning Investigation of Downburst-Prone Environments in Canada

Abstract Thunderstorms are recognized as one of the most disastrous weather threats in Canada because of their power to cause substantial damage to human-made structures and even result in fatalities. It is therefore essential for operational forecasting to diagnose thunderstorms that generate damaging downdrafts of negatively buoyant air, known as downbursts. This study develops several machine learning models to identify environments supportive of downbursts in Canada. The models are trained and evaluated using 38 convective parameters calculated based on ERA5 reanalysis vertical profiles prior to thunderstorms with (306 cases) and without (19 132 cases) downbursts across Canada. Various resampling techniques are implemented to adjust data imbalance. An increase in the performance of the random forest (RF) model is observed when the support vector machine synthetic minority oversampling technique is utilized. The RF model outperforms other tested models, as indicated by model performance metrics and calibration. Several model interpretability methods highlight that the RF model has learned physical trends and patterns from the input variables. Moreover, the thermodynamic parameters are deemed to have higher impacts on the model outcomes compared to parcel, kinematic, and composite variables. For example, a considerable rise in the downburst probability is detected with an increase in cold pool strength. This study serves as one of the earliest attempts toward the fledgling field of machine learning applications in weather forecasting systems in Canada. The findings suggest that the developed model has the potential to enhance the effectiveness of issuing severe thunderstorm warnings in Canada, although further assessment with operational meteorologists is needed to validate its practical application. Significance Statement Severe thunderstorms demand particular attention in forecasting as their outflow can pose a serious threat to both structures and human life. This study uses machine learning techniques to predict whether or not a thunderstorm generates a damaging outflow in Canada. Atmospheric conditions that could trigger a severe thunderstorm are identified and discussed. Results show that the models have the potential to assist forecasters in better analyzing and predicting thunderstorms that generate destructive winds. Consequently, taking advantage of promising machine learning tools can yield more reliable forecasts of damaging thunderstorms, thereby mitigating the economic and societal burdens of these storms on Canadian communities.

Implementation of Ensemble Machine Learning Classifier and Synthetic Minority Oversampling Technique for Sentiment Analysis of Sustainable Development Goals in Indonesia

As part of the Sustainable Development Goals (SDGs), governments worldwide have committed to improving people's lives to improve the quality of life for all, including the 17 such goals that were agreed upon in 2015 to benefit the human race as a whole. It would be interesting to see how society responds to the SDGs after approximately half of them have been achieved. This public response was analyzed in terms of sentiment. Within the total number of internet users in Indonesia, there are 18.45 million Twitter users. The platform enables anyone to write about anything they are experiencing in their lives, such as what is happening in their environment, what is happening in their education system, what is happening in the food industry, how people feel, and many more. The platform enables anyone to write about anything they are experiencing in their lives, such as what is happening in their environment, what is happening in their education system, what is happening in the food industry, how people feel, and many more. To model the data collected, the researchers used Ensemble Machine Learning Classifiers (EMLC) to model the data by using a machine learning classifier that uses machine learning techniques. The best model in this study is EMLC-Stacking with a data splitting of 80:20 and using SMOTE, which obtains an accuracy of 91%. This accuracy results from a 5% increase compared to when not using SMOTE. From 15,698 tweets, this research found that 47% were positive sentiments, 28% were negative sentiments, and 25% were neutral sentiments. The results that we measured offer hope that there will be a positive trend in the journey of the SDGs until 2030 if these findings are true.

Performance evaluation of SVM with synthetic minority over-sampling technique in sentiment classification

Performance evaluation of SVM with synthetic minority over-sampling technique in sentiment classification

Scientific text citation analysis using CNN features and ensemble learning model.

Citation illustrates the link between citing and cited documents. Different aspects of achievements like the journal's impact factor, author's ranking, and peers' judgment are analyzed using citations. However, citations are given the same weight for determining these important metrics. However academics contend that not all citations can ever have equal weight. Predominantly, such rankings are based on quantitative measures and the qualitative aspect is completely ignored. For a fair evaluation, qualitative evaluation of citations is needed in addition to quantitative ones. Many existing works that use qualitative evaluation consider binary class and categorize citations as important or unimportant. This study considers multi-class tasks for citation sentiments on imbalanced data and presents a novel framework for sentiment analysis in in-text citations of research articles. In the proposed technique, features are retrieved using a convolutional neural network (CNN), and classification is performed using a voting classifier that combines Logistic Regression (LR) and Stochastic Gradient Descent (SGD). The class imbalance problem is handled by the synthetic minority oversampling technique (SMOTE). Extensive experiments are performed in comparison with the proposed approach using SMOTE-generated data and machine learning models by term frequency (TF), and term frequency-inverse document frequency (TF-IDF) to evaluate the efficacy of the proposed approach for citation analysis. It is found that the proposed voting classifier using CNN features achieves an accuracy, precision, recall, and F1 score of 0.99 for all. This work not only advances the field of sentiment analysis in academic citations but also underscores the importance of incorporating qualitative aspects in evaluating the impact and sentiments conveyed through citations.

Optimization of Early Detection of Tuberculosis Through Machine Learning Using Clinical Data: Development and Evaluation of Multilayer Perceptron and Extreme Learning Machine for Tuberculosis Classification

This research takes an innovative step in the fight against Tuberculosis (TB), one of Indonesia's prominent public health challenges, by developing and evaluating Multilayer Perceptron (MLP) and Extreme Learning Machine (ELM) models in machine learning for early detection of TB using clinical data. The main result of this study was the discovery that the MLP model, when applied without the Synthetic Minority Over-sampling Technique (SMOTE), achieved an impressive accuracy of 95.00%, signaling significant progress in TB early detection efforts. This discovery not only highlights the great potential of applying machine learning technology in improving the accuracy of TB diagnosis but also paves the way for the possible application of advanced technology in the health sector to deal with infectious diseases. This research illustrates how machine learning technology can be integrated into clinical practice to effectively detect TB cases at an early stage, thus enabling faster and more precise treatment, which can ultimately reduce the spread of the disease. This is particularly important given TB's significant impact on public health, especially in developing countries. The results also open up opportunities for further research into the application of machine learning techniques to other infectious diseases, promising a paradigm shift in the way we detect and manage various health conditions.

Political social media bot detection: Unveiling cutting-edge feature selection and engineering strategies in machine learning model development

Over time, social media bots (SMBs), specifically political SMBs, have played a crucial role in influencing and spreading misinformation, manipulating public opinion, and harassing and intimidating users of online social networks (OSNs). This article aims to study previous works on the detection and analysis of political SMB activities and address critical challenges that significantly impact the effectiveness of SMB detection models. These challenges include feature engineering, feature selection (FS), and model implementation. Over 33 features were extracted from the Twibot-20 dataset, including content, user information, network, behavior, and temporal features. Various FS techniques are explored and compared to select the optimal features, comprising basic, filter, wrapper, embedded, and hybrid. The optimal features are then employed to train multiple machine-learning algorithms. To balance the dataset, the synthetic minority oversampling technique coupled with edited nearest neighbors (Smote-ENN) is used. The results showed an improvement in model performance, from an initial Area Under the Curve (AUC) of 90.40 % and accuracy of 81.60 % using the original set to a score of 99.50 % for the test set and 100 % for the training set in all used metrics. Decision Trees, Random Forest, Gradient Boosting, Adaboost, XGB, and Extra Trees emerge as the most effective for detecting political SMBs.

Optimizing double-layered convolutional neural networks for efficient lung cancer classification through hyperparameter optimization and advanced image pre-processing techniques.

Lung cancer remains a leading cause of cancer-related mortality globally, with prognosis significantly dependent on early-stage detection. Traditional diagnostic methods, though effective, often face challenges regarding accuracy, early detection, and scalability, being invasive, time-consuming, and prone to ambiguous interpretations. This study proposes an advanced machine learning model designed to enhance lung cancer stage classification using CT scan images, aiming to overcome these limitations by offering a faster, non-invasive, and reliable diagnostic tool. Utilizing the IQ-OTHNCCD lung cancer dataset, comprising CT scans from various stages of lung cancer and healthy individuals, we performed extensive preprocessing including resizing, normalization, and Gaussian blurring. A Convolutional Neural Network (CNN) was then trained on this preprocessed data, and class imbalance was addressed using Synthetic Minority Over-sampling Technique (SMOTE). The model's performance was evaluated through metrics such as accuracy, precision, recall, F1-score, and ROC curve analysis. The results demonstrated a classification accuracy of 99.64%, with precision, recall, and F1-score values exceeding 98% across all categories. SMOTE significantly enhanced the model's ability to classify underrepresented classes, contributing to the robustness of the diagnostic tool. These findings underscore the potential of machine learning in transforming lung cancer diagnostics, providing high accuracy in stage classification, which could facilitate early detection and tailored treatment strategies, ultimately improving patient outcomes.

Multiple Classifier System for Handling Imbalanced and Overlapping Datasets on Multiclass Classification

The performance of classification models suffer when the dataset contains imbalanced and overlapping data. These two conditions are already challenging separately and even more complex if they occur together. In the research, an ensemble method called a Multiple Classifier System was proposed to address these issues by combining K-Nearest Neighbour and Logistic Regression. The Synthetic Minority Oversampling Technique (SMOTE) method was also applied to balance the dataset. The One Versus One (OVO) decomposition technique helped the multiclass classification process. A simulation with 18 scenarios proves that the MCS-SMOTE model can handle these problems by providing good performance. The model’s performance is also tested using empirical data on Poverty in West Java in 2021. Empirical data also show that the proposed method performs well, with an accuracy rate of 80.09%, an F1 score of 0.782, and a G-Mean of 0.242. The areas with the highest poverty rates are Bogor, Bekasi City, Bandung City, Bekasi Regency, and Depok City, located near DKI Jakarta, the capital city. Based on existing predictor variables, poor households in West Java are more likely to occur when they do not have access to credit, the number of household members is more than three, multiple families live in one building, and the head of the household has not graduated from elementary school.

Analisis dan Optimalisasi Performa Algoritma Gaussian Naive Bayes pada Prediksi Metabolic Syndrome Menggunakan SMOTE

Metabolic syndrome is a complex global health problem, with symptoms such as abdominal obesity, insulin resistance, high blood pressure, high blood sugar, and abnormal blood lipids. With this global challenge, several studies have attempted to predict these diseases using machine learning methods. However, often, predictions about a disease result in data imbalance where minority classes are underrepresented. To balance the class proportions, the Synthetic Minority Over-sampling Technique (SMOTE) method replicates the minority class samples. In this research, the technique applied to predict is the Gaussian Naive Bayes (GNB) algorithm. The results show an increase in prediction accuracy by 0.2 from 0.81 to 0.83. This study confirms the critical role of the SMOTE oversampling method in machine learning using the Gaussian Naive Bayes (GNB) algorithm in Metabolic Syndrome prediction and its positive impact on diagnostic efficiency and public health.

Performance Evaluation of Hybrid Machine Learning Algorithms for Online Lending Credit Risk Prediction

ABSTRACT Peer-to-Peer systems are still in the early stages of development when it comes to the processing of credit and the appraisal of the risk associated with it. In this study, we used a hybrid convolutional neural network with logistic regression, a gradient-boosting decision tree, and a k-nearest neighbor to predict the credit risk in a P2P lending club. The lending clubs publicly available P2P loan data was used to train the model. In order to address the issue of data imbalance within the dataset, specifically between the non-defaulter and defaulter classes, the synthetic minority oversampling technique sampling approach is utilized. We developed the architecture of our hybrid model by removing the fully connected layer with the soft-max, which is the final layer of the fully connected CNN model and replaced by LR, GBDT, and k-NN algorithms. The experimental results show that the hybrid CNN-kNN model outperforms the CNN-GBDT and CNN-LR models based on the performance metrics accuracy, recall, F1-score, and area under the curve for both all input and important features. This shows that hybrid machine learning models effectively identify and categorize credit risk in peer-to-peer lending clubs, hence assisting in financial loss prevention.

DDoS Attack Detection in Edge-IIoT Network Using Ensemble Learning

Abstract As the number of IoT devices increases daily due to the rapid growth in technology, every device and network is vulnerable to attacks because it is exposed to the internet. Denial of Service (DoS) is a prevalent type of intrusion on the Internet of Things (IoT) network in which the server becomes down due to flooding requests. Distributed Denial of Service (DDoS) is a special type of DoS attack where the network of malicious computers called botnet consumes the target’s system resources by flooding the requests. Edge computing is closely related to Industrial Internet of Things (IIoT), and industry 4.0. Both of them are relatively emerging technologies so security is a crucial part of them. By incorporating our contributions to the current and innovative dataset Edge-IIoT, the proposed study presents a novel approach to detect DDoS attacks in an IIoT network in the domain of edge computing, whether the traffic is normal or malicious (DDoS traffic). This study explores various Ensemble Learning (EL) techniques to predict normal and malicious DDoS traffic along with the type of DDoS attack. The study applies various preprocessing techniques like Synthetic Minority Over Sampling Technique (SMOTE), label encoding, etc. to enhance the model’s performance and reveals how EL techniques performs better in terms of accuracy than the individual classifiers. Further, the performance of all EL techniques has been investigated in terms of all evaluation measures, including the elapsed time. This important addition not only broadens the focus of study in this area but also offers insightful comparisons of the efficiency and precision of various ensemble approaches as well as individual classifiers. The study achieved a maximum of 99.99% in all evaluation measures.

1D-CNN: Classification of normal delivery and cesarean section types using cardiotocography time-series signals

Abstract Cardiotocography (CTG) is considered the gold standard for monitoring fetal heart rate (FHR) during pregnancy and labor to estimate the danger of oxygen deprivation. Visual interpretation of CTG traces is complex and frequently results in high rates of false positives and false negatives, leading to unfavorable and unwanted outcomes such as fetal mortality or needless cesarean surgery. If the data are well-balanced, which is uncommon in medical datasets, machine learning techniques can be helpful in interpretation. This study is designed to determine classification performance under various data balance approaches. We propose a robust methodology for the automated extraction of features that use a deep learning model based on the one-dimensional convolutional neural network (1D-CNN). We used a public database containing 552 intrapartum CTG recordings. Due to the imbalance in the dataset, the experiments were conducted under a variety of conditions such as (i) an unbalanced dataset, (ii) undersampling, (iii) a weighted binary cross-entropy approach, and (iv) oversampling utilizing the synthetic minority oversampling technique (SMOTE). We found an excellent sensitivity (99.80% for the unbalanced dataset, 96.25% for the weighted binary cross-entropy approach, and 99.81% with SMOTE) except for the under sampling situation, in which the sensitivity was 85.71%. Moreover, the 1D-CNN model incorporating SMOTE yielded promising results in 88% specificity, 93.72% quality index (QI), and 95.10% area under the curve. The model exhibited excellent performance in terms of sensitivity in every scenario except for undersampling. The oversampling of training data with SMOTE yielded a decent level of specificity, demonstrating the model’s strong predictive capacity. In addition, the SMOTE scenario resulted in fewer training epochs, which is another accomplishment.

A novel generative adversarial network for improving crash severity modeling with imbalanced data

Traffic crash data is often greatly imbalanced with the majority of non-fatal crashes and only a small number of fatal crashes. Such data imbalance issue poses a challenge for crash severity modelling, especially for classifying and interpreting fatal crashes with very limited samples. To address the data imbalance issues, the data resampling techniques are commonly used methods to rebalance the number of samples among all categories of the dataset, such as under-sampling and over-sampling techniques. However, it is challenging for most traditional and existing deep learning-based resampling methods, e.g., synthetic minority oversampling technique (SMOTE) and Generative Adversarial Networks (GAN), to handle both continuous and discrete risk factors in traffic crash datasets, since they are built upon by smooth and continuous functions which are not applicable for processing discrete variables. Though some resampling methods are capable of handling both continuous and discrete variables, they may struggle with mode collapse issues associated with sparse discrete risk factors so that the diversity of the underlying data distribution can not be captured due to oversampling repetitive and similar samples. To address the aforementioned issues, the current study proposes a traffic crash data generation method based on the Conditional Tabular GAN (CTGAN) to rebalance crash datasets for improving performance of crash severity classification and interpretation. The designed experiments are conducted to evaluate contributions of the synthetic data for improving crash severity classification, the distribution consistency between synthetic and benchmark datasets, and the parameter recovery (i.e., the accuracy of parameter estimation and probability prediction) for various resampling strategies. A 4-year real-world dataset collected in Washington State, U.S., and Monte Carlo simulations are utilized for demonstrating the designed experiments. The results indicate that crash severity modeling using synthetic data generated by the mix-resampling of CTGAN and random under-sampling (CTGAN-RU) outperforms all baseline methods. In addition, the proposed deep generative method demonstrates the capability in maintaining distribution consistency and achieving accurate parameter recovery. This study can provide valuable insights for traffic safety researchers and engineers into crash severity modeling, especially when handling imbalanced crash data of various types.

Integrating SMOTE-Tomek and Fusion Learning with XGBoost Meta-Learner for Robust Diabetes Recognition

This research aims to develop a robust diabetes classification method by integrating the Synthetic Minority Over-sampling Technique (SMOTE)-Tomek technique for data balancing and using a machine learning ensemble led by eXtreme Gradient Boosting (XGB) as a meta-learner. We propose an ensemble model that combines deep learning techniques such as Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Units (BiGRU) with XGB classifier as the base learner. The data used included the Pima Indians Diabetes and Iraqi Society Diabetes datasets, which were processed by missing value handling, duplication, normalization, and the application of SMOTE-Tomek to resolve data imbalances. XGB, as a meta-learner, successfully improves the model's predictive ability by reducing bias and variance, resulting in more accurate and robust classification. The proposed ensemble model achieves perfect accuracy, precision, recall, specificity, and F1 score of 100% on all tested datasets. This method shows that combining ensemble learning techniques with a rigorous preprocessing approach can significantly improve diabetes classification performance.

Unmasking Banking Fraud: Unleashing the Power of Machine Learning and Explainable AI (XAI) on Imbalanced Data

Recognizing fraudulent activity in the banking system is essential due to the significant risks involved. When fraudulent transactions are vastly outnumbered by non-fraudulent ones, dealing with imbalanced datasets can be difficult. This study aims to determine the best model for detecting fraud by comparing four commonly used machine learning algorithms: Support Vector Machine (SVM), XGBoost, Decision Tree, and Logistic Regression. Additionally, we utilized the Synthetic Minority Over-sampling Technique (SMOTE) to address the issue of class imbalance. The XGBoost Classifier proved to be the most successful model for fraud detection, with an accuracy of 99.88%. We utilized SHAP and LIME analyses to provide greater clarity into the decision-making process of the XGBoost model and improve overall comprehension. This research shows that the XGBoost Classifier is highly effective in detecting banking fraud on imbalanced datasets, with an impressive accuracy score. The interpretability of the XGBoost Classifier model was further enhanced by applying SHAP and LIME analysis, which shed light on the significant features that contribute to fraud detection. The insights and findings presented here are valuable contributions to the ongoing efforts aimed at developing effective fraud detection systems for the banking industry.