Resampling Technique Research Articles

A re-sampling statistics based imprecise moment independent global sensitivity analysis methodology with limited data of uncorrelated and correlated geotechnical properties

Traditional Global Sensitivity Analysis (GSA) is often performed using variance-based Sobol’s GSA, considering statistics of inputs estimated from limited data to be precise. This can lead to inaccuracies in the importance ranking of inputs due to negligence of – i) epistemic uncertainties in their statistics, and ii) role of other moments of outputs in Sensitivity Indices (SIs). This study overcomes these limitations by proposing an imprecise moment independent GSA methodology. The methodology couples re-sampling statistical techniques, i.e., Jackknifing and Bootstrapping with Monte-Carlo Simulations based Borgonovo’s moment independent GSA to estimate distributions of SIs. The re-sampling techniques estimate epistemic uncertainties in the statistics of inputs by generating re-constituted samples. These epistemic uncertainties are then propagated via Borgonovo’s GSA to estimate their imprecise moment independent SIs. The methodology is further coupled with Nataf’s transformation and Moving Least Square-Response Surface Methods to deal with problems of correlated inputs and lack of explicit input-output relationships. The generalized nature of methodology is demonstrated for three real case studies (one tunnel and two slopes), with different correlation structures between inputs, input-outputs relationships (explicit/implicit), and failure mechanisms. The methodology estimated the distributions of SIs of inputs instead of their point estimates, indicating the propagation of epistemic uncertainties truthfully. The Jackknife-GSA was significantly efficient (∼99 %) with negligible differences in statistics of SIs as compared to Bootstrap-GSA. The correlation between inputs significantly affects the statistics of SIs. Further, a reduction in the imprecision of SIs of inputs with their increasing sample sizes was observed, which is consistent with the general understanding.

Handling the Imbalanced Problem in Agri-Food Data Analysis.

Imbalanced data situations exist in most fields of endeavor. The problem has been identified as a major bottleneck in machine learning/data mining and is becoming a serious issue of concern in food processing applications. Inappropriate analysis of agricultural and food processing data was identified as limiting the robustness of predictive models built from agri-food applications. As a result of rare cases occurring infrequently, classification rules that detect small groups are scarce, so samples belonging to small classes are largely misclassified. Most existing machine learning algorithms including the K-means, decision trees, and support vector machines (SVMs) are not optimal in handling imbalanced data. Consequently, models developed from the analysis of such data are very prone to rejection and non-adoptability in real industrial and commercial settings. This paper showcases the reality of the imbalanced data problem in agri-food applications and therefore proposes some state-of-the-art artificial intelligence algorithm approaches for handling the problem using methods including data resampling, one-class learning, ensemble methods, feature selection, and deep learning techniques. This paper further evaluates existing and newer metrics that are well suited for handling imbalanced data. Rightly analyzing imbalanced data from food processing application research works will improve the accuracy of results and model developments. This will consequently enhance the acceptability and adoptability of innovations/inventions.

Learning from Imbalanced Data: Integration of Advanced Resampling Techniques and Machine Learning Models for Enhanced Cancer Diagnosis and Prognosis

Background/Objectives: This study aims to evaluate the performance of various classification algorithms and resampling methods across multiple diagnostic and prognostic cancer datasets, addressing the challenges of class imbalance. Methods: A total of five datasets were analyzed, including three diagnostic datasets (Wisconsin Breast Cancer Database, Cancer Prediction Dataset, Lung Cancer Detection Dataset) and two prognostic datasets (Seer Breast Cancer Dataset, Differentiated Thyroid Cancer Recurrence Dataset). Nineteen resampling methods from three categories were employed, and ten classifiers from four distinct categories were utilized for comparison. Results: The results demonstrated that hybrid sampling methods, particularly SMOTEENN, achieved the highest mean performance at 98.19%, followed by IHT (97.20%) and RENN (96.48%). In terms of classifiers, Random Forest showed the best performance with a mean value of 94.69%, with Balanced Random Forest and XGBoost following closely. The baseline method (no resampling) yielded a significantly lower performance of 91.33%, highlighting the effectiveness of resampling techniques in improving model outcomes. Conclusions: This research underscores the importance of resampling methods in enhancing classification performance on imbalanced datasets, providing valuable insights for researchers and healthcare professionals. The findings serve as a foundation for future studies aimed at integrating machine learning techniques in cancer diagnosis and prognosis, with recommendations for further research on hybrid models and clinical applications.

Predictive Modeling of Customer Response to Marketing Campaigns

In today’s data-driven marketing landscape, predicting customer responses to marketing campaigns is essential for optimizing both engagement and Return On Investment (ROI). This study aims to develop a predictive model using a Decision Tree (DT) to identify key factors influencing customer behavior and improve campaign targeting. The methodology involves building the DT model, initially achieving an accuracy of 87.3%. However, the model faced challenges with precision and recall due to class imbalance. To address this, a resampling technique was applied, which significantly improved model performance, increasing recall from 44% to 83.1% and the F1-score from 49% to 74.2%. Key influential features identified include the recency of a customer’s purchase, their duration as a customer, and their response history to previous campaigns. This study demonstrates the practicality and interpretability of the DT model, offering actionable insights for marketing professionals seeking to enhance campaign effectiveness and customer targeting.

On the use of Change History Data to Enhance Class Change-Proneness Prediction Models

As software evolves, new artifacts are created, modified, or removed. One of these main artifacts generated in the development of object-oriented software is the class. Classes have a very dynamic life cycle that can result in additional costs to the project. One way to mitigate this is to detect, in the early stages of the development, classes that are prone to change. Some approaches in the literature adopt Machine Learning (ML) algorithms to predict the change-proneness of a class. However, most of these approaches do not consider the temporal dependency between training instances, i.e., they consider that the instances are independent. To overcome such a limitation, this study presents an approach for predicting change-proneness based on the class change history. The approach adopts the sliding window method and is evaluated to obtain six kinds of models, which are derived by using, as predictors, different sets of metrics: structural, evolutionary, and smell-based. The evaluation uses five systems, four ML algorithms, and also explores some resample techniques to deal with imbalanced data. Regardless of the kind of model analyzed and the algorithm used, our approach overcomes the traditional one in 378 (~80) cases, out of 420, considering all systems, kinds of models, indicators, and algorithms. Moreover, the results show that our approach presents the best performance when the set of evolutionary metrics is used as predictors. There is no improvement when smell-based metrics are added. The Random Forest algorithm with the resampling technique ADA reaches the best performance among the ML algorithms evaluated.

Predicting Multiple Outcomes Associated with Frailty based on Imbalanced Multi-label Classification.

Frailty syndrome is prevalent among the elderly, often linked to chronic diseases and resulting in various adverse health outcomes. Existing research has predominantly focused on predicting individual frailty-related outcomes. However, this paper takes a novel approach by framing frailty as a multi-label learning problem, aiming to predict multiple adverse outcomes simultaneously. In the context of multi-label classification, dealing with imbalanced label distribution poses inherent challenges to multi-label prediction. To address this issue, our study proposes a hybrid resampling approach tailored for handling imbalance problems in the multi-label scenario. The proposed resampling technique and prediction tasks were applied to a high-dimensional real-life medical dataset comprising individuals aged 65years and above. Several multi-label algorithms were employed in the experiment, and their performance was evaluated using multi-label metrics. The results obtained through our proposed approach revealed that the best-performing prediction model achieved an average precision score of 83%. These findings underscore the effectiveness of our method in predicting multiple frailty outcomes from a complex and imbalanced multi-label dataset.

Comparing Sentinel-2 and Landsat 9 for land use and land cover mapping assessment in the north of Congo Republic: a case study in Sangha region

ABSTRACT A study of land use and land cover (LULC) mapping using satellite data was conducted in the Congo Basin rainforest in the Sangha area of the northern Congo Republic, which is crucial for sustainable land management. However, the heterogeneous nature of LULC features makes data classification difficult in this area because persistent cloud cover is challenging for observing the land surface and tropical humid conditions characterizing the study area. This study compares and evaluates the potential of two of the most widely used and popular satellite image sources, the recently launched Landsat 9 and Sentinel-2, to generate land-use land cover (LULC) maps in the Sangha area using pixel-based supervised machine learning algorithms, Random Forest (RF), for classification. All procedures were performed using ArcGIS Pro. The potential to improve Landsat 9 performance was tested using the nearest resampling technique, and different bands were resampled from 30 × 30 to 10 × 10 m. Owing to the heterogeneous characteristics of the Sangha study area, six classes were defined: dense forest, open forest, wetland forest, water bodies, urban areas, and bare soils. To classify and compare Sentinel-2 and Landsat 9, the shortwave infrared (SWIR), Near Infrared (NIR), and Red, Green, Blue (RGB) bands were used. These two satellite images were compared to test the quality of their results, particularly for assessing the accuracy of the LULC classifications and identifying which dataset had the highest accuracy. Results show that overall accuracy was 93.80% for Sentinel-2 while it was 91.60% for Landsat 9, similarly, the Kappa coefficient was calculated 0.89 and 0.85 for Sentinel-2 and Landsat 9, respectively. Therefore, Sentinel-2 exhibits significant classification ability compared to the nearest resample technique Landsat 9, despite the improved resolution of the latter, which offers a scientific basis for choosing the appropriate satellite imagery to create accurate LULC maps.

Analyzing Resampling Techniques for Addressing the Class Imbalance in NIDS using SVM with Random Forest Feature Selection

The purpose of Network Intrusion Detection Systems (NIDS) is to ensure and protect computer networks from harmful actions. A major concern in NIDS development is the class imbalance problem, i.e., normal traffic dominates the communication data plane more than intrusion attempts. Such a state of affairs can pose certain hazards to the effectiveness of detection algorithms, including those useful for detecting less frequent but still highly dangerous intrusions. This paper aims to utilize resampling techniques to tackle this problem of class imbalance in NIDS using a Support Vector Machine (SVM) classifier alongside utilizing features selected by Random Forest to improve the feature subset selection process. The analysis highlights the combativeness of each sampling method, offering insights into their efficiency and practicality for real-world applications. Four resampling techniques are analyzed. Such techniques include Synthetic Minority Over-sampling Technique (SMOTE), Random Under-sampling (RUS), Random Over-sampling (ROS) and SMOTE with two different combinations i.e., RUS SMOTE and RUS ROS. Feature selection was done using Random Forest, which was improved by Bayesian methods to create subsets of features with feature rankings determined by Cumulative Feature Importance Score (CFIS). The CIDDS-2017 dataset is used for the performance evaluation, and the metrics used include accuracy, precision, recall, F-measure and CPU time. The algorithm that performs best overall in the CFIS feature subsets is SMOTE, and the features that give the best result are selected at the 90% level with 25 features. This subset accomplishes a relative accuracy enhancement of 0.08% than the other approaches. The RUS+ROS technique is also fine but somehow slower than SMOTE. On the other hand, RUS+SMOTE shows relatively poor results although it consumes less time in terms of computational time compared to other methods, giving about 50% of the performance shown by the other methods. This paper's novelty is adapting the RUS method as a standalone test for screening new and potentially contaminated datasets. The standalone RUS method is more efficient in terms of computations; the algorithm returned the best result of 98.13% accuracy at 85% at the CFIS level of 34 features with a computation time of 137.812 s. It is also noted that SMOTE is considered to be proficient among all resampling techniques used for handling the problem of class imbalance in NIDS, vice 90% CFIS feature subset. Future research directions could include using these techniques in different data sets and other machine learning and deep learning methods together with ROC curve analysis to provide useful pointers to NIDS designers on how to select the right data mining tools and strategies for their projects.

Penilaian Pembayaran Kredit dengan Logistic Regression dan Random Forest pada Home Credit

Global economic development has led to the high complexity of society's needs. Financial institutions are here to provide facilities to meet the increasingly complex needs of society. However, the existence of problem loans can be a serious threat so classification techniques in data mining are used to overcome this problem. This research develops a model that can predict customers' ability to make credit payments so that financial institutions can avoid problematic credit. In this research, the SMOTE resampling technique is used to see the effect of sampling in dealing with class imbalance and conducting credit assessments. The research results show that the model built using SMOTE has better AUC than the model without SMOTE. From the two machine learning algorithms, logistic regression and random forest, the results show that the random forest model with SMOTE has the best performance with an accuracy value of 90%, precision of 92%, recall of 88%, F1-score of 90%, and AUC value of 0.97. Based on the best model, ten important features were obtained that influence the process of assessing credit repayment capabilities, namely the normalized score from external data sources, the period for changing customer numbers, the number of previous installment payments, the customer's age, registration time, the period for applying for credit at the credit bureau, the period for changing identity documents, the time for updating information at the credit bureau, and the length of time the customer has worked. In addition, this research produces visualizations via dashboards that can be used to improve the process of assessing credit repayment capabilities.

MSlocPRED: deep transfer learning-based identification of multi-label mRNA subcellular localization.

Subcellular localization of messenger ribonucleic acid (mRNA) is a universal mechanism for precise and efficient control of the translation process. Although many computational methods have been constructed by researchers for predicting mRNA subcellular localization, very few of these computational methods have been designed to predict subcellular localization with multiple localization annotations, and their generalization performance could be improved. In this study, the prediction model MSlocPRED was constructed to identify multi-label mRNA subcellular localization. First, the preprocessed Dataset 1 and Dataset 2 are transformed into the form of images. The proposed MDNDO-SMDU resampling technique is then used to balance the number of samples in each category in the training dataset. Finally, deep transfer learning was used to construct the predictive model MSlocPRED to identify subcellular localization for 16 classes (Dataset 1) and 18 classes (Dataset 2). The results of comparative tests of different resampling techniques show that the resampling technique proposed in this study is more effective in preprocessing for subcellular localization. The prediction results of the datasets constructed by intercepting different NC end (Both the 5' and 3' untranslated regions that flank the protein-coding sequence and influence mRNA function without encoding proteins themselves.) lengths show that for Dataset 1 and Dataset 2, the prediction performance is best when the NC end is intercepted by 35 nucleotides, respectively. The results of both independent testing and five-fold cross-validation comparisons with established prediction tools show that MSlocPRED is significantly better than established tools for identifying multi-label mRNA subcellular localization. Additionally, to understand how the MSlocPRED model works during the prediction process, SHapley Additive exPlanations was used to explain it. The predictive model and associated datasets are available on the following github: https://github.com/ZBYnb1/MSlocPRED/tree/main.

Influence of Preprocessing Methods of Automated Milking Systems Data on Prediction of Mastitis with Machine Learning Models

Missing data and class imbalance hinder the accurate prediction of rare events such as dairy mastitis. Resampling and imputation are employed to handle these problems. These methods are often used arbitrarily, despite their profound impact on prediction due to changes caused to the data structure. We hypothesize that their use affects the performance of ML models fitted to automated milking systems (AMSs) data for mastitis prediction. We compare three imputations—simple imputer (SI), multiple imputer (MICE) and linear interpolation (LI)—and three resampling techniques: Synthetic Minority Oversampling Technique (SMOTE), Support Vector Machine SMOTE (SVMSMOTE) and SMOTE with Edited Nearest Neighbors (SMOTEEN). The classifiers were logistic regression (LR), multilayer perceptron (MLP), decision tree (DT) and random forest (RF). We evaluated them with various metrics and compared models with the kappa score. A complete case analysis fitted the RF (0.78) better than other models, for which SI performed best. The DT, RF, and MLP performed better with SVMSMOTE. The RF, DT and MLP had the overall best performance, contributed by imputation or resampling (SMOTE and SVMSMOTE). We recommend carefully selecting resampling and imputation techniques and comparing them with complete cases before deciding on the preprocessing approach used to test AMS data with ML models.

Effect of Random Under sampling, Oversampling, and SMOTE on the Performance of Cardiovascular Disease Prediction Models

Cardiovascular Disease (CVD) or commonly known as Heart Disease is a leading cause of mortality globally, prompting extensive research into predictive models to assess individual risk and plan preventive measures. Machine learning approaches such as Random Forest, Support Vector Machine (SVM), and LASSO Logistic Regression have showed promise. Recent studies have indicated that traditional resampling methods like Random Oversampling, Random Undersampling, and SMOTE may not significantly improve model discrimination. This study aims to evaluate the impact of these techniques on the performance of Cardiovascular Disease (CVD) prediction models, utilizing data from the UCI Machine Learning Heart Disease database. By employing LASSO Logistic Regression, Random Forest, and Support Vector Machine (SVM) with resampling techniques, including Random Oversampling, Random Undersampling, and SMOTE. This research seeks to enhance understanding of model performance in addressing class imbalances within the dataset and contribute to refining cardiovascular disease (CVD) prediction strategies. This study demonstrates that the use of the SMOTE technique significantly enhances the performance of cardiovascular disease (CVD) prediction models. Specifically, when combined with the Random Forest algorithm, SMOTE achieves the best performance in terms of accuracy, sensitivity, and specificity. This highlights the importance of selecting appropriate resampling techniques to handle class imbalance in datasets. Consequently, this research contributes to refining CVD prediction strategies and provides new insights into improving prediction accuracy in imbalanced medical data.

An approach for two-dimensional convolutional neural networks for hourly passenger boarding demand prediction based on uneven smart-card data

An invaluable resource for understanding passenger boarding patterns and forecasting future travel demand is the tap-on smart-card data. Positive instances, on the other hand—boarding at a given bus stop at a certain time—are less common than negative instances when looking at the smart-card data (or instances) by boarding stops and by time of day. Machine learning algorithms that are used to estimate hourly boarding numbers at a certain location have been shown to be much less accurate when the data is imbalanced. Before using the smart-card data to forecast bus boarding demand, this research tackles the problem of data imbalance in the data. To create fake traveling instances to add into a synthetic training dataset containing more evenly distributed traveling and non-traveling examples, we suggest using deep generative adversarial networks (Deep-GAN). Next, a deep neural network, or DNN, is trained on the synthetic dataset to predict which instances from a given stop in a certain time frame will travel and which ones won't. According to the findings, resolving the data imbalance problem may greatly enhance the predictive model's functionality and make it more accurate in predicting ridership profiles. The suggested strategy may create a synthetic training set with a better similarity so diversity and, therefore, a stronger prediction capability, according to a comparison of the Deep-GAN's performance with other conventional resampling techniques. The study emphasizes the importance of the issue and offers helpful recommendations for enhancing the quality of the data and model performance for individual travel behavior analysis and travel behavior prediction.

Predicting rock art sites in the Pajeú watershed, Brazil

This paper presents an Archaeological Predictive Model (APM) to predict rock art archaeological sites in the Pajeú Watershed, a semiarid region in Pernambuco, Brazil. The model uses Machine Learning (ML) algorithms and re-sampling techniques to account for the unbalanced data set of rock art sites and test different inductive methods for predicting site location. The results show a satisfactory statistical evaluation, with high true positive rates with all ML algorithms and resampling techniques used, indicating a high potential for predicting rock art site locations. The predictive maps generated from the model output, show that certain features, such as aspect, elevation and the distance to different lithologies, are particularly important. The overall model's performance could be corroborated with a test in another semi-arid region, next to the Pajeú watershed, where areas with high favorability of finding rock art sites are predicted near to already known archaeological sites.

Enhancing Customer Churn Prediction With Resampling: A Comparative Study

In this competitive business world, accurately predicting customer churn is crucial to maintaining and preventing revenue loss. However, due to the imbalanced nature of customer churn data, traditional machine learning algorithms often fail to identify churned customers accurately. This has led to exploring resampling techniques, demonstrating their efficacy in addressing this issue. However, current studies in the customer churn prediction field frequently overlook the untapped potential of comprehensive investigation and comparison of resampling techniques. Instead of exploring and comparing various resampling methods, many studies predominantly rely on a single resampling method, such as SMOTE. Hence, this paper aims to compare and evaluate the effectiveness of several resampling methods, including oversampling, undersampling, and hybrid techniques. We utilized the benchmark dataset, telecommunication customer churn, from IBM Watson, where approximately 26.5% of the customers have churned, indicating that the data is imbalanced. Our results demonstrate that the combination of random forest with a hybrid sampling method – SMOTE-ENN obtained the best result. The combination yields an F1 score of 95.3% and an accuracy of 96.0%, surpassing the studies that utilized the same dataset. This highlights the benefits of comparing resampling techniques in predicting customer churn, specifically in imbalanced datasets.

Analysis of risk factors and development of a nomogram prediction model for renal tubular acidosis in primary Sjogren syndrome patients

ObjectiveTo investigate the risk factors of renal tubular acidosis (RTA) in patients with primary Sjögren’s syndrome (pSS) and create a personalized nomogram for predicting pSS-RTA patients.MethodData from 99 pSS patients who underwent inpatient treatment at our hospital from January 2012 to January 2024 were retrospectively collected and analyzed. Bootstrap resampling technique, single-factor, and multi-factor logistic regression analyses were used to explore the risk factors for pSS-RTA. A nomogram was developed based on the results of the multivariate logistic model. The model was evaluated through receiver operating characteristic curve, C-index, calibration curve, and decision curve analysis. In addition, we graded the severity of pSS-RTA patients and used univariate analysis to assess the relationship between pSS-RTA severity and risk factors.ResultsA multivariate logistic regression analysis revealed that concurrent thyroid disease, long symptom duration, subjective dry mouth, and positive RF were independent risk factors for pSS-RTA patients. Based on them, a personalized nomogram predictive model was established. With a p-value of 0.657 from the Hosmer-Lemeshow test, the model demonstrated a good fit. The AUC values in the training and validation groups were 0.912 and 0.896, indicating a strong discriminative power of the nomogram. The calibration curves for the training and validation groups closely followed the diagonal line with a slope of 1, confirming the model’s reliable predictive ability. Furthermore, the decision curve analysis showed that the nomogram model had a net benefit in predicting pSS-RTA, emphasizing its clinical value.This study did not find an association between the severity of pSS-RTA and risk factors.DiscussionWe developed a nomogram to predict RTA occurrence in pSS patients, and it is believed to provide a foundation for early identification and intervention for high-risk pSS patients.

RSANMDA: Resampling based subview attention network for miRNA-disease association prediction

Many studies have demonstrated the importance of accurately identifying miRNA-disease associations (MDAs) for understanding disease mechanisms. However, the number of known MDAs is significantly fewer than the unknown pairs. Here, we propose RSANMDA, a subview attention network for predicting MDAs. We first extract miRNA and disease features from multiple similarity matrices. Next, using resampling techniques, we generate different subviews from known MDAs. Each subview undergoes multi-head graph attention to capture its features, followed by semantic attention to integrate features across subviews. Finally, combining raw and training features, we use a multilayer scoring perceptron for prediction. In the experimental section, we conducted comparative experiments with other advanced models on both HMDD v2.0 and HMDD v3.2 datasets. We also performed a series of ablation studies and parameter tuning exercises. Comprehensive experiments conclusively demonstrate the superiority of our model. Case studies on lung, breast, and esophageal cancers further validate our method's predictive capability for identifying disease-related miRNAs.

From super-Earths to sub-Neptunes: Observational constraints and connections to theoretical models

The growing number of well-characterized exoplanets smaller than Neptune enables us to conduct more detailed population studies. We have updated the PlanetS catalog of transiting planets with precise and robust mass and radius measurements and use this comprehensive catalog to explore mass-radius (M–R) diagrams. On the one hand, we propose new M–R relationships to separate exoplanets into three populations: rocky planets, volatile-rich planets, and giant planets. On the other hand, we explore the transition in radius and density between super-Earths and sub-Neptunes around M-dwarfs and compare them with those orbiting K- and FG-dwarfs. Using Kernel density estimation method with a re-sampling technique, we estimated the normalized density and radius distributions, revealing connections between observations and theories on composition, internal structure, formation, and evolution of these exo-planets orbiting different spectral types. First, the substantial 30% increase in the number of well-characterized exoplanets orbiting M-dwarfs compared with previous studies shows us that there is no clear gap in either composition or radius between super-Earths and sub-Neptunes. The “water-worlds” around M-dwarfs cannot correspond to a distinct population, their bulk density and equilibrium temperature can be interpreted by several different internal structures and compositions. The continuity in the fraction of volatiles in these planets suggests a formation scenario involving planetesimal or hybrid pebble-planetesimal accretion. Moreover, we find that the transition between super-Earths and sub-Neptunes appears to happen at different masses (and radii) depending on the spectral type of the star. The maximum mass of super-Earths seems to be close to 10 M⊕ for all spectral types, but the minimum mass of sub-Neptunes increases with the star’s mass, and is around 1.9 M⊕, 3.4 M⊕, and 4.3 M⊕, for M-dwarfs, K-dwarfs, and FG-dwarfs, respectively. The precise value of this minimum mass may be affected by observational bias, but the trend appears to be reliable. This effect, attributed to planet migration, also contributes to the fading of the radius valley for M-planets compared to FGK-planets. While sub-Neptunes are less common around M-dwarfs, smaller ones (1.8 Re < Rp < 2.8 R⊕) exhibit lower density than their equivalents around FGK-dwarfs. Nonetheless, the sample of well-characterized small exoplanets remains limited, and each new discovery has the potential to reshape our understanding and interpretations of this population in the context of internal structure, composition, formation, and evolution models. Broader consensus is also needed for internal structure models and atmospheric compositions to enhance density interpretation and observable predictions for the atmospheres of these exoplanets.

Optimizing credit card fraud detection: a deep learning approach to imbalanced datasets

Imbalanced datasets pose a significant challenge in credit card fraud detection, hindering the training effectiveness of models due to the scarcity of fraudulent cases. This study addresses the critical problem of data imbalance through an in-depth exploration of techniques, including cross-entropy loss minimization, weighted optimization, and synthetic minority oversampling technique-based resampling, coupled with deep neural networks (DNNs). The urgent need to combat class imbalances in credit card fraud datasets is underscored, emphasizing the creation of reliable detection models. The research method delves into the application of DNNs, strategically optimizing and resampling the dataset to enhance model performance. The study employs a dataset from October 2018, containing 284,807 transactions, with a mere 492 classified as fraudulent. Various resampling techniques, such as undersampling and SMOTE oversampling, are evaluated alongside weighted optimization. The results showcase the effectiveness of SMOTE oversampling, achieving an accuracy of 99.83% without any false negatives. The study concludes by advocating for flexible strategies, integrating cutting-edge machine learning methods, and developing adaptive defenses to safeguard against emerging financial risks in credit card fraud detection.

Enhancing flood mapping through ensemble machine learning in the Gamasyab watershed, Western Iran.

Floods are among the natural hazards that have seen a rapid increase in frequency in recent decades. The damage caused by floods, including human and financial losses, poses a serious threat to human life. This study evaluates two machine learning (ML) techniques for flood susceptibility mapping (FSM) in the Gamasyab watershed in Iran. We utilized random forest (RF), support vector machine (SVM), ensemble models, and a geographic information system (GIS) to predict FSM. The application of these models involved 10 effective factors in flooding, as well as 82 flood locations integrated into the GIS. The SVM and RF models were trained and tested, followed by the implementation of resampling techniques (RT) using bootstrap and subsampling methods in three repetitions. The results highlighted the importance of elevation, slope, and precipitation as primary factors influencing flood occurrence. Additionally, the ensemble model outperformed both the RF and SVM models, achieving an area under the curve (AUC) of 0.9, a correlation coefficient (COR) of 0.79, a true skill statistic (TSS) of 0.83, and a standard deviation (SD) of 0.71 in the test phase. The tested models were adapted to available input data to map the FSM across the study watershed. These findings underscore the potential of integrating an ensemble model with GIS as an effective tool for flood susceptibility mapping.