Enhancing the Effectiveness of Machine Learning-Based Phishing Email Detection via an Improved Pre-Processing Technique for Data Security

Musculoskeletal disorders (MSDs) are a major health concern for children. Traditional assessment methods, which are based on subjective assessments, may be inaccurate. The main objective of this research is to evaluate Synthetic Minority Over-sampling Technique(SMOTE)-based machine learning algorithms for predicting MSDs in elementary school students with an unbalanced dataset. This study is the first to use these algorithms to increase the accuracy of MSD prediction in this age group. This cross-sectional study was conducted in 2024 on 438 primary school students (boys and girls, grades 1 to 6) in Hamedan, Iran. Random sampling was performed from 12 public and private schools. The dependent variable was the presence or absence of MSD, assessed using the Cornell questionnaire. Given the imbalanced nature of the data, SMOTE-based techniques were applied. Finally, the performance of six machine learning algorithms, including Random Forest (RF), Naive Bayes (NB), Artificial Neural Network (ANN), Decision Tree (DT), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM) was compared based on five SMOTE family techniques, including SVM-SMOTE, SMOTE-NC, ADASYN, Borderline SMOTE, and the SMOTE method, for predicting musculoskeletal disorders in primary school students. This study analyzed 438 students, with 28 (6.39%) having musculoskeletal disorders (MSD). Machine learning models were tested on both imbalanced and SMOTE-balanced data. Before SMOTE, sensitivity was low (e.g., DT: 18%), but after applying SMOTE, it improved significantly (DT: 85%). Area Under the Curve (AUC) for RF and XGBoost increased from 65 to 99%. Among SMOTE-based techniques, SMOTE-NC achieved the highest accuracy for XGBoost (93.65%), RF (93.41%), ANN (92.80%), SVM (90.24%), and DT (86.58%). Borderline-SMOTE yielded the highest accuracy (96%) for XGBoost and RF. RF and XGBoost performed best overall. Key predictors of MSD were regional facilities, BMI, and gender. The findings of this study demonstrate the effectiveness of SMOTE in addressing class imbalance and improving the accuracy of MSD prediction among students. Overall, RF and XGBoost outperformed other algorithms. Additionally, key factors influencing MSD included regional facilities, body mass index (BMI), and gender, highlighting the significance of environmental and physiological factors in the development of this disorder.

Using supervised machine learning algorithms in pavement degradation monitoring

Every year, phishing results in losses of billions of dollars and is a major threat to the Internet economy. Phishing attacks are now most often carried out by email. To better comprehend the existing research trend of phishing email detection, several review studies have been performed. However, it is important to assess this issue from different perspectives. None of the surveys have ever comprehensively studied the use of Natural Language Processing (NLP) techniques for detection of phishing except one that shed light on the use of NLP techniques for classification and training purposes, while exploring a few alternatives. To bridge the gap, this study aims to systematically review and synthesise research on the use of NLP for detecting phishing emails. Based on specific predefined criteria, a total of 100 research articles published between 2006 and 2022 were identified and analysed. We study the key research areas in phishing email detection using NLP, machine learning algorithms used in phishing detection email, text features in phishing emails, datasets and resources that have been used in phishing emails, and the evaluation criteria. The findings include that the main research area in phishing detection studies is feature extraction and selection, followed by methods for classifying and optimizing the detection of phishing emails. Amongst the range of classification algorithms, support vector machines (SVMs) are heavily utilised for detecting phishing emails. The most frequently used NLP techniques are found to be TF-IDF and word embeddings. Furthermore, the most commonly used datasets for benchmarking phishing email detection methods is the Nazario phishing corpus. Also, Python is the most commonly used one for phishing email detection. It is expected that the findings of this paper can be helpful for the scientific community, especially in the field of NLP application in cybersecurity problems. This survey also is unique in the sense that it relates works to their openly available tools and resources. The analysis of the presented works revealed that not much work had been performed on Arabic language phishing emails using NLP techniques. Therefore, many open issues are associated with Arabic phishing email detection.

The classification of imbalanced datasets is a prominent task in text mining and machine learning. The number of samples in each class is not uniformly distributed; one class contains a large number of samples while the other has a small number. Overfitting of the model occurs as a result of imbalanced datasets, resulting in poor performance. In this study, we compare different oversampling techniques like synthetic minority oversampling technique (SMOTE), support vector machine SMOTE (SVM-SMOTE), Border-line SMOTE, K-means SMOTE, and adaptive synthetic (ADASYN) oversampling to address the issue of imbalanced datasets and enhance the performance of machine learning models. Preprocessing significantly enhances the quality of input data by reducing noise, redundant data, and unnecessary data. This enables the machines to identify crucial patterns that facilitate the extraction of significant and pertinent information from the preprocessed data. This study preprocesses the data using various top-level preprocessing steps. Furthermore, two imbalanced Twitter datasets are used to compare the performance of oversampling techniques with six machine learning models including random forest (RF), SVM, K-nearest neighbor (KNN), AdaBoost (ADA), logistic regression (LR), and decision tree (DT). In addition, the bag of words (BoW) and term frequency and inverse document frequency (TF-IDF) features extraction approaches are used to extract features from the tweets. The experiments indicate that SMOTE and ADASYN perform much better than other techniques thus providing higher accuracy. Additionally, overall results show that SVM with ’linear’ kernel tends to attain the highest accuracy and recall score of 99.67% and 1.00% on ADASYN oversampled datasets and 99.57% accuracy on SMOTE oversampled dataset with TF-IDF features. The SVM model using 10-fold cross-validation experiments achieved 97.40 mean accuracy with a 0.008 standard deviation. Our approach achieved 2.62% greater accuracy as compared to other current methods.

Gender-based violence can include sexual, physical, mental, and economic harm inflicted in public or in private. This violence also has a direct psychological effect, physical and financial consequences, and it has multiple underlying reasons, such as social, economic, cultural, political, and religious aspects. By applying multiple resampling techniques, this study aims to improve the precision and accuracy of supervised machine learning classifications of gender-based violence (GBV) using the SDHS dataset. The class imbalance between GBV-positive and GBV-negative instances makes it very challenging to produce reliable classification machine learning models. To address this issue, oversampling machine learning approaches, including synthetic minority over-sampling technique (SMOTE), adaptive synthetic (ADASYN), and random over-sampling (ROS), were employed to classify the GBV data in Somalia. The logistic regression (LR), decision tree (CART), random forest (RF), naïve Bayes (NB), k-nearest Neighbors (KNN), and support vector machine (SVM) methods were trained and evaluated. In addition, oversampling techniques were employed for improving the imbalanced datasets. Receiver operating characteristic curve (ROC) and the area under the curve (AUC) were used to assess each machine learning classifier and to compare performance on the original GBV dataset. Among the resampling techniques, SMOTE (RF = 0.992, CART = 0.969, and KNN = 0.957) outperformed ADASYN (RF = 0.912, CART = 0.910, and KNN = 0.876) and ROS (RF = 0.920, CART = 0.919, and KNN = 0.880) across almost all evaluation metrics. The classifiers that performed the best were random forest (RF) and classification and regression trees (CART), then k-nearest Neighbors. After resampling the imbalanced dataset, we may therefore conclude that the random forest (AUC = 0.972), CART (AUC = 0.969) and KNN (AUC = 0.957) machine learning classifiers are better at accurately classifying the k-nearest Neighbors dataset. In addition, compared to the other oversampling techniques, SMOTE was used to the machine learning classifiers to balance the imbalanced class distributions in favour of the minority class. In addition, SMOTE with the Mathews correlation coefficient (MCC) outperformed ADASYN and ROS resampling techniques. The MCC values for SMOTE reached their highest values (RF = 0.86, CART = 0.85, and KNN = 0.80), indicating strong overall predictive reliability of the machine learning models. Therefore, the findings of this analysis will assist government and non-government organizations in making policy decisions to GBV risks.

Selection and implementation of classification algorithms along with proper preprocessing methods are important for the accuracy of predictive models. This paper compares some well-known and frequently used algorithms for classification tasks and performs in depth analysis. In this study we analyzed four most frequently used algorithm viz random forest (RF), decision tree (DT), logistic regression (LR) and support vector machine (SVM). To conduct the study on the well-known Oxford Parkinson’s disease Detection dataset obtained from the UCI Machine Learning Repository. We evaluated the algorithms' performance using six distinct approaches. Firstly, we used the classifiers where we didn’t used any method to enhance the performance of the classifier. Secondly, we applied Principal Component Analysis (PCA) to minimize the dimensionality of the dataset. Thirdly, we used collinearity-based feature elimination (CFE) method where we applied correlation among the features and if the correlation between a pair of features exceeds the threshold of 0.9, we eliminated one from the pair. Fourthly, we adopt synthetic minority oversampling technique (SMOTE) to synthetically increase the instances of the minority class. Fifth, we combined PCA+SMOTE and on sixth method, we combined CFE + SMOTE. The study demonstrates that SVM is highly effective for Parkinson’s disease classification. SVM maintained high accuracy, precision, recall and F1-score across various preprocessing techniques including PCA, CFE and SMOTE, making it robust and reliable for clinical applications. RF showed improved results with SMOTE. However, it experienced reduced performance with PCA and CFE, indicating its dependence on original feature interactions. DT benefited from PCA, while LR showed limited improvements and sensitivity to oversampling. These findings emphasize the importance of selecting appropriate preprocessing techniques to enhance model performance.

The global cost of credit card fraud continues to rise, driven by the increasingly concentrated and sophisticated attacks. This situation underscores the necessity for more effective detection and prevention methods. In response to the growing need for better fraud detection and prevention, machine learning has witnessed significant advancements in recent years. This paper provides an overview and comparison of various models. On one hand, there are traditional supervised learning models, such as Logistic Regression, Decision Trees, and Support Vector Machines (SVM). On the other hand, ensemble methods like Random Forest, Gradient Boosting, and XGBoost are also covered. Given the highly imbalanced nature of credit card fraud datasets, the study also examines the impact of the Synthetic Minority Over-sampling Technique (SMOTE) on classification performance. While SMOTE has been shown to improve a models performance for weaker classifiers, its benefits for advanced ensemble methods remain less clear. Consequently, this paper will identify which models benefit most from oversampling and assess whether high-performing classifiers can mitigate the effects of imbalance without the need for data augmentation. When comparing the models performances, Random Forest and XGBoost demonstrated superior performance both with and without SMOTE. Without SMOTE, two models, Logistic Regression and SVM, yielded high accuracy but near-zero performance on key classification metrics, highlighting their inability to effectively detect minority class instances.

Sentiment analysis, a type of natural language processing (NLP) analyzes the text data to extract and identify subjective information including attitudes, opinions, and feelings. Sentiment analysis can be used to examine audience feedback and reviews in the context of multilingual product reviews. In this paper, a sentiment analysis model using machine learning approaches has been developed for multilingual product reviews in Roman Urdu or Sindhi to determine how the public feels about certain posts, products, etc. The importance of sentiment analysis for product context reviews in many languages in Roman is multifaceted. It can offer insightful information on the preferences of the likes and dislikes of the audience. To accomplish multilingual sentiment analysis, a dataset of reviews in Roman Urdu and Sindhi languages from diverse online platforms and social media sources like YouTube, Facebook, TikTok, Daraz, and Instagram was collected.To identify pertinent features essential for categorizing reviews into negative, positive, or neutral sentiments based on polarity, the Term Frequency Inverse Document Frequency (TF-IDF) method was used. For classification, five different machine learning classifiers including Linear Regression (LR), Naive Bayes (NB), Support Vector Machine (SVM), Random Forest (RF), and K-nearest neighbors (KNN) were used. The classification results were measured in terms of precision score, recall score, and F1-score. With TF-IDF, the SVM, and LR outperformed than other classifiers and obtained an F1-score of 0.77%, and 0.78%. To further improve the classification accuracy, the Synthetic Minority Over-sampling TEchnique (SMOTE) was used to manage the class imbalance problem. With SMOTE, the classification accuracy of LR and SVM was improved to 0.79% and 0.80%.

Postoperative pain is a frequent clinical concern following endodontic treatment. This study aimed to develop and validate supervised machine learning models to predict the occurrence of postoperative pain in cases of irreversible pulpitis. A prospective sample of 354 patients aged 18 to 60 years undergoing standardised endodontic treatment was analysed. In the original randomised clinical trials from which the data were derived, each patient had only one eligible tooth included. Clinical variables included postoperative pain at 24 and 72 h, treated tooth group, occlusal reduction, photobiomodulation therapy, use of non-steroidal anti-inflammatory drugs (NSAIDs), sex and age. Eight supervised machine learning algorithms were trained to predict pain occurrence, including Logistic Regression, Support Vector Machine, Gradient Boosting, Random Forest, Decision Tree, K-Nearest Neighbours, AdaBoost and Multilayer Perceptron. The dataset was divided into training (70%) and testing (30%) sets using stratified sampling. Class imbalance in the training set, characterised by a lower proportion of cases with moderate or severe pain, was addressed using the Synthetic Minority Oversampling Technique. Hyperparameters were optimised through grid search combined with stratified five-fold cross validation. Model performance was evaluated using the area under the curve (AUC), accuracy, precision, recall and F1-score, with 95% confidence intervals estimated by bootstrapping. The predictive models achieved good discrimination of pain outcomes. Logistic Regression showed the best test performance at 24 h (AUC 0.74 [95% CI: 0.61 to 0.85], precision 0.81 [95% CI: 0.73 to 0.88]). At 72 h, the Support Vector Machine achieved the highest performance (AUC 0.81 [95% CI: 0.69 to 0.92], precision 0.88 [95% CI: 0.79 to 0.94]). Age and sex emerged as the most influential predictors across models. Supervised machine learning models demonstrated promising performance for predicting postoperative pain following endodontic treatment. Logistic Regression and Support Vector Machine algorithms presented the most consistent results, supporting their potential clinical application for personalised pain management.

The internet, while offering extensive services and information, has also become a platform for malicious activities, particularly through harmful websites that threaten cybersecurity. Detecting and classifying these websites is crucial for protecting users from online threats. Traditional detection methods, primarily based on blacklists and signature-based techniques, struggle to match the pace with the dynamic evolving strategies of cybercriminals. Recent advancements in Machine Learning (ML) show promise, though they remain works in progress. This research addressed this challenge by exploring the usage of Natural Language Processing and Machine Learning techniques used to classify websites as benign or malicious. Unlike many existing studies that relied on URL features alone, this study incorporated a more comprehensive feature set, including URL, content, and additional web attributes, which enhanced classification accuracy. Using an imbalanced dataset skewed towards malicious sites, this study solved using SMOTE (Synthetic Minority Over-sampling Technique) the class imbalance problem, improving model performance. Utilized Hashing Vectorizer (HashingV) and TF-IDF (Term Frequency-Inverse Document Frequency), were adopted to transform textual features into their vector representations while PCA (Principal Component Analysis) and truncated Singular Value Decomposition (truncSVD), were then used to optimize feature representation across different dimensions. Five ML classifiers include Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbors (KNN), and Logistic Regression (LR) were tested for classification, and performance was evaluated using metrics such as precision and recall, accuracy, F1-Score. The results revealed that Random Forest classifier utilizing HashingV recorded the best results, with accuracies of 99.9563% using truncSVD and 99.9561% with PCA.

BackgroundWarfarin is a commonly prescribed anticoagulant, and its dosing requires careful monitoring. This study used machine learning-based models to predict optimal warfarin dosage and identify factors influencing the International Normalized Ratio (INR) status in patients with cardiovascular diseases (CVDs).MethodsThis study involved 490 patients with CVDs on warfarin therapy at a hospital. Data were collected from patient records and direct interviews using a questionnaire. The various machine learning (ML) algorithms, including Support Vector Machine (SVM), Multinomial Logistic Regression (MLR), Random Forest (RF), Decision Tree (DT), and Ensemble Models, predict the optimal warfarin dosage for patients. Data were balanced using the Synthetic Minority Over-sampling Technique (SMOTE) algorithm to address class imbalances, and model performance was evaluated using metrics such as Precision, F1 Score, Accuracy, and Area Under the ROC Curve (AUC), with all analyses performed in Python using Jupyter Notebook.ResultsAfter balancing the data using SMOTE, ML algorithms were evaluated, with RF and SVM achieving similar accuracy of 75.7% and AUC values of 94% for RF and 93% for SVM. The ensemble (RF, MLR) and ensemble (SVM, MLR, RF) models outperformed others, achieving an accuracy of 76.4%, sensitivity of 75.2%, specificity of 92.1%, and AUC values of 95% and 94%, respectively. The DT model showed the lowest performance with an accuracy of 67.8%, an AUC of 79%, and a precision of 69%. Feature importance analysis indicated that INR, BMI, and warfarin indications were the most influential factors in predicting warfarin dosage, while gender, amiodarone, and nationality had minimal impact.ConclusionEnsemble ML algorithms, particularly those combining RF and SVM, show strong potential for accurately predicting warfarin dosages in cardiovascular patients. Key predictors such as INR, BMI, and warfarin indication improved model accuracy, while less impactful factors included gender and amiodarone use, supporting RF-SVM ensembles as effective tools for personalized dosing.

Phishing is the most-used malicious attempt in which attackers, commonly via emails, impersonate trusted persons or entities to obtain private information from a victim. Even though phishing email attacks are a known cybercriminal strategy for decades, their usage has been expanded over last couple of years due to the COVID-19 pandemic, where attackers exploit people’s consternation to lure victims. Therefore, further research is needed in the phishing email detection field. Recent phishing email detection solutions that extract representational text-based features from the email’s body have proved to be an appropriate strategy to tackle these threats. This paper proposes a comparison approach for the combined usage of Natural Language Processing (TF-IDF, Word2Vec, and BERT) and Machine Learning (Random Forest, Decision Tree, Logistic Regression, Gradient Boosting Trees, and Naive Bayes) methods for phishing email detection. The evaluation was performed on two datasets, one balanced and one imbalanced, both of which were comprised of emails from the well-known Enron corpus and the most recent emails from the Nazario phishing corpus. The best combination in the balanced dataset proved to be the Word2Vec with the Random Forest algorithm, while in the imbalanced dataset the Word2Vec with the Logistic Regression algorithm.

Timely detection of breast cancer is crucial for improving patient outcomes. While machine learning (ML) models have shown promise in supporting diagnosis, there is still a need for frameworks that combine predictive accuracy with model interpretability and balanced evaluation. This study compares three widely used supervised ML algorithms, Support Vector Classifier (SVC), Random Forest, and XGBoost, using the Wisconsin Diagnostic Breast Cancer dataset. To address class imbalance, the dataset was balanced using the Synthetic Minority Oversampling Technique, and hyperparameter tuning was also performed through GridSearchCV. Each model was evaluated using accuracy, precision, recall, F1-score, and receiver operating characteristic area under the curve. XGBoost exhibited the best results, achieving 98.60% accuracy and perfect recall for malignant cases, which are crucial for reducing false negatives in clinical settings. Random Forest also demonstrated better results, while SVC showed slightly lower accuracy, but it still maintained balanced class-wise performance. Feature importance analysis was applied to these models to enhance clarity and highlight key diagnostic features. SVC could not generate feature importance output due to its kernel-based approach. This study presents a reproducible and interpretable ML-based framework for breast cancer classification. By integrating model optimization, class balancing, and explainability, the proposed approach provides a robust foundation for future clinical decision-support systems.

Analyzing user interface (UI) bugs is an important step taken by testers and developers to assess the usability of the software product. UI bug classification helps in understanding the nature and cause of software failures. Manually classifying thousands of bugs is an inefficient and tedious job for both testers and developers. Objective of this research is to develop a classification model for the User Interface (UI) related bugs using supervised Machine Learning (ML) algorithms and Natural Language Processing (NLP) techniques. Also, to assess the effect of different sampling and feature vectorization techniques on the performance of ML algorithms. Classification is based upon ‘Summary’ feature of the bug report and utilizes six classifiers i.e., Gaussian Naïve Bayes (GNB), Multinomial Naïve Bayes (MNB), Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF) and Gradient Boosting (GB). Dataset obtained is vectored using two vectorization techniques of NLP i.e., Bag of Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF). ML models are trained after vectorization and data balancing. The models ' hyperparameter tuning (HT) has also been done using the grid search approach to improve their efficacy. This work provides a comparative performance analysis of ML techniques using Accuracy, Precision, Recall and F1 Score. Performance results showed that a UI bug classification model can be built by training a tuned SVM classifier using TF-IDF and SMOTE (Synthetic Minority Oversampling Techniques). SVM classifier provided the highest performance measure with Accuracy: 0.88, Precision: 0.86, Recall: 0.85 and F1: 0.85. Result also inferred that the performance of ML algorithms with TF-IDF is better than BoW in most cases. This work provides classification of bugs that are related to only the user interface. Also, the effect of two different feature extraction techniques and sampling techniques on algorithms were analyzed, adding novelty to the research work.

Kerogen classification helps hydrocarbon explorers assess the ability of rocks to produce oil and natural gas. The traditional methods of Rock-eval pyrolysis and elemental analysis still rely on previous data interpretations and often possess inaccuracies. We propose using machine learning approaches to enhance the accuracy and speed of kerogen type classification in the Niger Delta Basin utilizing geochemical data. Geochemical properties such as S1, S2, S3, Tmax, HI, OI, TOC, and PI were derived from the analyzed oil and gas well samples. Various supervised machine learning algorithms such as Random Forest, Gradient Boosting, Support Vector Machines (SVM) and Decision Trees were used to assign kerogen to Types I to IV. Performance measures were determined by computing accuracy, precision, recall and the F1 score. Ensemble methods showed the highest levels of precision and reliability among all the algorithms. It was determined that Oxygen Index, S3 and Tmax played the central role in determining kerogen quality compared to other characteristics. The algorithms (Decision Tree, Random Forest, Gradient Boosting, Ada Boosting, Bagging and Extra Trees) showed comparable results in classification precision. Applying machine learning techniques substantially improves the accuracy and objectivity of kerogen classification and exploring ensemble methods produces geoscientific results that are much more precise when compared with those obtained using conventional methods. Subsequently, the author found that only three of the features showed nearly equal percent contributions. The three highest percentage contributions came from oxygen index (17.5%), carbon dioxide generated through pyrolysis (17.3%) and temperature (16.2%). This information has been added to the current knowledge available in the field of geosciences