Synthetic Minority Oversampling Technique Research Articles

Analysis of ensemble machine learning classification comparison on the skin cancer MNIST dataset

This study aims to analyze the performance of various ensemble machine learning methods, such as Adaboost, Bagging, and Stacking, in the context of skin cancer classification using the skin cancer MNIST dataset. We also evaluate the impact of handling dataset imbalance on the classification model’s performance by applying imbalanced data methods such as random under sampling (RUS), random over sampling (ROS), synthetic minority over-sampling technique (SMOTE), and synthetic minority over-sampling technique with edited nearest neighbor (SMOTEENN). The research findings indicate that Adaboost is effective in addressing data imbalance, while imbalanced data methods can significantly improve accuracy. However, the selection of imbalanced data methods should be carefully tailored to the dataset characteristics and clinical objectives. In conclusion, addressing data imbalance can enhance skin cancer classification accuracy, with Adaboost being an exception that shows a decrease in accuracy after applying imbalanced data methods.

Predicting Online Gaming Behavior: A Comparative Analysis of Random Forest and Gaussian Naive Bayes Models

With the rising impact and economic benefits of the online gaming industry, online gaming companies need to understand players’ behavior to evaluate their products better and adjust their developing strategy. This paper uses machine learning models to predict players’ online gaming behaviors. The study utilizes the dataset from Kaggle, which contains 40,034 samples with 13 features related to player demographics, game preferences, and gameplay behaviors. The primary objective is to classify two target variables: ‘EngagementLevel’ and ‘InGamePurchases.’ Data preprocessing steps included handling missing values, encoding categorical features, normalizing numerical data, and addressing class imbalances using the Synthetic Minority Over-sampling Technique (SMOTE). The Random Forests (RF) and Gaussian Naïve Bayes (GNB) models were employed to predict the target variables. The RF model significantly outperformed the GNB model in both classification tasks, especially when predicting the in-game purchases. The RF model’s robustness is attributed to its ability to handle complex, non-linear relationships and interactions between features, while the GNB model’s performance was limited by its assumptions of feature independence and normally distributed data. The findings suggest that RF is a more effective tool for predicting online gaming behaviors, particularly in scenarios with complex feature interactions. Future research could incorporate additional machine learning models and more diverse datasets to further enhance predictive accuracy and offer a more comprehensive understanding of online gaming behaviors.

Leveraging Explainable Artificial Intelligence (XAI) for Expert Interpretability in Predicting Rapid Kidney Enlargement Risks in Autosomal Dominant Polycystic Kidney Disease (ADPKD)

Autosomal dominant polycystic kidney disease (ADPKD) is the predominant hereditary factor leading to end-stage renal disease (ESRD) worldwide, affecting individuals across all races with a prevalence of 1 in 400 to 1 in 1000. The disease presents significant challenges in management, particularly with limited options for slowing cyst progression, as well as the use of tolvaptan being restricted to high-risk patients due to potential liver injury. However, determining high-risk status typically requires magnetic resonance imaging (MRI) to calculate total kidney volume (TKV), a time-consuming process demanding specialized expertise. Motivated by these challenges, this study proposes alternative methods for high-risk categorization that do not rely on TKV data. Utilizing historical patient data, we aim to predict rapid kidney enlargement in ADPKD patients to support clinical decision-making. We applied seven machine learning algorithms—Random Forest, Logistic Regression, Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), Gradient Boosting Tree, XGBoost, and Deep Neural Network (DNN)—to data from the Polycystic Kidney Disease Outcomes Consortium (PKDOC) database. The XGBoost model, combined with the Synthetic Minority Oversampling Technique (SMOTE), yielded the best performance. We also leveraged explainable artificial intelligence (XAI) techniques, specifically Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP), to visualize and clarify the model’s predictions. Furthermore, we generated text summaries to enhance interpretability. To evaluate the effectiveness of our approach, we proposed new metrics to assess explainability and conducted a survey with 27 doctors to compare models with and without XAI techniques. The results indicated that incorporating XAI and textual summaries significantly improved expert explainability and increased confidence in the model’s ability to support treatment decisions for ADPKD patients.

Deep learning-based high-frequency jump test for detecting stock market manipulation: evidence from China’s securities market

PurposeThis study aims to tackle the critical issue of detecting stock market manipulation, which undermines the integrity and stability of financial markets globally. Even enhanced with machine learning, traditional statistical methods often struggle to analyze high-frequency trading data effectively due to inherent noise and the limited availability of publicly known manipulation cases. This leads to poor model generalization and a tendency toward over-fitting. Focusing on China's securities market, our study introduces an innovative approach that employs deep learning-based high-frequency jump tests to overcome these challenges and to develop a more effective method for identifying manipulative activities.Design/methodology/approachWe employed the “Jump Variation – Time-of-Day” (JV-TOD) non-parametric technique for jump tests on high-frequency data, coupled with the synthetic minority over-sampling technique (SMOTE) algorithm for re-balancing sample data. Our approach trains a deep neural network (DNN) on refined data to enhance its ability to identify manipulation patterns accurately.FindingsOur results show that the deep neural network model, calibrated with high-frequency price jump data, identifies manipulation behavior more specifically and accurately than traditional models. The model achieved an accuracy rate of 94.64%, an F1-score of 95.26% and a recall rate of 95.88%, significantly outperforming traditional models. These results demonstrate the effectiveness of our approach in mitigating over-fitting and improving the robustness of market manipulation detection.Practical implicationsThe proposed model provides regulatory entities and financial institutions with a more efficient tool to monitor and counteract market manipulation, thereby improving market fairness and investor protection.Originality/valueBy integrating the JV-TOD jump test with deep learning, this study proposed a new approach to market manipulation detection. The innovation is in its capacity to detect subtle manipulation signals that traditional methods typically overlook. Our model, which is trained on jump test data enhanced by the SMOTE algorithm, excels at learning complex manipulation patterns. This enhances both detection accuracy and robustness. In contrast to existing methods that are challenged by the noisy and intricate nature of high-frequency data, our approach shows enhanced performance in identifying nuanced market manipulations, offering a more effective and reliable method for detecting market manipulation.

Ppulsed field ablation and ultra-high-density mapping for PVI: use of machine learning and data augmentation to guide procedure and identify recurrent tachycardia mechanisms at one-year follow-up

Abstract Background In managing atrial fibrillation (AF), radiofrequency and cryoablation have been cornerstone techniques for achieving pulmonary vein isolation (PVI). Recently, pulsed-field ablation (PFA) has introduced a novel method for PVI. There remains a gap in knowledge regarding the permanent efficacy of ablation, related explicitly to acute lesion characteristics following PVI. Purpose Our study delves into an in-depth examination of acute lesion characteristics following PFA-PVI through ultra-high-density mapping (UHDM). We aim to identify specific clinical, anatomical, and periprocedural lesion features independently related to 1) intraoperative identification of UHDM non-isolated gaps with electrical conduction after first isolation and 2) three months follow-up recurrency of specific arrhythmias. Methods Results The present study includes 204 patients submitted to PFA-PVI for AF. UHDM guided all procedures to identify non-isolated gaps with electrical conduction. Perioperative and 3-month follow-up data were collected prospectively and analyzed. To build our prediction model, avoiding biases related to the unbalanced nature of the data, data augmentation was performed with SMOTE (Synthetic Minority Over-sampling Technique). Two machine learning (ML) models have been built, using logistic regression as learner, to predict the presence of isolation gaps identified by UHDM and follow-up recurrence of arrhythmias. A 20-fold cross-validation has been performed to train and test the models. The non-isolated gap was detected and immediately corrected in 14 (6.9%) patients and was present more often in patients with larger left atria (LA) (p<0.0001) and those with persistent AF (p=0.02). The ML model achieved an AUC of 0.88 in the prediction of the non-isolated gap after PFA (Precision: 0.65; Sens.: 0.90; F1: 0.76; Spec.: 0.83; NPV: 0.96). At three months follow-up, no patient experienced recurrent AF; recurrent roof-dependent atrial tachycardia was present in 10 (4.9%). Patients with recurrent atrial tachycardia had a significantly narrower remaining atrial-roof conduction bridge (p=0.01) identified intra-procedurally by UHDM, significantly larger LA (p=0.03), and non-significant trend for older age (p=0.07). The ML model achieved an AUC of 0.86, predicting recurrent tachycardia after PFA (Precision: 0.63; Sens.: 0.86; F1: 0.72; Spec.: 0.82; NPV: 0.94). Conclusions Consistent use of UHDM can help identify non-isolated gaps with electrical conduction that may occur even after PVI with updated technologies, such as PFA. Non-isolated gaps should be expected, particularly in patients with larger LA, where UHDM could be of particular use. Moreover, UHDM can help predict the eventual recurrence of arrhythmias. Again, LA size plays an essential role in such recurrencies, together with the size of the remaining conducting tissue "bridges" within the LA roof, measure by UHDM.

Machine learning to improve the understanding of rabies epidemiology in low surveillance settings

In low and middle-income countries, a large proportion of animal rabies investigations end without a conclusive diagnosis leading to epidemiologic interpretations informed by clinical, rather than laboratory data. We compared Extreme Gradient Boosting (XGB) with Logistic Regression (LR) for their ability to estimate the probability of rabies in animals investigated as part of an Integrated Bite Case Management program (IBCM). To balance our training data, we used Random Oversampling (ROS) and Synthetic Minority Oversampling Technique. We developed a risk stratification framework based on predicted rabies probabilities. XGB performed better at predicting rabies cases than LR. Oversampling strategies enhanced the model sensitivity making them the preferred technique to predict rare events like rabies in a biting animal. XGB-ROS classified most of the confirmed rabies cases and only a small proportion of non-cases as either high (confirmed cases = 85.2%, non-cases = 0.01%) or moderate (confirmed cases = 8.4%, non-cases = 4.0%) risk. Model-based risk stratification led to a 3.2-fold increase in epidemiologically useful data compared to a routine surveillance strategy using IBCM case definitions. Our study demonstrates the application of machine learning to strengthen zoonotic disease surveillance under resource-limited settings.

Towards the Development of the Clinical Decision Support System for the Identification of Respiration Diseases via Lung Sound Classification Using 1D-CNN

Respiratory disorders are commonly regarded as complex disorders to diagnose due to their multi-factorial nature, encompassing the interplay between hereditary variables, comorbidities, environmental exposures, and therapies, among other contributing factors. This study presents a Clinical Decision Support System (CDSS) for the early detection of respiratory disorders using a one-dimensional convolutional neural network (1D-CNN) model. The ICBHI 2017 Breathing Sound Database, which contains samples of different breathing sounds, was used in this research. During pre-processing, audio clips were resampled to a uniform rate, and breathing cycles were segmented into individual instances of the lung sound. A One-Dimensional Convolutional Neural Network (1D-CNN) consisting of convolutional layers, max pooling layers, dropout layers, and fully connected layers, was designed to classify the processed clips into four categories: normal, crackles, wheezes, and combined crackles and wheezes. To address class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied to the training data. Hyperparameters were optimized using grid search with k−fold cross-validation. The model achieved an overall accuracy of 0.95, outperforming state-of-the-art methods. Particularly, the normal and crackles categories attained the highest F1-scores of 0.97 and 0.95, respectively. The model’s robustness was further validated through 5−fold and 10−fold cross-validation experiments. This research highlighted an essential aspect of diagnosing lung sounds through artificial intelligence and utilized the 1D-CNN to classify lung sounds accurately. The proposed advancement of technology shall enable medical care practitioners to diagnose lung disorders in an improved manner, leading to better patient care.

Ensemble of hybrid model based technique for early detecting of depression based on SVM and neural networks

The prevalence of depression has increased dramatically over the last several decades: it is frequently overlooked and can have a significant impact on both physical and mental health. Therefore, it is crucial to develop an automated detection system that can instantly identify whether a person is depressed. Currently, machine learning (ML) and artificial neural networks (ANNs) are among the most promising approaches for developing automated computer-based systems to predict several mental health issues, such as depression. This study propose an ensemble of hybrid model-based techniques that aims to build a strong detection model that considers many psychological and sociodemographic characteristics of an individual to detect whether a person is depressed. Support vector machines (SVM) and multilayer perceptrons (MLP) are the two fundamental methods used to construct the suggested ensemble approach. The hybrid DeprMVM served as a meta-learner. In this study, the hybrid DeprMVM is a level-1 learner, whereas the SVM and MLP networks are level-0 learners. After the classifiers are trained and tested at level 0, their outputs are based on both the independent and dependent variables in the new data set that was used to train the meta-classifier. The training data class imbalance was reduced by applying the synthetic minority oversampling technique (SMOTE) and cluster sampling together, which improved the accuracy for detecting depression. Additionally, it can effectively reduce the risk of over-fitting from simply duplicating data points. To further confirm the effectiveness of the proposed method, various performance evaluation metrics were calculated and compared with previous studies conducted on this specific dataset. In conclusion, among all the techniques for identifying depression, the suggested ensemble approach had the best accuracy, at 99.39%, and an F1-score of 99.51%.

Enhancing Machine Learning Models Through PCA, SMOTE-ENN, and Stochastic Weighted Averaging

Predicting survival outcomes in critical accidents has been a focal point in machine learning research. This study addresses several limitations of existing methods, including insufficient management of data imbalance, lack of emphasis on hyperparameter tuning, and proneness to overfitting. Many existing models struggle to generalize effectively on imbalanced datasets or depend on default hyperparameter settings, resulting in biased predictions. By integrating Principal Component Analysis (PCA), hyperparameter optimization, and resampling methods, as well as combining Edited Nearest Neighbors (ENN) with the Synthetic Minority Oversampling Technique (SMOTE), the model significantly improves predictive accuracy and model generalization. An ensemble model combining seven machine learning algorithms—Logistic Regression, Support Vector Machine, KNN, Random Forest, XGBoost, LightGBM, and CatBoost—was applied to predict survival outcomes. Stochastic Weighted Averaging (SWA) was applied to mitigate overfitting and enhance generalization. The accuracy increased from 91.97% to 94.89% after SWA was applied in this specific scenario. The combination of PCA-based dimensionality reduction, hyperparameter tuning, and resampling techniques (ENN + SMOTE) ensured the model handled data imbalance and optimized predictive accuracy. The final model demonstrated excellent performance, with Area Under the Curve (AUC) and Average Precision (AP) values both reaching 0.98, indicating high accuracy and precision. These improvements were validated using the Titanic dataset in a binary classification problem of predicting passenger survival. The results emphasize that ensemble learning, enhanced by SWA, offers a powerful framework for handling imbalanced and complex datasets, providing significant advancements in predictive modeling accuracy. This study provides insights into how machine learning techniques can be effectively combined to solve classification challenges in real-world scenarios.

Machine Learning Approach for Rock Mass Classification with Imbalanced Database of TBM Tunnelling in Himalayan Geology

AbstractThe geological condition of the Himalayan region is very complex and challenging. So far, empirical and analytical approaches for rock mass characterization have been a common practice in the Himalayas. Due to the limitations of input parameters and governing equations in design practices, rock mass characterization in tunnel boring machine (TBM) excavated tunnels is crucial. This research introduces robust machine learning (ML) approaches to predict rock mass quality conditions in complex geological environments, leveraging a large database of TBM parameters and rock mass rating (RMR) values. To do so, a total of 6879 stable phase TBM cycle data were collected from 12 km long tunnel in Nepal. The pre-processed parameters were randomly split into a training set (80%) and a testing set (20%). Seven individual classifiers consisting of logistic regression (LR), support vector machine (SVM), decision tree (DT), random forest (RF), k-nearest neighbor (KNN), extreme gradient boosting (XGBoost), and bagging, and stacking ensemble classifier were exploited with optimal hyperparameters. The comprehensive assessment carried out has shown that the ensemble classifier gave highest overall accuracy as compared to other individual classifiers. More importantly, the synthetic minority over-sampling technique (SMOTE) performs better to handle the imbalanced database, while the RF and stacking classifier demonstrated the best prediction performance with accuracy of 92%. Moreover, for the minority rock mass class, the RF shows better performance compared to stacking classifier. The authors emphasize that the effective application of ML-based data-driven approach shows substantial potential for rock mass characterization in TBM tunnelling.

An Improved Design for a Cloud Intrusion Detection System Using Hybrid Features Selection Approach with ML Classifier

The rapid adoption of cloud computing has introduced new security concerns, particularly regarding data privacy and protection from sophisticated cyberattacks. Intrusion Detection Systems (IDSs) based on Machine Learning (ML) offer improved detection of malicious behaviour in network traffic. However, existing IDS solutions struggle with large-dimensional data and imbalanced datasets, resulting in higher false positive rates (FPR) and reduced detection rates (DR). In this paper, we propose an improved Cloud IDS leveraging a hybrid features selection approach using Information Gain (IG), Chi-square (CS), and Particle Swarm Optimization (PSO). To address the challenge of imbalanced datasets, the Synthetic Minority Over-sampling Technique (SMOTE) is employed. The Random Forest (RF) classifier is used to detect and classify attacks. The system is evaluated on the UNSW-NB15 and Kyoto datasets, achieving accuracies of over 98% and 99%, respectively, outperforming other methods in terms of detection accuracy.

An advancement in AdaSyn for imbalanced learning: An application to fraud detection in digital transactions

Imbalanced Learning is a significant issue in machine learning, affecting the performance and accuracy of binary or multi-classification algorithms, especially in large-scale data handling and classification. There are some popular techniques to covert this imbalanced data into a balanced one such as undersampling, under-sampling with tomek links, randomized oversampling, synthetic minority oversampling technique (SMOTE), and adaptive synthetic generation (ADASYN). Generally, the ADASYN algorithm could be used to propagate minority sample points to rise the imbalanced ratio between majority and minority sample points, but in some cases, it may conflict with decision boundary points and noisy points. This paper proposed a Refitted AdaSyn Algorithm (RAA) with Gaussian Distribution (GD). So that new minority samples are distributed much closer to the center of the minority sample to spotlight the conflicts. The classification accuracy has improved with RAA over formal ADASYN. For examining the proposed work the imbalanced benchmark datasets like European, Banksim, Paymentcard, and UCI credit card are considered. Vanilla Generative Adversarial Network (GAN) is a deep learning model used to classify fraud and non-fraud transactions, demonstrating significant differences between balanced and imbalanced learning approaches and achieving an accuracy of 97.5% on dataset DS4.

Precipitation Retrieval from FY-3G/MWRI-RM Based on SMOTE-LGBM

Using the FY-3G/MWRI-RM observations, this paper proposes a precipitation retrieval method that combines the Synthetic Minority Over-sampling Technique with Light Gradient Boosting Machine (SMOTE-LGBM) and analyzes the impact of MWRI-RM channel settings on precipitation retrieval. The SMOTE-LGBM-based model consists of two LGBM models for precipitation identification and estimation, respectively. The SMOTE method is used to address the imbalance between precipitation and non-precipitation samples. Using the Integrated Multi-Satellite Retrievals for the Global Precipitation Measurement (IMERG) product as a reference, we validate the retrieved precipitation by the SMOTE-LGBM-based model with an independent testing dataset. The critical success indexes are 0.483 and 0.526, and the Pearson correlation coefficients are 0.611 and 0.645 for the ocean and land regions, respectively. The spatial distributions of the retrieved and IMERG accumulated precipitation in the testing dataset are similar. In addition, we visualize and analyze the cases of Meiyu and two typhoons. The results indicate that the SMOTE-LGBM-based model effectively represents the spatial distribution characteristics of precipitation and achieves high agreement with IMERG precipitation products. Overall, the SMOTE-LGBM-based model successfully retrieves precipitation from MWRI-RM and provides accurate precipitation products for FY-3G/MWRI-RM for the first time.

PRO-SMOTEBoost: An adaptive SMOTEBoost probabilistic algorithm for rebalancing and improving imbalanced data classification

In the field of data mining and machine learning, dealing with imbalanced datasets is one of the most complex problems. The class imbalance issue significantly affects the classification of minority classes when using common classification algorithms. These algorithms often prioritize improving the performance of the majority class at the expense of the minority class, leading to misclassifying negative instances as positive ones. To address this problem, the Synthetic Minority Over-sampling Technique (SMOTE) has gained popularity to rebalance imbalanced data for classification. However, in this paper, we propose two algorithms to enhance the performance of imbalanced classification further. The first algorithm is PRO-SMOTE, an improvement over SMOTE. PRO-SMOTE relies on conditional probabilities to effectively rebalance imbalanced classes and improve the predictive performance metrics satisfactorily and reliably. By considering conditional probabilities, PRO-SMOTE can reduce the majority classes and optimally increase the minority class. Second, the PRO-SMOTEBoost algorithm, in turn, is based on the PRO-SMOTE to overcome classification anomalies and problems encountered by machine learning algorithms during classification, especially the weak ones. PRO-SMOTEBoost aims to maximize predictive precision to the greatest extent possible by combining the strengths of PRO-SMOTE with boosting techniques. Evaluating these algorithms using traditional machine learning algorithms such as Random Forests, C4.5, Naive Bayes, and Support Vector Machines has demonstrated excellent classification results. The performance metrics, encompassing F1-score, G-means, Precision, Accuracy, Recall, AUC-ROC, and Precision-Recall-curves, achieved by the proposed algorithm demonstrate a range that extends from over 90% to a flawless score of 100%. Compared to using these traditional algorithms individually, the utilization of PRO-SMOTEBoost has shown a significant improvement of 10% to 40% in performance metrics. Overall, the proposed algorithms, PRO-SMOTE and PRO-SMOTEBoost, offer effective solutions to address the challenges posed by imbalanced datasets. They provide improved predictive metrics and demonstrate their superiority when compared to traditional even modern machine learning algorithms.

Comparative Analysis of Machine Learning Models for Predicting Student Success in Online Programming Courses: A Study Based on LMS Data and External Factors

Early prediction of student performance in online programming courses is essential for implementing timely interventions to enhance academic outcomes. This study aimed to predict academic success by comparing four machine learning models: Logistic Regression, Random Forest, Support Vector Machine (SVM), and Neural Network (Multilayer Perceptron, MLP). We analyzed data from the Moodle Learning Management System (LMS) and external factors of 591 students enrolled in online object-oriented programming courses at the Universidad Estatal de Milagro (UNEMI) between 2022 and 2023. The data were preprocessed to address class imbalance using the synthetic minority oversampling technique (SMOTE), and relevant features were selected based on Random Forest importance rankings. The models were trained and optimized using Grid Search with cross-validation. Logistic Regression achieved the highest Area Under the Receiver Operating Characteristic Curve (AUC-ROC) on the test set (0.9354), indicating strong generalization capability. SVM and Neural Network models performed adequately but were slightly outperformed by the simpler models. These findings suggest that integrating LMS data with external factors enhances early prediction of student success. Logistic Regression is a practical and interpretable tool for educational institutions to identify at-risk students, and to implement personalized interventions.

Machine learning‐aided process design using limited experimental data: A microwave‐assisted ammonia synthesis case study

AbstractAn open research question lies in how machine learning (ML) can accelerate the design optimization of chemical processes which are at very early experimental development stage with limited data availability. As an example, this article investigates the design of an intensified microwave‐assisted ammonia production reactor with 46 experimental data. We present an integrated approach of neural networks and synthetic minority oversampling technique to quantify the nonlinear input‐output relationships of this process. For ammonia concentration predictions at discrete operating conditions, the approach demonstrates 96.1% average accuracy over other ML methods (e.g., support vector regression 84.2%). The approach has also been applied for continuous optimization, identifying the optimal synthesis conditions at 597.37 K, 0.55MPa with feed flow rate of 1.67 ×10−3 m3/s kg and hydrogen to nitrogen ratio of 1 which is consistent with experimental observations. The data‐driven model enables to integrate this reactor with existing ammonia production infrastructure and benchmark with conventional techniques.

Leveraging survival analysis in cost-aware deepnet for efficient hard drive failure prediction

AbstractMany real-world datasets, such as those used for failure and anomaly detection, are severely imbalanced, with a relatively small number of failed instances compared to the number of normal instances. To address these issues, this paper leverages the Backblaze hard disk drives (HDDs) data and makes several contributions to hard drive failure prediction. This research explores 1D convolutional neural networks (CNN) to utilize the sequential nature of hard drive sensor data. The performance of 1D CNN models is compared to traditional machine learning (ML) algorithms, such as the synthetic minority over-sampling technique (SMOTE) and weighted logistic regression (WLR), demonstrating superior results, suggesting the potential effectiveness of the proposed approaches. In addition to these efforts, this paper aims to provide a comprehensive understanding of hard drive longevity and the critical factors contributing to their eventual failure through survival analysis. The 1D CNN models employ weighted binary cross-entropy (WCE) loss and modified focal loss (MFL) functions to manage class imbalanced issues commonly observed in hard drive data. The findings suggest that 1D CNN models outperform traditional ML models, with regularization techniques like dropout and early stopping proving effective in controlling overfitting. Notably, the 1D CNN model with WCE loss demonstrated the best overall performance with a $$G_{mean}$$ G mean of 0.692, successfully maximizing the FDR without increasing the FAR. In parallel, the research also employs Cox regression to identify key SMART parameters influencing drive failure. The high concordance index (c-index) of the Cox model (0.958) adds confidence to the insights derived. The research thus sets a solid groundwork for data center management strategies, with a future focus on practical implementation and evaluation of these findings.

Application of Dual-Tree Complex Wavelet Transform in Islanding Detection for a Hybrid AC/DC Microgrid with Multiple Distributed Generators

This paper presents the design and validation of a novel adaptive islanding detection method (AIDM) for a hybrid AC/DC microgrid network using a combination of Artificial Intelligence (AI) and Signal Processing (SP) approaches. The proposed AIDM is aimed to detect and discriminate between the different fault/disturbance conditions that result in islanding and/or non-islanding conditions in a hybrid microgrid. For the islanding and non-islanding conditions detection by the AIDM, firstly, fault/disturbance signals are obtained from a test microgrid. Secondly, these signals are decomposed using Dual-Tree Complex Wavelet Transform. Thirdly, a Synthetic Minority Oversampling Technique (SMOTE) is applied for data preprocessing to increase the accuracy of the classifier. Finally, an artificial neural network (ANN) is used as the classifier for training and testing the proposed AIDM for different microgrid configurations and event scenarios. The proposed method is tested with different data categories from three different microgrid test systems with different scenarios. All modeling and simulations are executed in MATLAB Simulink Version 2023a. Results indicate that the proposed scheme could detect and discriminate between islanding and non-islanding conditions accurately in terms of dependability, precision, and accuracy. An average accuracy of 99–100% could be achieved when tested and validated with microgrid networks adapted from IEEE 13-bus systems.

Unravelling incipient accidents: a machine learning prediction of incident risks in highway operations

PurposeSafety research has focused on drivers, pedestrians and vehicles, with scarce attention given to highway traffic officers (HTOs). This paper develops a robust prediction model which enables highway safety authorities to predict exclusive incidents occurring on the highway such as incursions and environmental hazards, respond effectively to diverse safety risk incident scenarios and aid in timely safety precautions to minimise HTO incidents.Design/methodology/approachUsing data from a highway incident database, a supervised machine learning method that employs three algorithms [namely Support Vector Machine (SVM), Random Forests (RF) and Naïve Bayes (NB)] was applied, and their performances were comparatively analysed. Three data balancing algorithms were also applied to handle the class imbalance challenge. A five-phase sequential method, which includes (1) data collection, (2) data pre-processing, (3) model selection, (4) data balancing and (5) model evaluation, was implemented.FindingsThe findings indicate that SVM with a polynomial kernel combined with the Synthetic Minority Over-sampling Technique (SMOTE) algorithm is the best model to predict the various incidents, and the Random Under-sampling (RU) algorithm was the most inefficient in improving model accuracy. Weather/visibility, age range and location were the most significant factors in predicting highway incidents.Originality/valueThis is the first study to develop a prediction model for HTOs and utilise an incident database solely dedicated to HTOs to forecast various incident outcomes in highway operations. The prediction model will provide evidence-based information to safety officers to train HTOs on impending risks predicted by the model thereby equipping workers with resilient shocks such as awareness, anticipation and flexibility.

Identifying Potential Natural Antibiotics from Unani Formulas through Machine Learning Approaches.

The Unani Tibb is a medical system of Greek descent that has undergone substantial dissemination since the 11th century and is currently prevalent in modern South and Central Asia, particularly in primary health care. The ingredients of Unani herbal medicines are primarily derived from plants. Our research aimed to address the pressing issues of antibiotic resistance, multi-drug resistance, and the emergence of superbugs by examining the molecular-level effects of Unani ingredients as potential new natural antibiotic candidates. We utilized a machine learning approach to tackle these challenges, employing decision trees, kernels, neural networks, and probability-based methods. We used 12 machine learning algorithms and several techniques for preprocessing data, such as Synthetic Minority Over-sampling Technique (SMOTE), Feature Selection, and Principal Component Analysis (PCA). To ensure that our model was optimal, we conducted grid-search tuning to tune all the hyperparameters of the machine learning models. The application of Multi-Layer Perceptron (MLP) with SMOTE pre-processing techniques resulted in an impressive accuracy precision and recall values. This analysis identified 20 important metabolites as essential components of the formula, which we predicted as natural antibiotics. In the final stage of our investigation, we verified our prediction by conducting a literature search for journal validation or by analyzing the structural similarity with known antibiotics using asymmetric similarity.