Enhanced islanding detection using a hybrid machine learning approach

Vortex core detection remains an unsolved problem in the field of experimental and computational fluid dynamics. Available methods such as the Q, delta, and swirling strength criterion are based on a decomposed velocity gradient tensor but detect spurious vortices (false positives and false negatives), making these methods less robust. To overcome this, we propose a new hybrid machine learning approach in which we use a convolutional neural network to detect vortex regions within surface streamline plots and an additional deep neural network to detect vortex cores within identified vortex regions. Furthermore, we propose an automatic labeling approach based on K-means clustering to preprocess our input images. We show results for two classical test cases in fluid mechanics: the Taylor–Green vortex problem and two rotating blades. We show that our hybrid approach is up to 2.6 times faster than a pure deep neural network-based approach and furthermore show that our automatic K-means clustering labeling approach achieves within 0.45% mean square error of the more labour-intensive, manual labeling approach. At the same time, by using a sufficient number of samples, we show that we are able to reduce false positives and negatives entirely and thus show that our hybrid machine learning approach is a viable alternative to currently used vortex detection tools in fluid mechanics applications.

A chemistry-informed hybrid machine learning approach to predict metal adsorption onto mineral surfaces

Nowadays, smartphones seamlessly blend into every aspect of our lives, including as handheld assistants for individuals with disabilities. Therefore, this research addresses the need for a robust system that can classify Kazakh banknotes. By capitalizing on the availability of smartphones and the ability to integrate detectors with classifiers this study introduces classifiers of Kazakh banknote images specifically designed for banknotes ranging from 500 KZT to 20,000 KZT. It compares traditional and hybrid machine learning (ML) approaches, utilizing a dataset of diverse banknote images, aiming for both lightweight and high accuracy. Competitive performance is demonstrated by the traditional approach, enhanced by thoughtful feature engineering. The hybrid approach, utilizing features from a pre-trained ResNet-18 model, showcases remarkable accuracy and robustness. Evaluation metrics reveal significant achievements, with the traditional approach attaining 94.00% accuracy and the hybrid approach excelling at 99.11%. Model stacking, combining classifiers from both approaches, outperforms individual classifiers, achieving 95.00% and 99.55% accuracy for the traditional and hybrid ML approaches, respectively. Our methodology’s comparable outcome in classifying Thai banknotes and coffee beans roasting levels demonstrates their versatility in image classification tasks that rely on color differentiation, showcasing the potential beyond banknote recognition.

This study investigates the buckling behavior of columns with variable cross-sections using analytical, numerical, and hybrid machine learning (ML) approaches. Initially, the power series method is employed to calculate the buckling loads of columns with both constant and varying cross-sections under diverse boundary conditions. Then a finite element (FE) analyses of the columns are performed to obtain the buckling loads and the results are validate by comparing them with results from power series method. Once validated, the FE model is used to generate a large dataset encompassing a wide range of cross-sections, lengths, and material properties, as per the samples obtained through the Sobol sampling method. A hybrid ML model is then developed by integrating the XGBoost algorithm with the particle swarm optimization (PSO) technique for hyperparameter tuning. This hybrid PSO-XGBoost model is trained to predict the buckling loads of columns with varying cross-sections. Its performance for input parameters outside the training dataset is evaluated using statistical metrics and scatter plots. The results demonstrate excellent agreement between the FE analysis and the power series method, confirming the reliability of both approaches. The PSO-XGBoost model achieved remarkable predictive accuracy, with R 2 values of 0.999 and 0.996 for the training and testing datasets, respectively. Furthermore, SHapley Additive exPlanations (SHAP) analysis is conducted to explore the influence and interactions of input parameters on buckling loads, providing valuable insights into the model’s interpretability and the underlying mechanics of column buckling.

Automated anomaly detection in panoramic dental x-rays is a crucial step in streamlining post diagnosis treatment. It can reduce clinical time for a patient and also aid in giving them faster access to medical care. In this paper, we propose a hybrid deep learning and machine learning based approach to detect evident dental caries/periapical infection, altered periodontal bone height, and third molar impactions using panoramic dental radiographs. We use a Convolutional Neural Network as a feature extractor for an input image and use a Support Vector Machine to classify the image as either "Normal" or "Anomalous" based on the extracted features. We compare the performance of this model with the performance of a Convolutional Neural Network and a Support Vector Machine for the same classification task. We also compare our best model with other existing models trained to detect carries and periodontal bone loss. The results obtained with the hybrid deep learning and machine learning approach outperformed the existing methods in the literature.

At present, food products are designed by trial and error and the sensorial ratings are determined by a tasting panel. To expedite the development of new food products, a hybrid machine learning and mechanistic modeling approach is proposed. Sensorial ratings are predicted using a machine learning model trained with historical data for the food under consideration. The approach starts by identifying a set of food ingredient candidates and the key operating conditions in food processing based on heuristics, databases, etc. Food characteristics such as color, crispness, and flavors are related to these ingredients and processing conditions (which are design variables) using mechanistic models. The desired food characteristics are optimized by varying the design variables to obtain the highest sensorial ratings. To solve this gray-box optimization problem, a genetic algorithm is utilized where the design constraints (representing the desired food characteristics) are handled as penalty functions. A chocolate...

Diabetes mellitus is one of medical science’s most important research topics because of the disease’s severe consequences. High blood glucose levels characterize it. Early detection of diabetes is made possible by machine learning techniques with their intelligent capabilities to accurately predict diabetes and prevent its complications. Therefore, this study aims to find a machine learning approach that can more accurately predict diabetes. This study compares the performance of various classical machine learning models with the hybrid machine learning approach. The hybrid model includes the homogenous model, which comprises Random Forest, AdaBoost, XGBoost, Extra Trees, Gradient Booster, and the heterogeneous model that uses stacking ensemble methods. The stacking ensemble or stacked generalization approach is a meta-classifier in which multiple learners collaborate for prediction. The performance of the homogeneous hybrid models, Stacked Generalization and the classic machine learning methods such as Naive Bayes and Multilayer Perceptron, k-Nearest Neighbour, and support vector machine are compared. The experimental analysis using Pima Indians and the early-stage diabetes dataset demonstrates that the hybrid models achieve higher accuracy in diagnosing diabetes than the classical models. In the comparison of all the hybrid models, the heterogeneous model using the Stacked Generalization approach outperformed other models by achieving 83.9% and 98.5%. Doi: 10.28991/ESJ-2023-07-01-08 Full Text: PDF

<span lang="EN-US">The cirrhosis and cirrhosis-related problems are connected to the degree of fibrosis in the liver. The purpose of this paper is to propose an automated method for identifying liver fibrosis using ultrasound shear wave elastography (700) images that is based on a hybrid machine learning approach using a convolutional neural network (CNN) with two types of classifier (SoftMax and support vector machine (SVM)). The dataset gathered from hospitals is used in the training and testing phases of the model. The objective is to develop a hybrid machine learning model that can classify images based on their stage of fibrosis. The suggested system comprises three stages. The first is the preprocessing step, which starts with countor detection and continues with the "contrast limited adaptive histogram equalization (CLAHE)" technique to show the properties of liver tissue. In the second step, the CNN algorithm was utilized, which was based on several images to extract deep features and identify shear wave elastography (SWE) samples. In the third step, SVM and SoftMax functions are used to classify liver fibrosis. A five-class model (normal, F1, F2, F3, and F4) was developed. The result illustrates how successfully the CNN-SoftMax and CNN-SVM classifiers classified liver fibrosis in the test dataset, with 97.18% and 98.59% accuracy, respectively.</span>

Machine learning approaches have a valuable contribution in improving competency in automated decision systems. Several machine learning approaches have been developed in the past studies in individual disease diagnosis prediction. The present study aims to develop a hybrid machine learning approach for diagnosis predictions of multiple diseases based on the combination of efficient feature generation, selection, and classification methods. Specifically, the combination of latent semantic analysis, ranker search, and fuzzy-rough-k-nearest neighbor has been proposed and validated in the diagnosis prediction of the primary tumor, post-operative, breast cancer, lymphography, audiology, fertility, immunotherapy, and COVID-19, etc. The performance of the proposed approach is compared with single and other hybrid machine learning approaches in terms of accuracy, analysis time, precision, recall, F-measure, the area under ROC, and the Kappa coefficient. The proposed hybrid approach performs better than single and other hybrid approaches in the diagnosis prediction of each of the selected diseases. Precisely, the suggested approach achieved the maximum recognition accuracy of 99.12%of the primary tumor, 96.45%of breast cancer Wisconsin, 94.44%of cryotherapy, 93.81%of audiology, and significant improvement in the classification accuracy and other evaluation metrics in the recognition of the rest of the selected diseases. Besides, it handles the missing values in the dataset effectively.

Cryptocurrencies are defined as digital mediums of exchange, that use strong cryptography for securing the transactions and verifying the ownership of the coins. Blockchain operates in the background to guarantee the security, transparency and traceability of the transactions. Consequently, cryptocurrencies became more and more popular and established their considerable presence in financial sector. However, one of the major drawbacks in the cryptocurrency market is the unreliability and unpredictability of their values, that poses a major risk for any kind of investment. Predicting the price of cryptocurrencies is therefore a hot research domain today. This paper proposes a novel method to predict the prices, that is based on a hybrid machine learning and swarm intelligence approach. The results of the conducted experiments suggest that the proposed model obtains higher accuracy than other recent similar approaches, and that it can be successfully applied for this important task.

<div class="section abstract"><div class="htmlview paragraph">In recent years, diesel engine emissions regulations have been strengthened worldwide, necessitating the evaluation of regulatory values under transient conditions. Consequently, the need to assess transient states in the development of diesel engines has increased significantly. The evaluation using MBD (Model Based Development) is considered a promising method for achieving both low fuel consumption and simultaneous reduction of NOx and soot emissions. However, the mechanism of soot formation is complex, making it challenging to model mathematically directly. In this paper, hybrid machine learning approaches combining a physical model and a machine learning model are used to validate the prediction of soot emissions under transient conditions in a diesel engine with an EGR system. Various parameters such as fuel consumption and emissions predicted by the physical model are compared with measurements to validate the accuracy of the physical model. The prediction of soot emissions by the physical model is based on the Hiroyasu model. From these results, it is demonstrated that the physical model has sufficient accuracy to be used in hybrid machine learning approaches. However, it is shown that the physical model is inadequate as a prediction approach for soot emissions. Gaussian Process Regression (GPR), Support Vector Regression (SVR), Random Forest (RF), and Gradient Boosting Decision Tree (GBDT) are used to develop the machine learning models, and each model is trained on data under steady-state conditions. The prediction accuracy of each model and the physical model is compared and validated. The results show that the hybrid machine learning approaches have higher predictive accuracy than the physical model for soot emissions predictions in both steady-state and transient conditions. The GPR model with the highest prediction accuracy shows a test R<sup>2</sup> of 0.87 under steady-state conditions and relative errors with the measured values of less than 10% for both Non-load Transient Cycle (NRTC) and Low Load Cycle (LLC), which are engine test cycles.</div></div>

Ultra-high-performance concrete (UHPC) is a sustainable construction material; it can be applied as a substitute for cement concrete. Artificial intelligence methods have been used to evaluate concrete composites to reduce time and money in the construction industries. So, this study applied machine learning (ML) and hybrid ML approaches to predict the compressive and flexural strength of UHPC. A dataset of 626 compressive strength and 317 flexural strength data points was collected from the published research articles, where fourteen important variables were selected as input parameters for the analysis of hybrid ML and ML algorithms. This research used XGBoost, LightGBM, and hybrid XGBoost- LightGBM algorithms to predict UHPC materials. Grid search (GS) techniques were used to adjust model hyper-parameters in search of improved high accuracy and efficiency. ML and hybrid ML models were train, and the test stage utilized statistical assessments such as coefficient of determination (R-square), root mean square error (RMSE), mean absolute error (MAE), and coefficient of efficiency (CE). The results presented hybrid ML algorithm was superior to the XGBoost and LightGBM algorithms in terms of R-square and RMSE values for both compressive and flexural strength prediction. A hybrid ML model and two ML models showed CS considerable R-square values above 0.94 at the testing stages and just over 0.97 at the training phase. Hybrid ML model performance accuracy for CS prediction R-square value found that almost 0.996 for training and 0.963 for testing phases. At the same time, the FS prediction result showed that the R-square value of the Hybrid ML model and two traditional ML models were found at almost 0.95 for the training phase and around 0.81 for the testing phase. But among them, the hybrid XGB-LGB model prediction performance was high accuracy and lowest error for CS and FS of UHPC trained and its hyperparameters optimized. Additionally, the SHAP investigation reveals the impact and relationship of the input variables with the output variables. SHAP analysis outcome reveals that curing age and steel fiber content input parameter had the highest positive impact on compressive strength and flexural strength of UHPC.

Tropical Cyclones (TCs) are among the most impactful weather phenomena, with climate change intensifying their duration and strength, posing significant risks to ecosystems and human life. Accurate TC detection, encompassing localization and tracking of TC centers, has become a critical focus for the climate science community. Traditional methods often rely on subjective threshold tuning and might require several input variables, thus making the tracking computationally expensive. We propose a cost-effective hybrid Machine Learning (ML) approach consisting in splitting the TC detection into two separate sub-tasks: localization and tracking. The TC task localization is fully data-driven: multiple Deep Neural Networks (DNNs) architectures have been explored to localize TC centers using a different set of input fields related to the cyclo-genesis, aiming also at reducing the number of input drivers required for detection. A neighborhood matching algorithm is then applied to join previously localized TC center estimates into potential trajectories over time. We train the DNNs on 40 years of ERA5 reanalysis data and International Best Track Archive for Climate Stewardship (IBTrACS) records across the East and West North Pacific basins. The hybrid approach is then compared with four state-of-the-art deterministic trackers (namely OWZ, TRACK, CNRM and UZ), reporting comparable or even better results in terms of Probability of Detection and False Alarm Rate, additionally capturing the interannual variability and spatial distribution of TCs in the target domain. The resulting hybrid ML model represents the core component of a Digital Twin (DT) application implemented in the context of the EU-funded interTwin project.

The swift progression of technology has increased the complexity of cyber fraud, posing an escalating challenge for the banking sector to reliably and efficiently identify fraudulent credit card transactions. Conventional detection approaches fail to adapt to the advancing strategies of fraudsters, resulting in heightened false positives and inefficiency within fraud detection systems. This study overcomes these restrictions by creating an innovative stacking hybrid machine learning (ML) approach that combines decision trees (DT), random forests (RF), support vector machines (SVM), XGBoost, CatBoost, and logistic regression (LR) within a stacking ensemble framework. This method uses stacking to integrate diverse ML models, enhancing predictive performance, with a meta-model consolidating base model predictions, resulting in superior detection accuracy compared to any single model. The methodology utilizes sophisticated data preprocessing techniques, such as correlation-based feature selection and principal component analysis (PCA), to enhance computing efficiency while preserving essential information. Experimental assessments of a credit card transaction dataset reveal that the stacking ensemble model exhibits higher performance, achieving an F1-score of 88.14%, thereby efficiently balancing precision and recall. This outcome highlights the significance of ensemble methods such as stacking in attaining strong and dependable cyber fraud detection, emphasizing its capacity to markedly enhance the security of financial transactions.

Clinical prognosis evaluation of COVID-19 patients: An interpretable hybrid machine learning approach