Detection of visual faults in photovoltaic modules using a stacking ensemble approach

Accurate classification of Turkish voice commands is essential for advancing voice-controlled technologies and enabling seamless human-computer interaction in native language contexts. This study systematically evaluates multiple feature extraction models capturing temporal, spectral, and time-frequency characteristics of speech signals to enhance recognition accuracy. Six feature vector models were developed, with the final model integrating Information Gain-based feature selection and Linear Predictive Coding-derived formant frequencies to create a comprehensive and discriminative representation. Classification was performed using six widely adopted algorithms: Random Forest, k-Nearest Neighbors, Multilayer Perceptron, Logistic Model Tree, Support Vector Machine, and an Ensemble voting method combining Random Forest, Multilayer Perceptron, and Logistic Model Tree. The Ensemble voting classifier demonstrated superior performance, achieving an accuracy of 93.94%, significantly outperforming individual classifiers and baseline models. This study contributes to the literature by presenting a robust, explainable, and high-performing feature framework tailored for Turkish voice command recognition. The integration of spectral, temporal, and articulatory features enables improved discrimination of speech commands, offering valuable insights for future voice-activated applications in Turkish language environments.

The area of corporate bankruptcy prediction attains high economic importance, as it affects many stakeholders. The prediction of corporate bankruptcy has been extensively studied in economics, accounting and decision sciences over the past two decades. The corporate bankruptcy prediction has been a matter of talk among academic literature and professional researchers throughout the world. Different traditional approaches were suggested based on hypothesis testing and statistical modeling. Therefore, the primary purpose of the research is to come up with a model that can estimate the probability of corporate bankruptcy by evaluating its occurrence of failure using different machine learning models. As the dataset was not well prepared and contains missing values, various data mining and data pre-processing techniques were utilized for data preparation. Within this research, the task of resolving the issues induced by the imbalance between the two classes is approached by applying different data balancing techniques. We address the problem of imbalanced data with the random undersampling and Synthetic Minority Over Sampling Technique (SMOTE). We used five machine learning models (support vector machine, J48 decision tree, Logistic model tree, random forest and decision forest) to predict corporate bankruptcy earlier to the occurrence. We use data from 2009 to 2013 on Poland manufacturing corporates and selected the 64 financial indicators to be broken down. The main finding of the study is a significant improvement in predictive accuracy using machine learning techniques. We also include other economic indicators ratios, along with Altman’s Z-score variables related to profitability, liquidity, leverage and solvency (short/long term) to propose an efficient model. Machine learning models give better results while balancing the data through SMOTE as compared to random undersampling. The machine learning technique related to decision forest led to 99% accuracy, whereas support vector machine (SVM), J48 decision tree, Logistic Model Tree (LMT) and Random Forest (RF) led to 92%, 92.3%, 93.8% and 98.7% accuracy, respectively, with all predictive financial indicators. We find that the decision forest outperforms the other techniques and previous techniques discussed in the literature. The proposed method is also deployed on the web to assist regulators, investors, creditors and scholars to predict corporate bankruptcy.

Detecting harmful content or hate speech on social media is a significant challenge due to the high throughput and large volume of content production on these platforms. Identifying hate speech in a timely manner is crucial in preventing its dissemination. We propose a novel stacked ensemble approach for detecting hate speech in English tweets. The proposed architecture employs an ensemble of three classifiers, namely support vector machine (SVM), logistic regression (LR), and XGBoost classifier (XGB), trained using word2vec and universal encoding features. The meta classifier, LR, combines the outputs of the three base classifiers and the features employed by the base classifiers to produce the final output. It is shown that the proposed architecture improves the performance of the widely used single classifiers as well as the standard stacking and classifier ensemble using majority voting. We also present results on the use of various combinations of machine learning classifiers as base classifiers. The experimental results from the proposed architecture indicated an improvement in the performance on all four datasets compared with the standard stacking, base classifiers, and majority voting. Furthermore, on three of these datasets, the proposed architecture outperformed all state-of-the-art systems.

Genre classification is a process of grouping similarities, such as patterns, styles, or objectives with management data as already in the music (e.g. pop and rock). It is used along with the classification of topics. This paper will classify songs from audio signal to a hierarchy of musical genre by using feature extraction. Trimbral texture, rhythmic content and pitch content are used as the main feature sets. Feature selection is selected by using Particle Swarm Optimization (PSO) and sent selected feature to classification. The result in classification has low accuracy. Thus, using stacking ensemble method is to improve the prediction. In this paper, the purpose is to improve the prediction by using stacking ensemble method. Stacking ensemble that have the second level is base classifier and meta-classifier. In base classifier consists of 5 classification; K-Nearest Neighbors (k-NN), Decision Tree (DT), Random Forest, Support Vector Machines (SVM); and Naive Bayes. This process is generated to build multiple classifier predictors and sent it to meta-classifier. In the process of meta-classifier will create new model to predict test data. The new model has been created from neural network which train data is the output of base classifier.

Background/Objectives: Recent studies emphasized on using ensemble models over single ones to solve credit scoring problems. The objective of this study is to build a heterogeneous ensemble classifier model with an improved classification accuracy. Methods: This study focuses on developing a heterogeneous ensemble classifier using Logistic Regression, K-nearest neighbor, Decision tree, Random Forest, Naïve Base and Support vector machine as base classifiers and Random Forest, Logistic Regression and Support vector machine as meta-classifiers. The proposed model is built using these six base classifiers for ensemble aggregation. A feature selection algorithm based on the random forest technique is used for selecting the best features. A stacking and voting method are used for building ensemble model. Findings: The ensemble classifier gives superior predictive performance than single classifiers SVM, DT, RF, NB, KNN and LR with an accuracy of 91.56% for Australian dataset and 84.35% for German dataset. Novelty: The proposed model uses stacking and majority voting method for ensemble classification. Initially, stacking is applied to the base classifiers. This is done in two levels. First the training dataset is split into 10 folds for cross validation. The output of each classifier is taken, and the dataset is updated with the meta-features. In the second level, three meta-classifiers (MC), namely LR, SVM and RF are used. Majority voting is applied to the output of these meta-classifiers for the prediction. Keywords: Credit scoring; ensemble model; SVM; DT; RF; NB; KNN; LR

Early diagnosis of diabetes, which can cause death, is very important for the health of the person. In the literature, machine learning techniques are frequently used in diagnosis of many diseases, including diabetes. The aim of the study is to predict diabetes with high accuracy by using machine learning and preprocessing techniques. Pima Indian Diabetes dataset was used in the study. J48 (Decision Tree), Naïve Bayes, Support Vector Machine, Logistic Regression, Multilayer Perceptron, K Nearest Neighbor, Logistic Model Tree, and Random Forest were used for classification. Of the preprocessing methods, feature selection, imputing missing values, normalization and standardization are performed. According to the results obtained, the highest accuracy value got with the Random Forest algorithm as 80.869.

Emotion recognition plays a pivotal role in advancing Human-Computer Interaction (HCI) by enabling systems to understand and respond to human emotional states. Among various modalities, Speech Emotion Recognition (SER) stands out as a non-invasive, cost-effective, and temporally efficient approach for detecting emotions. This study leverages the RAVDESS dataset, which provides high-quality audio recordings for emotion classification. The proposed methodology involves preprocessing audio signals to remove noise, extracting temporal and spectral features in both time and frequency domains, and implementing machine learning models for multi-class emotion classification. The study evaluates and compares the performance of several classification models, including Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), Convolutional Neural Networks (CNN), and Decision Trees (DT). Experimental results demonstrate promising accuracy levels, highlighting the potential of these machine learning techniques in SER. This research contributes to the integration of SER within Brain-Computer Interfaces (BCI) and other emotion-aware applications, paving the way for enhanced interactive systems. Keywords – Speech Emotion Recognition -Machine Learning - Random Forest -Multilayer Perceptron - Support Vector Machine - Convolutional Neural Networks - Decision Tree - RAVDESS Dataset

In Software Development Life Cycle, fixing defect bugs is one of the essential activities of the software maintenance phase. Bug severity indicates how major or minor the bug impacts on the execution of the system and how rapidly the developer should fix it. Triaging a vast amount of new bugs submitted to the software bug repositories is a cumbersome and time-consuming process. Manual triage might lead to a mistake in assigning the appropriate severity level for each bug. As a consequence, a delay for fixing severe software bugs will take place. However, the whole process of assigning the severity level for bug reports should be automated. In this paper, we aim to build prediction models that will be utilized to determine the class of the severity (severe or non-severe) of the reported bug. To validate our approach, we have constructed a dataset from historical bug reports stored in JIRA bug tracking system. These bug reports are related to different closed-source projects developed by INTIX Company located in Amman, Jordan. We compare eight popular machine learning algorithms, namely Naive Bayes, Naive Bayes Multinomial, Support Vector Machine, Decision Tree (J48), Random Forest, Logistic Model Trees, Decision Rules (JRip) and K-Nearest Neighbor in terms of accuracy, F-measure and Area Under the Curve (AUC). According to the experimental results, a Decision Tree algorithm called Logistic Model Trees achieved better performance compared to other machine learning algorithms in terms of Accuracy, AUC and F-measure with values of 86.31, 0.90 and 0.91, respectively.

Classification of team sport activities using a single wearable tracking device

Graduation rates indicate school success. Predicting student graduation helps schools identify students in danger of dropping out and intervene early to enhance academic performance. It can also assist policymakers create graduation and dropout prevention initiatives. However, based on a literature search, predicting student graduation rates from admission test scores is difficult. School grades are a better predictor of timely tertiary graduation than acceptance test scores because college success requires cognitive abilities and self-regulation competencies, which are better indexed by school grades. Self-efficacy, school academic culture, and future expectations can also affect student graduation rates. Finally, the selective admissions modality needs to be refined. This study aims to (1) predict private high school graduation with eight algorithms: Random tree, Naïve Bayes Multinomial, Support Vector Machine (SVM), Random forest (RF), K-Nearest Neighbor, Ada Boost, Multilayer perceptron, Logistic regression, and (2) compare the performance of the eight algorithms. According to research, the Random tree, Naïve Bayes Multinomial, Random forest (RF), and Ada boost algorithms all perform at 99.49% for the first aim. For the second objective, the Random Tree approach outperforms other algorithms in Accuracy (99.49%), Precision (100%), F-Measure (99.74%), and consumption time (0 seconds). Therefore, the Random tree algorithm outperforms others. This research contributes in two ways: scientifically by testing eight algorithms—Random tree, Naïve Bayes Multinomial, Support Vector Machine (SVM), Random forest (RF), K-Nearest Neighbor, Ada Boost, Multilayer perceptron, and Logistic regression—to predict private high school graduation, and secondly by recommending school administrators to develop a selective enrollment model.

Periodontitis is increasingly associated with heart failure, and the goal of this study was to develop and validate a prediction model based on machine learning algorithms for the risk of heart failure in middle-aged and elderly participants with periodontitis. We analyzed data from a total of 2876 participants with a history of periodontitis from the National Health and Nutrition Examination Survey (NHANES) 2009 to 2014, with a training set of 1980 subjects with periodontitis from the NHANES 2009 to 2012 and an external validation set of 896 subjects from the NHANES 2013 to 2014. The independent risk factors for heart failure were identified using univariate and multivariate logistic regression analysis. Machine learning algorithms such as logistic regression, k-nearest neighbor, support vector machine, random forest, gradient boosting machine, and multilayer perceptron were used on the training set to construct the models. The performance of the machine learning models was evaluated using 10-fold cross-validation on the training set and receiver operating characteristic curve (ROC) analysis in the validation set. Based on the results of univariate logistic regression and multivariate logistic regression, it was found that age, race, myocardial infarction, and diabetes mellitus status were independent predictors of the risk of heart failure in participants with periodontitis. Six machine learning models, including logistic regression, K-nearest neighbor, support vector machine, random forest, gradient boosting machine, and multilayer perceptron, were built on the training set, respectively. The area under the ROC for the 6 models was obtained using 10-fold cross-validation with values of 0 848, 0.936, 0.859, 0.889, 0.927, and 0.666, respectively. The areas under the ROC on the external validation set were 0.854, 0.949, 0.647, 0.933, 0.855, and 0.74, respectively. K-nearest neighbor model got the best prediction performance across all models. Out of 6 machine learning models, the K-nearest neighbor algorithm model performed the best. The prediction model offers early, individualized diagnosis and treatment plans and assists in identifying the risk of heart failure occurrence in middle-aged and elderly patients with periodontitis.

This study proposes a workflow for land use and land cover (LULC) classification of Advanced Land Observing Satellite-2 (ALOS-2) Phased Array type L-band Synthetic Aperture Radar-2 (PALSAR-2) images of the Brazilian tropical savanna (Cerrado) biome. The following LULC classes were considered: forestlands; shrublands; grasslands; reforestations; croplands; pasturelands; bare soils/straws; urban areas; and water reservoirs. The proposed approach combines polarimetric attributes, image segmentation, and machine-learning procedures. A set of 125 attributes was generated using polarimetric ALOS-2/PALSAR-2 images, including the van Zyl, Freeman–Durden, Yamaguchi, and Cloude–Pottier target decomposition components, incoherent polarimetric parameters (biomass indices and polarization ratios), and HH-, HV-, VH-, and VV-polarized amplitude images. These attributes were classified using the Naive Bayes (NB), DT J48 (DT = decision tree), Random Forest (RF), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) algorithms. The RF, MLP, and SVM classifiers presented the most accurate performances. NB and DT J48 classifiers showed a lower performance in relation to the RF, MLP, and SVM. The DT J48 classifier was the most suitable algorithm for discriminating urban areas and natural vegetation cover. The proposed workflow can be replicated for other SAR images with different acquisition modes or for other types of vegetation domains.

Background: Accurate subtype identification of lymphoma cancer is crucial for effective diagnosis and treatment planning. Although standard deep learning algorithms have demonstrated robustness, they are still prone to overfitting and limited generalization, necessitating more reliable and robust methods. Objectives: This study presents an autoencoder-augmented stacked ensemble learning (SEL) framework integrating deep feature extraction (DFE) and ensembles of machine learning classifiers to improve lymphoma subtype identification. Methods: Convolutional autoencoder (CAE) was utilized to obtain high-level feature representations of histopathological images, followed by dimensionality reduction via Principal Component Analysis (PCA). Various models were utilized for classifying extracted features, i.e., Random Forest (RF), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), AdaBoost, and Extra Trees classifiers. A Gradient Boosting Machine (GBM) meta-classifier was utilized in an SEL approach to further fine-tune final predictions. Results: All the models were tested using accuracy, area under the curve (AUC), and Average Precision (AP) metrics. The stacked ensemble classifier performed better than all the individual models with a 99.04% accuracy, 0.9998 AUC, and 0.9996 AP, far exceeding what regular deep learning (DL) methods would achieve. Of standalone classifiers, MLP (97.71% accuracy, 0.9986 AUC, 0.9973 AP) and Random Forest (96.71% accuracy, 0.9977 AUC, 0.9953 AP) provided the best prediction performance, while AdaBoost was the poorest performer (68.25% accuracy, 0.8194 AUC, 0.6424 AP). PCA and t-SNE plots confirmed that DFE effectively enhances class discrimination. Conclusion: This study demonstrates a highly accurate and reliable approach to lymphoma classification by using autoencoder-assisted ensemble learning, reducing the misclassification rate and significantly enhancing the accuracy of diagnosis. AI-based models are designed to assist pathologists by providing interpretable outputs such as class probabilities and visualizations (e.g., Grad-CAM), enabling them to understand and validate predictions in the diagnostic workflow. Future studies should enhance computational efficacy and conduct multi-centre validation studies to confirm the model’s generalizability on extensive collections of histopathological datasets.

Short message service (SMS) is considered as one of the most popular means of communication, it allows to the mobile phone users to exchange a short text message with a low cost. Its growing popularity and its dependence on mobile phone has increased the number of attacks, caused by sending an unsolicited message like SMS spam. In this paper, we address a comparative study, between multilayer perceptron (MLP), support vector machine (SVM), random forest and k-nearest neighbors (KNN). For extracting the feature vectors the bag-of-words (BOW) and the TF-IDF methods are applied. These feature vectors are used as input for training and testing the different machine-learning classifiers mentioned above. The results of different machine-learning classifiers, based on their accuracy, precision, recall, F-measure, and ROC (receiver operating characteristic) curve have shown that the MLP outperforms SVM, random forest and KNN in SMS spam detection. Although the MLP has achieved the highest accuracy by using the BOW, than by using the TF-IDF method.

Anemia is one of the common adverse reactions after hip fracture surgery. The traditional method to solve anemia is allogeneic transfusion. However, the transfusion may lead to some complications such as septicemia and fever. So far, few studies have reported roles of machine learning in predicting whether blood transfusion is needed or not after hip fracture surgery. Therefore, the purpose of this study is to develop machine learning models to predict the likelihood of postoperative blood transfusion in patients undergoing hip fracture surgery. This study enrolled 1355 patients who underwent hip fracture surgery at the Affiliated Hospital of Qingdao University from January 2016 to December 2021. Among all patients, 210 cases received postoperative blood transfusion. All patients were randomly divided into a training group and a testing group at a ratio of 7:3. In the training group, univariate and multivariate logistic regression analyses were used to determine independent risk factors for the postoperative transfusion. Then, based on these independent risk factors, tenfold cross-validation method was utilized to develop five machine learning models, including logistic, multilayer perceptron (MLP), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The receiver operating characteristic (ROC) curve, area under ROC curve (AUC), and Matthews correlation coefficient (MCC) were generated to evaluate the performance of the models. Calibration plot and decision curve analysis (DCA) were used to test the performance, stability, and clinical applicability of the models. The models were validated using the testing group; and the ROC curve, MCC, calibration plot, and DCA curves were also generated to validate the performance, stability, and clinical applicability of the models. To further verify the robustness of the model, we randomly grabbed 70% of the samples in the testing set, performed 1000 iterations, and calculated the AUC and confidence interval of the five models. Finally, we used SHapley Additive exPlanations (SHAP) to explain these models. Multivariate logistic regression analysis showed that there were 8 independent risk factors, including age, blood transfusion history, albumin (ALB), globulin (GLO), total bilirubin (TBIL), indirect bilirubin (IBIL), hemoglobin (HB), and blood loss > 200ml. We finally selected five independent risk factors including HB, GLO, age, IBIL, and blood loss > 200ml. Based on these five independent risk factors, we generated six characteristic variables, namely HB, HB × HB, HB × blood loss, GLO × HB, age, age × IBIL, and established five machine learning models using a tenfold cross-validation method. In the training group, the AUC values of logistic, RF, MLP, SVM, and XGB were 0.9320, 0.8911, 0.9327, 0.9225, and 0.8825, respectively, and the average AUC was 0.9122 ± 0.0212. The MCC values were 0.65, 0.77, 0.65, 0.66, and 0.68, respectively, and the calibration plot and DCA performed well. In the testing group the AUC values of logistic, RF, MLP, SVM, and XGB were 0.8483, 0.7978, 0.8576, 0.8598, and 0.8216, respectively. The average AUC was 0.8370 ± 0.0238, and the MCC values were 0.41, 0.35, 0.40, 0.41, and 0.41, respectively. The calibration plot and DCA in the testing group also showed good performance. The AUC values and confidence intervals of the 1000-iteration model were: logistic (AUC, min confidence interval [CI]-max confidence interval [CI] 0.848, 0.804-0.903), RF (AUC, minCI-maxCI 0.797, 0.734-0.857), MLP (AUC, minCI-maxCI 0.858, 0.812-0.902), SVM (AUC, minCI-maxCI 0.859, 0.819-0.910), and XGB (AUC, minCI-maxCI 0.821, 0.764-0.894). The model performed well. Finally, according to SHAP, among all five models, HB played the most important role in model prediction and interpretation. The five models we developed all performed well in predicting the likelihood of blood transfusion after hip fracture surgery. Therefore, we believed that the prediction model based on machine learning had great application prospects in clinical practice, which could help clinicians better predict the risk of blood transfusion after hip fracture surgery.