Search Results (104)

On-grid solar microgrids (SMGs) are increasingly deployed to support sustainable and distributed energy generation. However, the low fault current levels, power-electronic interfaces, and dynamic operating conditions of SMGs create significant challenges for conventional protection systems, which may struggle to accurately detect and locate line faults (LFs). While artificial intelligence (AI) has shown promise in addressing these challenges, there remains limited comparative evidence regarding the suitability of different AI techniques for LF detection in on-grid SMGs under identical operating conditions. Therefore, this study investigates and compares the performance of four AI techniques, namely, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Support Vector Machine (SVM), and Random Forest (RF), for LF detection in on-grid SMGs. An on-grid SMG test system based on the IEEE 6-bus benchmark is implemented in MATLAB/Simulink 2025a to simulate various LF conditions and generate voltage and current datasets for model training and testing. All models are trained and evaluated under identical performance metrics, including accuracy, precision, recall, F1-score, noise robustness, and computational speed. The results show that deep learning (DL) models outperform classical machine learning approaches, with CNN achieving the highest performance of 99.79% accuracy and a 99.78% F1-score, followed by LSTM with 98.97% accuracy and a 98.92% F1-score. SVM and RF achieved accuracies of 98.25% and 95.75%, respectively, while requiring less than three minutes of training time, highlighting their suitability for real-time and resource-constrained applications. These findings provide a robust comparative benchmark for AI-based LF detection in on-grid SMGs and offer practical guidance for selecting appropriate AI techniques based on performance and computational requirements. Full article

Aim: This study aimed to detect the maxillary dental midline region on orthodontic frontal photographs using a YOLOv8-based deep learning approach and to evaluate how the detection outputs affect the classification performance of various machine learning algorithms in distinguishing symmetric from asymmetric midline conditions. Materials and Methods: A total of 146 standardized frontal photographs (72 with midline deviation ≥ 2 mm from the facial midline, defined by the soft-tissue nasion–subnasal line; 74 symmetric) were analyzed. YOLOv8 was used to obtain bounding-box and keypoint predictions, which were converted into a numerical feature vector and used to train 11 classifiers (including Naive Bayes, Logistic Regression with L1 and ElasticNet penalties, Support Vector Machine, AdaBoost, and others). Performance was assessed using accuracy (with 95% Wilson confidence intervals), precision, recall, F1-score, and ROC-AUC. Optimization of hyperparameters for the downstream classifiers employed five-fold cross-validation along with grid search inside the training data set (n = 126) while final classifier assessment was done using a reserved test data set (n = 20). As the YOLOv8 object detector was trained using the full image dataset before extracting features, the classification metrics presented here should be considered as exploratory results only. Results: YOLOv8 achieved mAP@0.5 = 0.995 for midline detection. Naive Bayes attained the highest classification accuracy of 75% (95% CI: 53–89%) with ROC-AUC = 0.75. AdaBoost achieved 65% (95% CI: 43–82%). Several models defaulted to majority-class prediction (accuracy = 40%), indicating insufficient feature discriminability. Conclusions: YOLOv8 detected the maxillary dental midline under the present internal experimental conditions. However, because leakage-free outer k-fold validation of the complete detection-plus-classification pipeline was not performed, the classification results should be considered preliminary. Future work should address information leakage, incorporate facial reference frame normalization, include inter-observer reliability assessment, and validate the approach on larger datasets. Full article

This study evaluated six supervised machine learning (ML) models for early detection of subclinical ketosis and low-grade ruminal acidosis in dairy cows during the transition period. Ninety-four Holstein cows were monitored for 21 days postpartum using in-line milk analyzers and intraruminal sensors that continuously recorded milk composition, behavioral, and physiological parameters. Based on clinical examination, blood β-hydroxybutyrate concentration, and fat-to-protein ratio, cows were classified as healthy (n = 44), subclinical ketosis (n = 24), or subclinical acidosis (n = 26). Among the tested models, Random Forest and XGBoost achieved perfect accuracy within this dataset, while Logistic Regression reached 89.5%, Decision Tree 84.2%, and both Naive Bayes and Support Vector Machine 78.9%. These results suggest that ensemble approaches, particularly Random Forest and XGBoost, show strong potential for integration with precision livestock technologies, but their apparent performance should be interpreted cautiously and confirmed in larger, multi-farm studies. Full article

Background/Objectives: Mesothelioma is a rare and aggressive form of cancer that primarily affects the lining of the lungs, abdomen, or heart. It typically arises from exposure to asbestos and is often diagnosed at advanced stages. Limited datasets and complex tissue structures contribute to delays in diagnosis. This study aims to develop a novel hybrid model to improve the accuracy and timeliness of mesothelioma diagnosis. Methods: The proposed approach integrates automatic image segmentation, transformer-based model training, class-based feature extraction, and image transformation techniques. Initially, CT images were processed using the segment anything model (SAM) for region-focused segmentation. These segmented images were then used to train transformer models (CaiT and PVT) to extract class/type-specific features. Each class-based feature set was transformed into an image using Decoder, GAN, and NeRV techniques. Discriminative score and class centroid analysis were then applied to select the most informative image representation for each input. Finally, classification was performed using a residual-based support vector machine (SVM). Results: The proposed hybrid method achieved a classification accuracy of 99.80% in diagnosing mesothelioma, demonstrating its effectiveness in handling limited data and complex tissue characteristics. Conclusions: The results indicate that the proposed model offers a highly accurate and efficient approach to mesothelioma diagnosis. By leveraging advanced segmentation, feature extraction, and representation techniques, it effectively addresses the major challenges associated with early and precise detection of mesothelioma. Full article

Air compressors are vital across various sectors—automotive, manufacturing, buildings, and healthcare—as they provide pressurized air for air suspension systems in vehicles, supply power pneumatic machines throughout industrial production lines, and support non-clinical infrastructure within hospital environments, including pneumatic control systems, isolation room pressurization, and laboratory equipment operation. Ensuring that such components are reliable is critical, as unexpected failures can disrupt facility functions and compromise patient safety. Predictive maintenance (PdM) has emerged as a key factor in enhancing the reliability and operational efficiency of medical devices by leveraging sensor data and artificial intelligence (AI)-based algorithms to detect component degradation before functional failures occur. In this paper, a predictive maintenance solution for condition monitoring and fault prediction for the exhaust valve, bearings, water pump, and radiator of an air compressor is presented, by comparing a hybrid deep neural network (DNN) as a feature extractor and a support vector machine (SVM) for condition classification: a pure DNN classifier as well as a standalone SVM model. Additionally, each model was trained and validated on three devices—NVIDIA T4 GPU, Raspberry Pi 4 Model B, and NVIDIA Jetson Nano—and performance reports in terms of latency, energy consumption, and CO₂ emissions are presented. Moreover, three model agnostic explainable AI (XAI) methods were employed to increase the transparency of the hybrid model’s final decision: Shapley additive explanations (SHAP), local interpretable model-agnostic explanations (LIME) and partial dependence plots (PDP). The hybrid model achieves on average 98.71%, 99.25%, 98.78%, and 99.01% performance in terms of accuracy, precision, recall, and F1-score across all devices Additionally, the DNN baseline and SVM model achieve on average 93.2%, 88.33%, 90.45%, and 89.37%, as well as 93.34%, 88.11%, 95. 41%, and 91.62% performance in terms of accuracy, precision, recall, and F1-score across all devices. The integration of XAI methods within the PdM pipeline offers enhanced transparency, interpretability, and trustworthiness of predictive outcomes, thereby facilitating informed decision-making among maintenance personnel. Full article

Focusing on the characteristic tea resource Zijuan tea, this study addresses the difficulty of grading on production lines and the complexity of quality evaluation. On the basis of the fusion of near-infrared (NIR) spectroscopy and visual features, a novel method is proposed for classifying different tenderness levels and quantitatively assessing key anthocyanin components in Zijuan tea fresh leaves. First, NIR spectra and visual feature data were collected, and anthocyanin components were quantitatively analyzed using UHPLC-Q-Exactive/MS. Then, four preprocessing techniques and three wavelength selection methods were applied to both individual and fused datasets. Tenderness classification models were developed using Particle Swarm Optimization–Support Vector Machine (PSO-SVM), Random Forest (RF), and Convolutional Neural Networks (CNNs). Additionally, prediction models for key anthocyanin content were established using linear Partial Least Squares Regression (PLSR), nonlinear Support Vector Regression (SVR) and RF. The results revealed significant differences in NIR spectral characteristics across different tenderness levels. Model combinations such as TEX + Medfilt + RF and NIR + Medfilt + CNN achieved 100% accuracy in both training and testing sets, demonstrating robust classification performance. The optimal models for predicting key anthocyanin contents also exhibited excellent predictive accuracy, enabling the rapid and nondestructive detection of six major anthocyanin components. This study provides a reliable and efficient method for intelligent tenderness classification and the rapid, nondestructive detection of key anthocyanin compounds in Zijuan tea, holding promising potential for quality control and raw material grading in the specialty tea industry. Full article

Rockfalls on railways are considered a natural disaster under the topic of landslides. It is an event that varies regionally due to landforms and climate. In addition to traffic density, the Karabük–Yenice railway line also passes through mountainous areas, river crossings, and experiences heavy seasonal rainfall. These conditions necessitate the implementation of proactive measures to mitigate risks such as rockfalls, tree collapses, landslides, and other geohazards that threaten the railway line. Undetected environmental events pose a significant threat to railway operational safety. The study aims to provide early detection of environmental phenomena using vibrations emitted through fiber optic cables. This study presents a real-time hazard detection system that integrates Distributed Acoustic Sensing (DAS) with a hybrid ensemble learning model. Using fiber optic cables and the Luna OBR-4600 interrogator, the system captures environmental vibrations along a 6 km railway corridor in Karabük, Türkiye. CatBoosting, Support Vector Machine (SVM), LightGBM, Decision Tree, XGBoost, Random Forest (RF), and Gradient Boosting Classifier (GBC) algorithms were used to detect the incoming signals. However, the Voting Classifier hybrid model was developed using SVM, RF, XGBoost, and GBC algorithms. The signaling system on the railway line provides critical information for safety by detecting environmental factors. Major natural disasters such as rockfalls, tree falls, and landslides cause high-intensity vibrations due to environmental factors, and these vibrations can be detected through fiber cables. In this study, a hybrid model was developed with the Voting Classifier method to accurately detect and classify vibrations. The model leverages an ensemble of classification algorithms to accurately categorize various environmental disturbances. The system has proven its effectiveness under real-world conditions by successfully detecting environmental events such as rockfalls, landslides, and falling trees with 98% success for Precision, Recall, F1 score, and accuracy. Full article

This research introduces a novel hybrid machine learning framework for automated quality prediction and classification of silicon solar modules in production lines. Unlike conventional approaches that rely solely on encapsulation loss rate (ELR) for performance evaluation—a method limited to assessing encapsulation-related power loss—our framework integrates unsupervised clustering and supervised classification to achieve a comprehensive analysis. By leveraging six critical performance parameters (open circuit voltage (V_OC), short circuit current (I_SC), maximum output power (P_max), voltage at maximum power point (VPM), current at maximum power point (IPM), and fill factor (FF)), we first employ k-means clustering to dynamically categorize modules into three performance classes: excellent performance (ELR: 0–0.77%), good performance (0.77–8.39%), and poor performance (>8.39%). This multidimensional clustering approach overcomes the narrow focus of traditional ELR-based methods by incorporating photoelectric conversion efficiency and electrical characteristics. Subsequently, five machine learning classifiers—decision trees (DT), random forest (RF), k-nearest neighbors (KNN), naive Bayes classifier (NBC), and support vector machines (SVMs)—are trained to classify modules, achieving 98.90% accuracy with RF demonstrating superior robustness. Pearson correlation analysis further identifies V_OC, P_max, and VPM as the most influential quality determinants, exhibiting strong negative correlations with ELR (−0.953, −0.993, −0.959). The proposed framework not only automates module quality assessment but also enhances production line efficiency by enabling real-time anomaly detection and yield optimization. This work represents a significant advancement in solar module evaluation, bridging the gap between data-driven automation and holistic performance analysis in photovoltaic manufacturing. Full article

Agricultural festivals play a vital role in promoting sustainable farming, local economies, and cultural heritage. Understanding public sentiment toward these events can provide valuable insights to enhance event organization, marketing strategies, and economic sustainability. In this study, we collected and analyzed social media data from Twitter to evaluate public perceptions of Al-Baha’s agricultural festivals. Sentiment analysis was performed using both traditional machine learning and deep learning approaches. Specifically, six machine learning models including Multinomial Naïve Bayes (MNB), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), k-Nearest Neighbors (KNN), and XGBoost (XGB) were compared against AraBERT, a transformer-based deep learning model. Each model was evaluated based on accuracy, precision, recall, and F1-score. The results demonstrated that AraBERT achieved the highest performance across all metrics, with an accuracy of 85%, confirming its superiority in Arabic sentiment classification. Among traditional models, SVM and RF performed best, whereas MNB and KNN struggled with sentiment detection. These findings highlight the role of sentiment analysis in supporting sustainable agricultural and tourism initiatives. The insights gained from sentiment trends can help festival organizers, policymakers, and agricultural stakeholders make data-driven decisions to enhance sustainable event planning, optimize resource allocation, and improve marketing strategies in line with the Sustainable Development Goals (SDGs). Full article

Persistent atrial fibrillation (AF), a prevalent cardiac arrhythmia, is primarily sustained by rotor-type reentries, with their localization crucial for successful ablation treatment. Fractionated atrial electrogram (EGM) signals have been associated with the tips of the rotors and are thus considered as ablation targets. However, the typical noise problems of physiological signals affect the results of EGM processing tools, and consequently the ablation outcome. This study proposes a data fusion framework based on the Joint Directors of Laboratories model with six levels and information quality (IQ) assessment for locating rotor tips from EGMs simulated in a two-dimensional model of human atrial tissue under AF conditions. Validation tests were conducted using a set of 13 IQ criteria and their corresponding metrics. First, EGMs were contaminated with different types of noise and artifacts (power-line interference, spikes, loss of samples, and loss of resolution) to assess tolerance. The signals were then preprocessed, and five statistical features (sample entropy, approximate entropy, Shannon entropy, mean amplitude, and standard deviation) were extracted to generate rotor location maps using a wavelet fusion technique. Fuzzy inference was applied for situation and risk assessment, followed by IQ mapping using a support vector machine by level. Finally, the IQ criteria were optimized through a particle swarm optimization algorithm. The proposed framework outperformed existing EGM-based rotor detection methods, demonstrating superior functionality and performance compared to existing EGM-based rotor detection methods. It achieved an accuracy of approximately 90%, with improvements of up to 10% through tuning and adjustments based on IQ variables, aligned with higher-level system requirements. The novelty of this approach lies in evaluating the IQ across signal-processing stages and optimizing it through data fusion to enhance rotor tip position estimation. This advancement could help specialists make more informed decisions in EGM acquisition and treatment application. Full article

Lameness detection in horses is a critical challenge in equine veterinary practice, particularly when symptoms are mild. This study aimed to develop a predictive system using a support vector machine (SVM) to identify the affected limb in horses trotting in a straight line. The system analyzed data from inertial measurement units (IMUs) placed on the horse’s head, withers, and pelvis, using variables such as vertical displacement and retraction angles. A total of 287 horses were included, with 256 showing single-limb lameness and 31 classified as sound. The model achieved an overall accuracy of 86%, with the highest success rates in identifying right and left forelimb lameness. However, there were challenges in identifying sound horses, with a 54.8% accuracy rate, and misclassification between forelimb and hindlimb lameness occurred in some cases. The study highlighted the importance of specific variables, such as vertical head and withers displacement, for accurate classification. Future research should focus on refining the model, exploring deep learning methods, and reducing the number of sensors required, with the goal of integrating these systems into equestrian equipment for early detection of locomotor issues. Full article

The classification of the wireless propagation channel between Line-of-Sight (LOS) or Non-Line-of-Sight (NLOS) is useful in the operation of wireless communication systems. The research community has increasingly investigated the application of machine learning (ML) to LOS/NLOS classification and this paper is part of this trend, but not all the different aspects of ML have been analyzed. In the general ML domain, poisoning and adversarial attacks and the related mitigation techniques are an active area of research. Such attacks aim to hamper the ML classification process by poisoning the data set. Mitigation techniques are designed to counter this threat using different approaches. Poisoning attacks in LOS/NLOS classification have not received significant attention by the wireless communication community and this paper aims to address this gap by proposing the application of a specific mitigation technique based on outlier detection algorithms. The rationale is that poisoned samples can be identified as outliers from legitimate samples. In particular, the study described in this paper proposes a recent outlier detection algorithm, which has low computing complexity: the sparse data observers (SDOs) algorithm. The study proposes a comprehensive analysis of both conventional and novel types of attacks and related mitigation techniques based on outlier detection algorithms for UltraWideBand (UWB) channel classification. The proposed techniques are applied to two data sets: the public eWINE data set with seven different UWB LOS/NLOS different environments and a radar data set with the LOS/NLOS condition. The results show that the SDO algorithm outperforms other outlier detection algorithms for attack detection like the isolation forest (iForest) algorithm and the one-class support vector machine (OCSVM) in most of the scenarios and attacks, and it is quite competitive in the task of increasing the UWB LOS/NLOS classification accuracy through sanitation in comparison to the poisoned model. Full article

Pole tower grounding bodies are part of the normal structure of the power system, providing relief from fault currents and equalizing overvoltage channels. They are important devices; however, in the harsh environment of the soil, they are prone to corrosion or even fracture, which in turn affects the normal utilization of the transmission line, so accurately assessing the condition of grounding bodies of the power grid is critical. To assess the operational status of a grounding body in a timely manner, this paper proposes a multi-parameter pulsed eddy current (PEC) time-domain characteristic signal corrosion classification method for the detection of the state of a pole tower grounding body. The method firstly theoretically analysed the influence of multi-parameter changes on the PEC response time-domain feature signal caused by grounding body corrosion and extracts the decay time constant (DTC), and the decay time constant stabilization value (DTCSV) and time to stabilization (TTS) were obtained based on the DTC time domain characteristics for describing the corrosion of the grounding body. Subsequently, DTCSV and TTS were used as inputs to a support vector machine (SVM) to classify the corrosion of the grounding body. A simulation model was constructed to investigate the effect of multiparameter time on the DTCSV and TTS of the tower grounding body based on the single-variable method, and the multiparameter time-domain characterization method used for corrosion assessment was validated. Four defects with different corrosion levels were classified using the optimized SVM model, with an accuracy rate of 95%. Finally, a PEC inspection system platform was built to conduct classification tests on steel bars with different degrees of corrosion, and the results show that the SVM classification model based on DTCSV and TTS has a better discriminatory ability for different corrosive grounders and can be used to classify corrosion in the grounders of poles towers to improve the stability of power transmission. Full article

Fault detection and classification in transmission lines are critical for maintaining the reliability and stability of electrical power systems. Quick and accurate fault detection allows for timely intervention, minimizing equipment damage, and reducing downtime. This study addresses the challenge of effective fault classification, particularly when dealing with smaller, more practical datasets. Initially, the study examined the performance of conventional machine learning algorithms on a comprehensive dataset of 7681 samples, demonstrating high accuracy owing to the inherent symmetry of sinusoidal voltage and current signals. However, the true efficacy of these algorithms was evaluated by minimizing the dataset to 231 training samples, with the remainder being used for testing. A novel Multi-Target Ensemble Classifier was developed to improve classification accuracy. The proposed algorithm achieved an impressive overall accuracy of 0.829165, outperforming traditional methods, including the K-Nearest Neighbors Classifier, support vector classification, random forest classifier, decision tree classifier, AdaBoost classifier, gradient boosting classifier, and Gaussian NB. This research highlights the importance of efficient fault classification techniques in power systems and proposes a superior solution in the form of a multitarget ensemble classifier. Full article

The reliable operation of power transformers is essential for grid stability, yet existing fault detection methods often suffer from inaccuracies and high false alarm rates. This study introduces a machine learning framework leveraging voltage signals for early fault detection. Simulating diverse fault conditions—including single line-to-ground, line-to-line, turn-to-ground, and turn-to-turn faults—on a laboratory-scale three-phase transformer, we evaluated decision trees, support vector machines, and logistic regression models on a dataset of 6000 samples. Decision trees emerged as the most effective, achieving 99.90% accuracy during 5-fold cross-validation and 95% accuracy on a separate test set of 400 unseen samples. Notably, the framework achieved a low false alarm rate of 0.47% on a separate 6000-sample healthy condition dataset. These results highlight the proposed method’s potential to provide a cost-effective, robust, and scalable solution for enhancing transformer fault detection and advancing grid reliability. This demonstrates the efficacy of voltage-based machine learning for transformer diagnostics, offering a practical and resource-efficient alternative to traditional methods. Full article