Search Results (8,996)

Electric bicycles are popular due to their environmental benefits and convenience. However, electric bicycle fires caused by series arc faults remain a serious safety concern. This study focuses on series arc fault identification for electric bicycles under complex operating conditions, covering state of charge (SoC), torque, and speed variations, and simultaneously considers normal state, DC-side series arc fault, and AC-side series arc fault conditions. Five time-domain features, namely root mean square (RMS), standard deviation (STD), skewness (SK), kurtosis (KUR), and current amplitude (CA), and three frequency-domain features, namely amplitude–frequency energy (AFE), amplitude–frequency mean (AFM), and amplitude–frequency kurtosis (AFK), are extracted. An improved principal component analysis (PCA)-based feature fusion method transforms the eight original time–frequency features into a five-dimensional PCA-fused feature representation consisting of PC1, PC2, PC3, fused PC4–PC7, and PC8. The fused features are classified using a radial basis function (RBF)-support vector machine (SVM) model. The proposed method achieves 98.68% test accuracy, 0.9869 Macro-F1, and 0.9931 Macro-AUC. A classifier comparison and feature-level latency analysis are also provided to clarify the accuracy–cost tradeoff and deployment feasibility. The results indicate that the proposed method can provide an interpretable and lightweight solution for electric bicycle controllers, battery management systems (BMSs), and onboard safety-monitoring applications. Full article

Rapid and non-destructive detection of nitrogen content in greenhouse cucumber leaves is essential for precision fertilization, yet traditional chemical methods are destructive and time-consuming, and existing spectral technologies suffer from high cost and poor field adaptability. This study aims to propose a high-precision detection scheme for cucumber leaf nitrogen content based on a lightweight model, suitable for complex scenarios. A total of 698 cucumber leaf images covering three growth stages were collected to build a segmentation dataset. Four categories and eight types of deep learning segmentation models were optimized and compared, and the optimal one was selected to extract leaf regions. Nine color features were extracted and combined with Kjeldahl-measured nitrogen content to construct and optimize three machine learning models, forming a deep learning segmentation–color feature extraction–machine learning prediction process. The results showed that YOLOv11n achieved the best segmentation accuracy, with an IoU of 0.9212 and AP of 0.9998 for high-resolution images. The optimized XGBoost had the highest prediction accuracy, with an MAE of 0.469, MSE of 0.461, and RMSE of 0.679, which are 10.15%, 8.71%, and 4.36% lower than Support Vector Regression with Radial Basis Function kernel (SVR_RBF) respectively, and its predicted nitrogen content aligned well with true values. The proposed scheme integrating YOLOv11n and XGBoost offers a lightweight technical solution for nitrogen nutrition diagnosis and precise fertilization of greenhouse cucumbers. Full article

PM_2.5 is a major air pollutant that threatens urban air quality and public health. Its concentration is influenced by both meteorological conditions and air pollutants, exhibiting complex nonlinear and temporal characteristics. Traditional statistical methods are limited in their ability to model complex relationships among environmental variables, while machine learning models still require improvements in hyperparameter optimization and interpretability. Therefore, developing an accurate and interpretable PM_2.5 estimation model remains an important research objective. This study used daily air-quality and meteorological data collected in Wuhan from 2016 to 2025 to develop six machine learning models: Decision Tree (DT), Random Forest (RF), XGBoost, LightGBM, Support Vector Machine (SVM), and Multilayer Perceptron (MLP). The Particle Swarm Optimization (PSO) algorithm was employed to optimize the hyperparameters of these models. By comparing the root mean square error (RMSE), coefficient of determination (R²), and mean absolute error (MAE) of each model on both the training and test sets, the PSO-MLP model was identified as the best-performing model. Furthermore, the Shapley Additive Explanations (SHAP) method was applied to perform both global and local interpretation analyses of the best-performing model. The results indicate that the PSO-MLP model achieved the highest estimation performance among all evaluated models, with an R² value of 0.746 on the test set. SHAP analysis revealed that CO, Temperature (Temp), and NO₂ were the most influential predictors, while all variables exhibited distinct nonlinear relationships with PM_2.5 concentration. These findings may contribute to PM_2.5 concentration estimation, air-quality management, and environmental decision-making. Full article

Raw sentiment extracted from Chinese financial news is noisy and difficult to use directly for market prediction. This study proposes a mathematical filtering framework that converts noisy Chinese financial news sentiment into reliable quantitative signals for financial market prediction. Three daily sentiment measures were constructed from Chinese financial news: sentiment mean, sentiment dispersion, and polarity imbalance. Seven filtering methods were applied to each measure, including exponential smoothing, autoregressive filtering, ARIMA filtering, moving average smoothing, discrete wavelet transform, Savitzky–Golay filtering, and Kalman filtering. The seven filtered outputs were averaged to produce an ensemble-smoothed sentiment signal. Support vector machines and neural networks were then used to compare the predictive performance of raw and filtered signals for stock index log returns and realized volatility. Filtering reduced the standard deviation of sentiment mean by 48%, sentiment dispersion by 55%, and polarity imbalance by 50%, while mean levels remained stable. Filtered sentiment consistently outperformed raw sentiment across all model configurations. The improvement was larger for realized volatility than for returns: the best support vector machine reduced volatility prediction error by 16.9% and return prediction error by 5.8%. A moderate neural network with 20 hidden neurons achieved optimal performance for both outcomes. Mathematical filtering extracts stable and informative sentiment signals from Chinese financial news. Filtered sentiment is more useful than raw sentiment for predicting market volatility, and the improvement holds across multiple machine learning models. Full article

Diagnosing bearing faults remains a crucial challenge, particularly in effectively extracting fault information and achieving high diagnostic accuracy. To address this issue, this study presents a model for diagnosing bearing faults, which comprises three primary stages: feature extraction, feature selection, and classification. In the feature extraction stage, features are extracted from raw motor signals using empirical mode decomposition (EMD) and fast Fourier transform (FFT). In the feature selection stage, an effective method based on binary grey wolf optimization (BGWO) and the equilibrium optimizer (EO) is developed to remove redundant and irrelevant features. Finally, k-nearest neighbours (KNNs) and support vector machine (SVM) classifiers are used to identify bearing fault conditions. The proposed model is evaluated using four datasets: the University of California, Irvine (UCI) benchmark datasets, a motor bearing fault current-signal dataset, the Case Western Reserve University (CWRU) benchmark dataset, and the Machinery Failure Prevention Technology (MFPT) benchmark dataset. The experimental results show that the proposed method improves bearing fault diagnosis accuracy and demonstrates strong robustness compared with conventional methods. Full article

Background/Objectives: Preoperative differentiation among benign thyroid nodules, follicular variant papillary thyroid carcinoma (FV-PTC), and classical papillary thyroid carcinoma (C-PTC) remains clinically challenging. FV-PTC is particularly difficult to identify due to its substantial sonographic and cytological overlap with both benign nodules and other malignant subtypes, frequently resulting in overtreatment or delayed diagnosis. This study aimed to develop and validate an interpretable multimodal model for accurate three-class discrimination using routine ultrasound images, with a specific focus on improving the preoperative identification of FV-PTC. Methods: This retrospective study included 479 pathologically confirmed thyroid nodules from 462 patients. Conventional ultrasound features and radiomics features extracted from grayscale ultrasound and color Doppler flow imaging were used to construct three predictive models: a Conventional Ultrasound model (conventional ultrasound features only), a Radiomics model (radiomics features only), and an Integrated model (combined features). Each model was trained using four machine learning classifiers. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score. Model interpretability was assessed using SHapley Additive exPlanations (SHAP) analysis, and clinical usefulness was evaluated using decision curve analysis (DCA). Results: The support vector machine (SVM)-based Integrated Model achieved the best overall performance. In the independent testing cohort, the AUCs were 0.853 for FV-PTC, 0.882 for C-PTC and 0.928 for benign nodules. The Integrated Model showed the greatest improvement for FV-PTC, with a ΔAUC of 0.141 compared with the Conventional Ultrasound Model. SHAP (SHapley Additive exPlanations) analysis identified wavelet-HL_gldm_Dependence and wavelet-HH_glcm_InverseVariance as the two most important radiomics predictors in both the Radiomics Model and the Integrated Model, demonstrating robust cross-model stability and high discriminative power. Conclusions: The SVM-based Integrated Model demonstrated promising performance for three-class classification of thyroid nodules and enhanced the preoperative identification of FV-PTC. This approach may provide an interpretable and noninvasive decision-support tool for refining subtype-specific risk stratification and supporting individualized clinical management. Full article

Reliable diagnosis of incipient transformer faults is essential for preventing catastrophic failures and enabling predictive asset management in power systems. Although dissolved gas analysis (DGA) is the most established diagnostic tool for assessing transformer internal condition, fault discrimination remains difficult when gas features are highly correlated, redundant, and only partially separable across fault classes. This study presents a PCA-enhanced artificial neural network (ANN) framework for multiclass transformer fault diagnosis using DGA data. The method is developed on 595 samples classified into six IEC 60599 fault categories and uses a 15-feature representation comprising raw gas concentrations, total hydrocarbon content, and engineered gas-ratio descriptors. To identify an evidence-based diagnostic representation, principal component analysis (PCA) was evaluated across all dimensionalities from k = 1 to 15 before ANN training. The proposed model was benchmarked against alternative feature sets and conventional classifiers, including Gaussian Naïve Bayes, k-nearest neighbours, support vector machines, and ANN without PCA. The best-performing configuration was obtained at k = 13, yielding a test accuracy of 68.1%, compared with 63.9% for ANN without PCA, 56.3% for raw-gas-only ANN, and 33.6% for the IEC three-ratio feature configuration. In addition to improving diagnostic performance, the PCA stage revealed interpretable component structures associated with dominant gas and ratio patterns underlying fault separation. The results indicate that PCA-based feature extraction improves ANN generalization by reducing redundancy and multicollinearity in DGA-derived variables, and provides a practical, lightweight, and interpretable framework for transformer fault diagnosis. Full article

Accurate streamflow prediction in small catchments remains challenging due to their rapid response times, threshold-driven behaviors, and high spatial heterogeneity. This study develops and evaluates a novel modeling approach combining physics-informed feature selection with machine learning algorithms. Overall, 1825 model configurations were tested across fifteen algorithms (including Random Forest, XGBoost, LightGBM, CatBoost, Support Vector Machines, and deep learning methods) using multiple physics-informed input structures based on classical rainfall–runoff theory and mass balance conservation. Models were evaluated for predicting minimum, average, and maximum daily water levels and discharge. Results demonstrate that models structured around Green-Ampt infiltration assumptions consistently outperformed alternative configurations, with Random Forest achieving good performance for water level predictions. Causal models outperformed autoregressive approaches while the residuals analysis showed limitations in predicting extreme values. Feature importance analysis revealed that channel and catchment morphology and initial soil moisture conditions were dominant predictors, aligning with hydrological process understanding. Full article

Accurately mapping surface freshwater bodies (e.g., ponds, reservoirs, and small lakes) is vital for managing insular ecosystems and communities. However, satellite-based extraction in coastal settings is challenged by seawater intrusion, complex topography, and cloud cover. Focusing on bedrock islands outside China’s Pearl River Estuary, this study developed a robust method to address these issues. We used both Gaofen-1 (GF-1) optical and Gaofen-3 (GF-3) Synthetic Aperture Radar (SAR) imagery, supported by field-collected water quality samples from surface freshwater body shorelines for model training and validation. The performance of two index-based methods (the Normalized Difference Water Index, NDWI, and the Normalized Difference Vegetation Index, NDVI), two machine learning algorithms (Random Forest, RF, and Support Vector Machine, SVM), and a U-Net convolutional neural network (U-Net) deep learning model was compared. The U-Net model achieved the highest accuracy, with Area Under the Curve (AUC) values of 0.881 (GF-1) and 0.840 (GF-3). It effectively discriminated freshwater from seawater and mitigated cloud interference, demonstrating superior precision and robustness over traditional methods. This work establishes a high-precision framework for monitoring island freshwater resources, supporting sustainable water management. The proposed framework provides a practical tool for tracking freshwater availability under climate variability and anthropogenic pressures, contributing to the monitoring of Sustainable Development Goal (SDG) indicator 6.3.2 on ambient water quality. Full article

To address the demand for high-precision, high-efficiency, and standardized hydrographic information in intelligent shipping, this study systematically investigates key technologies for high-resolution hydrographic data parsing and intelligent information services. Focusing on the East China Sea, a space–air–ground integrated monitoring data access system is established. A hybrid data assimilation method combining four-dimensional variational (4D-Var) and ensemble Kalman filter is adopted to realize quality control, deep fusion, and optimal state estimation of multi-source heterogeneous hydrographic observations. A hybrid tidal harmonic response model is further developed to improve the refined forecasting accuracy of tide levels and ocean currents. A hierarchically decoupled system architecture is designed, and modules for data production, sharing, exchange, and visualization are developed in compliance with the international S-100 standard. By integrating hybrid spatiotemporal indexing, multi-level caching, and intelligent query optimization, the system achieves low-latency and high-concurrency service capabilities. Experimental results show that, compared with conventional models, the proposed framework reduces tidal forecast RMSE by approximately 15.8% under extreme weather, raises the continuity index of current vectors to 0.93, and cuts the S-100 product generation latency to less than 30 s. This research establishes a full-chain technical system from data parsing and product generation to intelligent services, providing a reliable technical support platform for ship intelligent navigation, dynamic route planning, and maritime safety assurance. Full article

Background/Objectives: Pes planus and pes cavus are common foot deformities, which may lead to pain, functional limitations, and impairment of foot biomechanics. While calcaneal pitch, talar declination, and Meary angles, commonly used in diagnosis, provide objective information, their lack of a gold standard and the observer’s dependence on manual measurements limit their reliability. Therefore, in this study, these angles obtained from weight-bearing lateral foot radiographs were evaluated according to literature references, and the aim was to determine the model that provides the most accurate prediction in the diagnosis of pes planus using machine learning algorithms. It should be emphasized that, because the diagnostic labels were derived from literature-based thresholds of these same angles, the machine-learning task addressed here is the automated reproduction and standardization of expert, angle-threshold-based classification, rather than an independent clinical diagnosis from raw images. Methods: This retrospective study was conducted using weight-bearing lateral foot radiographs of 697 male patients obtained from the archives of public hospitals in Gaziantep. Calcaneal pitch, Meary angle, and talar declination angles were evaluated in both feet, and the data were labeled as normal, pes planus, and pes cavus. The dataset, consisting of a total of 1394 feet, was divided into training and test groups and analyzed using Random Forest, XGBoost, Logistic Regression, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) algorithms; the diagnostic performance of the models was compared using measures such as accuracy, F1 score, sensitivity, and specificity. Results: A total of 1394 feet from 697 male patients (mean age 24.8 ± 5.57 years) were analyzed using five machine learning algorithms with calcaneal pitch angle (CPA), Meary angle (MA), and talar declination angle (TDA) as reference labels. Ensemble-based methods showed superior performance, with XGBoost achieving perfect classification (Accuracy = 1.000) under all three labels for the left foot and 0.996–1.000 for the right foot, while Random Forest reached 0.986–1.000 across all experiments. Logistic Regression and SVM yielded moderate accuracies (0.905–0.973), whereas KNN consistently performed the weakest (0.905–0.964), particularly in the pes cavus subgroup. The near-perfect accuracy obtained when the labeling angle was itself included among the predictors reflects, at least in part, the algebraic reconstruction of the threshold rule from a same-source variable rather than genuine diagnostic generalization; results should therefore be interpreted with this in mind. Conclusions: This study demonstrates that machine learning, particularly ensemble methods such as XGBoost and Random Forest, provides high accuracy and consistency in diagnosing foot arch deformities based on radiographic angle measurements. Traditional models, such as Logistic Regression, still hold value in terms of clinical interpretability despite their lower performance. The findings suggest that machine learning-based approaches can offer objective, rapid, and reliable decision support tools for diagnosing pes planus and pes cavus, but external validation studies are necessary for clinical generalizability. Full article

Partial discharge (PD) is a key indicator of insulation degradation in high-voltage transformers and can provide early warning of incipient failure. Although artificial neural networks (ANNs) have been applied to PD classification, their performance may be affected by redundant features and overfitting when using expanded feature spaces. This study proposes a PD severity classification framework that combines physics-informed feature engineering, principal component analysis (PCA), and a multilayer perceptron (MLP) neural network. PD measurements were acquired from a physical transformer using the IEC 60270 electrical measurement method, yielding 294 samples labelled into four severity classes: normal, low, medium, and high PD. Two measured variables, namely PD magnitude and applied voltage, were expanded into a 10-dimensional feature space using energy-based, ratio-based, logarithmic, and normalized features. PCA was then used to reduce the feature space, and the retained principal components were used as inputs to the classifier. The results show that the first two principal components captured more than 90% of the total variance and enabled the MLP to achieve 98.3% test accuracy, matching the performance obtained using all 10 engineered features and improving on classification based on the raw measurements alone (91.5%). The proposed PCA-ANN model also achieved perfect precision and recall for the medium- and high-severity classes on the test set, and outperformed K-nearest neighbours, support vector machine, and Gaussian Naïve Bayes models in 5-fold cross-validation. These findings indicate that PCA can reduce feature dimensionality without loss of diagnostic performance, providing an efficient approach for transformer PD severity classification. Full article

The growing worldwide prevalence of Diabetes Mellitus highlights the urgent need for effective early detection methods to enable prompt intervention. This study develops a machine learning-based decision-support prototype for predicting diabetes risk using health metrics from the DiaHealth dataset, a recently published Bangladeshi open-source dataset for Type 2 diabetes prediction. Five supervised learning algorithms were evaluated: Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Decision Tree (DT), and Random Forest (RF). Models were assessed across three stages: before feature scaling, after standardisation, and following hyperparameter optimisation via GridSearchCV, using accuracy, precision, recall, and F1-score as evaluation metrics. LR and SVM showed marked improvements after standardisation, consistent with their sensitivity to feature magnitude, whilst tree-based approaches such as DT and RF remained largely unchanged. KNN displayed minimal sensitivity to scaling, which is discussed in relation to the feature distributions of the dataset. Following hyperparameter tuning, RF achieved the highest accuracy of 95%, outperforming all other models. RF predictions were interpreted using Local Interpretable Model-agnostic Explanations (LIME) to promote transparency in model decision-making. The best-performing model was subsequently deployed as an interactive web-based prototype application using Streamlit, providing real-time prediction outputs. These findings demonstrate how preprocessing choices and hyperparameter tuning can differentially affect algorithm performance and illustrate the potential of combining explainable AI with practical deployment for diabetes risk assessment in a research context. Full article

River water quality monitoring data are often non-stationary and nonlinear and may contain occasional abnormal values. To support anomaly early warning, this study proposes an LSTM–SOA–DA framework. Water quality monitoring data for six indicators, including pH, DO, COD_Mn, NH₃-N, TP, and TN, were collected from the Bahekou section in Xi’an at 4 h intervals from 2021 to 2023 and chronologically divided into training and testing sets at an 8:2 ratio. The Seagull Optimization Algorithm (SOA) was used to optimize the L2 regularization coefficient, initial learning rate, and number of hidden units of the Long Short-Term Memory (LSTM) network, establishing an LSTM-SOA forecasting model. Compared with traditional LSTM, BP neural network, Support Vector Machine (SVM), Extreme Learning Machine (ELM), and other optimization-based LSTM models, the proposed model achieved better RMSE and R² performance, indicating improved prediction accuracy. Based on the residuals between observed and predicted values, the DA method was then used to determine indicator-specific anomaly thresholds from the residual distributions. The model identified 193 abnormal points in the test set. After manual rechecking, the Precision, Recall, and F1-score reached 87.6%, 93.9%, and 90.64%, respectively. These results suggest that the LSTM–SOA–DA framework can effectively identify abnormal fluctuations in river water quality data and support timely water environment management. Full article

Water quality monitoring is a fundamental element of sustainable aquaculture management, as changes in parameters of physicochemical and biological properties directly affect the health, growth performance, and productivity of the aquaculture systems. Although traditional machine learning (ML) methods have demonstrated effectiveness in water quality classification, their performance often depends on large amounts of labeled data, which can be challenging and expensive to collect in real-world aquaculture environments. This study explores a few-shot learning (FSL) framework for data-efficient water quality classification under limited supervision to address this limitation. Several FSL models, including prototypical networks (ProtoNet), Siamese Networks, and Matching Networks were developed and evaluated in a comparative experimental framework against the traditional machine learning classifiers logistic regression, random forest, support vector machine and extreme gradient boosting. Low-data learning scenarios were simulated using a structured episodic evaluation approach. Experimental results demonstrate FSL techniques outperform traditional machine learning methods across all evaluated scenarios. Among the tested methods, ProtoNet achieved the highest performance, attaining an accuracy of 94.46% and an ROC-AUC score of 98.65%, indicating superior discriminative capability and robustness. Siamese Networks also demonstrated competitive performance under highly constrained data conditions. Furthermore, latent-space visualization, confusion matrix analysis, paired t-test statistical analysis, and ablation studies confirmed that episodic meta-learning enables the learning of highly discriminative latent representations with strong generalization capability under limited labeled data conditions. The findings highlight that FSL provides a robust and scalable framework for intelligent water quality classification in aquaculture systems, particularly in scenarios where labeled data are scarce, offering significant potential for sustainable aquaculture monitoring applications. Full article