Search Results (5,479)

The spread of COVID-19 is influenced by multiple factors, including control policies, virus characteristics, individual behaviors, and environmental conditions, exhibiting highly complex nonlinear dynamic features. The time series of new confirmed cases shows significant nonlinearity and non-stationarity. Traditional prediction methods that rely solely on one-dimensional case data struggle to capture the multi-dimensional features of the data and are limited in handling nonlinear and non-stationary characteristics. Their prediction accuracy and generalization capabilities remain insufficient, and most existing studies focus on single-step forecasting, with limited attention to multi-step prediction. To address these challenges, this paper proposes a multi-module fusion prediction model—TSMixer-BiKSA network—that integrates multi-feature inputs, Variational Mode Decomposition (VMD), and a dual-branch parallel architecture for 1- to 3-day-ahead multi-step forecasting of new COVID-19 cases. First, variables highly correlated with the target sequence are selected through correlation analysis to construct a feature matrix, which serves as one input branch. Simultaneously, the case sequence is decomposed using VMD to extract low-complexity, highly regular multi-scale modal components as the other input branch, enhancing the model’s ability to perceive and represent multi-source information. The two input branches are then processed in parallel by the TSMixer-BiKSA network model. Specifically, the TSMixer module employs a multilayer perceptron (MLP) structure to alternately model along the temporal and feature dimensions, capturing cross-time and cross-variable dependencies. The BiGRU module extracts bidirectional dynamic features of the sequence, improving long-term dependency modeling. The KAN module introduces hierarchical nonlinear transformations to enhance high-order feature interactions. Finally, the SA attention mechanism enables the adaptive weighted fusion of multi-source information, reinforcing inter-module synergy and enhancing the overall feature extraction and representation capability. Experimental results based on COVID-19 case data from Italy and the United States demonstrate that the proposed model significantly outperforms existing mainstream methods across various error metrics, achieving higher prediction accuracy and robustness. Full article

In this study, we introduced a novel Trajectory-Channel Transport Model (TCTM) to unravel spatiotemporal dynamics of PM_2.5 pollution. By integrating high-resolution simulations from the Weather Research and Forecasting (WRF) model with the Nested Air-Quality Prediction Modeling System (WRF-NAQPMS) and 72 h backward-trajectory analysis, TCTM enables the precise identification of source regions, the delineation of key transport corridors, and a quantitative assessment of regional contributions to receptor sites. Focusing on four Yangtze River Delta cities (Hangzhou, Shanghai, Nanjing, Hefei) during a January 2020 pollution event, the results demonstrate that TCTM’s Weighted Concentration Source (WCS) and Source Pollution Characteristic Index (SPCI) outperform traditional PSCF and CWT methods in source-attribution accuracy and resolution. Unlike receptor-based statistical approaches, TCTM reconstructs pollutant transport processes, quantifies spatial decay, and assigns contributions via physically interpretable metrics. This innovative framework offers actionable insights for targeted air-quality management strategies, highlighting its potential as a robust tool for pollution mitigation planning. Full article

Rapid global urbanization poses complex challenges that demand advanced data-driven forecasting solutions for smart cities. Traditional statistical and standalone Long Short-Term Memory (LSTM) models often struggle to capture non-linear dynamics and long-term dependencies in urban time-series data. This review critically examines hybrid LSTM models that integrate LSTM with complementary algorithms, including CNN, GRU, ARIMA, and SVM. These hybrid architectures aim to enhance prediction accuracy, integrate diverse data sources, and improve computational efficiency. This study systematically reviews principles, trends, and real-world applications, quantitatively evaluating hybrid LSTM models using performance metrics such as mean absolute error (MAE), root mean square error (RMSE), and the coefficient of determination (R²), while identifying key study limitations. The case studies considered include traffic management, environmental monitoring, energy forecasting, public health, infrastructure assessment, and urban waste management. For example, hybrid models have achieved substantial accuracy improvements in traffic congestion forecasting, reducing their mean absolute error by up to 29%. Despite the inherent challenges related to structural complexity, interpretability, and data requirements, ongoing research on attention mechanisms, model compression, and explainable AI has significantly mitigated these limitations. Thus, hybrid LSTM models have emerged as vital analytical tools capable of robust spatiotemporal prediction, effectively supporting sustainable urban development and data-driven decision-making in evolving smart city environments. Full article

The demand for large-scale, heavy-duty autonomous pavement-sweeping robots is rising due to urban growth, hygiene needs, and labor shortages. Ensuring their health and safe operation in dynamic outdoor environments is vital, as terrain unevenness and slope gradients can accelerate wear, increase maintenance costs, and pose safety risks. This study introduces an AI-driven condition monitoring (CM) framework designed to detect terrain unevenness and slope gradients in real time, distinguishing between safe and unsafe conditions. As system vibration levels and energy consumption vary with terrain unevenness and slope gradients, vibration and current data are collected for five CM classes identified: safe, moderately safe terrain, moderately safe slope, unsafe terrain, and unsafe slope. A simple-structured one-dimensional convolutional neural network (1D CNN) model is developed for fast and accurate prediction of the safe to unsafe classes for real-time application. An in-house developed large-scale autonomous pavement-sweeping robot, PANTHERA 2.0, is used for data collection and real-time experiments. The training dataset is generated by extracting representative vibration and heterogeneous slope data using three types of interoceptive sensors mounted in different zones of the robot. These sensors complement each other to enable accurate class prediction. The dataset includes angular velocity data from an IMU, vibration acceleration data from three vibration sensors, and current consumption data from three current sensors attached to the key motors. A CM-map framework is developed for real-time monitoring of the robot by fusing the predicted anomalous classes onto a 3D occupancy map of the workspace. The performance of the trained CM framework is evaluated through offline and real-time field trials using statistical measurement metrics, achieving an average class prediction accuracy of 92% and 90.8%, respectively. This demonstrates that the proposed CM framework enables maintenance teams to take timely and appropriate actions, including the adoption of suitable maintenance strategies. Full article

This study explores the application of spiking neural networks (SNNs) for click-through rate (CTR) prediction in personalized online advertising systems, introducing a novel hybrid model, the Temporal Rate Spike with Attention Neural Network (TRA–SNN). By leveraging the biological plausibility and energy efficiency of SNNs, combined with attention-based mechanisms, the TRA–SNN model captures temporal dynamics and rate-based patterns to achieve performance comparable to state-of-the-art Artificial Neural Network (ANN)-based models, such as Deep & Cross Network v2 (DCN-V2) and FinalMLP. The models were trained and evaluated on the Avazu and Digix datasets, using standard metrics like AUC-ROC and accuracy. Through rigorous hyperparameter tuning and standardized preprocessing, this study ensures fair comparisons across models, highlighting SNNs’ potential for scalable, sustainable deployment in resource-constrained environments like mobile devices and large-scale ad platforms. This work is the first to apply SNNs to CTR prediction, setting a new benchmark for energy-efficient predictive modeling and opening avenues for future research in hybrid SNN–ANN architectures across domains like finance, healthcare, and autonomous systems. Full article

Precisely predicting photovoltaic (PV) output is crucial for reliable grid integration; so far, most models rely on site-specific sensor data or treat large meteorological datasets as black boxes. This study proposes an explainable machine-learning framework that simultaneously ranks the most informative weather parameters and reveals their physical relevance to PV generation. Starting from 27 local and plant-level variables recorded at 15 min resolution for a 1 MW array in Çanakkale region, Türkiye (1 August 2022–3 August 2024), we apply a three-stage feature-selection pipeline: (i) variance filtering, (ii) hierarchical correlation clustering with Ward linkage, and (iii) a meta-heuristic optimizer that maximizes a neural-network R² while penalizing poor or redundant inputs. The resulting subset, dominated by apparent temperature and diffuse, direct, global-tilted, and terrestrial irradiance, reduces dimensionality without significantly degrading accuracy. Feature importance is then quantified through two complementary aspects: (a) tree-based permutation scores extracted from a set of ensemble models and (b) information gain computed over random feature combinations. Both views converge on shortwave, direct, and global-tilted irradiance as the primary drivers of active power. Using only the selected features, the best model attains an average R² ≅ 0.91 on unseen data. By utilizing transparent feature-reduction techniques and explainable importance metrics, the proposed approach delivers compact, more generalized, and reliable PV forecasts that generalize to sites lacking embedded sensor networks, and it provides actionable insights for plant siting, sensor prioritization, and grid-operation strategies. Full article

This study investigates the effects of transcutaneous electroacupuncture stimulation (TEAS) on eyeblink rate, EEG, and heart rate variability (HRV), emphasising whether eyeblink data—often dismissed as artefacts—can serve as useful physiological markers. Sixty-six participants underwent four TEAS sessions with different stimulation frequencies (2.5, 10, 80, and 160 pps, with 160 pps as a low-amplitude sham). EEG, ECG, PPG, and respiration data were recorded before, during, and after stimulation. Using non-parametric statistical analyses, including Friedman’s test, Wilcoxon, Conover–Iman, and bootstrapping, the study found significant changes across eyeblink, EEG, and HRV measures. Eyeblink laterality, particularly at 2.5 and 10 pps, showed strong frequency-specific effects. EEG power asymmetry and spectral centroids were associated with HRV indices, and 2.5 pps stimulation produced the strongest parasympathetic HRV response. Blink rate correlated with increased sympathetic and decreased parasympathetic activity. Baseline HRV measures, such as lower heart rate, predicted participant dropout. Eyeblinks were analysed using BLINKER software (v. 1.1.0), and additional complexity and entropy (‘CEPS-BLINKER’) metrics were derived. These measures were more predictive of adverse reactions than EEG-derived indices. Overall, TEAS modulates multiple physiological markers in a frequency-specific manner. Eyeblink characteristics, especially laterality, may offer valuable insights into autonomic function and TEAS efficacy in neuromodulation research. Full article

Positron emission tomography (PET) and liquid biopsy have independently transformed prostate cancer management. This systematic review explores the complementary roles of PET imaging and liquid biopsy in prostate cancer, focusing on their combined diagnostic, monitoring, and prognostic potential. A systematic search of PubMed, Scopus, and Cochrane Library databases was conducted to identify human studies published in English up to January 2025. Seventeen studies met the inclusion criteria and were analyzed according to PRISMA guidelines. Across the included studies, PET-derived imaging metrics, such as metabolic activity and radiotracer uptake, correlated consistently with liquid biopsy biomarkers, including circulating tumor cells and cell-free DNA. Their joint application demonstrated added value in early detection, treatment monitoring, and outcome prediction, particularly in castration-resistant prostate cancer. Independent and synergistic prognostic value was noted for both modalities, including survival outcomes such as overall survival and progression-free survival. Combining PET imaging and liquid biopsy emerges as a promising, non-invasive strategy for improving prostate cancer diagnosis, monitoring, and therapeutic stratification. While preliminary findings are encouraging, large-scale prospective studies are essential to validate their integrated clinical utility. Full article

Accurate, energy-efficient climate regulation is crucial for scaling smart greenhouse production. While nonlinear model predictive control (NMPC) can co-optimize yield and resource use, its efficacy hinges on short-range weather information and real-time solver feasibility. This paper investigates the performance of advanced NMPC strategies for smart greenhouse climate control, with particular emphasis on the roles of AI-driven disturbance prediction and warm-start initialization for real-time optimization. Six controller configurations, including feedback-only, LSTM-based forecast, and ideal disturbance models, each with and without warm-start, were tested in a 40-day simulation of a lettuce smart greenhouse. Performance metrics included final biomass, constraint violations, resource costs, profit, and solver time. Results show that feedback-only controllers maximize yield and profit, incurring higher CO₂ costs but lower heating costs, alongside greater constraint violations compared to the predictive strategies. Predictive and ideal disturbance-aware controllers effectively reduce resource consumption and improve constraint compliance at the expense of lower yields. Importantly, warm-start initialization significantly accelerates computation without affecting control quality. The study also demonstrates that penalty parameters, rather than economic weight settings, predominantly determine aggregate constraint violation. The findings provide actionable insights for designing and deploying NMPC-based greenhouse controllers, highlighting the importance of warm-start techniques and the trade-offs between productivity, resource efficiency, and environmental compliance. Full article

The gas-production potential of shale gas is a comprehensive evaluation metric that assesses the reservoir quality, gas-content properties, and gas-production capacity. Currently, the evaluation of gas-production potential is generally conducted through qualitative comparisons of relevant parameters, which can lead to multiple solutions and make it difficult to establish a comprehensive evaluation index. This paper introduces a gas-production potential evaluation method based on the Analytic Hierarchy Process (AHP). It uses judgment matrices to analyze key parameters such as gas content, brittleness index, total organic carbon content, the length of high-quality gas-layer horizontal sections, porosity, gas saturation, formation pressure, and formation density. By integrating fuzzy mathematics, a mathematical model for gas-production potential is established, and corresponding gas-production levels are defined. The model categorizes gas-production potential into four levels: when the gas-production index exceeds 0.65, it is classified as a super-high-production well; when the gas-production index is between 0.45 and 0.65, it is classified as a high-production well; when the gas-production index is between 0.35 and 0.45, it is classified as a medium-production well; and when the gas-production index is below 0.35, it is classified as a low-production well. Field applications have shown that this model can accurately predict the gas-production potential of shale gas wells, showing a strong correlation with the unobstructed flow rate of gas wells, and demonstrating broad applicability. Full article

In today’s increasingly interconnected digital world, cyber threats have grown in frequency and sophistication, making intrusion detection systems a critical component of modern cybersecurity frameworks. Traditional IDS methods, often based on static signatures and rule-based systems, are no longer sufficient to detect and respond to complex and evolving attacks. To address these challenges, Artificial Intelligence and machine learning have emerged as powerful tools for enhancing the accuracy, adaptability, and automation of IDS solutions. This study presents a novel, hybrid ensemble learning-based intrusion detection framework that integrates deep learning and traditional ML algorithms with explainable artificial intelligence for real-time cybersecurity applications. The proposed model combines an Artificial Neural Network and Support Vector Machine as base classifiers and employs a Random Forest as a meta-classifier to fuse predictions, improving detection performance. Recursive Feature Elimination is utilized for optimal feature selection, while SHapley Additive exPlanations (SHAP) provide both global and local interpretability of the model’s decisions. The framework is deployed using a Flask-based web interface in the Amazon Elastic Compute Cloud environment, capturing live network traffic and offering sub-second inference with visual alerts. Experimental evaluations using the NSL-KDD dataset demonstrate that the ensemble model outperforms individual classifiers, achieving a high accuracy of 99.40%, along with excellent precision, recall, and F1-score metrics. This research not only enhances detection capabilities but also bridges the trust gap in AI-powered security systems through transparency. The solution shows strong potential for application in critical domains such as finance, healthcare, industrial IoT, and government networks, where real-time and interpretable threat detection is vital. Full article

Background: Colorectal cancer (CRC) is a major contributor to cancer mortality on a global scale, with polyps being critical precursors. The accurate classification of colorectal polyps (CRPs) from colonoscopy images is essential for the timely diagnosis and treatment of CRC. Method: This research proposes a novel hybrid model, CRP-ViT, integrating ResNet50 with Vision Transformers (ViTs) to enhance feature extraction and improve classification performance. This study conducted a comprehensive comparison of the CRP-ViT model against traditional convolutional neural networks (CNNs) and emerging quantum neural networks (QNNs). Experiments were conducted for binary classification to predict the presence of polyps and multi-classification to predict specific polyp types (hyperplastic, adenomatous, and serrated). Results: The results demonstrate that CRP_QNN-ViT achieved superior classification performance while maintaining computational efficiency. CRP_QNN-ViT achieved an accuracy of 98.18% for training and 97.73% for validation on binary classification and 98.13% during training and 97.92% for validation on multi-classification tasks. In addition to the key metrics, computational parameters were compared, where CRP_QNN-ViT excelled in computational time. Conclusions: This comparative analysis reveals the potential of integrating quantum computing into medical image analysis and underscores the effectiveness of transformer-based architectures for CRP classification. Full article

This study investigates the development of cognitive, emotional, and social skills in pre-service teachers through extracurricular activities, addressing 21st century challenges in preparing educators for diverse learning environments. It was hypothesized that extracurricular activities would positively influence cognitive skills (self-efficacy, self-regulation), emotional dimensions (professional interest), social competencies (teacher–student relationships), and academic achievement. This study employed predictive correlational methodology based on an integrated theoretical framework combining Social Cognitive Theory, Self-Determination Theory, Self-Regulation Theory, and Interpersonal Relationships Theory within formal–informal learning contexts. A psychometrically robust instrument (“Scale on the Contribution of Extracurricular Activities to Professional Development”) was developed and validated through exploratory and confirmatory factor analyses, yielding a five-factor structure with strong reliability indicators (Cronbach’s α = 0.91–0.93; CR = 0.816–0.912; AVE = 0.521–0.612). Data from 775 pre-service teachers (71.1% female) across multiple disciplines at a Turkish university were analyzed using structural equation modeling (χ²/df = 2.855, RMSEA = 0.049, CFI = 0.93, TLI = 0.92). Results showed that extracurricular participation significantly influenced self-efficacy (β = 0.849), professional interest (β = 0.418), self-regulation (β = 0.191), teacher–student relationships (β = 0.137), and academic achievement (β = 0.167). Notably, an unexpected negative relationship emerged between self-efficacy and academic achievement (β = −0.152). The model demonstrated strong explanatory power for self-efficacy (R² = 72.8%), professional interest (R² = 78.7%), self-regulation (R² = 77.2%), and teacher–student relationships (R² = 63.1%) while explaining only 1.8% of academic achievement variance. This pattern reveals distinct developmental pathways for professional versus academic competencies, leading to a comprehensive practical implications framework supporting multidimensional assessment approaches in teacher education. These findings emphasize the strategic importance of extracurricular activities in teacher education programs and highlight the need for holistic approaches beyond traditional academic metrics, contributing to Sustainable Development Goal 4 by providing empirical evidence for integrating experiential learning opportunities that serve both academic researchers and educational practitioners seeking evidence-based approaches to teacher preparation. Full article

Magnetic tiles are an important component of permanent magnet motors, and the quality of magnetic tiles directly affects the performance and service life of a motor. It is necessary to perform defect detection on magnetic tiles in industrial production and remove those with defects. The YOLOv8-AHF algorithm is proposed to improve the ability of network feature information extraction and solve the problem of missed detection or poor detection results in surface defect detection due to the small volume of permanent magnet motor tiles, which reduces the deviation between the predicted box and the true box simultaneously. Firstly, a hybrid module of a combination of atrous convolution and depthwise separable convolution (ADConv) is introduced in the backbone of the model to capture global and local features in magnet tile detection images. In the neck section, a hybrid attention module (HAM) is introduced to focus on the regions of interest in the magnetic tile surface defect images, which improves the ability of information transmission and fusion. The Focal-Enhanced Intersection over Union loss function (Focal-EIoU) is optimized to effectively achieve localization. We conducted comparative experiments, ablation experiments, and corresponding generalization experiments on the magnetic tile surface defect dataset. The experimental results show that the evaluation metrics of YOLOv8-AHF surpass mainstream single-stage object detection algorithms. Compared to the You Only Look Once version 8 (YOLOv8) algorithm, the performance of the YOLOv8-AHF algorithm was improved by 5.9%, 4.1%, 5%, 5%, and 5.8% in terms of mAP@0.5, mAP@0.5:0.95, F1-Score, precision, and recall, respectively. This algorithm achieved significant performance improvement in the task of detecting surface defects on magnetic tiles. Full article

Precise evaluation of risk and reliability is crucial for decision making and predicting the outcome of investment in a photovoltaic power system (PVPS) due to its intermittent source. This paper explores different methodologies for risk evaluation and reliability assessment, which can be categorized into qualitative, quantitative, and hybrid qualitative and quantitative (HQQ) approaches. Qualitative methods include failure mode analysis, graphical analysis, and hazard analysis, while quantitative methods include analytical methods, stochastic methods, Bayes’ theorem, reliability optimization, multi-criteria analysis, and data utilization. HQQ methodology combines table-based and visual analysis methods. Currently, reliability assessment techniques such as mean time between failures (MTBF), system average interruption frequency index (SAIFI), and system average interruption duration index (SAIDI) are commonly used to predict PVPS performance. However, alternative methods such as economical metrics like the levelized cost of energy (LCOE) and net present value (NPV) can also be used. Therefore, a risk and reliability approach should be applied together to improve the accuracy of predicting significant aspects in the photovoltaic industry. Full article