Search Results (1,480)

Reliable localization is critical for robot navigation in complex indoor environments. In this paper, we propose an uncertainty-aware localization method that enhances the reliability of localization outputs without modifying the prediction model itself. This study introduces a percentile-based rejection strategy that filters out unreliable 3-degree-of-freedom pose predictions based on aleatoric and epistemic uncertainties the network estimates. We apply this approach to a multi-modal end-to-end localization that fuses RGB images and 2D LiDAR data, and we evaluate it across three real-world datasets collected using a commercialized serving robot. Experimental results show that applying stricter uncertainty thresholds consistently improves pose accuracy. Specifically, the mean position error, calculated as the average Euclidean distance between the predicted and ground-truth (x, y) coordinates, is reduced by 41.0%, 56.7%, and 69.4%, and the mean orientation error, representing the average angular deviation between the predicted and ground-truth yaw angles, is reduced by 55.6%, 65.7%, and 73.3%, when percentile thresholds of 90%, 80%, and 70% are applied, respectively. Furthermore, the rejection strategy effectively removes extreme outliers, resulting in better alignment with ground truth trajectories. To the best of our knowledge, this is the first study to quantitatively demonstrate the benefits of percentile-based uncertainty rejection in multi-modal and end-to-end localization tasks. Our approach provides a practical means to enhance the reliability and accuracy of localization systems in real-world deployments. Full article

Background: Brain tumors can severely impair neurological function, leading to symptoms such as headaches, memory loss, motor coordination deficits, and visual disturbances. In severe cases, they may cause permanent cognitive damage or become life-threatening without early detection. Methods: To address this, we propose an interpretable deep ensemble model for tumor detection in Magnetic Resonance Imaging (MRI) by integrating pre-trained Convolutional Neural Networks—EfficientNetB7, InceptionV3, and Xception—using a soft voting ensemble to improve classification accuracy. The framework is further enhanced with a Light Gradient Boosting Machine as a meta-learner to increase prediction accuracy and robustness within a stacking architecture. Hyperparameter tuning is conducted using Optuna, and overfitting is mitigated through batch normalization, L2 weight decay, dropout, early stopping, and extensive data augmentation. Results: These regularization strategies significantly enhance the model’s generalization ability within the BR35H dataset. The framework achieves a classification accuracy of 99.83 on the MRI dataset of 3060 images. Conclusions: To improve interpretability and build clinical trust, Explainable Artificial Intelligence methods Grad-CAM++, LIME, and SHAP are employed to visualize the factors influencing model predictions, effectively highlighting tumor regions within MRI scans. This establishes a strong foundation for further advancements in radiology decision support systems. Full article

IP spoofing is a critical component in many cyberattacks, enabling attackers to evade detection and conceal their identities. This study rigorously compares eight deep learning models—LSTM, GRU, CNN, MLP, DNN, RNN, ResNet1D, and xLSTM—for their efficacy in detecting IP spoofing attacks. Overfitting was mitigated through techniques such as dropout, early stopping, and normalization. Models were trained using binary cross-entropy loss and the Adam optimizer. Performance was assessed via accuracy, precision, recall, F1 score, and inference time, with each model executed a total of 15 times to account for stochastic variability. Results indicate a powerful performance across all models, with LSTM and GRU demonstrating superior detection efficacy. After ONNX conversion, the MLP and DNN models retained their performance while achieving significant reductions in inference time, miniaturized model sizes, and platform independence. These advancements facilitated the effective utilization of the developed systems in real-time network security applications. The comprehensive performance metrics presented are crucial for selecting optimal IP spoofing detection strategies tailored to diverse application requirements, serving as a valuable reference for network anomaly monitoring and targeted attack detection. Full article

The prestressed concrete-filled double skin steel tube (CFDST) lattice tower has emerged as a promising structural solution for large-capacity wind turbine systems due to its superior load-bearing capacity and economic efficiency. The steel–concrete composite adapter (SCCA) is a key component that connects the upper tubular steel tower to the lower lattice segment, transferring axial loads. However, the compressive behaviour of the SCCA remains underexplored due to its complex multi-shell configuration and steel–concrete interaction. This study investigates the axial compression behaviour of SCCAs through refined finite element simulations, identifying diagonal extrusion as the typical failure mode. The analysis clarifies the distinct roles of the outer and inner shells in confinement, highlighting the dominant influence of outer shell thickness and concrete strength. A sensitivity-based parametric study highlights the significant roles of outer shell thickness and concrete strength. To address the high cost of FE simulations, a 400-sample database was built using Latin Hypercube Sampling and engineering-grade material inputs. Using this dataset, five neural networks were trained to predict SCCA capacity. The Dropout model exhibited the best accuracy and generalization, confirming the feasibility of physics-informed, data-driven prediction for SCCAs and outperforming traditional empirical approaches. A graphical prediction tool was also developed, enabling rapid capacity estimation and design optimization for wind turbine structures. This tool supports real-time prediction and multi-objective optimization, offering practical value for the early-stage design of composite adapters in lattice turbine towers. Full article

This work proposes a methodology for the automated sizing of transistors in analog integrated circuits, based on a modular and hierarchical representation of the circuit. The methodology combines structured design techniques and systematic design flow to generate a hierarchy of simplified macromodels that define their specifications locally and are interconnected with other macromodels or transistor-level primitive blocks. These primitive blocks can be described using symbolic models or pre-characterized data from look-up tables (LUTs). The symbolic representation of the system is obtained using Modified Nodal Analysis (MNA), and the exploration of each block is performed using local design spaces constrained by top-level specifications. The methodology is validated through the design of low dropout voltage regulators (LDOs) for DC-DC integrated power systems using open-source tools and three process design kits: Sky130A, GF180MCU, and IHP-SG13G2. Results show that the methodology allows the exploration of several topologies and technologies, demonstrating its versatility and modularity, which are key aspects in analog design. Full article

We investigate the stability of linear discrete-time control systems with a fuzzy logic feedback under sporadic sensor data loss. In our framework, each state measurement is a fuzzy number, and occasional “packet dropouts” are modeled by a lacunary subsequence of missing readings. We introduce a novel mathematical approach using lacunary statistical convergence in fuzzy paranormed spaces to analyze such systems. Specifically, we treat the sequence of fuzzy measurements as a double sequence (indexed by time and state component) and consider an admissible ideal of “negligible” index sets that includes the missing–data pattern. Using the concept of ideal fuzzy—paranorm convergence (I-fp convergence), we formalize a lacunary statistical consistency condition on the fuzzy measurements. We prove that if the closed-loop matrix $A-BK$ is Schur stable (i.e., $\parallel A-BK\parallel <1$) in the absence of dropouts, then under the lacunary statistical consistency condition, the controlled system is practically stable despite intermittent measurement losses. In other words, for any desired tolerance, the state eventually remains within that bound (though not necessarily converging to zero). Our result yields an explicit, non-probabilistic (distribution-free) analytical criterion for robustness to sensor dropouts, without requiring packet-loss probabilities or Markov transition parameters. This work merges abstract convergence theory with control application: it extends statistical and ideal convergence to double sequences in fuzzy normed spaces and applies it to ensure stability of a networked fuzzy control system. Full article

Deep learning has significantly advanced medical image analysis by enabling accurate, automated diagnosis across diverse clinical tasks such as lesion classification and disease detection. However, the practical deployment of these systems is still hindered by two major challenges: the limited availability of expert-annotated data and substantial domain shifts caused by variations in imaging devices, acquisition protocols, and patient populations. Although recent semi-supervised domain generalization (SSDG) approaches attempt to address these challenges, they often suffer from two key limitations: (i) reliance on computationally expensive uncertainty modeling techniques such as Monte Carlo dropout, and (ii) inflexible shared-head classifiers that fail to capture domain-specific variability across heterogeneous imaging styles. To overcome these limitations, we propose MultiStyle-SSDG, a unified semi-supervised domain generalization framework designed to improve model generalization in low-label scenarios. Our method introduces a multi-style ensemble pseudo-labeling strategy guided by entropy-based filtering, incorporates prototype-based conformity and semantic alignment to regularize the feature space, and employs a domain-specific multi-head classifier fused through attention-weighted prediction. Additionally, we introduce a dual-level neural-style transfer pipeline that simulates realistic domain shifts while preserving diagnostic semantics. We validated our framework on the ISIC2019 skin lesion classification benchmark using 5% and 10% labeled data. MultiStyle-SSDG consistently outperformed recent state-of-the-art methods such as FixMatch, StyleMatch, and UPLM, achieving statistically significant improvements in classification accuracy under simulated domain shifts including style, background, and corruption. Specifically, our method achieved 78.6% accuracy with 5% labeled data and 80.3% with 10% labeled data on ISIC2019, surpassing FixMatch by 4.9–5.3 percentage points and UPLM by 2.1–2.4 points. Ablation studies further confirmed the individual contributions of each component, and t-SNE visualizations illustrate enhanced intra-class compactness and cross-domain feature consistency. These results demonstrate that our style-aware, modular framework offers a robust and scalable solution for generalizable computer-aided diagnosis in real-world medical imaging settings. Full article

Mine water hazards represent one of the principal threats to safe coal mine operations; therefore, accurately predicting mine water inflow is critical for drainage system design and water hazard mitigation. Because mine water inflow is governed by the combined influence of multiple hydrogeological factors and thus exhibits pronounced non-linear characteristics, conventional approaches are inadequate in terms of forecasting accuracy and medium- to long-term predictive capability. To address this issue, this study proposes a Chaos-Autoformer-based method for predicting mine water inflow. First, the univariate inflow series is mapped into an m-dimensional phase space by means of phase-space reconstruction from chaos theory, thereby fully preserving its non-linear features; the reconstructed vectors are then used to train and forecast inflow with an improved Chaos-Autoformer model. On top of the original Autoformer architecture, the proposed model incorporates a Chaos-Attention mechanism and a Lyap-Dropout scheme, which enhance sensitivity to small perturbations in initial conditions and complex non-linear propagation paths while improving stability in long-horizon forecasting. In addition, the loss function integrates the maximum Lyapunov exponent error and earth mode decomposition (EMD) indices so as to jointly evaluate dynamical consistency and predictive performance. An empirical analysis based on monitoring data from the Liangshuijing Coal Mine for 2022–2025 demonstrates that the trained model delivers high accuracy and stable performance. Ablation experiments further confirm the significant contribution of the chaos-aware components: when these modules are removed, forecasting accuracy declines to only 76.5%. Using the trained model to predict mine water inflow for the period from June 2024 to June 2025 yields a root mean square error (RMSE) of 30.73 m³/h and a coefficient of determination (R²) of 0.895 against observed data, indicating excellent fitting and predictive capability for medium- to long-term tasks. Extending the forecast to July 2025–November 2027 reveals a pronounced annual cyclical pattern in future mine water inflow, with markedly higher inflow in summer than in winter and an overall slowly declining trend. These findings show that the Chaos-Autoformer can achieve high-precision medium- and long-term predictions of mine water inflow, thereby providing technical support for proactive deployment and refined management of mine water hazard prevention. Full article

Education about epilepsy plays a vital role in reducing stigma, improving seizure response, and preventing school dropout among affected learners. Despite this importance, there is a lack of a structured conceptual framework guiding epilepsy education in primary schools, where children’s foundational learning and social development take place. This study aims to develop a conceptual framework that integrates epilepsy education into the life skills curriculum to reduce epilepsy-related stigma from an early age. A qualitative multi-methods approach was employed during the empirical phase, which was conducted in two stages using an exploratory–descriptive design. Data were collected from teachers, life skills education advisors (LEAs), and learners to explore their views on incorporating epilepsy education into the life skills curriculum of primary schools. The findings informed the development of a conceptual framework guided by the Three-Legged Stool Model and Dickoff’s Practice-Oriented Theory. This educational framework is tailored for primary school settings and highlights the roles of learners and teachers in promoting self-esteem through knowledge acquisition, value formation, and skill development, all underpinned by the Ubuntu philosophy. Full article

Metastatic cancer, characterized by poor survival outcomes and grim prognosis, represents the final stage of malignancy. The current evidence regarding the prophylactic effects of glucagon-like peptide-1 (GLP-1) receptor agonists and sodium–glucose cotransporter 2 (SGLT2) inhibitors on metastatic cancer remains largely unexamined. With a confirmatory approach based on the Cochrane recommendation, we conducted a frequentist-based network meta-analysis (NMA) of randomized controlled trials (RCTs) evaluating such medications. The primary outcome was the incidence of metastatic cancer, while secondary outcomes included safety profiles assessed through dropout rates. The findings were reaffirmed by sensitivity analysis with a Bayesian-based NMA. This NMA of 207,606 participants from 67 RCTs revealed that only efpeglenatide demonstrated a statistically significant reduction in metastatic cancer events compared to controls (odds ratio = 0.26, 95% confidence intervals = 0.09 to 0.70, p = 0.010, number needed to treat = 188.4). Efpeglenatide’s efficacy was not confined to specific cancer types. Safety profiles were comparable across all treatments. These findings indicate that efpeglenatide may possess a broad, systemic preventive effect against metastatic cancers, potentially operating through mechanisms that are not restricted to individual organ systems. Further research is warranted to elucidate the molecular pathways underlying its anti-metastatic properties and to explore its role in preventive oncology. Full article

This research examines the factors influencing drop out among adult college students. As the traditional-age student population (ages 19–24) declines, the older, part-time, adult learners have emerged as a critical enrollment demographic for higher education institutions. These learners often pursue higher education for career advancement, re-skilling, or re-employment. However, many encounter difficulties in sustaining their academic engagement due to low motivation, limited basic learning skills, or external constraints. Despite the growing presence of adult learners in Korean universities, limited research has analyzed drop-out factors within this specific context. To address this gap, this study applies Bean and Metzner’s nontraditional undergraduate student attrition model, using data from the Korean Educational Longitudinal Study (KELS). It investigates how background characteristics, academic variables, environmental factors, and academic and psychological outcomes influence the drop out of adult learners. The findings reveal that academic variables significantly impact drop-out intentions, while student engagement and social integration show minimal effects. These results offer valuable theoretical insights and practical implications for enhancing adult learner retention in higher education. Full article

Student dropout remains a critical challenge in higher education, especially within public universities that serve diverse and vulnerable populations. This research presents the design and evaluation of an early warning system based on an XGBoost classifier, trained exclusively on data collected at the time of student enrollment. Using a retrospective dataset of nearly 40,000 first-year students (2014–2024) from a Mexican public university, the model incorporated academic, socioeconomic, demographic, and perceptual variables. The final XGBoost model achieved an AUC-ROC of 0.6902 and an F1-score of 0.6946 for the dropout class, with a sensitivity of 88%. XGBoost was chosen over Random Forest due to its superior ability to detect students at risk, a critical requirement for early intervention. The model flagged 59% of incoming students as high-risk, with considerable variability across academic programs. The most influential predictors included age, high school GPA, conditioned admission, and other family responsibilities and economic constraints. This research demonstrates that early warning systems can transform enrollment data into timely and actionable insights, enabling universities to identify vulnerable students earlier and respond more effectively, allocate support more efficiently, and enhance their efforts to reduce dropout rates and improve student retention. Full article

Convolutional neural networks (CNNs) and their improved models (like DenseNet-121) have achieved significant results in image classification tasks. However, the performance of these models is still constrained by issues such as hyperparameter optimization and gradient vanishing and exploding. Owing to their unique exploration and exploitation capabilities, evolutionary algorithms offer new avenues for addressing these problems. Simultaneously, to prevent these algorithms from falling into a local optimum during the search process, this study designs a novel interpolation algorithm. To achieve better image classification performance, thus enhancing classification accuracy and boosting model stability, this paper utilizes a hybrid algorithm based on the horned lizard algorithm with quadratic interpolation and the giant armadillo optimization with Newton interpolation (HGAO) to optimize the hyperparameters of DenseNet-121. It is applied to five datasets spanning different domains. The learning rate and dropout rate have notable impacts on the outcomes of the DenseNet-121 model, which are chosen as the hyperparameters to be optimized. Experiments are conducted using the HGAO algorithm on five image datasets and compared with nine state-of-the-art algorithms. The performance of the model is evaluated based on accuracy, precision, recall, and F1-score metrics. The experimental results reveal that the combination of hyperparameters becomes more reasonable after optimization with the HGAO algorithm, thus providing a crucial improvement. In the comparative experiments, the accuracy of the image classification on the training set increased by up to 0.5%, with a maximum reduction in loss of 0.018. On the test set, the accuracy rose by 0.5%, and the loss decreased by 54 points. The HGAO algorithm provides an effective solution for optimizing the DenseNet-121 model. The designed method boosts classification accuracy and model stability, which also dramatically augments hyperparameter optimization effects and resolves gradient difficulties. Full article

Background/Objectives: DTP3 (diphtheria–tetanus–pertussis vaccine, third dose) coverage is a key indicator of the strength and continuity of routine immunization programs, which demonstrably reduces the burden of infectious diseases globally. This study aims to assess trends in DTP3 vaccination coverage across Asian regions and countries from 2012 to 2023, focusing on changes associated with the COVID-19 pandemic. Methods: DTP3 vaccination data were obtained from official WHO/UNICEF Estimates of National Immunization Coverage (WUENIC) and analyzed using Joinpoint regression to detect statistically significant changes in vaccination trends. Data were grouped by five Asian subregions based on the UN geoscheme (Central, Eastern, Southeastern, Southern, and Western Asia), and trends were weighted using birth cohort sizes. The presence of joinpoints and annual percentage changes (APCs) was calculated, and potential pandemic-related disruptions were contextualized. Results: At the continental level, Asia experienced a modest 0.4% annual increase in DTP3 coverage between 2012 and 2023, with a significant joinpoint detected in 2018. Following this, Southeast Asia’s coverage declined at an annual rate of −4.32% before beginning to recover in 2021, while South Asia showed a similar pattern. Country-level analysis revealed significant heterogeneity, with a comparison between 2019 and 2023 showing profound post-pandemic declines in some nations, such as Lebanon (–21%) and Myanmar (–9.4%), while others, like Iraq and the Philippines, achieved substantial recoveries with coverage increasing by over 6 percentage points. These trends contrasted with persistent declines in fragile states (e.g., Afghanistan, Yemen) and sustained high coverage in others (e.g., Bangladesh, Israel). The pandemic, systemic weaknesses, emerging vaccine hesitancy, and misinformation were identified as key influences. Conclusions: There is progress in DTP3 coverage across Asia. There were pandemic-related disruptions, particularly in regions with fragile health systems. Strategies to address zero-dose and dropout children, improve service continuity, and counter misinformation are essential to meet immunization targets under the Immunization Agenda 2030. Full article

Background: Mental health issues among PhD students are rising, a trend believed to be driven by academic and social challenges. Method: A total of 1265 doctorate students from a large university in Barcelona, Spain (739 women; 414 men; 112 marked other options), with a mean age of 32.36 years (SD = 8.20, range: 23–67), were evaluated by means of standardized instruments. Results: Totals of 40.6% and 46.5% of the sample exceeded the cut-off point for anxiety and depression symptoms, and 57.7% for life satisfaction. The proportion of females exceeding the cut-off point was significantly higher than that of males for both anxiety (women: 43.8%, men: 34.5%) and depression (women: 49.3%, men: 39.8%), but not for life satisfaction (women: 57.6%, men: 58.4%). Arts and Humanities PhD students’ disciplines reported higher anxiety and depression scores than those in Social Sciences, Experimental Sciences and Mathematics, and Health Sciences, respectively, while Social Sciences students showed higher life satisfaction and mentoring support than the other groups. Depression scores were significant predictors of life satisfaction across all doctoral programs. Conclusions: These findings highlight the importance of mentoring in supporting doctoral students’ mental health and life satisfaction and can also inform policies in educational institutions, given that PhD students experiencing psychopathological disorders are at a higher risk of academic failure and dropout. Full article