Search Results (228)

As modern software systems continue to grow in scale and structural complexity, log anomaly detection has become an essential component of system monitoring and fault diagnosis. However, existing approaches often struggle to adequately capture sequential dependencies in log data and to remain robust under distributional changes. To mitigate these issues, this paper presents BERT-LogAnom, an unsupervised framework for log anomaly detection that combines contextual representation learning, sequential modeling, and adaptive decision mechanisms. Specifically, a BERT-based encoder is employed to learn global contextual semantics from log sequences, while a gated residual bidirectional Long Short-Term Memory (GR-BiLSTM) network is introduced to model bidirectional temporal dependencies without disrupting the learned contextual information. To characterize normal system behavior from unlabeled logs, two self-supervised objectives—masked log key prediction and volume hypersphere minimization—are jointly optimized during training. Furthermore, a Dynamic Thresholding Prediction Module (DTPM) is incorporated to adjust anomaly decision boundaries in response to short-term statistical fluctuations and longer-term distribution drift. Experiments conducted on three public benchmark datasets (HDFS, BGL, and Thunderbird) show that BERT-LogAnom achieves consistently superior performance compared with representative baseline methods across precision, recall, and F1-score. Additional ablation studies further confirm the contribution of each major component in the proposed framework. Full article

In mechanical engineering, interest in reliable and practicable technologies for nano- and microstructuring of tool surfaces is increasing. Femtosecond laser structuring offers a promising approach that combines high processing speeds with high precision. However, a knowledge gap remains regarding the optimal process parameters for achieving specific surface patterns on hot-work tool steel substrates. The current study aims to investigate the effects of laser scanning parameters on the formation of self-organized surface structures and the resulting topography and morphology. Therefore, samples were irradiated using a 300 fs laser with linearly polarized light (λ = 1030 nm). Scanning electron microscopy revealed four structure types: laser-induced periodic surface structures (LIPSSs), micrometric ripples, micro-crater structures, and pillared microstructures. The results for surface area and line roughness indicate that high laser pulse overlaps lower the strong ablation threshold more effectively than high scanning line overlaps, promoting the formation of pillared microstructures. For efficient ablation and increased surface roughness, higher pulse overlaps are therefore advantageous. In contrast, at low fluences, higher scanning line overlaps support a more homogeneous formation of nanostructures and reduce waviness. Full article

Background/Objectives: Patients with WPW syndrome have a risk of sudden cardiac death that can be assessed using an electrophysiological study. In symptomatic patients, the preferred route is intracardiac, whereas in asymptomatic children, transesophageal. Our study aimed to evaluate the risk using a transesophageal study, considering a threshold age of 12 years for sedation. Methods: We investigated 41 asymptomatic WPW children with a mean age of 12.5 ± 4.4 years (range 1 to 18 years old), with 48.8% being male. We determined three values: (1) the accessory pathway effective refractory period (APERP), (2) the minimal cycle length demonstrating 1:1 conduction through the accessory pathway, and (3) the shortest RR interval between two consecutive pre-excited beats during atrial fibrillation. Results: Children under 12 years had a mean age of 7.5 ± 2.5 years, while those over 12 years had a mean age of 15.5 ± 1.9 years. Sedation was administered exclusively to children under 12 years of age. Orthodromic reentrant tachycardia was induced in four children, and atrial fibrillation was induced in 14 children. Comparing the group under 12 with the group over 12, the mean APERP was 296 ± 38 ms vs. 286 ± 45 ms (p = 0.48), the average 1:1 conduction over the accessory pathway was 287.3 ± 41 ms vs. 282 ± 46 ms (p = 0.71), and the average shortest pre-excited RR interval during atrial fibrillation was 280 ms vs. 262 ms years (p = 0.75). Conclusions: Asymptomatic children under 12 years of age showed a lower incidence of inducible atrial fibrillation. They had accessory pathways with reduced risk, except one, and no children under 12 years underwent catheter ablation. Full article

Out-of-distribution (OOD) detection is essential for ensuring the reliability of machine learning models deployed in safety-critical applications. Existing methods often rely solely on statistical properties of feature distributions while ignoring the geometric structure of learned representations. We propose TopoAD, a topology-aware OOD detection framework that leverages Euler Characteristic Curves (ECCs) extracted from intermediate convolutional activation maps and fuses them with standardized energy scores. Specifically, we employ a computationally efficient superlevel-set filtration with a local estimator to capture topological invariants, avoiding the high cost of persistent homology. Furthermore, we introduce task-adaptive aggregation strategies to effectively integrate multi-scale topological features based on the complexity of distribution shifts. We evaluate our method on CIFAR-10 against four diverse OOD benchmarks spanning far-OOD (Textures), near-OOD (SVHN), and semantic shift scenarios. Our results demonstrate that TopoAD-Gated achieves superior performance on far-OOD data with 89.98% AUROC on Textures, while the ultra-lightweight TopoAD-Linear provides an efficient alternative for near-OOD detection. Comprehensive ablation studies reveal that cross-layer gating effectively captures multi-scale topological shifts, while threshold-wise attention provides limited benefit and can degrade far-OOD performance. Our analysis demonstrates that topological features are particularly effective for detecting OOD samples with distinct structural characteristics, highlighting TopoAD’s potential as a sustainable solution for resource-constrained applications in texture analysis, medical imaging, and remote sensing. Full article

Parametric tiered-seating design can be framed as a constrained multi-objective optimization problem in which a low-dimensional decision vector is evaluated by a deterministic operator with sequential feasibility rejection and visibility constraints. This study introduces an oracle-preserving, learning-assisted screening workflow, where a multi-output multilayer perceptron (MLP) is used only to prioritize candidates for evaluation. Here, multi-output denotes a single network trained to predict the full objective vector jointly. Candidates are sampled within bounded decision ranges and evaluated by an operator that propagates section-coupled geometric state and enforces hard clearance thresholds through a Vertical Sightline System (VSS), i.e., a deterministic row-wise sightline/clearance evaluator that enforces hard clearance thresholds. The oracle-evaluated set is reduced to its mixed-direction Pareto-efficient subset and filtered by feature-space proximity to a fixed validation reference using nearest-neighbor distances in standardized 11-dimensional features, yielding a robustness-oriented pool. A compact shortlist is derived via TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution; used here strictly as a post-Pareto decision-support ranking rule), and preference uncertainty is assessed by Monte Carlo weight sampling from a symmetric Dirichlet distribution. In an archived run under a fixed oracle budget, 1235 feasible designs are evaluated, producing 934 evaluated Pareto solutions; proximity filtering retains 187 robust candidates and TOPSIS reports a traceable top-30 shortlist. Stability is supported by concentrated top-k frequencies under weight perturbations and by audits under single-feature-drop ablations and tested rounding precisions. Overall, the workflow enables reproducible multi-objective screening and reporting for feasibility-dominated seating design. Full article

Chronic obstructive pulmonary disease (COPD) is a major health burden worldwide and in Taiwan, ranking as the third leading cause of death globally, and its prevalence in Taiwan continues to rise. Readmission within 14 days is a key indicator of disease instability and care efficiency, driven jointly by patient-level physiological vulnerability (such as reduced lung function and multiple comorbidities) and healthcare system-level deficiencies in transitional care. To mitigate the growing burden and improve quality of care, it is urgently necessary to develop an AI-based prediction model for 14-day readmission. Such a model could enable early identification of high-risk patients and trigger multidisciplinary interventions, such as pulmonary rehabilitation and remote monitoring, to effectively reduce avoidable early readmissions. However, medical data are commonly characterized by severe class imbalance, which limits the ability of conventional machine learning methods to identify minority-class cases. In this study, we used real-world clinical data from multiple hospitals in Kaohsiung City to construct a prediction framework that integrates data generation and ensemble learning to forecast readmission risk among patients with chronic obstructive pulmonary disease (COPD). CTGAN and kernel density estimation (KDE) were employed to augment the minority class, and the impact of these two generation approaches on model performance was compared across different augmentation ratios. We adopted a stacking architecture composed of six base models as the core framework and conducted systematic comparisons against the baseline models XGBoost, AdaBoost, Random Forest, and LightGBM across multiple recall thresholds, different feature configurations, and alternative data generation strategies. Overall, the results show that, under high-recall targets, KDE combined with stacking achieves the most stable and superior overall performance relative to the baseline models. We further performed ablation experiments by sequentially removing each base model to evaluate and analyze its contribution. The results indicate that removing KNN yields the greatest negative impact on the stacking classifier, particularly under high-recall settings where the declines in precision and F1-score are most pronounced, suggesting that KNN is most sensitive to the distributional changes introduced by KDE-generated data. This configuration simultaneously improves precision, F1-score, and specificity, and is therefore adopted as the final recommended model setting in this study. Full article

Traditional retrieval-augmented generation (RAG) methods struggle with hierarchical documents, often causing semantic fragmentation, structural loss, and inefficient retrieval due to fixed strategies. To address these challenges, this paper proposes HiSem-RAG, a hierarchical semantic-driven RAG method. It comprises three key modules: (1) hierarchical semantic indexing, which preserves boundaries and relationships between sections and paragraphs to reconstruct document context; (2) a bidirectional semantic enhancement mechanism that incorporates titles and summaries to facilitate two-way information flow; and (3) a distribution-aware adaptive threshold strategy that dynamically adjusts retrieval scope based on similarity distributions, balancing accuracy with computational efficiency. On the domain-specific EleQA dataset, HiSem-RAG achieves 82.00% accuracy, outperforming HyDE and RAPTOR by 5.04% and 3.98%, respectively, with reduced computational costs. On the LongQA dataset, it attains a ROUGE-L score of 0.599 and a BERT_F1 score of 0.839. Ablation studies confirm the complementarity of these modules, particularly in long-document scenarios. Full article

The deployment of Advanced Driver-Assistance Systems (ADAS) in economically constrained markets frequently relies on hardware architectures that lack dedicated graphics processing units. Within such environments, the integration of deep neural networks faces significant hurdles, primarily stemming from strict limitations on energy consumption, the absolute necessity for deterministic real-time response, and the rigorous demands of safety certification protocols. Meanwhile, traditional geometry-based lane detection pipelines continue to exhibit limited robustness under adverse illumination conditions, including intense backlighting, low-contrast nighttime scenes, and heavy rainfall. Motivated by these constraints, this work re-examines geometry-based lane perception from a sensor-level viewpoint and introduces a Binary Line Segment Filter (BLSF) that leverages the inherent structural regularity of lane markings in bird’s-eye-view (BEV) imagery within a computationally lightweight framework. The proposed BLSF is integrated into a complete pipeline consisting of inverse perspective mapping, median local thresholding, line-segment detection, and a simplified Hough-style sliding-window fitting scheme combined with RANSAC. Experiments on a self-collected dataset of 297 challenging frames show that the inclusion of BLSF significantly improves robustness over an ablated baseline while sustaining real-time performance on a 2 GHz ARM CPU-only platform. Additional evaluations on the Dazzling Light and Night subsets of the CULane and LLAMAS benchmarks further confirm consistent gains of approximately 6–7% in F₁-score, together with corresponding improvements in IoU. These results demonstrate that interpretable, geometry-driven lane feature extraction remains a practical and complementary alternative to lightweight learning-based approaches for cost- and safety-critical ADAS applications. Full article

This review provides a comprehensive analysis of modern strategies for the synthesis, functionalization, and application of carbon nanotubes (CNTs) and graphene for the development of high-performance polymer composites in the field of strain sensing. The paper systematically organizes key synthesis methods for CNTs and graphene (chemical vapor deposition (CVD), such as arc discharge, laser ablation, microwave synthesis, and flame synthesis, as well as approaches to their chemical and physical modification aimed at enhancing dispersion within polymer matrices and strengthening interfacial adhesion. A detailed examination is presented on the structural features of the nanofillers, such as the CNT aspect ratio, graphene oxide modification, and the formation of hybrid 3D networks and processing techniques, which enable the targeted control of the nanocomposite’s electrical conductivity, mechanical strength, and flexibility. Central focus is placed on the fundamental mechanisms of the piezoresistive response, analyzing the role of percolation thresholds, quantum tunneling effects, and the reconfiguration of conductive networks under mechanical load. The review summarizes the latest advancements in flexible and stretchable sensors capable of detecting both micro- and macro-strains for structural health monitoring, highlighting the achieved improvements in sensitivity, operational range, and durability of the composites. Ultimately, this analysis clarifies the interrelationship between nanofiller structure (CNTs and graphene), processing conditions, and sensor functionality, highlighting key avenues for future innovation in smart materials and wearable devices. Full article

This study introduces a fully uncertainty-aware forecasting framework for NBA games that integrates team-level performance metrics, rolling-form indicators, and spatial shot-chart embeddings. The predictive backbone is a recurrent neural network equipped with Monte Carlo dropout, yielding calibrated sequential probabilities. The model is evaluated against strong baselines including logistic regression, XGBoost, convolutional models, a GRU sequence model, and both market-only and non-market-only benchmarks. All experiments rely on strict chronological partitioning (train ≤ 2022, validation 2023, test 2024), ablation tests designed to eliminate any circularity with bookmaker odds, and cross-season robustness checks spanning 2012–2024. Predictive performance is assessed through accuracy, Brier score, log-loss, AUC, and calibration metrics (ECE/MCE), complemented by SHAP-based interpretability to verify that only pre-game information influences predictions. To quantify economic value, calibrated probabilities are fed into a frictionless betting simulator using fractional-Kelly staking, an expected-value threshold, and bootstrap-based uncertainty estimation. Empirically, the uncertainty-aware model delivers systematically better calibration than non-Bayesian baselines and benefits materially from the combination of shot-chart embeddings and recent-form features. Economic value emerges primarily in less-efficient segments of the market: The fused predictor outperforms both market-only and non-market-only variants on moneylines, while spreads and totals show limited exploitable edge, consistent with higher pricing efficiency. Sensitivity studies across Kelly multipliers, EV thresholds, odds caps, and sequence lengths confirm that the findings are robust to modelling and decision-layer perturbations. The paper contributes a reproducible, decision-focused framework linking uncertainty-aware prediction to economic outcomes, clarifying when predictive lift can be monetized in NBA markets, and outlining methodological pathways for improving robustness, calibration, and execution realism in sports forecasting. Full article

This work demonstrates a three-step method for the synthesis and production of submicron spherical gold particles using laser ablation in liquid (LAL), laser-induced fragmentation in liquid (LFL), laser-induced nanochain formation, and laser melting in liquid (LML). The nanoparticles were characterized using transmission electron microscopy (TEM), dynamic light scattering (DLS), and UV–visible spectroscopy. In the first stage, spherical gold nanoparticles with a size of 20 nm were obtained using LAL and LFL. Subsequent irradiation of gold nanoparticle colloids with radiation at a wavelength of 532 nm leads to the formation of gold nanochains. Irradiation of nanochain colloids with radiation at a wavelength of 1064 nm leads to the formation of large spherical gold particles with a size of 50 to 200 nm. The formation of submicron gold particles upon irradiation of 2 mL of colloid occurs within the first minutes of irradiation and is complete after 480,000 laser pulses. Increasing the laser pulse energy leads to the formation of larger particles; after exceeding the threshold energy (321 mJ/cm²), fragmentation is observed. Increasing the concentration of nanoparticles in the initial colloid up to 150 μg/mL leads to a linear increase in the size of submicron nanoparticles. The use of picosecond pulses for irradiating nanochains demonstrates the formation of the largest particles (200 nm) compared to nanosecond pulses, which may be due to the effect of local surface melting. The described technique opens the possibility of synthesizing stable gold nanoparticles over a wide range of sizes, from a few to hundreds of nanometers, without the use of chemical reagents. Full article

In response to the safety threats posed by unauthorized unmanned aerial vehicles (UAVs), the importance of anti-UAV systems is becoming increasingly apparent. In tasks involving UAV detection, small UAVs are particularly difficult to detect due to their low resolution. Therefore, this study proposed YOLO-CoOp, a lightweight multi-module collaborative optimization framework for detecting small UAVs. First, a high-resolution feature pyramid network (HRFPN) was proposed to retain more spatial information of small UAVs. Second, a C3k2-WT module integrated with wavelet transform convolution was proposed to enhance feature extraction capability and expand the model’s receptive field. Then, a spatial-channel synergistic attention (SCSA) mechanism was introduced to integrate spatial and channel information and enhance feature fusion. Finally, the DyATF method replaced the upsampling with Dysample and the confidence loss with adaptive threshold focal loss (ATFL), aiming to restore UAV details and balance positive–negative sample weights. The ablation experiments show that YOLO-CoOp achieves 94.3% precision, 93.1% recall, 96.2% mAP⁵⁰, and 57.6% mAP⁵⁰⁻⁹⁵ on the UAV-SOD dataset, with improvements of 3.6%, 10%, 5.9%, and 5% over the baseline model, respectively. The comparison experiments demonstrate that YOLO-CoOp has fewer parameters while maintaining superior detection performance. Cross-dataset validation experiments also demonstrate that YOLO-CoOp exhibits significant performance improvements in small object detection tasks. Full article

We study UAV-assisted 5G uplink connectivity for disaster response, in which a UAV (unmanned aerial vehicle) acts as an aerial base station to restore service to ground users. We formulate a joint control problem coupling UAV kinematics (bounded acceleration and velocity), per-subchannel uplink power allocation, and uplink non-orthogonal multiple access (UL-NOMA) scheduling with adaptive successive interference cancellation (SIC) under a minimum user-rate constraint. The wireless channel follows 3GPP urban macro (UMa) with probabilistic line of sight/non-line of sight (LoS/NLoS), realistic receiver noise levels and noise figure, and user equipment (UE) transmit-power limits. We propose a bounded-action proximal policy optimization with generalized advantage estimation (PPO-GAE) agent that parameterizes acceleration and power with squashed distributions and enforces feasibility by design. Across four user distributions (clustered, uniform, ring, and edge-heavy) and multiple rate thresholds, our method increases the fraction of users meeting the target rate by 8.2–10.1 percentage points compared to strong baselines (OFDMA with heuristic placement, PSO-based placement/power, and PPO without NOMA) while reducing median UE transmit power by $64.6\%$. The results are averaged over at least five random seeds, with $95\%$ confidence intervals. Ablations isolate the gains from NOMA, adaptive SIC order, and bounded-action parameterization. We discuss robustness to imperfect SIC and CSI errors and release code/configurations to support reproducibility. Full article

We explore the wettability modulation induced on alumina (Al₂O₃) targets by femtosecond laser texturing to demonstrate the stable and durable hydrophilic character of the surface. Specifically, we identify a suitable operational regime to tailor micro-nanostructures onto Al₂O₃ plates and accurately assess the ablation threshold in our experimental conditions. A periodic geometry with triangular patterns of various groove depths, ranging from 3.2 ± 0.1 to 17.1 ± 0.1 µm, was optimized for establishing a long-term wetting response. The latter was monitored on daily basis over a time interval exceeding 40 days by collecting the contact angle measurements of samples with and without a post-process thermal annealing, adopted to stabilize the surface wettability soon after the laser treatment. The results show that deeper grooves significantly enhance and maintain the hydrophilic character, particularly in samples without post-process thermal annealing, where superhydrophilicity (θ < 5°) is demonstrated to persist the entire time throughout the test. These findings disclose the potential for an effective fine-tuning of the alumina wettability, thus opening up the possibility of specific applications requiring long-term control of surface–liquid interactions, such as biomedical implants, and orthopedic and dental prostheses. Full article

This study presents the development and evaluation of multifunctional, thermoresponsive nanogels based on poly(N-vinylcaprolactam-co-N-vinylpyrrolidone) (P(NVCL-co-NVP)) with a poly(ethylene glycol) methyl ether methacrylate (PEGMA) shell and galactose (GAL) targeting ligand for colon cancer therapy. The nanogels were engineered to encapsulate two chemotherapeutic agents, curcumin (CUR) and 5-fluorouracil (5-FU), along with gold nanorods (GNRDs) to enable a synergistic chemo-photothermal treatment approach. These nanogels exhibit excellent biocompatibility and stability and a temperature-responsive drug release profile, leveraging the volume-phase transition temperature (VPTT) of the polymer network for controlled delivery. The inclusion of GNRDs permits efficient photothermal conversion upon near-infrared (NIR) irradiation, resulting in localized hyperthermia and, theoretically, improved cytotoxicity when combined with chemotherapeutics. In vitro studies on colon cancer cells demonstrated enhanced drug accumulation, photothermal ablation when the GNRD concentration was above a threshold, and superior antitumor efficacy of the CUR/5-FU-loaded systems. The effectiveness of the chemo/photothermal combination could not be demonstrated, possibly due to the low concentration of GNRD and/or the use of a single irradiation step only. This work highlights the potential of P(NVCL-co-NVP):PEGMA:GAL nanogels as versatile nanocarriers for combined chemo-photothermal therapy. A more effective chemo/photothermal combination for colon cancer treatment can be achieved through the optimization of the GNRD loading/irradiation dosage. Full article