Search Results (7,749)

This paper presents a cascaded control strategy for neutral-point-clamped three-level (NPC-3L) inverter-fed permanent magnet synchronous motors (PMSMs), integrating continuous-control-set model-predictive control (CCS-MPC) with mid-point voltage regulation and an online Lyapunov-stable neural-network (NN) disturbance observer. The outer CCS-MPC loop optimizes voltage vector application for accurate current tracking and harmonic suppression, while the inner loop balances mid-point voltage by adjusting the dwell times of P/N small-voltage vectors (VVs). The NN-based disturbance observer compensates parameter mismatches in real time, reducing steady-state dq-axis current errors. To validate the effectiveness of the proposed strategy, experiments are conducted using a three-phase PMSM fed by three-phase NPC-3L inverters. Experimental results demonstrate substantial improvements in mid-point voltage balance, current quality, and robustness against model uncertainties. Full article

Sandflies spread the neglected vector-borne disease anthroponotic cutaneous leishmaniasis (ACL), which only affects humans. Despite decades of control, asymptomatic carriers, vector pesticide resistance, and low public awareness prevent eradication. This study proposes a fractional-order optimal control model that integrates biological and behavioral aspects of ACL transmission to better understand its complex dynamics and intervention responses. We model asymptomatic human illnesses, insecticide-resistant sandflies, and a dynamic awareness function under public health campaigns and collective behavioral memory. Four time-dependent control variables—symptomatic treatment, pesticide spraying, bed net use, and awareness promotion—are introduced under a shared budget constraint to reflect public health resource constraints. In addition, Caputo fractional derivatives incorporate memory-dependent processes and hereditary effects, allowing for epidemic and behavioral states to depend on prior infections and interventions; on the other hand, standard integer-order frameworks miss temporal smoothness, delayed responses, and persistence effects from this memory feature, which affect optimal control trajectories. Next, we determine the optimality conditions for fractional-order systems using a generalized Pontryagin’s maximum principle, then solve the state–adjoint equations numerically with an efficient forward–backward sweep approach. Simulations show that fractional (memory-based) dynamics capture behavioral inertia and cumulative public response, improving awareness and treatment efforts. Furthermore, sensitivity tests indicate that integer-order models do not predict the optimal allocation of limited resources, highlighting memory effects in epidemiological decision-making. Consequently, the proposed method provides a realistic and flexible mathematical basis for cost-effective and sustainable ACL control plans in endemic settings, revealing how memory-dependent dynamics may affect disease development and intervention efficiency. Full article

The implementation of Euro 7 emission standards demands advanced real-time NO_x monitoring systems for diesel vehicles. Existing unified models inadequately capture phase-dependent emission mechanisms during cold-start, urban, and highway operation. This study develops a novel Mixture of Experts (MoE) architecture with data-driven phase classification based on aftertreatment thermal dynamics. Real-world data from a Euro 6d commercial vehicle (3247 PEMS samples) were classified into three phases, cold (<70 °C coolant temperature), hot low-speed (<90 km/h), and hot high-speed (≥90 km/h), validated through t-SNE analysis (silhouette coefficient = 0.73). The key innovation integrates thermal–kinematic domain knowledge with specialized XGBoost regressors, achieving R² = 0.918 and a 58% RMSE reduction versus unified models (RMSE = 1.825 mg/s). The framework operates within real-time constraints (1.5 ms inference latency), integrating autoencoder-based anomaly detection (95.2% sensitivity) and Model Predictive Control (11–13% NO_x reduction). This represents the first systematic phase-specific NO_x modeling framework with validated Euro 7 OBM compliance capability, providing both methodological advances in expert allocation strategies and practical solutions for next-generation emission control systems. Full article

Laser powder bed fusion (L-PBF) is an additive manufacturing technique that enables the fabrication of complex geometries through a layer-by-layer approach, overcoming limitations of conventional manufacturing. In this study, multiaxial low-cycle fatigue (MLCF) tests were conducted on L-PBF Ti-6Al-4V (Ti64) specimens built in four different orientations, selected based on critical plane orientations identified from rolled titanium. Under proportional strain-controlled loading, the cyclic softening behavior, mean stress response, and fracture mechanisms of the material were systematically investigated. The results show that L-PBF Ti64 exhibits a three-stage softening characteristic (continuous softening, stable, and rapid softening). Fatigue cracks primarily initiate from inner-surface lack-of-fusion defects. Crack propagation shows cleavage and quasi-cleavage characteristics with tearing ridges, river patterns, and multi-directional striations. Proposed KBMP life prediction model, incorporating λ and building direction parameters, was developed. The KBMP-λ model demonstrates optimal accuracy, providing a reliable tool for the design of L-PBF titanium components subjected to complex multiaxial fatigue loading with relative errors within 20%. Full article

Background/Objectives: Conventional imaging assesses therapy response in stage IV solid-tumor patients in 8- to 12-week intervals, delaying detection of non-responders. We evaluated a quantitative PCR (qPCR) assay that interrogates size-distributed cell-free DNA (cfDNA) fragments to provide earlier insights into treatment efficacy. Methods: In this prospective study, 128 patients with metastatic lung, breast, or colorectal cancer provided plasma 12–21 days after the first dose of a new systemic regimen. The qPCR targets multi-copy retrotransposon element fragments of greater than 80 bp, greater than 105 bp, and greater than 265 bp, as well as an internal control. A model integrates these quantities into a Progression Score (PS) ranging from 0 to 100; higher values indicate probable disease progression. Results: The PS model yielded an area under (AUC) the receiver-operating-characteristic (ROC) curve of 0.93 for predicting radiographic progression at first imaging. Scores were strongly bimodal: 92% of patients with PS > 90 progressed, whereas 95% with PS < 10 did not. Intermediate scores (10–90) comprised a mixed cohort. Assay performance was unaffected by tumor genomic profile. Conclusions: This cfDNA-based Progression Score (PS) assay enables tumor- and therapy-agnostic, non-invasive monitoring of treatment response as early as two weeks after initiation. By flagging ineffective regimens well before standard imaging, the test can accelerate clinical decision-making, reduce exposure to futile therapy, and potentially improve outcomes in stage IV cancer. Early treatment plan changes may also avoid the high costs of ineffective treatments, prevent downstream toxicity-related hospitalizations, and free up limited imaging and infusion-suite capacity—yielding savings for patients, payers, and healthcare systems. Full article

Background/Objectives: Outcomes following Anterior Cruciate Ligament (ACL) reconstruction vary widely among patients, yet existing classification techniques often lack transparency and clinical interpretability. To address this gap, we developed a multi-modal framework that integrates gait dynamics with patient-specific characteristics to enhance personalized assessment of ACL reconstruction outcomes. Methods: Participants, both post-ACL reconstruction and healthy controls, were equipped with inertial measurement unit (IMU) sensors on bilateral wrists, ankles, and the sacrum during standardized locomotion tasks. Using the Phase Slope Index (PSI), we quantified causal relationships between sensor pairs, hypothesizing that (1) PSI-derived metrics capture discriminative biomechanical interactions; (2) task-specific differences in segment coordination patterns influence model performance; and (3) recovery duration modulates classifier confidence and the structure of high-dimensional data distributions. Classification models were trained using PSI features, and permutation-based sensor importance analyses were conducted to interpret task-specific biomechanical contributions. Results: PSI-based classifiers achieved 96.37% accuracy in distinguishing ACL reconstruction outcomes, validating the first hypothesis. Permutation importance revealed that jogging tasks produced more focused importance distributions across fewer sensor pairs while improving accuracy, confirming task-specific coordination effects (hypothesis two). Visualization via t-SNE demonstrated that longer recovery durations corresponded to reduced model confidence but more coherent feature clusters, supporting the third hypothesis. Conclusions: By integrating causal gait metrics and patient recovery profiles, this approach enables interpretable and high-performing ACL outcome prediction. Quantitative evaluation measures—including model confidence and t-SNE cluster coherence—offer clinicians objective tools for personalized rehabilitation monitoring and data-driven return-to-sport decisions. Full article

Fall detection systems are a critical application of human pose estimation, frequently struggle with achieving real-world robustness due to their reliance on domain-specific datasets and a limited capacity for generalization to novel conditions. Models trained on controlled, canonical camera views often fail when subjects are viewed from new perspectives or are partially occluded, resulting in missed detections or false positives. This study tackles these limitations by proposing the Viewpoint Invariant Robust Aggregation Graph Convolutional Network (VIRA-GCN), an adaptation of the Richly Activated GCN for fall detection. The VIRA-GCN introduces a novel dual-strategy solution: a synthetic viewpoint generation process to augment training data and an efficient inference-time aggregation method to form consensus-based predictions. We demonstrate that augmenting the Le2i dataset with simulated rotations and occlusions allows a standard pose estimation model to achieve a significant increase in its fall detection capabilities. The VIRA-GCN achieved 99.81% accuracy on the Le2i dataset, confirming its enhanced robustness. Furthermore, the model is suitable for low-resource deployment, utilizing only 4.06 M parameters and achieving a real-time inference latency of 7.50 ms. This work presents a practical and efficient solution for developing a single-camera fall detection system robust to viewpoint variations, and introduces a reusable mapping function to convert Kinect data to the MMPose format, ensuring consistent comparison with state-of-the-art models. Full article

With the gradual increase in coal production capacity, the problem of water damage from the coal seam roof is becoming more and more prominent. Neogene loose strata overlie coal seams in eastern China, and pressurized aquifers commonly lie at the bottom of the loose strata. The aquifers are mainly composed of unconsolidated sand, gravel, and weakly consolidated marl, which has strong permeability and an extremely unfavorable impact on safe production. Identifying the target area to prevent and control roof water damage can reduce the likelihood of water damage accidents in mines. This study takes the 8₅ mining district of Wobei mine as an engineering case. The discriminant indexes are selected for aquifer thickness, gradation coefficient, marlstone thickness, permeability, grouting quantity, and grouting termination pressure. A model integrating the newly proposed Crowned Porcupine Optimization (CPO, 2024), Convolutional Neural Network (CNN), and Bidirectional Long Short-Term Memory (BiLSTM) was constructed to predict unit water influx. A zonal map was generated based on the expected unit water influx of the fourth aquifer after grouting. In addition, the prediction results are compared with those from other models. Results indicate that the CPO-CNN-BiLSTM model achieves a higher accuracy and fewer errors in water abundance prediction, with an RMSE of 2.58 × 10⁻⁵ and an R² of 0.982 for the testing dataset. According to the prediction result, the fourth aquifer after grouting in the 8₅ mining district is divided into five water abundance zones. The strong and medium–strong water abundance zones are mainly distributed in the study area’s eastern region. A small portion of them is distributed in the northwestern and northern areas. This study provides a new insight for predicting the water abundance of thick loose aquifers and a theoretical basis for safe mining under thick loose aquifers. Full article

The factors influencing urban pluvial flooding in cities with complex topography, such as hill–basin systems, are highly nonlinear and spatially heterogeneous due to the interplay between rugged terrain and intensive human activities. However, previous research has predominantly focused on plain, mountainous, and coastal cities. As a result, the waterlogging mechanisms in hill–basin areas remain notably understudied. In this study, we developed a geographically explainable artificial intelligence (GeoXAI) framework integrating Geographical Machine Learning Regression (GeoMLR) and Geographical Shapley (GeoShapley) values to analyze nonlinear impacts of flooding factors in Changsha, a typical hill–basin city. The XGBoost model was employed to predict flooding risk (validation AUC = 0.8597, R² = 0.8973), while the GeoMLR model verified stable nonlinear driving relationships between factors and flooding susceptibility (test set R² = 0.7546)—both supporting the proposal of targeted zonal regulation strategies. Results indicated that impervious surface density (ISD), normalized difference vegetation index (NDVI), and slope are the dominant drivers of flooding, with each exhibiting distinct nonlinear threshold effects (ISD > 0.35, NDVI < 0.70, Slope < 5°) that differ significantly from those identified in plain, mountainous, or coastal regions. Spatial analysis further revealed that topography regulates flooding by controlling convergence pathways and flow velocity, while vegetation mitigates flooding through enhanced interception and infiltration, showing complementary effects across zones. Based on these findings, we proposed tailored zonal management strategies. This study not only advances the mechanistic understanding of urban waterlogging in hill–basin regions but also provides a transferable GeoXAI framework offering a robust methodological foundation for flood resilience planning in topographically complex cities. Full article

With rapid advancements in large language models for natural language processing, their role in semantic-aware process mining is growing. We study semantics-aware process mining, where decisions must reflect both event logs and textual rules. We propose an online, adaptive multi-agent framework that operates over a single knowledge base shared across three tasks—semantic next-activity prediction (S_NAP), trace-level semantic anomaly detection (T_SAD), and activity-level semantic anomaly detection (A_SAD). The approach has three key elements: (i) cross-task corroboration at retrieval time, formed by pooling in-domain and out-of-domain candidates to strengthen coverage; (ii) feedback-to-index calibration that converts user correctness/usefulness into propensity-debiased, smoothed priors that immediately bias recall and first-stage ordering for the next query; and (iii) stability controls—consistency-aware scoring, confidence gating with failure-driven query rewriting, task-level trust regions, and a sequential rule to select the relevance–quality interpolation. We instantiate the framework with Mistral-7B-Instruct, Llama-3-8B, GPT-3.5, and GPT-4o and evaluate it using macro-F1. Compared to in-context learning, our framework improves S_NAP, T_SAD, and A_SAD by 44.0%, 15.6%, and 7.1%, respectively, and attains the best overall profile against retrieval-only and correction-centric baselines. Ablations show that removing index priors causes the steepest degradation, cross-task corroboration yields consistent gains—most visibly on S_NAP—and confidence gating preserves robustness to difficult inputs. The result is immediate serve-time adaptivity without heavy fine-tuning, making semantic process analysis practical under drift. Full article

The early design stage of modern compressors urgently requires high-accuracy, low-cost two-dimensional (2D) cascade loss prediction models. However, existing traditional loss models, predominantly based on early profile data, struggle to accurately predict the performance of modern Controlled Diffusion Airfoils (CDA). This study develops a comprehensive loss model system specifically for 2D cascades with modern CDA profiles. A numerical simulation database, encompassing the entire operating range of various subsonic, transonic, and supersonic profile designs, was first constructed to provide the data foundation for the model system development. Eight critical sub-models essential for the system were then identified based on an analysis of loss sources (including blade surface boundary layers and shock waves). A methodology combining physical mechanism analysis and data-driven techniques was applied to determine the final modeling scheme for each sub-model. Validation results demonstrate that within the parameter space covered by the database, the new model system achieves over 70% higher prediction accuracy compared to the traditional model system, with approximately 95% of prediction errors falling within ±0.02. It also accurately captures the variation trend of loss with incidence angle. The entire model system, consisting of a series of explicit formulas with clear physical meanings, can be easily integrated into compressor design processes and effectively support the design and analysis of airfoils during the preliminary stages of compressor development. Full article

The fast-increasing penetration of photovoltaic (PV) power raises the issue of grid stability due to its intermittency and lack of inertia in power systems. Solar irradiance forecasting effectively supports advanced control, mitigates power intermittency, and improves grid resilience. Irradiance forecasting based on data-driven methods aims to predict the direction and level of power variation and indicate quick action. This article presents a comprehensive review and comparative analysis of data-driven approaches for time-series solar irradiance forecasting. It systematically evaluates nineteen representative models spanning from traditional statistical methods to state-of-the-art deep learning architectures across multiple performance dimensions that are critical for practical deployment. The analysis aims to provide actionable insights for researchers and practitioners when selecting and implementing suitable forecasting solutions for diverse solar energy applications. Full article

Greenhouses play a vital role in modern agriculture by providing controlled environments for year-round crop production. However, climate regulation within these structures accounts for a significant portion of their energy consumption, often exceeding 50% of operational costs. Current greenhouse systems predominantly rely on reactive control strategies, leading to energy inefficiency and unstable internal conditions. Addressing this gap, the present study develops a machine learning-based framework that leverages time series forecasting models—specifically Long Short-Term Memory (LSTM)—that predict key climate parameters and generate optimal actuator control recommendations. The system utilizes multivariate environmental data to forecast temperature, humidity, and CO₂ levels and minimize a composite energy proxy through proactive adjustments to heating, ventilation, and lighting systems. Experimental results demonstrate high prediction accuracy (R² = 0.9835) and significant improvements in energy efficiency. By integrating predictive analytics with real-time sensor feedback, the proposed approach supports intelligent, energy-aware decision-making and advances the development of smart agriculture through proactive greenhouse climate management. Full article

Ensuring consistent quality and safety in agri-food processing is a strategic priority for firms seeking compliance with international standards such as ISO 9001 and ISO 22000. Traditional inspection practices in Ecuador’s food industry remain largely destructive, labor-intensive, and subjective, limiting real-time decision-making. This study developed a non-destructive, ISO-aligned framework for process-level quality control by integrating digital (RGB) imaging for surface-level inspection, hyperspectral imaging (HSI) for internal-quality prediction (e.g., moisture, firmness, and freshness), near-infrared spectroscopy (NIRS) for compositional and authenticity analysis, and deep learning (DL) models for automated classification of ripeness, maturity, and defects. Experimental results across four flagship commodities—bananas, cacao, coffee, and shrimp—achieved classification accuracies above 88% and ROC AUC values exceeding 0.90, confirming the robustness of AI-driven, multimodal (RGB–HSI–NIRS) inspection under semi-industrial conveyor conditions. Beyond technological performance, the findings demonstrate that digital inspection reinforces ISO principles of evidence-based decision-making, conformity verification, and traceability, thereby operationalizing the Plan–Do–Check–Act (PDCA) cycle at digital speed. The study contributes theoretically by advancing the conceptualization of Quality 4.0 as a socio-technical transformation that embeds AI-driven sensing and analytics within management standards, and practically by providing a roadmap for Ecuadorian SMEs to strengthen export competitiveness through automated, real-time, and auditable quality assurance. Full article

Background: Early cognitive abilities such as memory and executive function (EF) emerge rapidly in infancy and may provide a foundation for later language development. However, large-scale longitudinal evidence linking early cognition to subsequent receptive and expressive outcomes remains limited. Methods: Data were drawn from 6652 children in the Kids in Taiwan (KIT) longitudinal database. Hierarchical regression models tested whether memory and EF at 12 months predicted language comprehension and expression at 24 months, and whether cognition at 24 months predicted outcomes at 36 months, controlling for parental education, involvement, responsiveness, child gender, temperament, and previous language ability. All language variables were standardized to ensure comparability across ages and to minimize potential floor or ceiling effects. Results: Early memory consistently predicted receptive and expressive language at 24 and 36 months, whereas EF predicted expressive language at 24 months and both receptive and expressive language at 36 months. The overall inclusion of cognitive variables significantly increased model fit (all ΔFs, p < 0.001), indicating that early cognitive functioning contributes uniquely to subsequent language development beyond language stability. Conclusions: Findings from this large community-based Taiwanese cohort highlight the importance of early cognitive abilities in supporting subsequent language growth. Incorporating assessments of memory and EF into early developmental monitoring may help identify children who would benefit from enriched language experiences or targeted educational support. Integrating assessments of memory and EF into early developmental screening and intervention programs may enhance the early identification of children at risk for delayed language development and guide the design of play-based activities that strengthen cognitive foundations for language. Full article