Search Results (9,720)

The paper presents a hybrid intelligent expert diagnostic system (HIESD) of power transformer (PT) subsystems realized on the basis of integration of measuring and computing hardware and software complexes into a single functional architecture. HIESD performs online diagnostics of four main subsystems of PT: 1—insulating (liquid and solid insulation); 2—electromagnetic (windings, magnetic conductor); 3—voltage regulation; and 4—high-voltage inputs. Computational complexes and modules of the system are connected with the real object of power grids, 110/10 kV substation, which interact with each other and contain a relational database of retrospective offline data of the PT “life cycle” (including test and measurement results), supplemented by online monitoring data of the main subsystems, corrected by high-precision test measurements; analytical complex, in which the work of calculation modules of the operational state of PT subsystems is supplemented by predictive analytics and machine learning modules; and a knowledge base, sections of which are regularly updated and supplemented. The system architecture is tested at industrial facilities in terms of online transformer diagnostics based on dissolved gas analysis (DGA) data. Additionally, a theoretical model of diagnostics based on the electromagnetic characteristics of the transformer, which takes into account distorted and nonlinear modes of its operation, is presented. The scientific significance of the work consists of the presentation of the following new provisions: Methodology and algorithm for diagnostics of electromagnetic parameters of ST, taking into account nonlinearity and non-sinusoidality of winding currents and voltages; formation of optimal client–service architecture of training models of hybrid system based on the processes of data storage and management; and modification of the moth–flame algorithm to optimize the smoothing coefficient in the process of training a probabilistic neural network Full article

In parallel with technical training on knowledge and skills of task-specific medical or surgical procedures, wide arrays of soft skills training would contribute to obstetric safety in the contemporary healthcare setting. This article, as a service evaluation, explored the effect of a specialty-based Crew Resource Management (CRM) training series that transforms the concept of human factors into sustainable measures in fostering clinical safety culture of the Department of Obstetrics and Gynaecology (O&G) in the Queen Elizabeth Hospital. Within the last decade, a tri-phasic programme has been implemented by an inter-professional workgroup which consists of a consultant anaesthesiologist, medical specialists and departmental operations manager from O&G, a nurse simulation specialist, hospital administrators, and a research psychologist. (1) Phase I identified different patterns of attitudinal changes (in assertiveness, communication, leadership, and situational awareness, also known as “ACLS”) between doctors and nurses and between generic and specialty-based sessions for curriculum planning. (2) Phase II evaluated how these specific behaviours changed over 3 months following CRM training tailored for frontline professionals in O&G. (3) Phase III examined the coping style in conflict management and the level of sustainability in self-efficacy over 3 months following specialty-based CRM training. The findings showed the positive impacts of O&G CRM training on healthcare professionals’ increased attitude and behaviour in “ACLS” by 22.7% at a p < 0.05 level, character strengths in conflict management, and non-inferior or sustained level of self-efficacy under tough conditions in the clinical setting up to 3 months after training. As a way forward, incorporating a scenario-based O&G CRM programme into existing skills-based training is expected to change service framework with an innovative approach. In addition, exploring actual clinical outcomes representing a higher level of organisational impacts can be a strategic direction for further studies on the effect of this practical and educational approach on obstetric safety culture. Full article

As a staple cereal worldwide, winter wheat plays a pivotal role in food security. Leaf chlorophyll serves as a direct indicator of photosynthetic performance and nitrogen nutrition, making it critical for precision management and yield gains. Consequently, rapid, nondestructive, and high-accuracy remote-sensing retrievals are urgently needed to underpin field operations and precision fertilization. In this study, canopy hyperspectral reflectance together with destructive chlorophyll assays were systematically acquired from Yangling field trials conducted during 2018–2020. Three families of spectral indices were devised: classical empirical indices; two-dimensional optimal spectral indices (2D OSI) selected by correlation-matrix screening; and novel three-dimensional optimal spectral indices (3D OSI). The main contribution lies in devising novel 3D OSIs that combine three spectral bands and demonstrating how their fusion with classic two-band indices can improve chlorophyll quantification. Correlation analysis showed that most empirical vegetation indices were significantly associated with chlorophyll (p < 0.05), with the new double difference index (NDDI) giving the strongest relationship (R = 0.637). Within the optimal-index sets, the difference three-dimensional spectral index (DTSI; 680, 807, and 1822 nm) achieved a correlation coefficient of 0.703 (p < 0.05). Among all multi-input fusion schemes, fusing empirical indices with 3D OSI and training with RF delivered the best validation performance (R² = 0.816, RMSE = 0.307 mg g⁻¹, MRE = 11.472%), and external data further corroborated its feasibility. Altogether, integrating 3D spectral indices with classical vegetation indices and deploying RF enabled accurate, nondestructive estimation of winter wheat chlorophyll, offering a new hyperspectral pathway for monitoring crop physiological status and advancing precision agricultural management and fertilization, can guide in-season fertilization to optimize nitrogen use, thereby advancing precision agriculture. Full article

The agro-industry is among the largest methane emitters, posing a critical challenge for sustainability. In rural areas, producers lack effective technologies to manage daily organic waste. Anaerobic digestion (AD) offers a circular pathway by converting waste into biogas and biofertilizers; however, its adoption is limited by inappropriate designs and insufficient operational control. Theoretical-applied research addresses these barriers by improving the design and operation of small-scale biodigesters, elevating pH and Electrical Conductivity (EC) from passive indicators to first-order control variables. Based on the design of a compact biodigester previously validated in the Chillón Valley and replicated in Huaycán under a utility model patent process (INDECOPI, Exp. 001087-2025/DIN), a stoichiometric NaHCO${}_3$ strategy with joint pH–EC monitoring was formalized, defining operational windows (pH 6.92–6.97; EC 6200–6300 μS/cm and dose–response curves (0.3–0.4 kg/day for 3–4 day) to buffer VFA shocks and preserve methanogenic ionic strength. The system achieved stable productions of 370–462 L/day, surpassing the theoretical potential of 352.88 L/day calculated by Buswell’s equation. A multivariable predictive model (linear, quadratic, interaction terms pH × EC, temperature, and loading rate) was developed and validated with field data: R² = 0.78; MAPE = 2.7%; MAE = 11.2 L/day; RMSE = 13.8 L/day; r = 0.89; residuals normally distributed (Shapiro–Wilk p = 0.79). The proposed approach enables daily decision-making in low-instrumentation environments and provides a replicable and scalable pathway for the safe valorization of organic waste in rural areas. The design consolidates the shift from reactive to proactive and co-optimized pH–EC control, laying the foundation not only for standardized protocols and training in rural systems but also for improved environmental sustainability. Full article

Public transport bus services often experience financial inefficiencies due to high operational costs and unbalanced service allocation. To address these challenges, this study presents a machine learning-based framework aimed at optimizing financial and operational performance in public bus systems. A dataset comprising 57 routes including cost, service, and ridership data was analyzed to identify key factors correlated with net revenue. These features were integrated into multiple predictive models, among which support vector regression (SVR) with a Gaussian kernel and Bayesian optimization achieved the highest accuracy (R² = 0.99), indicating excellent generalization capability. Scenario simulations using the trained SVR model evaluated the effects of service and cost adjustments. Results showed that cutting personnel costs had the most significant effect on net income, followed by administrative and financial expenses. These findings highlight the importance of data-driven strategies such as route reallocation and workforce optimization. The proposed framework offers transit agencies a robust tool for improving efficiency and ensuring financial sustainability. Full article

(1) Background: Fiberoptic Endoscopic Evaluation of Swallowing (FEES) is one of the two gold-standard tools for assessing oropharyngeal dysphagia (alongside Videofluoroscopic Swallowing Study). Although generally considered safe, concerns about complications persist, particularly in systems where FEES is not routine and professional roles differ. The aim of this study was to evaluate the safety of FEES performed by both speech-language pathologists (SLPs) and physicians, in order to provide evidence of its safety in a healthcare system where the procedure is not yet widely established and to identify patient subgroups potentially at higher risk of procedure-related complications. (2) Methods: This retrospective study analyzed 964 consecutive FEES procedures. Examinations were carried out by trained SLPs or physicians. Data included demographics, clinical status, operator qualifications, setting, and complications, classified as minor (vomiting, poor tolerance, early termination) or major (laryngospasm, epistaxis). (3) Results: The overall complication rate was 1.14% (11/964): 0.6% minor and 0.5% major. All events were self-limiting. Complication rates did not differ between SLPs (1.05%) and physicians (1.23%) or by experience, setting, drug use, penetration–aspiration scale score, or nasogastric tube. Four complications occurred in amyotrophic lateral sclerosis patients, suggesting higher risk. (4) Conclusions: FEES is safe and well tolerated when performed by either physicians or SLPs. These findings underscore the value of task sharing in dysphagia diagnostics, demonstrating that a shared model increases service capacity, reduces delays, and facilitates timely management of dysphagia. Full article

Early detection of network traffic anomalies is critical for cybersecurity, as a single compromised host can cause data breaches, reputational damage, and operational disruptions. However, traditional systems based on signatures and static rules are often ineffective against sophisticated and evolving threats. This study proposes a hybrid deep learning architecture for proactive anomaly detection in local and metropolitan networks. The dataset underwent an extensive process of cleaning, transformation, and feature selection, including normalization of numerical fields, encoding of ordinal variables, and derivation of behavioral metrics. The EFMS-KMeans algorithm was applied to pre-label traffic as normal or anomalous by estimating dense centers and computing centroid distances, enabling the training of a sequential CNN-GRU network, where the CNN captures spatial patterns and the GRU models temporal dependencies. To address class imbalance, the SMOTE technique was integrated, and the loss function was adjusted to improve training stability. Experimental results show a substantial improvement in accuracy and generalization compared to conventional approaches, validating the effectiveness of the proposed method for detecting anomalous traffic in dynamic and complex network environments. Full article

Background: Healthcare 5.0 represents a shift toward intelligent, human-centric care systems. Intensive care units generate vast amounts of data that require real-time decisions, but current decision support systems lack comprehensive frameworks for safe integration of artificial intelligence. Objective: We developed and validated the Learn–Predict–Monitor–Detect–Correct (LPMDC) framework as a methodology for systematic artificial intelligence integration across the critical care workflow. The framework improves predictive analytics, continuous patient monitoring, intelligent alerting, and therapeutic decision support while maintaining essential human clinical oversight. Methods: Framework development employed systematic theoretical modeling integrating Healthcare 5.0 principles, comprehensive literature synthesis covering 2020–2024, clinical workflow analysis across 15 international ICU sites, technology assessment of mature and emerging AI applications, and multi-round expert validation by 24 intensive care physicians and medical informaticists. Each LPMDC phase was designed with specific integration requirements, performance metrics, and safety protocols. Results: LPMDC implementation and aggregated evidence from prior studies demonstrated significant clinical improvements: 30% mortality reduction, 18% ICU length-of-stay decrease (7.5 to 6.1 days), 45% clinician cognitive load reduction, and 85% sepsis bundle compliance improvement. Machine learning algorithms achieved an 80% sensitivity for sepsis prediction three hours before clinical onset, with false-positive rates below 15%. Additional applications demonstrated effectiveness in predicting respiratory failure, preventing cardiovascular crises, and automating ventilator management. Digital twins technology enabled personalized treatment simulations, while the integration of the Internet of Medical Things provided comprehensive patient and environmental surveillance. Implementation challenges were systematically addressed through phased deployment strategies, staff training programs, and regulatory compliance frameworks. Conclusions: The Healthcare 5.0-enabled LPMDC framework provides the first comprehensive theoretical foundation for systematic AI integration in critical care while preserving human oversight and clinical safety. The cyclical five-phase architecture enables processing beyond traditional cognitive limits through continuous feedback loops and system optimization. Clinical validation demonstrates measurable improvements in patient outcomes, operational efficiency, and clinician satisfaction. Future developments incorporating quantum computing, federated learning, and explainable AI technologies offer additional advancement opportunities for next-generation critical care systems. Full article

The failure to accurately identify abnormal vibrations in protected metro areas is a serious threat to the operational safety of metro tunnels and trains, and there is currently no suitable method for effectively improving the accuracy of abnormal vibration identification. To address this issue, an accurate method for identifying abnormal vibrations in a metro reserve based on spatially correlated dense measurement points is proposed. First, by arranging distributed optical fibers along the longitudinal length of a tunnel, dynamic strain vibration signals are extracted via phase-sensitive optical time-domain reflectometry analysis, and analysis of variance (ANOVA) and Pearson correlation analysis are used to jointly downscale the dynamic strain features. On this basis, a spatial correlation between the calculated values of the features of the target measurement points to be updated and its adjacent measurement points is constructed, and the spatial correlation credibility of the dynamic strain features between the dense measurement points and the target measurement points to be updated is calculated via quadratic function weighting and kernel density estimation methods. The weights are calculated, and the eigenvalues of the target measurement points are updated on the basis of the correlation credibility weights between the adjacent measurement points. Finally, a support vector machine (SVM) and back propagation (BP) identification model for the eigenvalues of the target measurement points are constructed to identify the dynamic strain eigenvalues of the abnormal vibrations in the underground tunnel. Numerical simulations and an experiment in an actual tunnel verify the effectiveness of the proposed method. Full article

As the core refrigeration equipment in cooling systems, the operational state of chiller units is crucial for ship support, equipment cooling, and mission stability. However, because of their sensitivity and the complexity of operating environments, obtaining large volumes of complete, fault-labeled data is difficult in practical engineering appli-cations. This limitation makes it challenging for traditional data-driven approaches to deliver accurate fault diagnoses. Furthermore, data collected from different devices or under varying operating conditions often differ significantly in both feature dimensions and distributions, i.e., data heterogeneity, which further complicates model transfer. To address these challenges, this study proposes a deep transfer learning–based fault di-agnosis method designed to leverage abundant knowledge from the source domain while adaptively learning features of the target domain. Given the persistent difficulties in collecting sufficient high-quality labeled fault data, traditional data-driven models continue to face restricted diagnostic performance on target equipment. At the same time, data heterogeneity across devices or operating conditions intensifies the challenge of cross-domain knowledge transfer. To overcome these issues, this study develops a heterogeneous transfer learning method that integrates a dual-channel autoencoder, domain adversarial training, and pseudo-label self-training. This combination enables precise small-sample knowledge transfer from the source to the target domain. Specifi-cally, the dual-channel autoencoder is first applied to align heterogeneous feature di-mensions. Then, a Gradient Reversal Layer (GRL) and a domain discriminator are in-troduced to extract domain-invariant features. In parallel, high-confidence pseu-do-labeled samples from the target domain are incorporated into joint training to im-prove generalization and robustness. Experimental results confirm that the method achieves high fault diagnosis accuracy in typical industrial application scenarios, ena-bling effective identification of common faults in various types of chiller units under conventional operating conditions, the proposed method achieves higher accuracy and F1-scores in multi-class fault diagnosis tasks compared with both traditional approaches and existing transfer learning methods. These findings provide a novel perspective for advancing the intelligent operation and maintenance of chiller units. Full article

Background: The accuracy and consistency of complete-arch digital impressions are fundamental for long-term success of implant-supported rehabilitations. Recently, artificial intelligence (AI)-assisted tools, such as SmartX (Medit Link v3.4.2, MEDIT Corp., Seoul, South of Korea), have been introduced to enhance scan body recognition and data alignment during intraoral scanning. Objective: This in vitro study aimed to evaluate the impact of SmartX on impression accuracy, consistency, operator confidence, and technique sensitivity in complete-arch implant workflows. Methods: Seventy-two digital impressions were recorded on edentulous mandibular models with four dummy implants, using six experimental subgroups based on scan body design (double- or single-wing), scanning technique (occlusal or combined straight/zigzag), and presence/absence of SmartX tool. Each group was scanned by both an expert and a novice operator (n = 6 scans per subgroup). Root mean square (RMS) deviation and scanning time were assessed. Data were tested for normality (Shapiro–Wilk). Parametric tests (t-test, repeated measures ANOVA with Greenhouse–Geisser correction) or non-parametric equivalents (Mann–Whitney U, Friedman) were applied as appropriate. Post hoc comparisons used Tukey HSD or Dunn–Bonferroni tests (α = 0.05). Results: SmartX significantly improved consistency and operator confidence, especially among novices, although it did not yield statistically significant differences in scan accuracy (p > 0.05). The tool mitigated early scanning errors and reduced dependence on operator technique. SmartX also enabled successful library alignment with minimal data; however, scanning time was generally longer with its use, particularly for beginners. Conclusions: While SmartX did not directly enhance trueness, it substantially improved scan reliability and user experience in complete-arch workflows. Its ability to minimize technique sensitivity and improve reproducibility makes it a valuable aid in both training and clinical settings. Further clinical validation is warranted to support its integration into routine practice. Full article

Objective evaluation of pilot fatigue is crucial for enhancing aviation safety. Although electroencephalography (EEG) is regarded as an effective tool for recognizing pilot fatigue, the direct application of deep learning models to raw EEG signals faces significant challenges due to issues such as massive data volume, excessively long training time, and model overfitting. Moreover, existing feature-based methods often suffer from data redundancy due to the lack of effective feature and channel selections, which compromises the model’s recognition efficiency and accuracy. To address these issues, this paper proposes a framework, named ASFT-Transformer, for fast and accurate detection of pilot fatigue. This framework first extracts time-domain and frequency-domain features from the four EEG frequency bands. Subsequently, it introduces a feature and channel selection strategy based on one-way analysis of variance and support vector machine (ANOVA-SVM) to identify the most fatigue-relevant features and pivotal EEG channels. Finally, the FT-Transformer (Feature Tokenizer + Transformer) model is employed for classification based on the selected features, transforming the fatigue recognition problem into a tabular data classification task. EEG data is collected from 32 pilots before and after actual simulator training to validate the proposed method. The results show that ASFT-Transformer achieved average accuracies of 97.24% and 87.72% based on cross-clip data partitioning and cross-subject data partitioning, which were significantly superior to several mainstream machine learning and deep learning models. Under the two types of cross-validation, the proposed feature and channel selection strategy not only improved the average accuracy by 2.45% and 8.07%, respectively, but also drastically reduced the average training time from above 1 h to under 10 min. This study offers civil aviation authorities and airline operators a tool to manage pilot fatigue objectively and effectively, thereby contributing to flight safety. Full article

We study motif-based optimization for sparse multilayer perceptrons (MLPs), where weights are shared and updated at the level of small neuron groups (‘motifs’) rather than individual connections. Building on Sparse Evolutionary Training (SET), our approach reduces the number of unique parameters and redundant multiply–accumulate operations by exploiting block-structured sparsity. Across Fashion-MNIST and a lung X-ray dataset, our Motif-SET improves training/inference efficiency with modest accuracy trade-offs, and we provide a principled recipe to choose motif size based on accuracy and efficiency budgets. We further compare against representative modern sparse training and compression methods, analyze failure modes such as overly large motifs, and outline real-world constraints on mobile/embedded targets. Our results and ablations indicate that motif size $m=2$ often offers a strong balance between compute and accuracy under resource constraints. Full article

This paper introduces a hybrid learning framework that synergistically combines Reinforcement Learning (RL) and Supervised Learning (SL) to train autonomous cyber-defense agents capable of operating effectively in dynamic and adversarial environments. The proposed approach leverages RL for strategic exploration and policy development, while incorporating SL to distill high-reward trajectories into refined policy updates, enhancing sample efficiency, learning stability, and robustness. The framework first targets specialized agent training, where each agent is optimized against a specific adversarial behavior. Subsequently, it is extended to enable the training of a generalized agent that learns to counter multiple, diverse attack strategies through multi-task and curriculum learning techniques. Comprehensive experiments conducted in the CybORG simulation environment demonstrate that the hybrid RL–SL framework consistently outperforms pure RL baselines across both specialized and generalized settings, achieving higher cumulative rewards. Specifically, hybrid-trained agents achieve up to 23% higher cumulative rewards in specialized defense tasks and approximately 18% improvements in generalized defense scenarios compared to RL-only agents. Moreover, incorporating temporal context into the observation space yields a further 4–6% performance gain in policy robustness. Furthermore, we investigate the impact of augmenting the observation space with historical actions and rewards, revealing consistent, albeit incremental, gains in SL-based learning performance. Key contributions of this work include: $\left(i\right)$ a novel hybrid learning paradigm that integrates RL and SL for effective cyber-defense policy learning, $\left(ii\right)$ a scalable extension for training generalized agents across heterogeneous threat models, and $\left(iii\right)$ empirical analysis on the role of temporal context in agent observability and decision-making. Collectively, the results highlight the promise of hybrid learning strategies for building intelligent, resilient, and adaptable cyber-defense systems in evolving threat landscapes. Full article

Objectives: To predict the progression of knee osteoarthritis (OA), a deep convolutional neural network model was developed and applied to basic images and clinical data. Design: A vision transformer-based model was trained using 5565 knee radiographs as baseline images from the osteoarthritis initiative (OAI), including 578 testing images. Each knee had a corresponding Kellgren and Lawrence (KL) stage after 48 months of follow-up. Another 274 cases from the Far Eastern Memorial Hospital were used for external validation. The data included a combination of single/pairing images and full/essential clinical factors. Area under the receiver operating characteristics (AUROC), accuracy, sensitivity, specificity, odds ratio, and ability to discriminate surgical candidates were applied to evaluate model performance. Results: In cases with OA progression, the AUROC for identifying surgical candidates was 0.844, 0.804, 0.766, and 0.718 in the combination of a single image with essential factors, single image with full factors, pairing images with essential factors, and pairing images with full factors, respectively. In OAI testing using the simplest input, AUROC of identifying OA progression was 0.808, with 74.1% accuracy, 91.8% sensitivity, and 71% specificity. In external validation, AUROC of identifying OA progression was 0.709, with 71.2% accuracy, 72.2% sensitivity, and 70.3% specificity. Positive model prediction had an odds ratio of 23.87 (CI: 11.24~50.67) in OAI and 5.92 (CI: 3.50~10.03) in external validation. Conclusions: Our model provides reliable prediction results for knee OA cases with the advantages of simplicity and flexibility. The model performance was excellent in progression cases, potentially making early intervention in OA patients more efficient. Full article