Search Results (200)

Ischaemic stroke constitutes a leading cause of global disability. Rapid extraction of the infarct core from multimodal computed tomography perfusion (CTP) imaging guides reperfusion therapy and clinical decision-making. Deep learning algorithms automate this delineation, yet hospital translation is hindered by high-dimensional data, inter-scanner variability, and the low contrast of early ischaemia. Architectural comparisons in the literature frequently carry methodological biases originating from disparate preprocessing protocols and data partitions. This study reduces these variables by evaluating three segmentation strategies under a shared preprocessing pipeline and an identical data partition using the ISLES 2024 dataset. Three models were trained on the same 133-patient partition using a shared preprocessing pipeline based on morphological skull-stripping and modality-specific clinical intensity ranges. The data, preprocessing, and partitions are held constant across models, while framework-dependent factors (optimiser, patch size, physical field of view, spatial resampling, augmentation policy, and model capacity) remain coupled to each architecture and are therefore treated as part of the compared strategy rather than as fully isolated variables. The first of these is a single-stage 5-channel nnU-Net, followed by a two-stage cascaded nnU-Net (2 and 7 channels) and a lightweight Transformer (SegFormer3D). Evaluation on a fixed 15-patient held-out test set isolated the architectural performance. The cascade model achieved the highest Dice Similarity Coefficient (0.224). The single-stage nnU-Net provided the most precise volumetric estimation, recording an Absolute Volume Difference (AVD) of 23.70 mL and a lesion-wise F1-score of 7.60%. On the other hand, SegFormer3D returned the lowest overall metrics (DSC 0.163, AVD 27.28 mL, F1 2.30%). In the small held-out cohort, paired statistical testing did not reveal significant differences between models, so the reported orderings describe the present dataset and experimental configuration rather than a general architectural law. Within these limits, the local inductive bias of the convolutional models retained an empirical advantage over the single Transformer evaluated when processing this moderately sized neuroimaging dataset, and complex cascade topologies offered only marginal gains compared with a well-calibrated single-stage network. Although the predictive segmentation of infarcted tissue at acute stages still demands computational improvements, these results suggest that preprocessing quality is at least as decisive for clinical impact as increasing the complexity of neural architectures. Full article

Background: Effective playing time (EPT) is a crucial determinant of the physical, technical, and cognitive development of young soccer players. Reducing match interruptions may enhance game rhythm and support player progression. This study examined the effects of a rapid-restart protocol, based on the availability of spare balls (SB), on EPT, sprint performance, and agility in young Tunisian players. Methods: Sixty male youth players (aged 11–16) from a Tunisian first-division club were randomly assigned to an experimental group (EG, n = 30) or a control group (CG, n = 30) across three age categories (U12, U14, U16). The EG played 10 weekly matches using the rapid-restart protocol, while the CG competed under standard conditions. Sprint performance (5 m, 10 m, 20 m) and agility (Illinois Agility Test, IAT) were assessed at baseline (T0), mid-intervention (T1), and post-intervention (T2). EPT was determined through video analysis. Results: Compared with controls, the EG showed significant improvements in sprint (5 m and 20 m) and IAT performance across all age categories (p < 0.01). EPT increased, providing additional opportunities for ball-in-play exposure during matches. The protocol also reduced contact between ball retrievers and players, thereby improving safety and minimizing interruptions. Conclusions: The rapid-restart protocol (RRP) effectively increased EPT and was associated with improvements in sprint and agility performance. Whether these improvements were mediated by changes in match intensity or physiological load remains to be determined. Its simplicity, low cost, and safety benefits make it a practical strategy for coaches, organizers, and the Tunisian Football Federation. This approach may represent a practical organizational strategy for improving match continuity and EPT during youth soccer competitions. Full article

Raman spectroscopy combined with machine learning offers a rapid, label-free approach for bacterial identification, but robust translation remains challenged by spectral variability, biological heterogeneity, and limited model interpretability. Here, we present an integrated evaluation of an optimized Spectral Transformer (ST) framework for Raman-based bacterial classification benchmarked against a systematically optimized one-dimensional convolutional neural network (1D-CNN). The comparison was performed using a curated 36-class dataset comprising 15 Gram-negative bacterial entries, 15 Gram-positive bacterial entries, one non-bacterial microorganism, and five background/reference classes, enabling evaluation of both species-level and fine-grained bacterial classification. Under 15 dB noise-augmented evaluation, the ST achieved 80.6% ± 0.3% accuracy and a Matthews correlation coefficient (MCC) of 0.801 ± 0.003, outperforming the 1D-CNN baseline with 72.9% ± 0.3% accuracy and an MCC of 0.721 ± 0.003. Integrated Gradients analysis combined with attention map visualization enabled multi-level model interpretation, revealing that the ST’s improved robustness correlates with more bounded attribution patterns during misclassification, whereas the 1D-CNN’s feature attribution becomes scattered under noise perturbation. Importantly, this interpretability-driven analysis identified model-specific failure modes in the baseline architecture, including an over-reliance on non-specific spectral regions under noise, which can inform future data collection strategies and guide refinements to experimental protocols. These results demonstrate that attention-based spectral modeling improves Raman-based bacterial classification under noise-perturbed conditions while enabling multi-level interpretability that bridges model understanding with actionable feedback on experimental design and data quality requirements. Full article

Background and Objective: Pulsed electromagnetic fields (PEMF) and extracorporeal magnetotransduction therapy (EMTT) have shown promising results in various musculoskeletal disorders; however, substantial heterogeneity in application parameters has hindered the establishment of clear relationships between electromagnetic dosing and clinical response. This systematic review aims to evaluate the safety and effectiveness of PEMF and EMTT therapies for treating chronic musculoskeletal injuries in adults, based on research from 2015 to 2026. By analyzing how specific dosage parameters (such as intensity, frequency, and duration) influence clinical results, the study seeks to establish standardized, evidence-based guidelines for electromagnetic treatment prescriptions. Methods: A systematic review was conducted in accordance with PRISMA 2020 guidelines and prospectively registered in PROSPERO (CRD420251059359). A comprehensive search was performed in PubMed/MEDLINE, CENTRAL, and ScienceDirect for the 2015–2025 period. Randomized clinical trials, quasi-experimental studies, and case reports were included. Study selection, data extraction, and risk of bias assessment were performed by two independent reviewers using RoB 2, ROBINS-I, and Joanna Briggs Institute checklists. Results were synthesized narratively following SWiM (Synthesis Without Meta-analysis) recommendations. Results: Twenty-eight studies (1060 participants) were included. A dosimetric dichotomy emerged: high-intensity protocols with rapid field variation rates (e.g., EMTT > 60 kT/s) were consistently associated with robust improvements in structural and mechanically driven pathologies. Conversely, low-intensity protocols (e.g., <5 mT) often yielded results indistinguishable from placebo or active controls, particularly in nociplastic pain conditions. Quantitative analysis indicated that in structural pathologies, functional gains were maintained or amplified post-treatment, whereas nociplastic conditions showed potential symptom recurrence. No serious adverse events were reported, confirming a favorable safety profile. Conclusions: PEMF and EMTT are promising adjunctive therapies for musculoskeletal disorders, with efficacy appearing sensitive to electromagnetic dosimetry. However, significant methodological heterogeneity and the use of combination therapies limit these findings to exploratory trends. The lack of standardized safety reporting and technical parameters (e.g., waveform, dB/dt) underscores a critical translational gap. Future research must prioritize rigorous, standardized randomized controlled trials to establish definitive, evidence-based therapeutic recommendations. Full article

The rapid growth of sensitive labeled data in healthcare, finance, user profiling, and commercial databases has created increasing demand for privacy-preserving collaborative data validation across different organizations. Following prior cryptographic studies, this paper uses private collaborative data cleaning (PCDC) to refer to a specific label-conflict detection task rather than general-purpose data cleaning: the goal is to identify records for which the identifiers match but the associated labels are inconsistent, without revealing the remaining private records. Existing PCDC protocols are mainly designed for direct two-party settings where data owners must remain online and participate in the main secure computation. To reduce this online burden, we propose SS-PCDC, a secret sharing-based PCDC framework in a cloud-assisted setting. Clients locally preprocess and secret-share their labeled datasets with two non-colluding cloud servers, which perform element matching, label consistency checking, and conflict detection over secret shares. Hash-based binning is used to reduce unnecessary secure comparisons. We instantiate the framework with two concrete protocols based on arithmetic secret sharing and Boolean secret sharing, respectively. We further extend exact PCDC to threshold-based fuzzy label conflict detection and propose SS-FPCDC, which reports a matched record as conflicting when the Hamming distance between its labels exceeds a public threshold. Security analyses show that the proposed protocols securely realize their corresponding ideal functionalities against a static semi-honest adversary corrupting at most one cloud server. Experimental results demonstrate the efficiency and scalability of SS-PCDC in its intended cloud-assisted setting, particularly for large datasets and longer labels. Full article

Background: Platelet concentrates are widely used in regenerative dentistry and maxillofacial surgery; however, the lack of protocol standardization and selection criteria results in contradictory clinical outcomes. This study aimed to perform a comparative analysis of the biological activity of various platelet concentrates obtained via different fractionation and activation procedures under uniform in vitro experimental conditions. Methods: Rat adipose-derived stem cells (ADSCs) and human EA.hy926 endothelial cells were used to evaluate four platelet concentrate types via tube formation, wound healing (scratch), and cell proliferation assays. Results: Platelet concentrates obtained by the single-centrifugation protocol (L-PRP-1) exhibited maximal retained platelet potential, corresponding to a peak 5-fold increase in cell migration. Chemical activation of plasma-based concentrates (L-PRP, P-PRP) with calcium/thrombin was critically required to trigger angiogenesis and accelerate endothelial chemotaxis. Conversely, plasma-free platelet concentrate (PFPC) exhibited a unique capacity for spontaneous activation and clot formation without exogenous inducers, triggering rapid angiogenesis and sustaining ADSC proliferation. Conclusions: Within the framework of our in vitro model, activated plasma-based forms are biologically justified for accelerated soft tissue healing and socket preservation, whereas the complete removal of plasma proteins suggests the potential utility of PFPC as a biomimetic matrix-carrier for maxillofacial tissue engineering. Full article

With the rapid development of artificial intelligence (AI) technologies, machine learning (ML) has been widely applied in concrete material design, performance prediction, and intelligent structural engineering. Compared with traditional empirical approaches, ML can efficiently establish complex nonlinear relationships among concrete mix proportions, environmental factors, and performance indicators, thereby improving prediction efficiency, reducing experimental costs, and enabling multi-objective optimization of mix proportions. This paper systematically reviews the recent research progress of ML technologies in the field of concrete engineering, with particular emphasis on typical algorithms, including supervised learning, unsupervised learning, and reinforcement learning. Their applications in predicting workability, mechanical properties, durability performance, and mix proportion optimization are comprehensively summarized. In addition, recent advances in ML applications for crack detection and digital twin technologies are also discussed. Moreover, deep learning and computer vision (CV) technologies have significantly promoted the development of crack identification and structural health monitoring, whereas the integration of digital twin and Internet of Things (IoT) technologies has further expanded the application of ML in smart infrastructure. Finally, the current challenges associated with data quality, model interpretability, and engineering applications are summarized, and future research directions are discussed. Overall, by linking algorithm choice to specific concrete performance-prediction tasks, this review clarifies the conditions under which ML delivers reliable results and provides a structured reference for both researchers and practitioners. The comparative analysis indicates that ensemble tree-based models—particularly random forest and gradient-boosting variants such as XGBoost—together with well-tuned neural networks consistently achieve the highest predictive accuracy across most concrete properties, with reported test-set coefficients of determination commonly between 0.90 and 0.99, whereas limited data availability, inconsistent validation protocols, and restricted model interpretability remain the principal obstacles to engineering deployment. Full article

The rapid growth of heterogeneous IoT devices in 5G environments has created stringent requirements for low-latency edge-based protocol processing. Existing static parsing frameworks lack adaptability to dynamic multi-protocol traffic, resulting in increased processing delays and quality-of-service (QoS) violations under bursty workloads. This paper presents HeteroEdge, a latency-aware adaptive protocol parsing framework for 5G Multi-access Edge Computing (MEC) environments. HeteroEdge integrates four tightly coupled components: (i) a lightweight machine-learning-based Heterogeneous Protocol Parsing Layer (HPPL) built on gradient-boosted decision trees (XGBoost); (ii) a Network Digital Twin (NDT) that maintains a compressed and continuously updated representation of IoT endpoint states; (iii) a Real-Time Inference Engine (RTIE) that dynamically reallocates parsing resources at 50 ms intervals; and (iv) a What-If Simulation (WIS) module that proactively evaluates resource-allocation strategies under hypothetical traffic scenarios. Experimental evaluation on a physical 5G MEC testbed comprising four Intel Xeon Silver 4316 edge nodes and 2000 emulated IoT endpoints spanning twelve protocol classes demonstrates the effectiveness of the proposed framework. HeteroEdge reduces median edge parsing latency (including parsing, classification, and queuing delays, but excluding the 5G radio component) by up to 44.7% compared with static MEC baselines, achieves a macro-averaged protocol classification accuracy of 97.8%, and sustains sub-7 ms edge parsing latency at a line-rate NIC injection throughput of 18 Gbps. Furthermore, latency spikes under bursty traffic are reduced by 39% at the 95th percentile, while SLA violation rates decrease by a factor of 3.9 relative to static resource allocation. These results demonstrate that HeteroEdge provides an effective and scalable solution for latency-critical IoT applications, including smart manufacturing, connected vehicles, and urban sensing. Full article

Mycelium-bound composites (MBCs) have emerged as a promising class of biofabricated materials that integrate fungal hyphal networks with lignocellulosic substrates to form lightweight, biodegradable structures without synthetic adhesives. Despite rapid growth in the field, the current literature remains fragmented, with inconsistent methodologies and widely varying reported material properties. This review advances the field by moving beyond descriptive synthesis toward a quantitative and conceptual integration of existing studies. We systematically analyze how key fabrication variables—including fungal species, substrate composition, growth conditions, and post-processing parameters—govern density, porosity, and mechanical performance. A process–structure–property (PSP) framework is proposed to combine these relationships and explain discrepancies across studies. We highlight the dominant role of densification and moisture conditioning in determining compressive strength, often outweighing species-level effects. A comparative synthesis of reported data reveals significant variability in compressive strength (0.05–1.2 MPa) and elastic modulus, attributable to inconsistencies in sample preparation, testing protocols, and environmental conditioning. To address this, we identify critical gaps in standardization and propose actionable testing protocols and reporting guidelines for reproducibility. Furthermore, we assess the technology readiness level (TRL) of MBC systems and distinguish between laboratory-scale innovations and commercially viable processes. While hybridization strategies and biofunctional applications offer promising avenues, their maturity varies widely. This work provides a decision-oriented framework for MBC design and a roadmap for transitioning these materials from experimental systems to scalable, standardized, and application-ready biomaterials. Full article

The rapid proliferation of Internet of Things (IoT) devices within 5G-enabled smart city environments has introduced unprecedented challenges in communication protocol management across heterogeneous network architectures. With connected IoT devices projected to reach 21.1 billion by the end of 2025 and approximately 39 billion by 2030, existing static protocol selection mechanisms are unable to accommodate the dynamic Quality of Service (QoS) requirements of different smart city applications, such as enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communication (URLLC), and massive Machine-Type Communication (mMTC). This paper presents APO-DRL (Adaptive Protocol Optimization using Deep Reinforcement Learning), a framework that utilizes a Dueling Double Deep Q-Network (D3QN) combined with a Prioritized Experience Replay mechanism for intelligent, real-time communication protocol selection and parameter optimization in heterogeneous IoT networks. The proposed framework formulates the protocol optimization problem as a Markov Decision Process (MDP), wherein the DRL agent dynamically selects the optimal communication protocol (NB-IoT, LTE-M, LTE Cat-1, or 5G NR) and adaptively tunes transmission parameters based on real-time network conditions. Experimental evaluation in a 3GPP TR 38.901 Urban Macro simulation environment with N = 30 devices demonstrates that APO-DRL achieves a 138.9% improvement in average throughput compared to Static Allocation (60.00 vs. 25.12 Mbps), while simultaneously achieving the highest QoS satisfaction (83.38%) across all methods, albeit with higher energy consumption and packet loss than Static Allocation. Relative to D3QN+PER, APO-DRL exhibits substantially lower cross-seed throughput variance (±0.88 vs. ±11.03 Mbps), confirming that QA-PER produces a more stable and reproducible learned policy. Full article

While data fitting is extensively used in polymer processing to extract fundamental rheological properties, its application for direct macroscopic geometric transfer between complex operational dies remains largely unexplored. Optimizing extrusion dies for corrugated plastic pipes traditionally requires time-consuming offline laboratory rheology, creating a major development bottleneck when dealing with proprietary, undocumented blends. To address this gap, this study introduces a novel, data-driven protocol for predicting the die pressure drop that eliminates the need for independent laboratory rheometry. Unlike traditional in situ methods that seek pure material properties, our approach back-calculates lumped, effective Power Law parameters directly from macroscopic pressure drops of existing converging dies. This uniquely embeds both material and geometric flow characteristics under actual processing conditions. Experimental validation demonstrates that this workflow, supported by an iterative refinement strategy, yields prediction errors typically within 10%. Ultimately, this lightweight computational tool provides engineers with a rapid-iteration framework to significantly accelerate early-stage die design. Full article

Leakage incidents at natural gas distribution stations (NGDSs) present severe fire and explosion risks, demanding immediate, data-driven emergency responses. While crucial for minimizing hazard impacts, real-time prediction of gas dispersion ranges remains a significant operational challenge. To partially address this critical safety need, this study introduces a rapid-response prediction framework prototype integrating computational fluid dynamics (CFD) with machine learning (ML). Specifically, a comprehensive database of 500 experimentally validated CFD leakage scenarios at 60 s was developed first, specifically focusing on mapping gas concentration contours within the critical 5–15% flammability range. To identify the most effective real-time predictive tool, three ML algorithms, including a backpropagation neural network (BPNN), long short-term memory (LSTM), and gated recurrent unit (GRU), were evaluated. The BPNN initially outperformed the sequence models, with a coefficient of determination (R²) of 0.96, a mean squared error (MSE) of 1.35, a mean absolute error (MAE) of 0.77, a maximum absolute error (MaxAE) of 4.94 and an average training time of 4.23 s per epoch. To further meet the stringent speed and precision demands of emergency scenarios, the model was enhanced via particle swarm optimization (PSO-BPNN). This optimized framework achieved exceptional accuracy (R² = 0.99, MSE = 0.34, and MAE = 0.38) while reducing the training time to just 1.42 s per epoch under the current computational configuration. The developed CFD-ML prototype provides a practical, highly efficient tool for NGDS operators and emergency responders, enabling them to instantly visualize hazard zones, optimize evacuation protocols, and safely mitigate leakage incidents before ignition occurs. Full article

The rapid expansion of Internet of Things (IoT) infrastructures in smart city environments has increased the demand for reliable intrusion detection systems (IDS). However, many existing studies rely on single-dataset evaluations and inconsistent experimental settings, which can lead to overly optimistic performance estimates. In this study, we propose a standardized benchmarking framework for evaluating artificial intelligence-based IDS across heterogeneous IoT datasets, including CIC-IoT 2023, BoT-IoT, and N-BaIoT. Multiple classical machine learning and deep learning models are evaluated under a unified preprocessing pipeline and a consistent evaluation protocol. A hybrid CNN–BiLSTM–Attention architecture is also implemented as a reference model within this framework. While several models achieve near-perfect performance under intra-dataset evaluation, cross-dataset experiments reveal substantial performance degradation and unstable metric behavior under distribution shifts. These results highlight the limitations of dataset-specific optimization and emphasize the necessity of cross-dataset validation for realistic IoT intrusion detection evaluation. All experiments are conducted under a binary intrusion detection setting (benign vs. attack) to enable consistent comparison across datasets. Consequently, the reported results reflect binary detection performance and do not capture attack-type discrimination. Full article

Polymerization shrinkage remains a primary cause of marginal failure in posterior composite restorations, contributing to interfacial gap formation and secondary caries development. Bioactive filler technologies represent a paradigm shift, offering simultaneous stress reduction and therapeutic ion release through engineered matrix–filler interactions. This narrative review synthesizes current evidence on how bioactive glass (including 45S5), amorphous calcium phosphate, and surface pre-reacted glass-ionomer fillers modulate polymerization shrinkage dynamics and mechanical performance in bulk-fill systems. These systems exhibit distinct mechanisms of bioactivity, with bioactive glass (45S5) promoting ion release and apatite formation, amorphous calcium phosphate (ACP) enabling rapid calcium phosphate ion delivery for remineralization, and surface pre-reacted glass-ionomer (S-PRG) fillers providing sustained multi-ion release with buffering and antibacterial potential. A comprehensive literature search was conducted in PubMed/MEDLINE, Scopus, and Web of Science for studies published up to June 2025, including experimental investigations and reviews assessing bioactive filler integration, with studies selected based on predefined inclusion and exclusion criteria focusing on relevance and reported outcomes. The available evidence indicates that optimized bioactive formulations reduce shrinkage stress by approximately 25–40%, decreasing from 35–40 MPa in conventional systems to 22–32 MPa in bioactive bulk-fill composites while maintaining flexural strength above 100 MPa and elastic modulus within clinically acceptable ranges (11–13 GPa). However, substantial heterogeneity in filler chemistry, loading protocols, and testing methodologies limits cross-study comparisons. This variability also reflects differences in testing conditions, material compositions, and evaluation protocols across studies. Full article

Background: Extracorporeal cardiopulmonary resuscitation (ECPR) has emerged as a promising strategy for refractory cardiac arrest, enabling the restoration of systemic perfusion when conventional resuscitation fails. However, uncertainties remain regarding patient selection, timing and implementation. Methods: A narrative review of experimental data, clinical studies, randomized trials and international recommendations was performed. Particular emphasis was placed on the interplay between physiological mechanisms, real-world organizational models and decision-making processes. Results: ECPR can restore effective circulation, preserve end organ perfusion and serve as a bridge to definitive etiologic treatment, with the potential to improve survival and neurological outcomes in highly selected patients. However, its effectiveness is strongly dependent on rapid deployment, structured systems of care and multidisciplinary coordination. Significant challenges remain, including in relation to the heterogeneity of protocols, high resource utilization, complications with extracorporeal support and the complexity of post-resuscitation management. Furthermore, ECPR fundamentally alters traditional resuscitation paradigms, introducing ethical dilemmas related to patient selection, prognostication and the allocation of limited resources. Conclusions: ECPR represents a transition from procedure-based resuscitation to system-based extracorporeal support. Its clinical benefit is contingent upon timely implementation within optimized organizational frameworks and integration with definitive treatment pathways. Future research should focus on refining selection criteria, standardizing care pathways and addressing ethical sustainability challenges to ensure appropriate and effective use of this evolving technology. Full article