Search Results (329)

Real-time fatigue classification on resource-constrained edge devices faces three unresolved computational challenges: just-in-time compilation latency spikes that violate the 50 ms inference budget, statistical moment features insensitive to temporal complexity signatures of fatigue, and binary anomaly outputs insufficient for actionable coaching decisions. A synthetic IMU dataset (9 subjects, 540,000 samples, 6 channels at 100 Hz) was generated as a reproducible computational benchmark, with fatigue signatures calibrated to published biomechanical effect sizes (sample entropy $d=+0.77$; permutation entropy $d=+0.38$). We present Safari (Stochastic Adaptive Fitness-Aware Real-time Inference), an end-to-end computational pipeline integrating: a dual-pathway entropy triplet (SampEn, PermEn, SpEn) replacing statistical moments; 16 pre-compiled polyhedral anchor kernels eliminating JIT latency; $O\left({(\Delta W)}^2\right)$-bounded runtime interpolation; subject-specific MaxEnt free-energy anomaly scoring; and a Banister fitness–fatigue adaptive threshold. Safari achieves AUC-ROC = 0.9820 (Monte Carlo 95% CI: 0.9726–0.9886), F1 = 0.8835, four-state accuracy = 83.3%, and worst-case latency = 7.2 ms on a Raspberry Pi 4. Entropy features achieve 1.55× higher discriminability than statistical moments. Safari is a computational framework for real-time fatigue monitoring, contributing a reproducible algorithmic benchmark for edge AI in movement analysis, with real-athlete validation as the recommended next step. Full article

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a debilitating multisystem illness characterised by post-exertional malaise, non-restorative sleep, and cognitive impairment, yet no objective diagnostic biomarkers have been established. Untargeted plasma metabolomics provides a broad view of the biochemical disturbances underlying ME/CFS; however, the high dimensionality of omics datasets and the limited interpretability of conventional classifiers nevertheless hinder translation into clinical practice. This study evaluates three ensemble classifiers—Explainable Boosting Machine (EBM), XGBoost, and LightGBM—for binary ME/CFS classification using plasma metabolomic and lipidomic profiles from 197 participants (106 ME/CFS; 91 healthy controls; 888 features). Feature dimensionality was reduced using a Pareto-Guided Recursive Neural Network (PRNN) pipeline. Model performance was assessed via 50-repeat stratified hold-out validation. EBM achieved the highest accuracy (0.909; 95% CI: 0.868–0.949) and area under the receiver operating characteristic curve (AUC: 0.940; 95% CI: 0.909–0.983), with XGBoost and LightGBM performing comparably. Interpretability analyses revealed that pairwise metabolite interaction terms—particularly proline & indole-3-lactate, tyrosine & N-acetylornithine, and maleic acid & arachidic acid—contributed the greatest discriminative signal. An ablation analysis comparing the full interaction-augmented EBM (AUC = 0.940) with a main-effects-only EBM (AUC = 0.882) confirmed that pairwise metabolite co-variation contributes additional discriminative value beyond individual metabolite levels, implicating amino acid catabolism, tryptophan–kynurenine pathway dysregulation, mitochondrial energy impairment, and lipid remodelling as central pathophysiological features. Global and instance-level explanations jointly demonstrated population-level metabolic signatures alongside individual heterogeneity, highlighting the added clinical value of explainable artificial intelligence (XAI) in metabolomics. These findings support EBM-based metabolomic profiling as an internally validated approach for ME/CFS classification, subject to external validation, calibration assessment, and prospective testing. Full article

Vision-based driver fatigue detection remains challenging because facial signals associated with fatigue are often ambiguous, while geometric indicators such as Eye Aspect Ratio (EAR) and Percentage of Eye Closure (PERCLOS) are prone to false positives caused by normal facial activity, including smiling or speaking. This paper proposes a context-aware framework that integrates behavioural, geometric, and emotional information for robust fatigue assessment. Facial landmarks are extracted using MediaPipe Face Mesh, while adaptive eye-closure detection is performed through multi-stage validation combining EAR trajectories, mouth activity, head-pose analysis, and event-level filtering. Emotion recognition is achieved using an EfficientNet-B0 convolutional neural network trained on the AffectNet dataset, enabling frame-level estimation of facial expression probabilities. These predictions are aggregated into descriptors representing emotional variability and fatigue-related emotional relevance over time. Behavioural information obtained from blinking, yawning, head nodding, and validated PERCLOS is fused with emotional context to construct a multi-level fatigue assessment model. The final Driver Fatigue Risk Index combines physiological eye-closure information with contextual behavioural–emotional analysis, providing an interpretable estimation of driver state rather than a binary classification alone. Experimental evaluation on the NTHU-DDD dataset achieved 94% accuracy and demonstrated improved robustness under non-frontal head poses and expressive facial behaviour. Full article

Hybrid additive manufacturing (HAM) integrates additive and subtractive processes within a unified production system, combining the geometric flexibility and material efficiency of additive manufacturing with the dimensional accuracy and surface quality of conventional machining. This review provides a comprehensive analysis of HAM technologies through a proposed four-criterion classification framework encompassing process integration strategy, additive manufacturing process type, machine architecture, and application domain. DED-based, PBF-based, and polymer-based hybrid systems are examined alongside integrated hybrid machines, retrofit solutions, and robotic architectures. A comparative analysis of representative commercial platforms evaluates build envelope, integration strategy, and monitoring capability. Documented performance outcomes across aerospace, automotive, energy, and biomedical sectors confirm substantial improvements in surface quality, fatigue performance, dimensional accuracy, and material efficiency relative to conventional manufacturing routes. Current limitations are critically assessed across technical, process integration, and economic dimensions, and a structured near-to-long-term research roadmap is proposed, prioritising in-process sensing and toolpath standardisation, digital twin-based adaptive process planning, and ultimately autonomous hybrid manufacturing cells with lifecycle certification. These findings position HAM as a central enabling technology for intelligent, flexible, and sustainable production within Industry 4.0 and Industry 5.0 paradigms. Full article

Background: Tick-borne encephalitis (TBE) is an endemic neuroinfectious disease prevalent in parts of Europe and is often associated with persistent neurological and cognitive sequelae. The aim of this study was to evaluate the long-term outcomes and predictors of post-encephalitic sequelae in adult patients with TBE in Latvia. Methods: A retrospective cohort with prospective follow-up was used that included 105 adult patients hospitalized with laboratory-confirmed TBE between 2018 and 2024. The patients’ clinical and demographic data were extracted from medical records, and reassessments were performed ≥6 months after discharge using structured clinical and neurological evaluations for neurocognitive, subjective, and neurological sequelae. Disease severity was classified using the Mickienė and Bogovič criteria, and sequelae severity was defined according to the Bohr criteria for post-encephalitic syndrome (PES). Results: Sequelae were observed in 52/105 (49.5%) patients and were more frequent in meningoencephalitis than in meningitis cases (18/25 [72.0%] vs. 33/77 [42.9%]). The most common persistent symptoms were impaired concentration (33/52 [63.5%]), fatigue (29/52 [55.8%]), and sleep disturbances (21/52 [40.4%]). Neurological sequelae included tremor (23/52 [44.2%]), vertigo (11/52 [21.2%]), and hearing impairment (5/52 [9.8%]). According to the Bohr criteria, most of the patients had mild sequelae (42/52 [80.8%]), while 10/52 [19.2%] had moderate sequelae; no severe cases were observed. In the multivariable analysis, increasing age was independently associated with greater sequelae severity (OR = 1.045 per year; 95% CI, 1.015–1.073; p = 0.003). Sex, comorbidities, biphasic disease, and length of hospital stay were not significant predictors. Acute neurological manifestations, particularly paresis (p = 0.002) and tremor (p = 0.019), were associated with worse outcomes. Although the disease severity scores correlated with sequelae in unadjusted analyses, neither the Mickienė nor the Bogovič classification independently predicted outcomes after adjustment. Conclusions: Nearly half of the hospitalized patients with TBE included in this study developed long-term sequelae, which were predominantly neurocognitive and mild in severity. Age was the primary independent predictor of worse outcomes, while acute neurological deficits such as paresis and tremor also indicated increased risk. These findings highlight the substantial burden of post-encephalitic syndrome and the need for structured long-term follow-up in TBE survivors. Full article

Fatigue detection in remote tower air traffic controllers is important for maintaining operational safety under sustained visual monitoring and high cognitive workload. This study proposes MFD-Net, a dual-stream multimodal fusion framework using eye-tracking and electrocardiogram (ECG) signals. The model separately encodes eye-tracking and ECG-derived temporal inputs, incorporates an ECG-derived RMSSD expert feature, and performs lightweight late fusion for fatigue-state classification. Under the mixed-subject random-window protocol, MFD-Net achieved an Accuracy of 85.20%, a Recall of 83.33%, and an AUC of 0.9337. Because overlapping windows from the same participant and scenario could appear in both training and test sets, this result should be interpreted as a potentially optimistic within-distribution estimate. Under the stricter zero-shot leave-one-subject-out (LOSO) protocol, performance decreased substantially, with an Accuracy of $70.95\pm 21.59\%$, a Recall of $22.98\pm 36.30\%$, and an AUC of $0.6025\pm 0.2984$. This low zero-shot Recall indicates limited subject-independent fatigue-detection capability. Lightweight target-subject calibration and sequential probability aggregation improved adaptation and temporal stability, although the calibration results should be interpreted cautiously because random target-subject windows were used for fine-tuning. These findings suggest that eye-tracking and ECG fusion are promising under controlled conditions, while practical deployment requires deployment-oriented calibration protocols, recall-oriented optimization, and further real-world validation. Full article

Wind turbines are increasingly deployed at larger scales and in harsher operating environments, leading to greater structural complexity, stronger load variability, and higher maintenance demands across both drivetrain and structural components. Reported field data indicate that gearboxes and bearings account for approximately 30–40% of total turbine downtime, while blade-related failures contribute roughly 20–25% of reported failure events, primarily through fatigue, delamination, leading-edge erosion, and lightning-induced defects. In parallel, large-scale and offshore turbines show increasing susceptibility to tower fatigue cracking, corrosion-assisted degradation, and flange joint bolt-preload loss under cyclic and environmental loading. This review provides a comprehensive applied-engineering synthesis of failure mechanisms, reliability challenges, and monitoring strategies for major wind turbine components, including gearboxes, bearings, blades, towers, and flange joints. A wide range of condition monitoring, structural health monitoring (SHM), and prognostics and health management (PHM) approaches is critically examined, including vibration analysis, acoustic emission, ultrasonic inspection, infrared thermography, impedance-based sensing, electromagnetic methods, machine vision, SCADA-based diagnostics, and artificial-intelligence-assisted fault classification. The review compares these techniques in terms of detectable damage types, spatial coverage, sensitivity, deployment practicality, and limitations under real operating conditions. In addition, statistical reliability methods and data-driven models are discussed to interpret failure trends and uncertainty. Recent AI-based studies have reported fault classification accuracies exceeding 90% under controlled or semi-controlled conditions; however, their field reliability remains constrained by data imbalance, domain shift, limited labeled failure datasets, model interpretability, and insufficient validation under realistic turbine operating environments. The main contribution of this review is an integrated applied synthesis that connects drivetrain and structural failure mechanisms with measurable monitoring indicators, diagnostic technologies, AI-enabled PHM limitations, and predictive-maintenance decision needs. The paper provides practical guidance for monitoring design, early fault detection, predictive maintenance, and long-term reliability improvement in next-generation wind turbine systems. Full article

Background: The diagnostic value of surface electromyography (sEMG) for identifying muscles affected by myofascial trigger points (TrPs) remains controversial. However, advances in pain neurophysiology and discussions regarding TrPs within the International Classification of Diseases (ICD-11) have renewed interest in objective diagnostic approaches. Objective: To synthesize current evidence on the diagnostic utility of sEMG for detecting TrP-related muscle alterations across different electromyographic signal analysis domains. Methods: A scoping review was conducted following JBI guidance and PRISMA-ScR guidelines. PubMed, Scopus, Web of Science, CINAHL and Cochrane were searched for studies involving adults with symptomatic or asymptomatic TrPs, myofascial pain syndrome, or TrP-related referred pain. Fifteen studies met the inclusion criteria. Analyses included amplitude-, frequency-, time–frequency-, and spatial-domain sEMG parameters. Results: Muscles affected by TrPs showed increased resting electromyographic activity and reduced activation during maximal voluntary contraction in several studies. Frequency domain analyses indicated changes in median frequency and muscle fatigue index, whereas time–frequency analyses suggested redistribution of sEMG signal energy toward lower-frequency components or altered spectral power during experimentally provoked referred pain. Spatial analyses revealed altered activation patterns, although these findings did not consistently correspond with TrP anatomical locations. Overall, the limited number of studies assessing diagnostic sensitivity and specificity prevents firm conclusions. Conclusions: sEMG may be useful as a non-invasive complementary tool for functional assessment and monitoring of TrP-related muscle dysfunction. However, current evidence does not support its use as a standalone diagnostic method. Time–frequency, machine learning-supported and spatial analyses appear promising for future clinical research, but standardized protocols and external validation are required before clinical diagnostic criteria can be proposed. Full article

Affected by inter-annotator cognitive differences, fatigue effects, and data poisoning, training data inevitably contains a certain proportion of noise, which severely impairs model performance. Traditional manual verification is costly and inefficient, while existing automatic detection methods generally suffer from limited precision, poor interpretability, and insufficient robustness. This paper proposes a noise label detection and correction method based on Bayesian weighted consensus inference. First, an ensemble of multiple lightweight heterogeneous models is constructed, and model prior knowledge and dataset noise are obtained on a clean validation set. Second, the model ensemble predicts noisy samples to extract two-dimensional consensus evidence. Then, prior knowledge and consensus evidence are fused, and the posterior probability of label noise is calculated via Bayesian inference to generate correction suggestions. Finally, high-confidence noisy labels are precisely screened based on the posterior probability threshold. Experimental results on three datasets show that the proposed method achieves a precision of 96.50%, a recall of 98.61%, an F₁-score of 97.54%, and a correction accuracy of 95.53%, with improvements of 5–20% over mainstream methods. With a computational cost comparable to that of basic ensemble methods, the proposed approach achieves a favorable balance among precision, robustness, and interpretability. It thus offers a promising and cost-effective solution for automated quality control of large-scale annotated datasets, especially in text classification tasks. Full article

Remote tower operations require air traffic controllers to maintain continuous visual monitoring and integrate information from panoramic displays, radar data, flight strips, and voice communication. Such screen-mediated and sustained surveillance tasks may lead to covert fatigue, which is difficult to capture using a single physiological or behavioral signal. To address this issue, this study proposes a Gated EEG–Eye Fusion Network (GEEF-Net) for window-level fatigue detection in remote tower controllers. EEG and eye-tracking signals were synchronously collected during simulated remote tower tasks and segmented into 5 s windows with a 2 s step. For each window, 53 EEG features and 47 eye-tracking features were extracted to construct a 100-dimensional multimodal representation. GEEF-Net adopts a lightweight modality-gating mechanism to adaptively weight EEG and eye-tracking representations before fatigue classification. Under the main subject-dependent validation setting, GEEF-Net achieved an Accuracy of 0.883, an F1-score of 0.788, and a ROC-AUC of 0.944, outperforming EEG-only, eye-only, and early-fusion baselines in most overall metrics. The gating analysis indicated that eye-tracking features received a higher average weight than EEG features, suggesting the importance of visual behavior in remote tower fatigue detection. Cross-subject validation showed that individual differences remain a major challenge, while few-shot subject-specific calibration improved model adaptation when limited target-subject samples were available. These findings suggest that EEG–eye-tracking fusion with lightweight modality gating is a feasible approach for fatigue detection in simulated remote tower tasks. However, larger datasets and operationally realistic validation considering shift work, circadian effects, and operational pressure are still required before the approach can be considered operationally reliable. Full article

Artificial muscles are an emerging class of actuators designed to mimic the compliant, efficient, and versatile behavior of biological muscles for fields including the following: soft robotics, prosthetics, wearable enhancements, haptic interfaces, and biomedical devices. These systems encompass various actuation mechanisms, including pneumatic, hydraulic, thermal, ionic, electrochemical, and electrostatic. Each with distinct tradeoffs in voltage, strain, output force, bandwidth, efficiency, and manufacturability. Among them, electrostatic actuators have attracted increased attention due to their fast response times, high energy densities, strong compatibility with soft materials, and scalability from microscale devices to large-area and stacked actuators. However, challenges such as dielectric breakdown, material fatigue, and fabrication complexity continue to limit widespread deployment. This review presents a structured classification of various artificial muscle technologies and an in-depth examination of electrostatic actuators including dielectric elastomers, electrostrictive and ferroelectric polymers, liquid crystal elastomers, electrostatic film motors, stacked architectures, and microscale/milliscale devices. In this review the operating principles, materials, architectures, performance characteristics, and failure modes of electrostatic actuators will be discussed. Additionally, a comparison will highlight tradeoffs across actuator families based on metrics such as voltage, force, strain, bandwidth, and manufacturability. Lastly, we outline future research directions in materials, physics-informed modeling, system integration, and scalable fabrication necessary to advance electrostatic artificial muscles toward practical, real-world deployment. Full article

In this paper, we propose an outcome-based contrastive loss for imbalanced binary classification to alert to next-day health deterioration using care records and meteorological data. Long-term care facilities maintain daily care and observation records to monitor the health of older adults. Such objective records are particularly valuable when sudden deterioration occurs, enabling timely coordination with medical institutions. Predicting deterioration one day in advance could provide care staff with an actionable window to intensify observation and adjust care plans (e.g., scheduling additional vital checks or increasing fluid intake monitoring). This could potentially reduce emergency transports and ease the burden on already understaffed care facilities. However, for such predictions to be useful in practice, false positives must be suppressed. Because deterioration events are rare, class imbalance generates an excess of false positives, causing alert fatigue and increasing the risk that actual events go unnoticed. To address these challenges, we propose an outcome-based contrastive loss that contrasts actual deteriorating samples against false alarms conditioned on mini-batch prediction outcomes. The proposed loss contracts same-label pairs to shape local structure within each ground-truth label. The loss also separates actual deteriorating samples from false alarms among samples predicted as deteriorating, thereby directly reducing unnecessary alerts. As a result, compared with random oversampling with standard cross-entropy, the proposed model improved precision from 3.97% to 12.94% (+8.97 percentage points), while limiting the F1-score decrease to 0.71 percentage points (from 7.28% to 6.57%). Pair-design ablations and UMAP projections supported this mechanism by indicating clearer separation between actually deteriorating and false-alarm samples in the learned representation space. These results suggest a viable direction for alert systems that produce fewer unnecessary alerts, reducing alert fatigue and supporting more reliable deterioration detection in care settings. Full article

Conventional P300-based brain–computer interfaces (BCIs) commonly rely on two-dimensional (2D) visual flashing, which may induce visual fatigue and limit immersion, thereby restricting long-term usability and system performance. To address these limitations, this study proposes an immersive P300-BCI framework integrating a three-dimensional morphological stimulation paradigm, termed 3D-Morph, with self-adaptive Bayesian linear discriminant analysis (SA-BLDA). Instead of using color or luminance flickering, the proposed paradigm employs dynamic 2D-to-3D morphological transformations of virtual objects in a virtual reality environment to enhance target-related event-related potentials while preserving visual immersion. SA-BLDA further adjusts the number of stimulation rounds according to classification confidence to balance accuracy and interaction efficiency. Experiments with 24 participants showed that the proposed system outperformed the conventional 2D paradigm. In offline analysis, the proposed method achieved an average classification accuracy of 94.17% and an information transfer rate (ITR) of 25.50 bits/min, significantly outperforming the 2D paradigm (87.29% accuracy, 22.75 bits/min ITR, both $p<0.001$, Cohen’s $d\ge 1.22$). In online experiments, the 3D-Morph paradigm achieved an average accuracy of 91.46% and an ITR of 37.23 bits/min, compared with 83.96% and 28.74 bits/min for the conventional 2D paradigm (both $p<0.01$, Cohen’s $d\ge 1.14$). The average response time was reduced by 0.46 s ($p<0.01$, Cohen’s $d=0.78$), and the processing time per stimulation round (PT) of SA-BLDA was significantly reduced from $48.54\pm 10.47$ ms in the 2D paradigm to $26.40\pm 9.41$ ms in the 3D-Morph paradigm ($p<0.01$, Cohen’s $d=2.34$), corresponding to a 45.61% reduction in computational time per round. NASA-TLX evaluations indicated a significantly lower subjective workload across all dimensions (all $p<0.05$, Cohen’s $d\ge 0.76$). These results demonstrate that combining 3D-Morph stimulation with SA-BLDA can significantly improve classification performance, interaction efficiency, and user experience, providing a feasible framework for immersive and practical P300-BCI applications. Full article

Weld-bonded joints combine localized metallic welding with structural adhesives and are increasingly used in lightweight multi-material structures. Although numerous studies have examined individual weld-bonding processes, the available literature remains fragmented with respect to process classification, adhesive–weld interaction and mechanical performance. This paper presents a critical review of hybrid weld-bonded joints published between 2000 and 2026, with emphasis on welding-based joining processes and their influence on joint behavior. The main weld-bonding techniques, including resistance spot weld-bonding (RSWB), friction stir weld-bonding (FSWB), friction stir spot weld-bonding (FSSWB) and laser weld-bonding (LWB), are systematically compared in terms of heat input, adhesive stability, load transfer mechanisms and mechanical performance. The analysis indicates that processes with lower heat input, such as FSWB and FSSWB, provide improved adhesive preservation and fatigue performance, whereas RSWB remains the most industrially established solution. The influence of different adhesive families (epoxy, polyurethane, acrylic and thermoplastic) is evaluated with respect to thermal resistance, rheological behavior during welding and long-term durability. Mechanical performance under static, fatigue and impact loading is critically assessed, highlighting typical strength improvements compared with purely welded joints and identifying dominant failure modes. In addition, numerical modeling approaches, including finite element and cohesive zone methods, are reviewed in terms of their ability to capture coupled thermomechanical and damage phenomena. The review further outlines key industrial applications, current technological limitations and future research directions, including advanced adhesive systems, low-heat-input processes, non-destructive testing and digital-twin-based optimization. Full article

Fatigue driving causes 20–30% of global traffic accidents. To address limitations in feature fusion and real-time performance, this study proposes an improved You Only Look Once version 8 (YOLOv8)-Long Short-Term Memory (LSTM) model with symmetry-aware spatiotemporal feature learning. In the spatial phase, Group Shuffle Convolution (GSConv) and Slim Neck structures are introduced to enhance facial feature detection while reducing parameters by 32.3%. In the temporal phase, an improved Inverted Transformer(iTransformer) with differential attention is integrated with an LSTM-Feed-Forward Network (FFN) architecture, achieving a 90.1% prediction accuracy and an 84.6% noise suppression rate. A standardized dataset of 13,200 images was constructed using a four-level classification system. By implementing TensorRT acceleration and multi-process parallel frameworks, the system optimizes single-frame latency to 38 ms—a 9.5× efficiency gain—while maintaining an overall detection accuracy of 92.4%. These results demonstrate that the proposed framework effectively balances model lightweighting with high precision, providing a robust and efficient solution for real-time driver monitoring in complex driving scenarios. Full article