Search Results (4,055)

Background/Objectives: Artificial intelligence (AI) has been increasingly used to support radiological assessment in dentistry. We benchmarked machine learning (ML), deep learning (DL), and a hybrid optimization-assisted approach for the automatic five-class image-level classification of dental restorations (filling, implant, root canal treatment, fixed partial denture/bridge, crown) on panoramic radiographs. Methods: We analyzed 353 anonymized panoramic images comprising 2137 labeled restorations, acquired on the same device. Images were cropped and enhanced (histogram equalization and CLAHE), and texture features were extracted with GLCM. A three-stage pipeline was evaluated: (i) GLCM-based features classified by conventional ML and a baseline DL model; (ii) Hybrid Grey Wolf–Particle Swarm Optimization (HGWO-PSO) for feature selection followed by SVM; and (iii) a CNN trained end-to-end on raw images. Performance was assessed with an 80/20 per-patient split and 5-fold cross-validation on the training set. While each panoramic radiograph may contain multiple restorations, in this study we modeled the task as single-label, image-level classification (dominant restoration type) due to pipeline constraints; this choice is discussed as a limitation and motivates multi-label, localization-based approaches in future work. The CNN baseline was implemented in TensorFlow 2.12 (CUDA 11.8/cuDNN 8.9) and trained with Adam (learning rate 1 × 10⁻⁴), with a batch size 32 and up to 50 epochs with early stopping (patience 5); data augmentation included horizontal flips, ±10° rotations, and ±15% brightness variation. A post hoc power analysis (G*Power 3.1; α = 0.05, β = 0.2) confirmed sufficient sample size (n = 353, power > 0.84). Results: The HGWO-PSO + SVM configuration achieved the highest accuracy (73.15%), with macro-precision/recall/F1 = 0.728, outperforming the CNN (68.52% accuracy) and traditional ML models (SVM 67.89%; DT 59.09%; RF 58.33%; K-NN 53.70%). Conclusions: On this single-center dataset, the hybrid optimization-assisted classifier moderately improved detection performance over the baseline CNN and conventional ML. Given the dataset size and class imbalance, the proposed system should be interpreted as a decision-supportive tool to assist dentists rather than a stand-alone diagnostic system. Future work will target larger, multi-center datasets and stronger DL baselines to enhance generalizability and clinical utility. Full article

The prevalence of advanced heart failure (AdHF) is increasing globally, driven by population aging and improved survival rates in chronic heart failure (CHF). Durable Mechanical Circulatory Support (DMCS), particularly Left Ventricular Assist Devices (LVADs), has become a cornerstone in AdHF management. However, its successful implantation requires a comprehensive preoperative evaluation integrating cardiac, hemodynamic, and systemic assessments. Echocardiography and cardiac magnetic resonance (CMR) provide critical data for risk stratification—e.g., LV ejection fraction < 25%, LV end-diastolic diameter < 60 mm, or free wall RV longitudinal strain (fwRVLS) > −14% predict poorer outcomes. Right heart catheterization (RHC) identifies hemodynamic contraindications (PVR > 6 WU, PAPi < 1.5, cardiac index < 2 L/min/m²), while cardiopulmonary exercise testing (CPET) remains pivotal for assessing functional reserve (peak VO₂ < 12 mL/kg/min or <50% predicted). Systemic assessment must address renal, hepatic, oncologic, and psychiatric comorbidities that influence surgical risk. Integrating these multimodal data within a multidisciplinary framework—spanning cardiologists, cardiac surgeons, anesthesiologists, and psychologists—optimizes selection and outcomes for DMCS candidates. Full article

Brain–Computer Interface (BCI) technology facilitates direct communication between the human brain and external devices by interpreting brain wave patterns associated with specific motor imagery tasks, which are derived from EEG signals. Although BCIs allow applications such as robotic arm control and smart assistive environments, they face major challenges, mainly due to the large variation in EEG characteristics between and within individuals. This variability is caused by low signal-to-noise ratio (SNR) due to both physiological and non-physiological artifacts, which severely affect the detection rate (IDR) in BCIs. Advanced multi-stage signal processing pipelines, including efficient filtering and decomposition techniques, have been developed to address these problems. Additionally, numerous feature engineering techniques have been developed to identify highly discriminative features, mainly to enhance IDRs in BCIs. In this review, several pre-processing techniques, including feature extraction algorithms, are critically evaluated using deep learning techniques. The review comparatively discusses methods such as wavelet-based thresholding and independent component analysis (ICA), including empirical mode decomposition (EMD) and its more sophisticated variants, such as Self-Adaptive Multivariate EMD (SA-MEMD) and Ensemble EMD (EEMD). These methods are examined based on machine learning models using SVM, LDA, and deep learning techniques such as CNNs and PCNNs, highlighting key limitations and findings, including different performance metrics. The paper concludes by outlining future directions. Full article

Integrating artificial intelligence (AI) with wearable sensor technologies can revolutionize the monitoring and management of various chronic diseases and acute conditions. AI-integrated wearables are categorized by their underlying sensing techniques, such as electrochemical, colorimetric, chemical, optical, and pressure/stain. AI algorithms enhance the efficacy of wearable sensors by offering personalized, continuous supervision and predictive analysis, assisting in time recognition, and optimizing therapeutic modalities. This manuscript explores the recent advances and developments in AI-powered wearable sensing technologies and their use in the management of chronic diseases, including COVID-19, Diabetes, and Cancer. AI-based wearables for heart rate and heart rate variability, oxygen saturation, respiratory rate, and temperature sensors are reviewed for their potential in managing COVID-19. For Diabetes management, AI-based wearables, including continuous glucose monitoring sensors, AI-driven insulin pumps, and closed-loop systems, are reviewed. The role of AI-based wearables in biomarker tracking and analysis, thermal imaging, and ultrasound device-based sensing for cancer management is reviewed. Ultimately, this report also highlights the current challenges and future directions for developing and deploying AI-integrated wearable sensors with accuracy, scalability, and integration into clinical practice for these critical health conditions. Full article

Understanding and accurately estimating cognitive workload is crucial for the development of adaptive, user-centered interactive systems across a variety of domains including augmented reality, automotive driving assistance, and intelligent tutoring systems. Cognitive workload assessment enables dynamic system adaptation to improve user experience and safety. In this work, we introduce a novel framework that leverages smooth pursuit eye movements as a non-invasive and temporally precise indicator of mental effort. A key innovation of our approach is the development of trajectory-independent algorithms that address a significant limitation of existing methods, which generally rely on a predefined or known stimulus trajectory. Our framework leverages two solutions to provide accurate cognitive load estimation, without requiring knowledge of the exact target path, based on Kalman filter and B-spline heuristic classifiers. This enables the application of our methods in more naturalistic and unconstrained environments where stimulus trajectories may be unknown. We evaluated these algorithms against classical supervised machine learning models on a publicly available benchmark dataset featuring diverse pursuit trajectories and varying cognitive workload conditions. The results demonstrate competitive performance along with robustness across different task complexities and trajectory types. Moreover, our framework supports real-time inference, making it viable for continuous cognitive workload monitoring. To further enhance deployment feasibility, we propose a federated learning architecture, allowing privacy-preserving adaptation of models across heterogeneous devices without the need to share raw gaze data. This scalable approach mitigates privacy concerns and facilitates collaborative model improvement in distributed real-world scenarios. Experimental findings confirm that metrics derived from smooth pursuit eye movements reliably reflect fluctuations in cognitive states induced by working memory load tasks, substantiating their use for real-time, continuous workload estimation. By integrating trajectory independence, robust classification techniques, and federated privacy-aware learning, our work advances the state of the art in adaptive human–computer interaction. This framework offers a scientifically grounded, privacy-conscious, and practically deployable solution for cognitive workload estimation that can be adapted to diverse application contexts. Full article

Population aging and rising rehabilitation demands highlight the need for advanced assistive devices to improve mobility in individuals with motor impairments. Existing back-support lifting nursing beds often lack adequate human–machine adaptability, safety, and emotional consideration. This study presents a human-centered, data-driven optimization pipeline that integrates behavior–emotion dual recognition, simulation verification, and parameter optimization with user demand mining, biomechanical simulation, and sustainable practices. The design utilizes GreenAI, focusing on low-power algorithms and eco-friendly materials, ensuring energy-efficient AI models and reducing the environmental footprint. A dual-channel data fusion method was developed, combining movement parameters from sit-to-lie transitions with emotional needs extracted from e-commerce reviews using the Term Frequency-Inverse Document Frequency (TF-IDF) and Latent Dirichlet Allocation (LDA) models. The fuzzy Kano model prioritized design objectives, identifying multi-position adjustment, joint protection, armrest optimization, and interaction comfort as key targets. An AnyBody-based human–device model quantified muscle (erector spinae, rectus abdominis, trapezius) and hip joint loads during posture changes. Simulations verified the design’s ability to improve load distribution, reduce joint stress, and enhance comfort. The optimized nursing bed demonstrated improved adaptability across user profiles while maintaining functional reliability. This framework offers a scalable paradigm for intelligent rehabilitation equipment design, with potential extension toward AI-driven adaptive control and clinical validation. This sustainable methodology ensures that the device not only meets rehabilitation goals but also contributes to a more environmentally responsible healthcare solution, aligning with global sustainability efforts. Full article

Junctionless (JL) thin-film transistors (TFTs) are promising candidates for low-cost, large-area electronic devices, but improvements in mobility and bias stability are still required. In this study, the effects of independent annealing of the indium oxide (InO_x) channel layer and the aluminum oxide (AlO_x) capping layer (CL) on the performance and reliability of InO_x/AlO_x heterostructure JL TFTs are examined. Devices were fabricated via solution deposition and photopatterning, and the InO_x and AlO_x layers were annealed at 250 °C and 400 °C. Increasing the annealing temperature from 250 °C to 400 °C, the InO_x layer crystallized and densified. The AlO_x layer remained amorphous at both temperatures, but its metal-hydroxyl content decreased with higher annealing. For both layers, JL TFTs annealed at 400 °C exhibited the best electrical performance (threshold voltage = 1.82 ± 0.40 V, subthreshold swing = 0.50 ± 0.07 V dec⁻¹, saturation mobility = 1.57 ± 0.37 cm² V⁻¹ s⁻¹). The threshold voltage shift under positive bias stress was 1.70 V, which demonstrates excellent bias stability. These results show that simultaneous high-temperature annealing of the channel and CL is essential to reduce trap-assisted scattering and stabilize electrostatics in JL TFTs, providing practical process guidelines for bias-stable and high-performance oxide electronics. Full article

Background: Lower-limb fractures often require prolonged use of assistive devices, which may increase mechanical stress on the upper extremities. However, the association between lower-limb fractures and subsequent carpal tunnel syndrome (CTS) remains unclear. Methods: This nationwide population-based cohort study used Taiwan’s National Health Insurance Research Database (2011–2019) to identify 10,140 patients with lower-limb fractures and 10,140 propensity score-matched controls. Cox regression analysis estimated CTS risk after adjusting for demographics and comorbidities. Results: Patients with lower-limb fractures demonstrated increased CTS risk compared to controls (adjusted hazard ratio [HR] = 1.12, 95% confidence interval [CI]: 1.003–1.26; p = 0.044), with stronger associations in males (HR = 1.28, 95% CI: 1.05–1.55) and younger adults aged 20–65 years (HR = 1.19, 95% CI: 1.03–1.38). Conclusions: Lower-limb fractures are associated with modestly increased CTS risk, particularly in males and younger patients. Though biologically plausible, this observational study cannot establish causality. Heightened clinical awareness may be warranted, though prospective validation is needed. Full article

In this work, a quantitative analysis of Li in natural brines was carried out by laser-induced breakdown spectroscopy (LIBS) assisted by the τ–algorithm for detailed analysis of the experimental line shapes (τLIBS). Brine samples were collected from different salars located in the Puna plateau (Northwest Argentina) and analyzed by LIBS in the form of solid pressed pellets. The emission intensities of Li I, H_α, and Mg I–II lines were measured and spatially integrated along the line of sight with temporal resolution by using a high-spectral-resolution spectrometer equipped with an intensified charge-coupled device (iCCD) detector. The plasma was characterized through the determination of the electron density and the temperature. The τ–algorithm calculated the optical thicknesses of the Li I lines to generate synthetic intensity profiles that were subsequently fitted to the experimental spectra. By applying the developed τLIBS approach, valuable spectroscopic insight was recovered about the physical processes occurring in the plasma, such as self-absorption. The analytical process involved an univariate external calibration process using the resonant Li I line at 6707.7 Å measured from a series of Li standard samples. Self-absorption effects were evaluated and subsequently compensated. The final LIBS results, with an enhanced accuracy of 15%, were validated by crosschecking them against those obtained with the standard AAS method. Full article

Upper limb disabilities resulting from stroke affect millions worldwide, yet current rehabilitation systems face limitations in portability, cost-effectiveness, and multi-joint integration. This study presents a cable-driven parallel exoskeleton integrating elbow, wrist, and finger assistance into a single portable device. The design strategically separates actuation components, housing all motors in a backpack unit, while limb-mounted modules serve as cable routing guides, achieving seven degrees of freedom within practical constraints of portability (1.2–1.5 kg) and cost-effectiveness (3D-printed components). The device incorporates seven servo motors controlled via Arduino with IMU feedback and PID algorithms. Kinematic and dynamic analyses informed mechanical design, while ARMAX system identification enabled controller optimization achieving 87.96% model fit. Experimental validation with eight healthy participants performing four upper limb exercises demonstrated consistent trends toward reduced activation in four monitored agonist muscles with exoskeleton assistance (21.3% average reduction, p = 0.087), with moderate effect sizes for proximal muscles (Cohen’s d = 0.70–0.79) and significant reductions in brachioradialis during radial/ulnar deviation (23.4%, p = 0.045). These findings provide preliminary evidence of the device’s potential to reduce muscular effort during assisted movements, warranting further clinical validation with patient populations. Full article

A new version of the L-CADEL elbow joint assisting device is presented as version v5. The design is revised based on the experience of previous versions and on the requirements that consider the application for physical exercise for the elderly people at home. A laboratory prototype has been created with lightweight, portable and easy-to-use functionality that is confirmed by lab test results. A web interface was developed to manage the device as well as to acquire and elaborate data. Results of lab tests are discussed to validate the design feasibility and to characterize the operation performance for future clinical assessments. Full article

Background/Objectives: Solar elastosis, a key histopathological alteration in skin photodamage, results from chronic UV exposure and photoaging. Clinically, it manifests as deep wrinkles, laxity, and a dull complexion. The growing demand for effective treatments has spurred the development of numerous therapeutic strategies. This systematic review aims to synthesize and critically evaluate the scientific evidence regarding interventions for treating the clinical and histological manifestations of solar elastosis, to provide an updated overview and guide future clinical practice. Methods: PubMed, Scopus, ProQuest, and Web of Science databases were searched for articles published in the last ten years. Clinical studies on adults with signs of solar elastosis and photoaging, evaluating therapeutic interventions, were included. Primary outcomes were clinical and histopathological improvements, while secondary outcomes included skin elasticity, safety, and patient satisfaction. This review was registered in the PROSPERO database under registration number CRD420251086680. Results: Twenty-two studies, totaling 608 participants, were included. The analyzed therapies comprised a wide range of strategies, including energy-based devices (laser, radiofrequency), stem cell derivatives, bioactive topical compounds, and growth factor-rich plasma. Device-assisted and biologically augmented interventions consistently improved visible photoaging outcomes and skin elasticity, with selective histologic remodeling, heterogeneous effects on barrier function, and an overall acceptable safety profile, with mild and transient adverse events. Patient satisfaction was consistently high. Conclusions: Therapeutic strategies in solar elastosis and photoaging, particularly those combining energy-based devices with regenerative agents, have proven effective in improving the structural and functional aspects of photodamaged skin. Although the results are promising, the current literature is limited by methodological heterogeneity and small sample sizes. High-quality randomized controlled trials with long-term follow-up are needed to establish standardized, evidence-based protocols. Full article

Ternary organic photovoltaics (OPVs) are considered as the next step beyond binary systems, aiming to achieve synergistic improvements in absorption, energetic alignment, and charge transport. However, despite their conceptual appeal, most ternary blends do not outperform binary counterparts, particularly under indoor illumination where photon flux and carrier dynamics impose strict limitations. To comprehensively understand this discrepancy, multiple ternary systems were systematically examined to ensure that the observed behaviors are representative rather than case specific. In this study, we systematically investigate this discrepancy by comparing representative donor–donor–acceptor (D–D–A) and donor–acceptor–acceptor (D–A–A) systems under both AM 1.5G and TL84 lighting. In all cases, the broadened absorption fails to yield effective photocurrent; instead, redundant excitations, reduced driving forces for charge separation, and disrupted percolation networks collectively diminish device performance. Recombination and transient analyses reveal that the third component often introduces energetic disorder and trap-assisted recombination instead of facilitating beneficial cascade pathways. Although the film morphology remains smooth, interfacial instability under low-light conditions further intensifies performance losses. The inclusion of several systems allows the identification of consistent mechanistic trends across different ternary architectures, reinforcing the generality of the conclusions. This work establishes a mechanistic framework linking molecular miscibility, energetic alignment, and percolation continuity to device-level behavior, clarifying why ternary strategies rarely deliver consistent efficiency improvements. Ultimately, indoor OPV performance is determined not by spectral breadth but by maintaining balanced charge transport and stable energetic landscapes, which represents an essential paradigm for advancing ternary OPVs from concept to practical application. Full article

Background: Children with spastic hand impairments resulting from cerebral palsy or neuromuscular disorders often exhibit a restricted range of motion and diminished functional use. Rehabilitation devices that assist joint mobilization can enhance therapeutic outcomes, yet few solutions target pediatric populations. Methods: This study aimed to design, implement, and preliminarily evaluate a biomechanical device tailored to promote flexo-extension, radial–ulnar deviation, and supination movements in spastic hands of school-aged children. A prototype combining a motor-driven actuation system, adjustable wrist and finger supports, and a MATLAB-based graphical user interface was developed. Two participants (aged 8 and 10) with clinically diagnosed spastic hemiparesis underwent 25-minute sessions over 15 consecutive days. Joint angles were recorded before and after each session using an electro-goniometer. Data normality was assessed via the Shapiro–Wilk test, and pre–post differences were analyzed with the Wilcoxon signed-rank test (α = 0.05). Results: Both participants demonstrated consistent increases in their active range of motion across all measured planes. Median flexo-extension improved by 12.5° (p = 0.001), ulnar–radial deviation by 7.3° (p = 0.002), and supination by 9.1° (p = 0.001). No adverse events occurred, and device tolerance remained high throughout the intervention. Conclusions: The device facilitated statistically significant enhancements in joint mobility in a small pediatric cohort, supporting its feasibility and safety in spastic hand rehabilitation. These preliminary findings warrant larger controlled trials to confirm the device’s efficacy, optimize treatment protocols, and assess its long-term functional benefits. Full article

Lower limb exoskeletons significantly enhance human functionality. However, simultaneously improving the load capacity of these devices while reducing metabolic costs presents a major challenge in the industry. This paper presents a lower limb exoskeleton that integrates both rigid and flexible structures to facilitate active assistance and passive load transfer at the hip joint. The load transfer experiments were conducted with weights of 10 kg and 15 kg. During static standing, the load transfer rates were recorded at 90.48% and 69.70%, respectively. In dynamic walking, these rates decreased to 62.07% and 43.69%. Furthermore, in metabolic experiments involving a load of 15 kg, metabolic costs in the exoskeleton assistance modes OFF (Assist OFF) and exoskeleton assistance ON (Assist ON) were reduced by 8.3% and 21.61%, respectively, compared to the exoskeleton-free condition (NE). Furthermore, the Assist ON mode further decreased metabolic costs by 13.22% compared to the Assist OFF mode. These findings demonstrate that the rigid-soft coupled lower limb exoskeleton exhibits exceptional load transfer capabilities and effective assistance, highlighting its potential to enhance human performance in weight-bearing activities. Full article