Search Results (17,220)

An intrusion into the operational network (OT) of a production site can cause serious damage by affecting productivity, reliability, and quality. The presence of embedded neural networks (NNs), such as classifiers, in physical devices opens the door to new attack vectors. Due to the stochastic behavior of the classifier and the difficulty of reproducing results, the Artificial Intelligence (AI) Act requires the NN’s behavior to be explainable. For this purpose, the platform HistoTrust enables tracing NN behavior, thanks to secure hardware components issuing attestations registered in a blockchain ledger. This solution helps to build trust between independent actors whose devices perform tasks in cooperation. This paper proposes going further by integrating a mechanism for detecting tampering of embedded NN, and using smart contracts executed on the blockchain to propagate the alert to the peer devices in a distributed manner. The use case of a bit-flip attack, targeting the weights of the NN model, is considered. This attack can be carried out by repeatedly injecting very small messages that can be missed by the Intrusion Detection System (IDS). Experiments are being conducted on the HistoTrust platform to demonstrate the feasibility of our distributed approach and to qualify the time required to detect intrusion and propagate the alert, in relation to the time it takes for the attack to impact decisions made by the AI. As a result, the blockchain may be a relevant technology to complement traditional IDS in order to face distributed attacks. Full article

Current approaches to dynamic sign language recognition commonly rely on dense landmark representations, which impose high computational cost and hinder real-time deployment on resource-constrained devices. To address this limitation, this work proposes a computationally efficient framework for real-time dynamic Mexican Sign Language (MSL) recognition based on a multimodal minimal angular-geometry representation. Instead of processing complete landmark sets (e.g., MediaPipe Holistic with up to 468 keypoints), the proposed method encodes the relational geometry of the hands, face, and upper body into a compact set of 28 invariant internal angular descriptors. This representation substantially reduces feature dimensionality and computational complexity while preserving linguistically relevant manual and non-manual information required for grammatical and semantic discrimination in MSL. A real-time end-to-end pipeline is developed, comprising multimodal landmark extraction, angular feature computation, and temporal modeling using a Bidirectional Long Short-Term Memory (BiLSTM) network. The system is evaluated on a custom dataset of dynamic MSL gestures acquired under controlled real-time conditions. Experimental results demonstrate that the proposed approach achieves 99% accuracy and 99% macro F1-score, matching state-of-the-art performance while using fewer features dramatically. The compactness, interpretability, and efficiency of the minimal angular descriptor make the proposed system suitable for real-time deployment on low-cost devices, contributing toward more accessible and inclusive sign language recognition technologies. Full article

Asthma is a common chronic disease in children, contributing to significant morbidity and healthcare utilization worldwide. The integration of artificial intelligence (AI) and machine learning (ML) into pediatric asthma care is rapidly advancing, offering new opportunities for early diagnosis, risk stratification, and personalized management. AI-driven tools can analyze complex clinical, genetic, and environmental data to identify asthma phenotypes and endotypes, predict exacerbations, and support timely interventions. In pediatric populations, these technologies enable non-invasive diagnostic approaches, remote monitoring through wearable devices, and improved medication adherence via smart inhalers and digital health platforms. Despite these advances, challenges remain, including the need for pediatric-specific datasets, transparency in AI decision-making, and careful attention to data privacy and equity. The integration of AI in pediatric asthma care and into the clinical decision system can offer personalized treatment plans, reducing the burden of the disease both for patients and health professionals. This is a narrative review on the applications of AI and ML in pediatric asthma care. Full article

The role of cardiac implantable electronic devices (CIEDs), including implantable cardioverter-defibrillators (ICDs) and cardiac resynchronization therapy (CRT) devices, in patients supported with left ventricular assist devices (LVADs) remains controversial. Although ICDs clearly reduce the risk of sudden cardiac death (SCD) and improve outcomes in advanced heart failure (HF), their benefit in patients with continuous-flow mechanical circulatory support is less certain. Initial small studies involving LVAD patients, particularly those with older pulsatile devices, suggested that ICDs confer a survival benefit during LVAD support. However, more recent evidence has been inconsistent. Some studies show modest protection against arrhythmic death, whereas others show no improvement in overall mortality. Similarly, CRT does not appear to offer significant additional hemodynamic benefits after LVAD implantation, and current evidence does not strongly support its routine continuation. Device-related complications—including lead failure, infection, electromagnetic interference, and inappropriate shocks—are major clinical concerns that can offset potential benefits. Accordingly, current guidelines recommend maintaining pre-existing ICD or CRT devices in LVAD patients but do not endorse the routine implantation of new devices after LVAD placement. The existing evidence highlights the need for a nuanced and individualized approach to CIED therapy in patients with LVAD. Future research should focus on randomized trials, registry-based analyses, and the exploration of novel technologies such as leadless pacing, subcutaneous ICDs, and advanced programming algorithms. Patient-centered outcomes, particularly quality of life and ethical considerations—such as ICD deactivation in end-of-life scenarios—must be considered in decision-making in this evolving field. Full article

The use of natural antimicrobials and advanced sensor technologies is increasingly explored to improve the safety and quality of dairy products like cheese. The current work evaluated the effect of sodium alginate edible films enriched with oregano essential oil (EO) on the microbial spoilage of Feta cheese and the fate of Escherichia coli O157:H7 and Listeria monocytogenes during storage. Samples were inoculated with approximately a 4 log CFU/g of pathogens and subsequently wrapped with edible films containing EO or left without, serving as controls. Samples were stored under aerobic and vacuum conditions at 4 and 12 °C. Microbiological analyses, pH, and sensory attributes were monitored during storage, while multispectral imaging (MSI) devices were used for rapid, non-invasive quality assessment. EO films moderately suppressed spoilage and pathogen survival, particularly under aerobic conditions. The MSI spectral data coupled with machine learning models provided reasonable results for the estimation of yeast and mould populations, with the best models coming from aerobic conditions, from benchtop-MSI data, with R² = 0.726 and RMSE = 0.426 from the Neural Networks model, and R² = 0.661 and RMSE = 0.696 from the LARS model. The results highlight the combined potential of natural antimicrobial films and MSI-based sensors for extending Feta cheese shelf life and enabling rapid, non-destructive monitoring, respectively. Full article

Background: Deep brain stimulation (DBS) is increasingly understood as a precision-oriented neuromodulation therapy capable of influencing distributed basal ganglia–thalamo–cortical and cerebellothalamic networks. Although its symptomatic benefits in Parkinson’s disease, essential tremor, and dystonia are well established, the extent to which DBS supports motor learning, adaptive plasticity, and participation in rehabilitation remains insufficiently defined. Traditional interpretations of DBS as a focal or lesion-like intervention are being challenged by electrophysiological and imaging evidence demonstrating multiscale modulation of circuit dynamics. Objectives and methods: DBS may enhance rehabilitation outcomes by stabilizing pathological oscillations and reducing moment-to-moment variability in motor performance, thereby enabling more consistent task execution and more effective physiotherapy, occupational therapy, and speech–language interventions. However, direct comparative evidence demonstrating additive or synergistic effects of DBS combined with rehabilitation remains limited. As a result, this potential is not fully realized in clinical practice due to interindividual variability, limited insight into how individual circuit architecture shapes therapeutic response, and the limited specificity of current connectomic biomarkers for predicting functional gains. Results: Technological advances such as tractography-guided targeting, directional leads, sensing-enabled devices, and adaptive stimulation are expanding opportunities to align neuromodulation with individualized circuit dysfunction. Despite these developments, major conceptual and empirical gaps persist. Few controlled studies directly compare outcomes with versus without structured rehabilitation following DBS. Heterogeneity in therapeutic response and rehabilitation access further complicates the interpretation of outcomes. Clarifying these relationships is essential for developing precision-informed frameworks that integrate DBS with rehabilitative strategies, recognizing that current connectomic and physiological biomarkers remain incompletely validated for predicting functional outcomes. Conclusions: This review synthesizes mechanistic, imaging, and technological evidence to outline a network-informed perspective of DBS as a potential facilitator of rehabilitation-driven functional improvement and identifies priorities for future research aimed at optimizing durable functional restoration. Full article

High-power-density LED devices have emerged as a prominent focus in current research and industrial development, largely due to their role in advancing LED lighting technologies. At high power and high current, the structure and area of the thermoelectrically separated copper substrate connected to the LEDs significantly influence the device’s optoelectronic performance, yet detailed studies in this area remain limited. To address this issue, blue and white LED devices with a maximum power rating of 400 W were fabricated and soldered onto copper substrates with diameters of 20 mm, 25 mm, and 32 mm. The influence of substrate area on the I–V and I–L characteristics of the LEDs was systematically measured and analyzed at different operating temperatures. Additionally, variations in operating voltage and luminous intensity with temperature were investigated under specific driving currents. Infrared thermal imaging was employed to examine the thermal field distribution under varying substrate sizes and current levels. The results show that increasing the copper substrate diameter from 20 mm to 25 mm and further to 32 mm leads to a significant improvement in LED optoelectronic performance. To determine the diameter threshold beyond which performance gains diminish, a 3D COMSOL 6.1. model was developed. The model reveals that expanding the diameter from 32 mm to 35 mm results in only a marginal improvement, while further increasing it to 40 mm offers a negligible additional benefit, thereby identifying the optimal substrate area for performance saturation. Full article

This study examines a seven-week informal familycentric rocketry pilot program designed for Latina girls in grades 5 and 6 and their parents. Grounded in Community Cultural Wealth and Culturally Sustaining Pedagogy, the program integrated Family Problem-Based Learning to position families as co-educators in science learning. Through activities such as designing NASA-style mission patches, constructing egg-drop devices, and launching rockets, the program sought to center family knowledge, bilingual practices, and cultural values within physical science experiences. Data reported here were collected through mid- and post-program surveys with both parents and daughters. Responses indicate strong engagement from families, with parents reporting increased high confidence in supporting their daughters’ science learning and daughters expressing enjoyment and strong interest in science learning. Both groups valued the use of English and Spanish and the program’s emphasis on collaborative, family-centered participation. Responses highlight the potential of culturally sustaining, familycentric approaches to address the underrepresentation of Latina women in Science, Technology, Engineering, and Math (STEM) by fostering a sense of belonging. This study contributes to informal science education by demonstrating how families can be centered in a program focused on physical science. School-based outreach of this kind may also strengthen families and parent–child relationships. Full article

The integration of artificial intelligence into the Industrial Internet of Things (IIoT), supported by edge computing architectures, marks a new paradigm of intelligent automation. Tiny Machine Learning (TinyML) is emerging as a key technology that enables the deployment of machine learning models on ultra-low-power devices. This study presents a systematic review of 110 peer-reviewed publications (2020–2025) identified from Scopus, Web of Science, and IEEE Xplore following the PRISMA protocol. Bibliometric and thematic analyses were conducted using Biblioshiny and VOSviewer to identify major trends, architectural approaches, and industrial applications of TinyML. The results reveal four principal research clusters: edge intelligence and energy efficiency, federated and explainable learning, human-centric systems, and sustainable resource management. Importantly, the surveyed industrial implementations report measurable gains—typically reducing inference latency to the millisecond range, lowering on-device energy cost to the sub-milliwatt regime, and sustaining high task accuracy, thereby substantiating the practical feasibility of TinyML in real IIoT settings. The analysis indicates a conceptual shift from engineering- and energy-focused studies toward cognitive, ethical, and security-oriented perspectives aligned with the principles of Industry 5.0. TinyML is positioned as a catalyst for the transition from automation to cognitive autonomy and as a technological foundation for building energy-efficient, ethical, and sustainable industrial ecosystems. Full article

Accurate malaria diagnosis is essential for effective case management and transmission control; however, the sensitivity, operational requirements, and field applicability of current conventional methods are limited. Hemozoin, an optically and magnetically active crystalline biomarker produced by Plasmodium species, offers a reagent-free target for next-generation diagnostics. This scoping review, following PRISMA-ScR and Joanna Briggs Institute guidance, synthesizes recent advances in hemozoin-based detection technologies and maps the current landscape. Twenty-four studies were reviewed, spanning eight major technology classes: magneto-optical platforms, magnetophoretic microdevices, photoacoustic detection, Raman/SERS spectroscopy, optical and hyperspectral imaging, NMR relaxometry, smartphone-based microscopy, and flow cytometry. Magneto-optical systems—including Hz-MOD, Gazelle™, and RMOD—demonstrated the highest operational readiness, with robust specificity but reduced sensitivity at low parasitemia. Photoacoustic Cytophone studies demonstrated promising sensitivity and noninvasive in vivo detection. Raman/SERS platforms achieved sub-100 infected cell/mL analytical sensitivity but remain laboratory-bound. Microfluidic and smartphone-based tools offer emerging, potentially low-cost alternatives. Across modalities, performance varied by parasite stage, with reduced detection of early ring forms. In conclusion, hemozoin-targeted diagnostics represent a rapidly evolving field with multiple viable translational pathways. While magneto-optical devices are closest to field deployment, further clinical validation, improved low-density detection, and standardized comparison across platforms are needed to support future adoption in malaria-endemic settings. Full article

Hybrid Split Federated Learning (HSFL for short) in emerging 6G-enabled UAV networks faces persistent challenges in data protection, device trust management, and long-term participation incentives. To address these issues, this study introduces S-HSFL, a security-enhanced framework that embeds verifiable federated learning mechanisms into HSFL and incorporates digital-signature-based authentication throughout the device selection process. This design effectively prevents model tampering and forgery attacks, achieving a defense success rate above 99%. To further strengthen collaborative training, we develop a MAB-GT device selection strategy that integrates multi-armed bandit exploration with multi-stage game-theoretic decision models, spanning non-cooperative, coalition, and repeated games, to encourage high-quality UAV nodes to provide reliable data and sustained computation. Experiments on the Modified National Institute of Standards and Technology (MNIST) dataset under both Independent and Identically Distributed (IID) and non-IID conditions demonstrate that S-HSFL maintains approximately 97% accuracy even in the presence of 30% adversarial UAVs. The MAB-GT strategy significantly improves convergence behavior and final model performance, while incurring only a 10–30% increase in communication overhead. The proposed S-HSFL framework establishes a secure, trustworthy, and efficient foundation for distributed intelligence in next-generation 6G UAV networks. Full article

The advent of sixth-generation (6G) imposes stringent demands on wireless networks, while traditional 2D rigid reconfigurable intelligent surfaces (RISs) face bottlenecks in regulatory freedom and scenario adaptability. To address this, stacked intelligent metasurfaces (SIMs) have emerged. This paper presents a systematic review of SIM technology. It first elaborates on the SIM multi-layer stacked architecture and wave-domain signal-processing principles, which overcome the spatial constraints of conventional RISs. Then, it analyzes challenges, including beamforming and channel estimation for SIM, and explores its application prospects in key 6G scenarios such as integrated sensing and communication (ISAC), low earth orbit (LEO) satellite communication, semantic communication, and UAV communication, as well as future trends like integration with machine learning and nonlinear devices. Finally, it summarizes the open challenges in low-complexity design, modeling and optimization, and performance evaluation, aiming to provide insights to promote the large-scale adoption of SIM in next-generation wireless communications. Full article

Mobile Global Positioning System (GPS) data offer a promising approach to inferring mental health status through behavioural analysis. Whilst previous research has explored location-based behavioural indicators including location clusters, entropy, and variance, persistent GPS measurement errors have compromised data reliability, limiting the practical deployment of smartphone-based digital phenotyping systems. This study develops and validates an algorithmic preprocessing method designed to mitigate inherent GPS measurement limitations in mobile health applications. We conducted comprehensive evaluation through controlled experimental protocols and naturalistic field assessments involving 38 participants over a seven-day period, capturing GPS data across diverse environmental contexts on both Android and iOS platforms. The proposed preprocessing algorithm demonstrated exceptional precision, consistently detecting major activity centres within an average 50-metre margin of error across both platforms. In naturalistic settings, the algorithm yielded robust location detection capabilities, producing spatial patterns that reflected plausible and behaviourally meaningful traits at the individual level. Cross-platform analysis revealed consistent performance regardless of operating system, with no significant differences in accuracy metrics between Android and iOS devices. These findings substantiate the potential of mobile GPS data as a reliable, objective source of behavioural information for mental health monitoring systems, contingent upon implementing sophisticated error-mitigation techniques. The validated algorithm addresses a critical technical barrier to the practical implementation of GPS-based digital phenotyping, enabling the more accurate assessment of mobility-related behavioural markers across diverse mental health conditions. This research contributes to the growing field of mobile health technology by providing a robust algorithmic framework for leveraging smartphone sensing capabilities in healthcare applications. Full article

This article offers a comprehensive technical and mechanical review of the Tesla turbine, an innovative device conceived by Nikola Tesla. The core research question guiding this review is: How can the design and application of the Tesla turbine be optimized to overcome its current efficiency limitations and unlock its full potential across various energy recovery technologies? The analysis focuses on the mechanical design of the turbine, illustrating the configuration of co-axial discs without blades mounted on a central shaft, and on the fluid dynamic phenomena that generate torque through the viscous boundary layer between the discs. Mathematical models based on the equations of viscous motion and CFD simulations are used to evaluate mechanical and fluid-dynamic losses, such as viscous friction, edge losses, and inlet duct losses. The work describes mechanical engineering challenges related to efficiency and performance, highlighting optimization techniques for the number and spacing of the discs, nozzle geometry, and thermal management to mitigate the risk of overheating. Finally, potential application areas in microturbine technology for low-enthalpy thermal cycles and energy recovery are examined. The article makes a significant contribution to applied mechanical engineering, offering design guidelines and an updated overview of the challenges and opportunities of Tesla turbine technology. Full article

The global transition towards sustainable energy has accelerated the development and deployment of offshore wind turbines. Jacket foundations, commonly installed in intermediate to deep water depths to access available space and higher load capacities, are built to withstand intensified hydrodynamic loads. Due to their structural complexity near the seabed, however, they are prone to local and global scour, which can compromise stability and increase maintenance costs. While extensive research has addressed scour protections around monopiles, limited attention has been given to complex foundation geometries or even hybrid configurations that combine energy-harvesting devices with structural support. These hybrid systems introduce highly unsteady flow fields and amplified turbulence effects that current design frameworks appear to be unable to capture. This study provides an experimental characterisation of scour damage in riprap-protected jackets as well as additional tests for a hybrid jacket foundation. A novel adaptation of a high-resolution overlapping sub-area methodology was employed. For the first time, it was successfully applied to quantify the damage to riprap protections for a complex offshore foundation. Results revealed that, although hybrid jackets showed the capacity to attenuate incident waves, the scour protection experienced damage numbers (S_3D) two to six times higher than conventional jackets due to flow amplifications. The findings highlight the need for revised design guidelines that can account for the complex hydrodynamic-structural interactions of next-generation marine harvesting technologies integrated into complex foundations. Full article