Search Results (290)

Distributed denial-of-service (DDoS) attacks pose a critical threat to the availability of the Internet of Medical Things (IoMT). This paper proposes an intrusion detection system (IDS) based on a hybrid neuro-fuzzy-inspired approach to identify DDoS attacks in IoMT environments. The architecture combines an ensemble of decision trees, a sigmoidal smoothing mechanism, and a multilayer neural meta-classifier, enabling the modeling of nonlinear relationships between legitimate and malicious traffic without requiring explicit fuzzy rules or a formal fuzzy inference mechanism. The evaluation was conducted using the public DoS/DDoS-MQTT-IoT dataset, which was extended by incorporating legitimate traffic generated by electrocardiography (ECG) monitoring devices to approximate real operational IoMT conditions. The model was validated using stratified cross-validation and bootstrap procedures. In the extended IoMT scenario including ECG traffic, the proposed approach achieved an area under the ROC curve (AUC) of 0.904 and an F1 score of 0.823. Finally, the IDS was integrated into an intrusion detection and prevention system (IDPS) capable of detecting anomalous traffic patterns within three seconds and automatically blocking malicious IP addresses after repeated detections. Full article

Impulsive alpha (α)-stable noise, characterized by heavy tails and intense outliers, is a key ingredient in simulating financial, medical, seismic, and digital communication technologies. It poses versatile challenges to conventional machine learning (ML) algorithms in predicting noise parameters for multidisciplinary artificial intelligence (AI)-embedded devices. In this study, we adopted a two-phase methodology to investigate the complexity and performance of supervised ML algorithms while classifying impulsive noise parameters. We generated synthetic datasets of α-stable noise distributions for experimentation in a controlled environment. It was followed by experimental evaluation to derive the complexity and performance of ML classifiers—k-nearest neighbors (KNN), Support Vector Machine (SVM), Naïve Bayes (NB), Decision Tree (DT), and Random Forest (RF). Moreover, we employed a very high channel noise level of −15 dB in the test datasets to ensure that the derived analysis applies to real-world devices. The results demonstrate the high performance of DT and RF in structured binary classification of the α regime and the sign of skewness, while incurring satisfactory computational costs. However, SVM and kNN are comparatively more robust for multi-class classification, albeit with higher memory and training costs. On the contrary, NB fails to address the skewed and impulsive behavior of α-stable noise. We observed that even the most effective classifiers struggle to achieve perfect accuracy in multi-class classification. Overall, the experimental results reveal significant trade-off relationships between the complexity and performance of ML classifiers. Conclusively, simple models are well-suited for coarse-grained tasks, such as α-approximation and sign-of-skewness classification. In contrast, sophisticated models can be deployed to predict noise parameters to some extent. Our study provides a clear set of trade-offs for future applied AI devices that address adversarial and impulsive noise. Full article

Kolmogorov–Arnold Networks (KANs) have recently gained increasing attention as an alternative to conventional neural architectures, mainly because they replace fixed activation functions with learnable univariate mappings defined along network edges. This design not only increases modeling flexibility but also makes it easier to interpret how inputs are transformed within the network while maintaining parameter efficiency. KANs are particularly well suited for sensor-driven systems where transparency, robustness, and computational constraints are critical. This study provides a survey of KAN-based approaches for processing sensor data. A literature review conducted from 2024 to 2026 examined the deployment of KAN models in industrial and mechanical sensing, medical and biomedical sensing, and remote sensing and environmental monitoring, utilizing a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-based methodology. We first revisit the theoretical foundations of KANs and their main architectural variants, including spline-based, polynomial-based, monotonic, and hybrid formulations, to structure the discussion. From a practical standpoint, we then examine how KAN modules are integrated into modern deep learning pipelines, such as convolutional, recurrent, transformer-based, graph-based, and physics-informed architectures. KAN-based models demonstrate comparable predictive performance as conventional machine learning models, while having fewer parameters and more interpretable representations. Several limitations persist, including computational overhead, sensitivity to noisy signals, and resource-constrained device deployment challenges. Real-world sensor systems encounter significant challenges in adopting KAN-based models, including scalability in large-scale sensor networks, integration with hardware architectures, automated model development, resilience to out-of-distribution conditions, and the need for standardized evaluation metrics. Collectively, these observations provide a clearer understanding of the current and potential limitations of KAN-based models, offering practical guidance on the development of interpretable and efficient learning systems for future sensor equipment applications. Full article

Background and Objectives: Chronic obstructive pulmonary disease (COPD) is a major cause of morbidity and mortality worldwide and is frequently associated with multiple comorbidities. Bioelectrical impedance analysis (BIA) provides additional information on body composition and may contribute to the multidimensional assessment of patients with COPD. This study aimed to explore the relationship between BIA-derived parameters and clinical characteristics in hospitalized patients with COPD. Materials and Methods: A cross-sectional analysis of baseline data from a prospective cohort was conducted. A total of 72 hospitalized patients with COPD were included, according to predefined inclusion and exclusion criteria. All patients underwent multifrequency BIA using the InBody 380 device. Sociodemographic, clinical, and paraclinical data were collected and analyzed in relation to BIA-derived parameters. Results: Among the bioimpedance-derived parameters, phase angle (PhA) showed a significant correlation with clinical indices of disease severity, including the body mass index, airflow obstruction, dyspnea, and exercise capacity (BODE) index and the modified Medical Research Council (mMRC) dyspnea scale. Hydration-related parameters reflecting extracellular fluid distribution were associated with the presence of heart failure as a comorbidity. In addition, the evaluation of body fat using bioimpedance identified a higher number of patients with excess body fat compared with obesity defined according to the classical body mass index–based criteria. Conclusions: BIA may provide clinically relevant information on body composition and fluid distribution in patients with COPD. These findings support the potential role of BIA as a complementary tool in the multidimensional evaluation of multimorbid patients with COPD, although further studies are needed to clarify its prognostic value and clinical applicability. Full article

The Internet of Things (IoT) plays an increasingly central role in healthcare by enabling continuous patient monitoring, remote diagnosis, and data-driven clinical decision-making through interconnected medical devices and sensing infrastructures. Despite these advances, IoT healthcare systems remain constrained by persistent challenges related to data privacy, computational efficiency, scalability, and regulatory compliance. Federated learning (FL) reduces reliance on centralised data aggregation but remains vulnerable to inference-based privacy risks, while edge-oriented approaches are limited by device heterogeneity and restricted computational and energy resources; the deployment of large language models (LLMs) further exacerbates concerns surrounding privacy exposure, communication overhead, and practical feasibility. This study introduces Trustworthy Intelligence (TI) as a guiding framework for privacy-preserving distributed intelligence in IoT healthcare, explicitly integrating predictive performance, privacy protection, and deployment-oriented system design. Within this framework, split learning (SL) is examined as a core architectural mechanism and extended to support split-aware LLM integration across heterogeneous devices, supported by a structured taxonomy spanning architectural configurations, system adaptation strategies, and evaluation considerations. The study establishes a systematic mapping between SL design choices and representative healthcare scenarios, including wearable monitoring, multi-modal data fusion, clinical text analytics, and cross-institutional collaboration, and analyses key technical challenges such as activation-level privacy leakage, early-round vulnerability, reconstruction risks, and communication–computation trade-offs. An energy- and resource-aware adaptive cut layer selection strategy is outlined to support efficient deployment across devices with varying capabilities. A proof-of-concept experimental evaluation compares the proposed SL–LLM framework with centralised learning (CL), federated learning (FL), and conventional SL in terms of training latency, communication overhead, model accuracy, and privacy exposure under realistic IoT constraints, providing system-level evidence for the applicability of the TI framework in distributed healthcare environments and outlining directions for clinically viable and regulation-aligned IoT healthcare intelligence. Full article

Future 6G-enabled smart hospital infrastructures will support latency-critical medical operations such as robotic surgery, autonomous monitoring, and real-time clinical decision systems, which require communication mechanisms that ensure both ultra-low latency and long-term cryptographic security. Existing security solutions either rely on classical cryptographic protocols that are vulnerable to quantum attacks or deploy isolated post-quantum primitives without providing a unified framework for secure real-time medical command transmission. This research presents a latency-aware, multi-layered post-quantum security architecture for 6G-enabled smart hospital environments. The proposed framework establishes an end-to-end secure command transmission pipeline that integrates hardware-rooted device authentication, post-quantum key establishment, hybrid payload protection, dynamic access enforcement, and tamper-evident auditing within a coherent system design. In contrast to existing approaches that focus on individual security mechanisms, the architecture introduces a structured integration of Kyber-based key encapsulation and Dilithium digital signatures with hybrid AES-based encryption and legacy-compatible key transport, while Physical Unclonable Function authentication provides hardware-bound device identity verification. Zero Trust access control, metadata-driven anomaly detection, and blockchain-style audit logging provide continuous verification and traceability, while threshold cryptography distributes cryptographic authority to eliminate single points of compromise. The proposed architecture is evaluated using a discrete-event simulation framework representing adversarial conditions in realistic 6G medical communication scenarios, including replay attacks, payload manipulation, and key corruption attempts. Experimental results demonstrate improved security and operational efficiency, achieving a 48% reduction in detection latency, a 68% reduction in false-positive anomaly detection rate, and a 39% improvement in end-to-end round-trip latency compared to conventional RSA-AES-based architectures. These results demonstrate that the proposed framework provides a practical and scalable approach for achieving post-quantum secure and low-latency command transmission in next-generation 6G smart hospital systems. Full article

In the 21st century, there have been radical changes in healthcare related to the transition from a universal approach to personalized medicine based on the unique characteristics of each patient. In large part, this has become possible due to the development and distribution of wearable medical devices that are capable of providing continuous monitoring of a variety of physiological parameters outside medical institutions. The most important of these devices are modern biosensors that allow real-time tracking of various biomarkers in the body, thereby opening up new opportunities for disease prevention, early diagnosis, and personalized treatment strategies. The most obvious example of the transformation is the implementation of wearable devices for continuous glucose monitoring (CGM), which has significantly facilitated the daily lives of millions of people with diabetes. Nevertheless, despite the examples of successful implementation of these devices, their large-scale distribution is associated with many challenges, such as the need for standardization, data transmission security, and the risks of immune responses to implantable devices or infections. This review examines all the current problems of wearable biosensors and possible ways to overcome them. Special emphasis will be placed on devices for continuous glucose monitoring as the most commercially successful representatives of this device class. Full article

The Internet of Medical Things (IoMT) transforms healthcare through interconnected medical devices but faces significant cybersecurity threats, particularly intrusion and exfiltration attacks. Centralized intrusion detection systems (IDSs) require data aggregation, presenting privacy and scalability risks. This paper proposes FedEnsemble-DP, a privacy-aware Federated Learning (FL) framework for decentralized intrusion detection in IoMT networks. The framework integrates three data balancing scenarios (Raw Imbalanced, Local SMOTE, Centralized SMOTE) with Differential Privacy (DP) and Secure Aggregation mechanisms. Extensive experiments on WUSTL-EHMS-2020 and CIC-IoMT-2024 datasets under non-IID settings (Dirichlet $\alpha$ = 0.3) demonstrate that models with strong privacy guarantees ($\epsilon$ = 3.0) frequently match or exceed non-private baselines. Key findings show Local SMOTE with $\epsilon$ = 3.0 achieved 94.60% accuracy and 0.9598 AUC, while Raw Imbalanced with $\epsilon$ = 3.0 attained 94.50% accuracy and 0.9494 AUC. Even with strict privacy ($\epsilon$ = 3.0), these results surpassed the non-private baseline (93.20% accuracy) in the raw scenario. Centralized SMOTE showed effectiveness but introduced training instability. These results indicate that local data balancing combined with calibrated DP noise can yield high detection performance while preserving privacy, effectively bridging security-performance and data confidentiality requirements in distributed healthcare networks. Full article

Urban emergency medical services (EMSs) depend on time-critical accessibility, spatial demand distribution, and resilient transport networks. This study examines how built-environment characteristics shape spatiotemporal population intensity (as a proxy for latent EMS demand) within Shenzhen’s 10 min ambulance-accessible Emergency Medical Circle (EMC), using high-resolution Baidu Huiyan mobile-device data. Human activity intensity was quantified in 200 × 200 m grids and modeled against 20 built-environment indicators using a Gradient Boosting Decision Tree (LightGBM), with SHAP employed for interpretable attribution. By analyzing the distribution density and variance of SHAP dependence patterns, pronounced diurnal shifts in dominant drivers were identified. Medical facility density anchors nocturnal demand, road network permeability dominates pre-dawn mobility, land-use entropy and functional diversity peak during the midday period, while transit hubs and mixed-use amenities consolidate evening activity. The results further reveal critical non-linear thresholds—such as medical facility density (~1.5–2.5 km⁻²) and building density (~45,000–60,000 m² km⁻²)—beyond which marginal contributions diminish or become negative, indicating that proximity alone does not guarantee effective emergency coverage. These findings provide quantitative, time-sensitive guidance for EMC planning, highlighting the need for balanced facility dispersion, network prioritization, and demand-aware spatial design. By integrating high-resolution population dynamics with visually interpretable machine learning, this study advances a human-centered and operationally grounded framework for resilient emergency medical systems. Full article

Cleanrooms are essential environments for the production of sterile pharmaceuticals and medical devices, where airflow stability and contamination control are critical. In this study, the influence of adjustable worktable height on air cleanliness was examined to determine whether height variation affects unidirectional airflow and particle concentration. Measurements were conducted under laboratory conditions in an ISO Class 6 cleanroom and in an industrial ISO Class 8 production line. Particle concentrations were recorded at table heights between 70 and 120 cm using a calibrated particle counter in accordance with ISO 14644-1 and ISO 21501-4. The measured data were evaluated against the classification limits defined in ISO 14644-1. Across all height levels, particle concentrations remained well below the permissible thresholds. In the ISO Class 6 cleanroom, measurement height showed a statistically significant effect on particles >5 μm, though this represented only a small contribution to the overall variance. In contrast, no significant height effect was observed in the ISO Class 8 cleanroom. Observed local differences were attributed to airflow distribution and the placement of air supply in-/outlets rather than table height. These results confirm that height-adjustable worktables can be implemented without affecting cleanroom classification, provided that uniform FFU placement and furniture positioning are considered during design and qualification. Full article

Three-dimensional (3D) anatomic modeling derived from high-resolution medical imaging, such as computed tomography (CT) and magnetic resonance imaging (MRI), has been increasingly adopted in preclinical testing and device development. This white paper describes a cardiac-specific workflow that integrates 3D printing and silicone molding for support device development and procedural simulation. Patient-derived computed tomography angiography data were segmented using FDA-cleared medical modeling software to isolate the left ventricular anatomy and were further processed in computer-aided design (CAD) to ensure accurate physiological wall thickness and structural fidelity. Material jetting 3D printing was performed on a Stratasys J750 using material distributions designed to mimic the mechanical properties of myocardium, thereby approximating myocardial compliance. In parallel, stereolithography apparatus molds were designed from the left ventricle CAD model to cast transparent, pliable left ventricular models in Sorta-Clear™ 18 silicone. The 3D-printed models preserved intricate morphological detail and were suitable for mechanical manipulation and device deployment studies, whereas silicone models offered tunable mechanical properties, transparency for visualization, and durability for repeated use. Together, these complementary modalities provided rapid manufacturing capability and application-relevant physical representation. Case-specific parameters, strengths, and limitations of both models in enhancing patient care and device testing are highlighted, with relevance to heart failure applications. Current knowledge gaps, workflow and integration challenges, and future opportunities are identified, positioning this work as a reference framework for continued innovation in anatomic modeling. Within the collaborative framework of Mayo Clinic’s Anatomic Modeling Unit and Simulation Center, this integrated modeling workflow demonstrates the value of multidisciplinary collaboration between engineers and clinicians. Clinically, these patient-specific left ventricular models may enable pre-procedural device sizing and positioning and may support simulation of mechanical circulatory support (MCS) deployment while identifying possible anatomic constraints prior to intervention. This workflow has direct applicability in advanced heart failure patients undergoing MCS support, such as the Impella axillary MCS device or the durable LVAD, with potential to reduce procedural uncertainty while reducing complications and improving peri-procedural outcomes. Additionally, these models also serve as high-accuracy educational tools, enabling trainees and multidisciplinary care teams to visualize and possibly rehearse procedural steps while gaining hands-on experience in a risk-free environment. Full article

The growing demand for sustainable and distributed energy solutions has driven increasing interest in triboelectric nanogenerators (TENGs) as platforms for energy harvesting and self-powered sensing. Biowaste-based triboelectric nanogenerators (BW-TENGs) represent an attractive strategy by coupling renewable energy generation with waste valorization under the principles of the circular bioeconomy. This review provides a comprehensive overview of BW-TENGs, encompassing fundamental triboelectric mechanisms, material categories, processing and surface-engineering strategies, device architectures, and performance evaluation metrics. A broad spectrum of biowaste resources—including agricultural residues, food and marine waste, medical plastics, pharmaceutical waste, and plant biomass—is critically assessed in terms of physicochemical properties, triboelectric behavior, biodegradability, biocompatibility, and scalability. Recent advances demonstrate that BW-TENGs can achieve electrical outputs comparable to conventional synthetic polymer TENGs while offering additional advantages such as environmental sustainability, mechanical compliance, and multifunctionality. Key application areas, including environmental monitoring, smart agriculture, wearable and implantable bioelectronics, IoT networks, and waste management systems, are highlighted. The review also discusses major challenges limiting large-scale deployment, such as material heterogeneity, environmental stability, durability, and lack of standardization, and outlines emerging solutions involving material engineering, hybrid energy-harvesting architectures, artificial intelligence-assisted optimization, and life cycle assessment frameworks. Full article

In this study, we present and analyze a fully optically transparent four-port ultra-wideband (UWB) antenna intended for MIMO applications. The antenna’s design is thoroughly described and extensively analyzed, focusing on current distributions across its structure, with all behavioral parameters explained. The proposed antenna design has been validated with both simulations and measurements. The antenna demonstrates excellent performance in terms of port matching, isolation, and efficiency, achieving an efficiency of 40%, which is impressive compared to optically transparent antennas in the literature. The radiation characteristics exhibit peak gains up to 4 dB with stable, symmetric, and linear polarized patterns maintained across the entire UWB range. Regarding diversity performance, the antenna displays outstanding behavior with an envelope correlation coefficient of less than 0.0016 and a diversity gain around 10 dB across the entire operating band. The antenna’s exceptional performance along with its optical transparency makes it suitable for various applications, such as medical non-invasive devices that can be easily integrated into glasses without obstructing vision. It can also be combined with solar cells for energy harvesting and communication purposes. Additionally, its structure is suitable for vehicular settings and can be seamlessly integrated into vehicle mirrors or windows. Full article

Following the discovery of therapeutic molecules and the identification of specific biological targets, preparation of regulatory dossiers entails extensive product development and characterization to support their safety, efficacy, and stability. We have examined the drug development and relevant regulatory considerations related to inhaled biological proteins in the accompanying article. This review focuses on the characterization of locally acting inhaled biological proteins. Drug product characterization is a regulatory requirement, and it ensures drug product safety, efficacy, stability, and usability by the target populations. Together, these two articles provide a comprehensive discussion based on our review and analysis of the available open literature. We have attempted to fill gaps and simulate discussion of challenges following sound scientific pathways. This approach has the prospect of addressing regulatory expectations leading to rapid solutions to unmet medical needs. The robustness of characterization strategies and the development of analytical methods used in the in vitro testing for the evaluation of drug product attributes is assured through application of the Design-of-Experiment (DOE) and Quality-by-Design (QBD) approaches. Drug product characterization entails a variety of in vitro studies evaluating drug products for purity and contamination, and determination of drug delivery by the intended route of administration. Measurement of the proportion of the labeled amount per dose and the form suitable for delivery to the intended target sites is central to this assessment. For respiratory Drug–Device combination products, the testing may vary with the product designs. However, determination of the single-dose content, delivered-dose uniformity, aerodynamic particle size distribution, and device robustness when used by the target populations is common to all combination products. Characterization of aerosol plumes is limited to inhalation aerosols that produce specific aerosol clouds upon actuation. The flow rate dependency of devices is also examined. Product characterization also includes safety-related product attributes such as degradation products and leachables. For inhaled biological proteins, safety-related in vitro testing includes additional testing to assure maintenance of the three-dimensional structural integrity and the sustained biological activity of the drug substance in the formulation, during aerosolization and upon deposition. This article discusses various tests employed for regulatory-compliant product characterization. In addition, the stability testing and handling of possible changes during product development and post-approval are discussed. Full article

Quantifying e-waste in Sub-Saharan Africa remains constrained by scarce data, weak institutional reporting, and the dominance of informal sector activity. We present the first nationwide assessment of e-waste generation and Random Forest-based national forecasting in Sierra Leone. A mixed-methods survey administered 6000 questionnaires across all 16 districts, targeting households, institutions, enterprises, and informal actors. The study documented devices in use, storage, and disposal across the following six categories: ICT, appliances, lighting, batteries, medical, and other electronics. Population growth and device adoption simulations were combined with lifespan distributions and a Random Forest model trained on survey and simulated historical data to construct e-waste flows and forecast quantities through to 2050, including disposal fate probabilities for repurposing versus discarding. The results showed sharp spatial disparities, with Western Urban (Freetown) averaging about 10 kg per capita compared to 1.8 kg per capita in rural areas. Long-term district patterns were highly concentrated: 50-year annual averages indicated that Western Area Urban contributes 15.3% of national totals, followed by Bo (12.7%) and Western Area Rural (12.1%), with the top five districts contributing 59.1%. By 2050, total national e-waste entering reuse and disposal pathways was projected to reach 23.4 kilo tons per year (kt yr⁻¹) with a 95% uncertainty interval (UI) of 11–42 kt yr⁻¹ (and a 99% interval extending to 50 kt yr⁻¹), corresponding to 0.9–3.4 kg/capita/year. Household appliances dominated total mass, ICT devices exhibited high reuse rates, and batteries showed minimal reuse despite high hazard potential. These findings provide critical evidence for e-waste policy, regulation, and infrastructure planning in data-scarce regions. Full article