Search Results (2,344)

The completeness and integrity of multimodal medical data are critical determinants of surgical success and postoperative recovery. However, because of issues such as poor sensor contact, small vibrations, and device discrepancies during signal acquisition, there are frequent missing values in patients’ medical data. This issue is especially prominent in rare or complex cases, where the inherent complexity and sparsity of multimodal data limit dataset diversity and degrade predictive model performance. As a result, clinicians’ understanding of patient conditions is restricted, and the development of robust algorithms to predict preoperative, intraoperative, and postoperative disease progression is hindered. To address these challenges, we propose Med-Diffusion, a diffusion-based generative framework designed to enhance sensor data by imputing missing multimodal clinical data, including both categorical and numerical variables. The framework integrates one-hot encoding, simulated bit encoding, and feature tokenization to improve adaptability to heterogeneous data types, utilizing conditional diffusion modeling for accurate data completion. Med-Diffusion effectively learns the underlying distributions of multimodal datasets, synthesizing plausible data for incomplete records, and it mitigates the data sparsity caused by poor sensor contact, vibrations, and device discrepancies. Extensive experiments demonstrate that Med-Diffusion accurately reconstructs missing multimodal clinical information and significantly enhances the performance of downstream predictive models. Full article

This study investigated the transformative potential of Compressive Sensing (CS) for optimizing multimodal biomedical signal fusion in Wireless Body Sensor Networks (WBSN), specifically targeting challenges in data storage, power consumption, and transmission bandwidth. Through a Systematic Mapping Study (SMS) and Systematic Literature Review (SLR) following the PRISMA protocol, significant advancements in adaptive CS algorithms and multimodal fusion have been achieved. However, this research also identified crucial gaps in computational efficiency, hardware scalability (particularly concerning the complex and often costly adaptive sensing hardware required for dynamic CS applications), and noise robustness for one-dimensional biomedical signals (e.g., ECG, EEG, PPG, and SCG). The findings strongly emphasize the potential of integrating CS with deep reinforcement learning and edge computing to develop energy-efficient, real-time healthcare monitoring systems, paving the way for future innovations in Internet of Medical Things (IoMT) applications. Full article

Indoor sports facilities present unique challenges for air quality management due to high crowd densities and limited ventilation. This study investigated air quality in a municipal athletic facility in Komotini, Greece, focusing on concentrations of airborne particulate matter (PM_1.0, PM_2.5, PM₁₀), humidity, and temperature across spectator zones, under varying mask scenarios. Sensing devices were installed in the stands to collect high-frequency environmental data. The system, based on optical particle counters and cloud-enabled analytics, enabled real-time data capture and retrospective analysis. The main experiment investigated the impact of spectators wearing medical masks during two basketball games. The results show consistently elevated PM levels during games, often exceeding recommended international thresholds in the spectator area. Notably, the use of masks by spectators led to measurable reductions in PM_1.0 and PM_2.5 concentrations, because they seem to have limited the release of human-generated aerosols as well as the amount of movement among spectators, supporting their effectiveness in limiting fine particulate exposure in inadequately ventilated environments. Humidity emerged as a reliable indicator of occupancy and potential high-risk periods, making it a valuable parameter for real-time monitoring. The findings underscore the urgent need for improved ventilation strategies in small to medium-sized indoor sports facilities and support the deployment of low-cost sensor networks for actionable environmental health management. Full article

Hand rehabilitation exoskeletons play a critical role in restoring motor function in patients with stroke or hand injuries. However, most existing designs rely on fixed-axis assumptions, neglecting the rolling–sliding coupling of finger joints that causes instantaneous center of rotation (ICOR) drift, leading to kinematic misalignment and localized pressure concentrations. This study proposes the Instant Radius Method (IRM) based on medical imaging to continuously model ICOR trajectories of the MCP, PIP, and DIP joints, followed by the construction of an equivalent ICOR through curve fitting. Crossing-type biomimetic kinematic pairs were designed according to the equivalent ICOR and integrated into a three-loop ten-linkage exoskeleton capable of dual DOFs per finger (flexion–extension and abduction–adduction, 10 DOFs in total). Kinematic validation was performed using IMU sensors (Delsys) to capture joint angles, and interface pressure distribution at MCP and PIP was measured using thin-film pressure sensors. Experimental results demonstrated that with biomimetic kinematic pairs, the exoskeleton’s fingertip trajectories matched physiological trajectories more closely, with significantly reduced RMSE. Pressure measurements showed a reduction of approximately 15–25% in mean pressure and 20–30% in peak pressure at MCP and PIP, with more uniform distributions. The integrated framework of IRM-based modeling–equivalent ICOR–biomimetic kinematic pairs–multi-DOF exoskeleton design effectively enhanced kinematic alignment and human–machine compatibility. This work highlights the importance and feasibility of ICOR alignment in rehabilitation robotics and provides a promising pathway toward personalized rehabilitation and clinical translation. Full article

Background: The high-precision analysis of multimode fibers (MMFs) is a critical task in numerous applications, including remote sensing, medical imaging, and environmental monitoring. In this study, we propose a novel deep interpretable network approach to reconstruct spectral images captured using CCD sensors. Methods: Our model leverages a Tiny-YOLO-inspired convolutional neural network architecture, specifically designed for spectral wavelength prediction tasks. A total of 1880 CCD interference images were acquired across a broad near-infrared range from 1527.7 to 1565.3 nm. To ensure precise predictions, we introduce a dynamic factor α and design a dynamic adaptive loss function based on Huber loss and Log-Cosh loss. Results: Experimental evaluation with five-fold cross-validation demonstrates the robustness of the proposed method, achieving an average validation MSE of 0.0149, an R² score of 0.9994, and a normalized error (μ) of 0.0005 in single MMF wavelength prediction, confirming its strong generalization capability across unseen data. The reconstructed outputs are further visualized as smooth spectral curves, providing interpretable insights into the model’s decision-making process. Conclusions: This study highlights the potential of deep learning-based interpretable networks in reconstructing high-fidelity spectral images from CCD sensors, paving the way for advancements in spectral imaging technology. Full article

Parkinson’s disease (PD), a progressive neurodegenerative disorder affecting over 10 million people worldwide, necessitates continuous symptom monitoring to optimize treatment and enhance quality of life. Effective communication between patients and healthcare providers (HCPs) is vital but often hindered by fragmented data and cognitive impairments. PARKA AI, a novel iOS application, leverages Apple Watch HealthKit data (e.g., tremor detection, mobility metrics, heart rate, and sleep patterns) and integrates it with self-reported logs (e.g., mood, medication adherence) to empower PD self-management and improve patient–HCP interactions. Employing a human-centered design approach, we developed a high-fidelity prototype using a large language model (LLM)— Google Gemini 1.5 Flash—to process and analyze self-reports and objective sensor-derived data from Apple Healthkit to generate patient-friendly summaries and concise HCP reports. PARKA AI provides accessible data visualizations, personalized self-management tools, and streamlined HCP reports to foster engagement and communication. This paper outlines the derived design requirements, prototype features, and illustrative use cases to show how LLMs can be used in digital health tools. Future work will focus on real-world usability testing to validate the application’s efficacy and accessibility. Full article

The Internet of Medical Things (IoMT) is the latest advancement in the Internet of Things (IoT). Researchers are increasingly drawn to its vast potential applications in secure healthcare systems. The growing use of internet-connected medical device sensors has significantly transformed healthcare, necessitating the development of robust methodologies to assess their integrity. As access to computer networks continues to expand, these sensors have become vulnerable to a wide range of security threats, thereby compromising their integrity. To prevent such lapses, it is essential to understand the complexities of the operational environment and to systematically identify technical vulnerabilities. This paper proposes a unified hesitant fuzzy-based healthcare system for assessing IoMT sensor integrity. The approach integrates the hesitant fuzzy Analytic Network Process (ANP) and the hesitant fuzzy Technique for Order Preference by Similarity to the Ideal Solution (TOPSIS). In this study, a hesitant fuzzy ANP is employed to construct a comprehensive network that illustrates the interrelationships among various integrity criteria. This network incorporates expert input and accounts for inherent uncertainties. The research also offers sensitivity analysis and comparative evaluations to show that the suggested method can analyse many medical device sensors. The unified hesitant fuzzy-based healthcare system presented here offers a systematic and valuable tool for informed decision-making in healthcare. It strengthens both the integrity and security of healthcare systems amid the rapidly evolving landscape of medical technology. Healthcare stakeholders and beyond can significantly benefit from adopting this integrated fuzzy-based approach as they navigate the challenges of modern healthcare. Full article

Parkinson’s disease (PD) presents an association of motor and non-motor impairments that impact the independence and quality of life of individuals. Rehabilitation programs must address multiple domains, simultaneously maintaining patients’ adherence and the implications of the disease. Immersive virtual-reality-based rehabilitation (IVRBR) is a promising alternative tool, or can be used in conjunction with traditional or passive programs, using interactive tasks in valid environments with specific training programs adapted to each individual’s needs. This narrative review synthesizes the medical literature published in the last decade from PubMed, Scopus, and Web of Science, on the effectiveness, limitations, and implementations of IVRBR in PD patients. Evidence from RTCs and non-RTCs suggests that IVRBR can improve balance, motor learning, and dual task performance. At the same time, the evidence suggests that it can improve cognitive and emotional status. The integration of objective assessment tools (motion and posture analyses, wearable sensors, center of pressures and machine learning models capable of predicting freezing gait-FoG) enhances clinical and individualized rehabilitation programs. However, the evidence base remains limited, with a small sample size, heterogeneity in measured outcomes, and short follow-up duration. In general, reported adverse reactions were minor, but required standardized reporting patterns. Implementation is challenging due to the equipment cost and varying technological demands, but also due to patient selection and training of the medical personnel. IVRBR is a feasible and engaging alternative or can form part of an individualized rehabilitation program in PD patients; however, future large RTCs, long-term follow-up with standardized protocols, cost-effectiveness analyses, and integration of predictive modeling are essential for its broader clinical usage. Full article

The burgeoning Internet of Medical Things (IoMT) offers unprecedented opportunities for real-time patient monitoring and predictive diagnostics, yet the current systems struggle with scalability, data confidentiality against quantum threats, and real-time privacy-preserving intelligence. This paper introduces Med-Q Ledger, a novel, multi-layered framework designed to overcome these critical limitations in the Medical IoT domain. Med-Q Ledger integrates a permissioned Hyperledger Fabric for transactional integrity with a scalable Holochain Distributed Hash Table for high-volume telemetry, achieving horizontal scalability and sub-second commit times. To fortify long-term data security, the framework incorporates post-quantum cryptography (PQC), specifically CRYSTALS-Di lithium signatures and Kyber Key Encapsulation Mechanisms. Real-time, privacy-preserving intelligence is delivered through an edge-based federated learning (FL) model, utilizing lightweight autoencoders for anomaly detection on encrypted gradients. We validate Med-Q Ledger’s efficacy through a critical application: the prediction of intestinal complications like necrotizing enterocolitis (NEC) in preterm infants, a condition frequently necessitating emergency colostomy. By processing physiological data from maternal wearable sensors and infant intestinal images, our integrated Random Forest model demonstrates superior performance in predicting colostomy necessity. Experimental evaluations reveal a throughput of approximately 3400 transactions per second (TPS) with ~180 ms end-to-end latency, a >95% anomaly detection rate with <2% false positives, and an 11% computational overhead for PQC on resource-constrained devices. Furthermore, our results show a 0.90 F1-score for colostomy prediction, a 25% reduction in emergency surgeries, and 31% lower energy consumption compared to MQTT baselines. Med-Q Ledger sets a new benchmark for secure, high-performance, and privacy-preserving IoMT analytics, offering a robust blueprint for next-generation healthcare deployments. Full article

The Internet of Medical Things (IoMT) is a rapidly expanding network of medical devices, sensors, and software that exchange patient health data. While IoMT supports personalized care and operational efficiency, it also introduces significant privacy risks, especially when handling sensitive health information. Data Identification and Classification (DIC) are therefore critical for distinguishing which data attributes require stronger safeguards. Effective DIC contributes to privacy preservation, regulatory compliance, and more efficient data management. This study introduces SDAIPA (SDAIA-HIPAA), a standardized hybrid IoMT data classification framework that integrates principles from HIPAA and SDAIA with a dual risk perspective—uniqueness and harm potential—to systematically classify IoMT health data. The framework’s contribution lies in aligning regulatory guidance with a structured classification process, validated by domain experts, to provide a practical reference for sensitivity-aware IoMT data management. In practice, SDAIPA can assist healthcare providers in allocating encryption resources more effectively, ensuring stronger protection for high-risk attributes such as genomic or location data while minimizing overhead for lower-risk information. Policymakers may use the standardized IoMT data list as a reference point for refining privacy regulations and compliance requirements. Likewise, AI developers can leverage the framework to guide privacy-preserving training, selecting encryption parameters that balance security with performance. Collectively, these applications demonstrate how SDAIPA can support proportionate and regulation-aligned protection of health data in smart healthcare systems. Full article

The sensory glove (also known as data or instrumented glove) plays a key role in measuring and tracking hand dexterity. It has been adopted in a variety of different domains, including medical, robotics, virtual reality, and human–computer interaction, to assess hand motor skills and to improve control accuracy. However, no particular technology has been established as the most suitable for all domains, so that different sensory gloves have been developed, adopting different sensors mainly based on optic, electric, magnetic, or mechanical properties. This work investigates the performances of the MANUS Quantum sensory glove that sources an electromagnetic field and measures its changing value at the fingertips during fingers’ flexion. Its performance is determined in terms of measurement repeatability, reproducibility, and reliability during both quasi-static and dynamic hand motor tests. Full article

With the advancement of medical care technology, the aging population has become a serious problem, and long-term care for the elderly is a major concern facing today’s society. Long-term care institutions take care of people with dysfunction or difficulties and provide them with continuous assistance. However, the shortage of specialists and the relative increase in costs have affected the burden on families. Long-term care has developed from traditional approaches to advanced ones at well-equipped facilities. We combine network technology with long-term care service with sensors that have alarm functions according to diverse needs, so that the elderly can receive complete care. Full article

Rapid access to defibrillators, blood products, and time-critical medicines can improve survival, yet urban congestion and fragmented infrastructure delay deliveries. We present and evaluate an end-to-end framework for beyond-visual-line-of-sight (BVLOS) UAV logistics in Essex (UK), integrating (I) strategic depot placement, (II) a hybrid obstacle-aware route planner, and (III) a time-window-aware (TWA) Mixed-Integer Linear Programming (MILP) scheduler coupled to a battery/temperature feasibility model. Four global planners—Ant Colony Optimisation (ACO), Genetic Algorithm (GA), Particle Swarm Optimisation (PSO), and Rapidly Exploring Random Tree* (RRT*)—are paired with lightweight local refiners, Simulated Annealing (SA) and Adaptive Large-Neighbourhood Search (ALNS). Benchmarks over 12 destinations used real Civil Aviation Authority no-fly zones and energy constraints. RRT*-based hybrids delivered the shortest mean paths: RRT* + SA and RRT* + ALNS tied for the best average length, while RRT* + SA also achieved the co-lowest runtime at $v=60\mathrm{km}{\mathrm{h}}^{-1}$. The TWA-MILP reached proven optimality in 0.11 s, showing that a minimum of seven UAVs are required to satisfy all 20–30 min delivery windows in a single wave; a rolling demand of one request every 15 min can be sustained with three UAVs if each sortie (including service/recharge) completes within 45 min. To validate against a state-of-the-art operations-research baseline, we also implemented a Vehicle Routing Problem with Time Windows (VRPTW) in Google OR-Tools, confirming that our hybrid planners generate competitive or shorter NFZ-aware routes in complex corridors. Digital-twin validation in AirborneSIM confirmed CAP 722-compliant, flyable trajectories under wind and sensor noise. By hybridising a fast, probabilistically complete sampler (RRT*) with a sub-second refiner (SA/ALNS) and embedding energy-aware scheduling, the framework offers an actionable blueprint for emergency medical UAV networks. Full article

This study presents a theoretical investigation of a terahertz (THz) surface plasmon resonance (SPR) optical biosensor utilizing a graphene-integrated Otto configuration. Through systematic numerical simulations, we demonstrate that actively modulating graphene’s conductivity via an external magnetic field enables tunable SPR behavior with high phase sensitivity. The proposed sensor achieves a phase sensitivity of up to $3.1043\times {10}^5$ deg RIU⁻¹ in liquid sensing and $2.5854\times {10}^4$ deg RIU⁻¹ in gas sensing. This simulation-based work establishes a foundational framework for the development of highly sensitive, magneto-optically tunable optical sensors, highlighting their potential in chemical detection and medical diagnostics. Full article

This paper presents the design and implementation of a blockchain-secured system for monitoring driver sobriety and real-time geolocation. The proposed platform integrates a Modular Sensor Battery (MSB) for detecting alcohol concentration in exhaled air, a centralized Data Collection Platform (DC Platform) for real-time data visualization and storage, and a complementary physiological monitoring device—the IoT Fit-Bit Smart Band (IFSB)—which captures heart rate and blood oxygen saturation as alternative indicators when breath-based sensing may be compromised. The MSB, the DC Platform, integration with the IoT FitBit Smart Band, and the blockchain-based data management architecture represent the authors’ direct contribution to both the conceptual design and technical implementation. These elements are introduced as part of a unified, fully integrated system designed to enable non-invasive sobriety monitoring and secure data integrity in vehicular contexts. To ensure data authenticity, a custom Ethereum smart contract stores cryptographic hashes of sensor readings, enabling decentralized, tamper-evident verification without exposing sensitive medical information. The system was validated in a controlled experimental environment, confirming its operational robustness and demonstrating its potential to improve road safety through secure, real-time sobriety detection and geolocation tracking. Full article