Self-healing and adhesive eutectogels with dual conductive networks for multimodal health monitoring and human-computer interaction.

ABSTRACT Background Stroke is a major cause of disability globally, with particularly severe effects in low-resource countries like Ghana. Survivors often experience upper limb motor impairments that limit independence, while access to advanced rehabilitation technologies remains limited. This highlights the need for affordable and effective solutions to support recovery. Objectives This study develops a low-cost mechanical hand exoskeleton to assist rehabilitation using pneumatic and biomechanical design principles suitable for resource-limited environments. Methods Pneumatic soft actuators made from 3D-printed TPU 95A bellows and PLA scaffolds were designed to generate finger flexion through controlled pressurization. A pneumatic box equipped with dual vacuum pumps, solenoid valves, silicone tubing, and an Arduino-based controller regulated airflow. Integrated flex sensors enabled real-time motion replication for bilateral training. Iterative prototyping and testing were performed to optimize performance and usability, and the final prototype was evaluated for functionality in hand rehabilitation tasks. Results The exoskeleton successfully assisted digit flexion and extension by mimicking movements of the healthy hand. It achieved a bend angle of 66.0° at 30 kPa in approximately 5 seconds, producing a flexion force of 3.82 N and a hyperextension force of 1.342 N at a 16.0° hyperextension angle. The glove weighed 207 g, and the pneumatic control box weighed 794 g. Conclusions This low-cost pneumatic exoskeleton offers a practical and accessible rehabilitation tool with strong potential to improve hand recovery outcomes for stroke patients in Ghana and similar settings.

ABSTRACT The increasing demand for skilled professionals in technical and vocational domains necessitates intelligent training systems that adapt to individual learners. Conventional assessment methods often fail to capture real-time progress and provide personalised feedback. Recent advances in Artificial Intelligence and wearable technologies enable continuous tracking of complex learner behaviour. This research explores the integration of Deep Learning (DL) and real-time feedback systems to predict and enhance vocational skill acquisition efficiency. Data were collected from multiple sources, including sensor data, task performance logs, user interaction behaviour, and biometric inputs such as eye tracking and hand movements. The data were normalised, and features were extracted using Principal Component Analysis (PCA) and selected through Adaptive Inertia Weight Particle Swarm Optimisation (AIW-PSO). A Residual Long Short-Term Memory (ResLSTM) network is employed to accurately predict individual skill acquisition efficiency. Based on model outputs, real-time feedback dynamically adapts training tasks to provide personalised guidance. The proposed framework achieves high performance, with an accuracy of 98.7% and strong results across recall, AUC, MCC, precision, and F1-score, demonstrating its effectiveness for smart vocational training systems.

Visual Outcomes in Cases of Endogenous Endophthalmitis: A Multicenter Study.

Hemispheric asymmetry of the ipsilateral silent period following voluntary movement of the opposite hand.

Perioperative quantification of clinical bradykinesia measurements in patients with Parkinson's disease using accelerometry.

This research paper introduces an alternative solution for foot movement rehabilitation, bridging the gap between advanced technology and practical, everyday application. By integrating methods of electrostimulation with an electronic glove device, a novel approach to lower limb muscle rehabilitation is proposed. The device utilizes sensors and deep learning (DL) models with which it is equipped, translating hand movements into leg muscle stimulation. It offers a more accessible rehabilitation solution, with customization potential, which could enable users to regain mobility with increased independence and efficiency.

Proprioception and vision relationship in aimed movement with restricted and reversed vision.

Hazy media with resultant difficulties in visualization hamper the surgical approach and outcomes in various vitreoretinal surgical scenarios, including eyes with keratoprosthesis in situ. We propose a novel chandelier-assisted bimanual infusion using a flute needle to overcome the inability to secure infusion safely in such eyes. The surgical technique was performed with the assistance of chandelier illumination. The irrigation tubing from the vitrectomy machine was connected to a flute needle for infusion. A bimanual technique was used with the flute needle connected to infusion in one hand and the cutter in the other hand. A 34-year-old monocular male patient with a keratoprosthesis in his seeing eye developed late-onset endophthalmitis with retroprosthetic membranes. The visual acuity had dropped from 20/20 to hand motions. Our novel bimanual technique helped secure infusion safely for vitrectomy. The patient recovered well to a visual acuity of 20/60 with a good anatomical outcome. Early vitrectomy may be essential for ensuring optimal outcomes in certain eyes with endophthalmitis. Surgical intervention in eyes with keratoprosthesis with secondary endophthalmitis is challenging due to difficulties in visualization. This was overcome in this case with a novel bimanual chandelier-assisted technique for securing infusion.

Ocular Manifestations of ROSAH Syndrome Caused by Different Mutations of the ALPK1 Gene.

This article explains “Applied Medi-Brain Energy-Tronic Treatment Method” for the Medical Treatments of SMA – Spinal Muscular Atrophy Disease, Paralyzed Patients, ALS patients, MPS, SSPE, DMD Patients with the Biomechanical Analysis of Bionic Prosthetic Robotic Artificial Hand Design.For many people, artificial limbs are devices that replace a lost organ or limb. The purpose of artificial limbs is to replace the lost limb and perform functions in daily life and increase the individual's quality of life. These limbs use advanced mechanisms, sensors and motors to mimic natural limbs. While traditional prosthetics often offer limited flexibility and functionality, artificial limbs are becoming more personalized, functional and aesthetically better thanks to 3D printers.The design to be discussed in this project will be an artificial hand prototype produced with PLA filament using 3D printers. The artificial hand design will aim to fulfill basic functions such as independent movement of the fingers, holding and grasping in a way that will comply with the biomechanical structure of the human hand.This “Applied Medi-Brain Energy-Tronic Treatment Method” is completely original and unique to the corresponding author of this article, Emin Taner ELMAS and then the system is integrated with the “Applied Medi-Brain Energy-Tronic Treatment Method”. This “Applied Medi-Brain Energy-Tronic Treatment Method” is not a treatment that has been applied so far, it was invented, first thought and designed by the author of this article, Emin Taner ELMAS, and can be put into practice with step-by-step development stages. The project contains the theory of a method tried to be developed that can treat SMA (Spinal Muscular Atrophy)disease and other similar neurological diseases. In the study, brain data will be examined with a 14-channel EEG Electroencephalography device. With this device, the signals in the brain will be examined and these signals will be transmitted to the patients’ muscles. Many physical and sensory functions cannot be performed in SMA patients. Coughing, swallowing, breathing, chewing, walking, hand, arm, leg and other muscle movements cannot occur. With this EEG device, the signals in the brain will be able to be seen as waves. By means of the special software of EEG device it is possible to manipulate the cube on the computer screen just by brain thinking and it is possible to simulate facial movements and facial expressions on the computer screen, as well.

The analysis of musculoskeletal system movements using electromyography (EMG) signals is a fundamental requirement in fields such as prosthetic control, human-machine interaction, and neuromuscular rehabilitation. This study presents a comprehensive approach that not only evaluates movement recognition accuracy but also quantitatively assesses the level of muscle force required for each movement. In the study, the muscle loading profile of each hand movement was created using EMG signal energy normalized to the Rest state. Five different classifier models were compared under 5-fold cross-validation (CV) and Leave-One-Subject-Out (LOSO) protocols. The results showed that the Extension movement had the highest normalized power value and that classification accuracy reached its highest level with SVM-RBF (86.95%). Furthermore, Out-of-Bag (OOB) error analysis revealed that the model converged stably around 600–800 trees, while accuracy differences between individuals were attributed to physiological variations. The proposed framework offers a new evaluation perspective for both ergonomic task design and clinical performance monitoring by assessing gesture recognition performance alongside muscle strength requirements.

BackgroundAccurate and objective assessment of motor performance is critical for effective stroke rehabilitation. While wrist-worn accelerometers are widely accepted as a valid tool for evaluating upper-limb motor performance, they primarily capture arm and forearm movements, overlooking hand and finger activity. This limitation reduces their ability to detect changes in distal function, hindering the broader integration of wearable-based motor performance metrics into clinical practice.ObjectiveTo determine whether finger-worn accelerometers, which capture both proximal and distal movements of the upper limbs, offer a more comprehensive assessment of motor performance by comparing their convergent validity with that of wrist-worn accelerometers.MethodsBilateral accelerometer data were collected from 24 stroke survivors using finger-worn and wrist-worn devices as they performed unscripted daily activities in a simulated home environment. Motor performance metrics from both sensor locations were analyzed for correlations with the Fugl-Meyer Assessment for Upper Extremity (FMA-UE) and sensitivity to differences in motor performance across impairment levels.ResultsFinger-worn accelerometer metrics showed stronger correlations with FMA-UE scores than those from wrist-worn sensors, largely due to their ability to capture fine hand movements. Additionally, finger-worn sensors demonstrated greater sensitivity in detecting performance differences between mildly and moderately impaired individuals.ConclusionsBy capturing both proximal and distal movements, finger-worn accelerometers demonstrate stronger convergent validity with standardized measures of post-stroke motor impairment compared to wrist-worn accelerometers. These findings highlight their potential for providing a more comprehensive assessment of motor performance in stroke survivors.

Mixed mechanism glaucoma occurs when secondary causes contribute to glaucoma in an eye with preexisting primary open-angle glaucoma (POAG) or primary angle-closure glaucoma. This study highlights its diagnostic and management challenges. A 63-year-old female presented with blurry vision and right eye pain for 2 months. She had undergone cataract surgery in the right eye 6 months earlier and developed elevated intraocular pressure (IOP) afterward. Her visual acuity in the right eye was hand movements, and IOP was 34 mmHg despite medications. Examination revealed signs of uveitis, leading to a diagnosis of secondary glaucoma. A glaucoma drainage device (GDD) was implanted, successfully controlling IOP. Follow-up revealed POAG signs in the left eye, prompting a revised diagnosis of mixed mechanism glaucoma in the right eye. GDD implantation was effective, but continued monitoring remained essential to maintain the target IOP.

Abstract - The loss of an upper limb significantly affects an individual’s daily functioning, independence, and overall quality of life. Modern prosthetic hands aim to restore these capabilities, yet conventional solutions remain expensive, complex, and inaccessible for many users. This project presents the development of a low-cost, customizable 3D Printed EMG-Controlled Prosthetic Hand that utilizes surface electromyography (sEMG) signals to interpret user intent and generate intuitive hand movements. By integrating affordable 3D printing materials, Arduino-based control electronics, servo actuation, and EMG signal processing, the proposed system enables responsive and natural hand functionality such as grasping and releasing. The prosthetic is lightweight, modular, and easy to fabricate, offering significant advantages for rehabilitation, research, and resource-limited environments. This work demonstrates a practical approach to bridging mechanical design and biomedical signal interpretation, providing a scalable and accessible prosthetic solution that enhances user comfort. Key Words: Electromyography(EMG), sEMG signal processing, Servo actuation, Arduino microcontroller, Biomedical Engineering, Myoelectric control

Hand gestures are essential in human communication, and recent technological advancements aim to extend this natural interaction to human-computer interfaces. This paper introduces a real-time volume control system that enables users to adjust sound levels using hand gestures, eliminating the need for physical components. The system relies on a standard computer camera to detect and interpret finger patterns, using MediaPipe to identify hand landmarks and OpenCV in Python to analyze live video frames. By calculating the distance between fingers, the system adjusts the volume through pycaw, offering a full range from minimum to maximum. A key innovation is its ability to address two major challenges: first, compensating for varying hand-camera distances (ranging from 40 to 300 cm), and second, defining a specific pattern of fingers to ensure only intentional gestures affect volume control. This prevents unintended hand movements from interfering with system operation. The gesture recognition process is enhanced through a set of algorithms that refine detection and improve reliability. With an impressive accuracy of 97.3%, the proposed system demonstrates the potential of gesture-based control in real-time applications, offering a seamless and intuitive user experience. It represents a significant step toward more natural and efficient human-machine interaction.

Radar-based hand motion recognition (HMR) presents several challenges, including sensor interference, clutter, and the limitations of small datasets, which collectively hinder the performance and real-time deployment of deep learning (DL) models. To address these issues, this paper introduces a novel real-time HMR framework that integrates advanced signal pre-processing, a hybrid convolutional neural network–support vector machine (CNN–SVM) architecture, and efficient hardware deployment. The pre-processing pipeline applies filtration, squared absolute value computation, and normalization to enhance radar data quality. To improve the robustness of DL models against noise and clutter, time-series radar signals are transformed into binarized images, providing a compact and discriminative representation for learning. A hybrid CNN-SVM model is then utilized for hand motion classification. The proposed model achieves a high classification accuracy of 98.91%, validating the quality of the extracted features and the efficiency of the proposed design. Additionally, it reduces the number of model parameters by approximately 66% relative to the most accurate recurrent baseline (CNN–GRU–SVM) and by up to 86% relative to CNN–BiLSTM–SVM, while achieving the highest SVM test accuracy of 92.79% across all CNN–RNN variants that use the same binarized radar images. For deployment, the model is quantized and implemented on two System-on-Chip (SoC) FPGA platforms—the Xilinx Zynq ZCU102 Evaluation Kit and the Xilinx Kria KR260 Robotics Starter Kit—using the Vitis AI toolchain. The system achieves end-to-end accuracies of 96.13% (ZCU102) and 95.42% (KR260). On the ZCU102, the system achieved a 70% reduction in execution time and a 74% improvement in throughput compared to the PC-based implementation. On the KR260, it achieved a 52% reduction in execution time and a 10% improvement in throughput relative to the same PC baseline. Both implementations exhibited minimal accuracy degradation relative to a PC-based setup—approximately 1% on ZCU102 and 2% on KR260. These results confirm the framework’s suitability for real-time, accurate, and resource-efficient radar-based hand motion recognition across diverse embedded environments.

A creative mechatronic device named the Gesture Controlled Robot uses an Accelerometer Sensor to control the robot's movement through natural hand motions. This project uses an MPU6050 sensor to detect the direction and movement of the user's hand instead of regular buttons or remote controls. A receiver attached to the robot gets the sensor data wirelessly using a Bluetooth (HC-05) module. The receiver then translates these signals and uses an Arduino microcontroller along with an L298N motor driver to move the motors correctly. The robot can easily follow real-time gestures because it can create commands like moving forward, backward, left, right, or stopping when the user tilts their hand in different directions. This system can serve as a starting point for making automated devices, assistive robots, and touchless control systems. It also shows how sensor technology, wireless communication, and embedded systems can be used together to build a robot control system that is quick to respond, low-cost, and simple to use.

Advances in robotic technology for hand rehabilitation, particularly soft robotic gloves, have significant potential to improve patient outcomes. While vision-based algorithms pave the way for fast and convenient hand pose estimation, most current models struggle to accurately track hand movements when soft robotic gloves are used, primarily due to severe occlusion. This limitation reduces the applicability of soft robotic gloves in digital and remote rehabilitation assessment. Furthermore, traditional clinical assessments like the Fugl-Meyer Assessment (FMA) rely on manual measurements and subjective scoring scales, lacking the efficiency and quantitative accuracy needed to monitor hand function recovery in data-driven personalised rehabilitation. Consequently, few integrated evaluation systems provide reliable quantitative assessments. In this work, we propose an RGB-based evaluation system for soft robotic glove applications, which is aimed at bridging these gaps in assessing hand function. By incorporating the Hand Mesh Reconstruction (HaMeR) model fine-tuned with motion capture data, our hand estimation framework overcomes occlusion and enables accurate continuous tracking of hand movements with reduced errors. The resulting functional metrics include conventional clinical benchmarks such as the mean per joint angle error (MPJAE) and range of motion (ROM), providing quantitative, consistent measures of rehabilitation progress and achieving tracking errors lower than 10°. In addition, we introduce adapted benchmarks such as the angle percentage of correct keypoints (APCK), mean per joint angular velocity error (MPJAVE) and angular spectral arc length (SPARC) error to characterise movement stability and smoothness. This extensible and adaptable solution demonstrates the potential of vision-based systems for future clinical and home-based rehabilitation assessment.

BackgroundAlzheimer's disease (AD) and other dementias pose a significant global challenge, with a projected substantial increase in prevalence over the coming decades (JANNATI, 2024). Early detection of AD, particularly during the preclinical stage, is crucial for implementing effective interventions to slow disease progression (ALTY, 2024). However, traditional cognitive assessment methods, such as the Mini‐Mental State Examination (MMSE), have notable limitations, including low sensitivity to mild cognitive changes and susceptibility to demographic factors like age and education level (ALTY, 2022). Furthermore, these tests are often time‐consuming and require specialized training for administration (JANNATI, 2024). These challenges underscore the urgent need for more sensitive, rapid, and accessible tools for dementia screening, particularly in primary care settings (ALTY, 2024).MethodThis analysis reviewed three studies published within the past five years, retrieved from the Medline database, focusing on novel approaches for early detection of AD. The first study evaluated the efficacy of the Digital Clock and Recall (DCR) test compared to the MMSE in identifying mild cognitive impairment (MCI) and early dementia. The second study investigated TapTalk, a smartphone‐based test that combines hand movement and speech analysis with blood biomarkers such as p‐tau181 to assess preclinical AD risk. The third study validated the TAS Test, an online tool that integrates motor‐cognitive functions and correlates them with p‐tau181 levels to classify preclinical AD risk.ResultThe studies revealed promising results. The DCR demonstrated higher accuracy and sensitivity than the MMSE in detecting MCI, requiring less than three minutes to administer and being less influenced by demographic factors. TapTalk identified hand movement and speech patterns associated with preclinical AD risk, showing potential as a non‐invasive and accessible tool. The TAS Test effectively detected subtle motor changes that may precede cognitive symptoms, highlighting its usefulness in early AD stages.ConclusionThese studies emphasize the potential of digital assessments and biomarkers as innovative, sensitive, and accessible methods for early detection of AD. Their large‐scale application could transform dementia screening and enable earlier, more effective interventions, particularly in primary care settings.