Traditional Human-Machine Interfaces (HMIs), such as keyboards and mice, have long facilitated efficient digital communication through hand movements. To address this limitation, electromyography (EMG)-based interfaces offer intuitive control through muscle activity with high signal amplitude and ease of acquisition. This study proposes an EMG-based Chunjiin speller system designed for users with limited hand mobility. The system incorporates a directional input method (up, down, left, right, and select) and a Korean keyboard layout to support accessible and efficient character input. EMG signals were collected using four surface electrodes attached to the extensor digitorum and flexor carpi radialis muscles on both forearms. After real-time preprocessing, three time-domain features-root mean square, slope sign change, and peak amplitude-were extracted to determine user intent. In Experiment 1, five discrete input commands were classified with an average accuracy of 94.67%. In Experiment 2, which involved continuous input for actual word construction, the system maintained an average accuracy of 93.87%. Notably, these performances were achieved without the use of deep learning models, relying solely on simple time-domain features, making it viable for real-time use in low-resource environments. The proposed system demonstrates practical usability and real-time performance, highlighting its potential for augmentative and alternative communication (AAC) applications. Its lightweight architecture and direction-based design further support flexible deployment for users with motor impairments across diverse contexts.

This study aims to compare the muscle activity of the lower limbs between barefoot and shod walking and to classify the two walking conditions using a machine learning approach. Walking is a fundamental human activity, and muscle activation patterns can vary depending on external conditions such as footwear. Despite the abundance of studies comparing different types of shoes, there is a lack of research focusing on quantitative differences between barefoot and shod walking. In this study, surface electromyography (sEMG) signals were collected from four lower limb muscles (Tibialis Anterior, Rectus Femoris, Vastus Medialis, and Medial Gastrocnemius) from five healthy young adults while they walked under both barefoot and shod conditions. The sEMG signals were preprocessed, segmented using gait event markers, and then analyzed to extract time-domain features including Root Mean Square (RMS), Mean Absolute Value (MAV), Waveform Length (WL), and Variance (VAR). A Random Forest classifier was then trained to distinguish between the two walking conditions. The results showed distinct differences in muscle activation patterns between the two conditions, and the classification model achieved an accuracy of approximately 95%. These findings suggest that machine learning models based on sEMG features can effectively differentiate gait conditions and may contribute to future personalized gait assessment and footwear evaluation systems.

This study investigates the fatigue properties of CoCrMo alloy for the durability evaluation of tibial components in orthopedic implants. Mechanical and fatigue tests were conducted in accordance with ASTM E8 and E606 standards, yielding key material properties such as an average elastic modulus of 234,338 MPa, a yield strength of 947 MPa, and an ultimate tensile strength of 1,230 MPa. These values were applied to finite element analysis (FEA) to predict fatigue life, utilizing a strain-based E-N curve derived from low-cycle fatigue tests. To ensure accuracy, FEA results were validated against physical test data, with the strain prediction error maintained within 1.1%, satisfying the ±5% tolerance recommended by ASME V&V 40. Furthermore, the tibial component withstood 10 million cycles under 900 N load in both physical and simulated fatigue tests, demonstrating sufficient fatigue durability. This study confirms that the experimentally derived mechanical properties of CoCrMo alloy can reliably predict the in vivo mechanical behavior of tibial components, and that validated FEA can effectively complement physical testing. These results provide valuable data for medical device design, structural validation, and regulatory approval processes, enhancing efficiency and credibility in orthopedic implant development.

The regulatory approval process for the manufacture, export, and import of medical devices mandates a series of procedures determined by device classification. Among these, the clinical trial phase is pivotal for demonstrating the safety and efficacy of the medical device. In particular, the thorough preparation of a clinical trial protocol at the initial stage is essential for facilitating the overall procedures and plays a key role in minimizing unnecessary time and cost expenditures during subsequent regulatory processes. Consequently, effective protocol preparation is a critical component in medical device development. However, practitioners in the field often face significant challenges due to the need to comply with evolving regulations and the limited accessibility of up-to-date clinical trial protocol examples. While various support services have been introduced to address these issues, they frequently fall short in providing immediate and practical assistance. This study developed and evaluated MEDIVA (MEDical Investigation Validation Assistant), a Retrieval-Augmented Generation (RAG)-based Large Language Model (LLM) tool designed to support the drafting of clinical trial protocols. The comparative analysis of completions generated by MEDIVA and a standard LLM lacking RAG capabilities based on pre-selected 4 representative questions likely to be encountered during protocol development demonstrated that MEDIVA provides more precise, actionable guidance through factually accurate and hallucination-free responses. It also delivers specific and consistent responses grounded in the latest regulatory information. The developed system is expected to extend its utility beyond protocol drafting, ultimately strengthening regulatory compliance capabilities, which are essential for the advancement of the medical device industry.

Aortic aneurysms, caused by abnormal expansion of the aortic wall, pose critical risks upon rupture. Circular stapler anastomosis offers a faster and safer alternative to suturing. This study evaluates leakage risk and fixation strength in aortic graft circular stapler anastomosis using finite element analysis (FEA). A simplified FEA model was developed and validated using existing leakage pressure data. Key parameters, including inter-row distance, triple-row structure and triple-row spacing were analyzed. The Factor of Safety (FoS) was defined to quantitatively compare leakage risks under varying conditions. The inter-row distance critically influenced leakage risk, with wider gaps increasing leakage likelihood. Conversely, the triple-row structure significantly enhanced fixation strength, reducing leakage risk. Internal spacing within the triple-row exhibited minimal sensitivity. This study establishes a design framework for safer and more effective aortic graft circular stapler anastomosis. Findings provide foundational data for optimizing design and assessing leakage risk.