The dental chair is essential equipment that positions patients for dentists to provide stable treatment. Particularly in cases of prolonged procedures, patient satisfaction with comfort becomes a crucial factor, often more significant than the performance of the medical device itself. However, there is a notable lack of domestic research focusing on user comfort satisfaction with dental chairs in Korea, as the development of these chairs has traditionally prioritized performance. Therefore, this study excludes performance evaluation and instead focuses solely on assessing comfort. A comparative analysis is conducted between conventional dental chair seats and newly developed seats, using both quantitative and qualitative assessments. Additionally, the correlation and statistical significance between the results are analyzed. The findings suggest that the development of a new chair seat with higher comfort and satisfaction levels could contribute to creating a more comfortable treatment environment for patients undergoing procedures on such seats.

Spiking Neural Networks (SNNs), inspired by the structure and efficiency of biological neural systems, are emerging as a powerful alternative to traditional artificial neural networks, especially in low-power and real-time processing applications. SNNs process information through discrete spikes, mimicking the temporal dynamics of biological neurons, which results in improved energy efficiency and computational effectiveness. This study proposes a novel dynamic temporal latency encoding method that adjusts spike timing based on input intensity through a tunable hyperparameter, allowing for enhanced accuracy and adaptability. The method was evaluated on MNIST and TIDIGITS datasets, achieving remarkable accuracy rates of 99.12% and 100%, respectively, surpassing traditional encoding approaches. Additionally, experiments conducted on the Caltech101 dataset, which includes images of varying resolutions, demonstrated the robustness and generalizability of the proposed encoding strategy. By optimizing the temporal characteristics of spike generation, this method effectively balances computational efficiency and accuracy, making it particularly suitable for neuromorphic applications that demand real-time, high-accuracy performance. These findings underscore the potential of dynamic temporal latency encoding in advancing the capabilities of SNNs for practical, energy-efficient tasks in the rapidly evolving field of neuromorphic computing.

Accurate recognition of user intentions in Human-Machine Interfaces (HMIs) for assistive robots, such as prosthetic hands, is crucial for user-friendly control. Surface electromyography (sEMG)-based HMIs offer great potential due to their non-invasive nature and ability to classify gestures with high accuracy using artificial intelligence-based pattern recognition. While considerable research has been conducted on classifying grasping postures, studies focusing on in-hand manipulation, the ability to rearrange objects within the hand, and thumb palpation, the process to identify object properties through thumb movements, remain limited. Prior studies have attempted to classify in-hand manipulation and thumb movements using sEMG. However, these studies either utilized both extrinsic forearm muscles and intrinsic hand muscles or employed high-density sEMG instead of commercial sEMG, making them unsuitable as generalizable methods for intention recognition in prosthetic control for amputees. This study proposes a ResNet-based model to classify 10 primitives for in-hand manipulation and thumb palpation using eight-channel sEMG from extrinsic forearm muscles. The model achieved an accuracy of over 87% for seven subjects and maintained an accuracy of over 75% through fine-tuning based user-specific calibration. These results demonstrate that the model can maintain high accuracy under electrode reattachment through fine-tuning. In conclusion, the proposed model utilized signals exclusively from forearm muscles through commercially available sEMG and demonstrated high classification accuracy exceeding 87.26% through user-specific calibration. This confirms its potential as a generalizable intention recognition system for in-hand manipulation.

Urethral stricture is a disease in which the diameter of the urethral lumen narrows as a result of chronic inflammation of the scarring of the urethral epithelium or corpus cavernosum. Treatment of urethral stricture has a high recurrence rate, and since a larger area than the stricture area must be incised or dilated during treatment, the area to be treated becomes larger and the recurrence rate increases with repeated treatment and recurrence. Therefore, in order to minimize the recurrence rate, it is necessary to develop a treatment method that can treat with a minimum area. The purpose of the current study is to develop and validate an endoscopic photothermal ablation method for the treatment of urethral strictures through numerical simulations and ex vivo tissue experiments. The 1470 nm wavelength and the radial optical fiber were selected. COMSOL Multiphysics software was used to simulate liver and urethral tissues. Ex vivo liver and urethral tissue experiments were conducted to investigate the extent of ablation area after laser irradiation under different irradiation conditions (25-400 J). The temperature distribution and ablation area in the tissues after the laser irradiation were concentric and uniform. Histologic images showed selective ablation area limited to the epithelial layer and lamina propria. Therefore, the proposed urethral stricture treatment could selectively ablate the urethral tissues under the selected irradiation condition (15 W for 5 s).

Electrocardiograms (ECGs) reflect various cardiac conditions, diseases, and individual characteristics. However, the development of automated ECG signal analysis programs remains challenging due to the presence of diverse types of noise. Consequently, there has been a growing interest in applying deep neural network (DNN) technologies to automate ECG analysis. Existing automated ECG analysis techniques primarily focus on detecting the peak points of P, QRS, and T waves. However, in practical ECG analysis, distinguishing the start and end points of these waveforms (P, QRS, T) is more critical. Such tasks often require additional neural networks, underscoring the need to develop techniques that can reduce the cost and time associated with network development. This study evaluates the ability of neural networks to identify the boundaries of P, QRS, and T waves using the Recognition Score as a performance metric. Six neural networks, each with two hidden layers (h2), were developed and trained over 2000 Epochs to distinguish waveform regions. However, the impact of increasing the number of hidden layers or adjusting the number of training Epochs on recognition performance has not been clearly identified. To address this, the number of hidden layers was increased to four (h4) and eight (h8), and training Epochs were set to 400 and 600 to compare recognition accuracy. For P and T waves, the training data demonstrated improved performance at 600 Epochs compared to 400 Epochs. However, the test data revealed a decrease in recognition accuracy by 13.3% and 1.1%, respectively. Additionally, networks with two hidden layers outperformed those with four and eight hidden layers. Specifically, the recognition performance for P, QRS, and T wave regions was 2.6, 1.2, and 1.4 times higher, respectively, in networks with two hidden layers compared to those with eight hidden layers. The results indicate that neural networks designed to distinguish the regions of P, QRS, and T waves can be effectively trained with a simple structure and fewer training Epochs. This finding suggests that even with the use of multiple neural networks, the development cost and time required for ECG analysis do not increase significantly.

With the implementation of ISO 13485:2016 in Korea, usability evaluation documentation has become a mandatory requirement for GMP audits, leading to increased demand. To ensure the reliability of evaluation processes and minimize operational discrepancies across institutions, this study aims to establish standardized operational guidelines for medical device usability evaluation institutions. This study developed an operational status analysis framework and conducted a survey of 17 domestic medical device usability evaluation institutions to examine their operational practices. Based on the survey findings, standardized operational guidelines for usability evaluation institutions were formulated. The analysis of the operational status of domestic usability evaluation institutions revealed that most institutions have dedicated personnel for usability evaluations, as well as designated evaluation and observation rooms. Based on these findings, proposed operational standards were categorized into three key areas: personnel, facilities, and quality management. For personnel, institutions must employ evaluators and observers, specifying their qualifications and roles. Regarding facilities and equipment, institutions should maintain separate evaluation and observation rooms, storage areas for medical devices, and document archives, while also ensuring proper equipment availability and scheduled maintenance. In terms of quality management, the proposed standards include documentation management practices such as maintaining records in physical archives or secure online servers. By establishing standardized operational guidelines for medical device usability evaluation institutions, this study contributes to enhancing consistency and reliability in usability evaluations. Furthermore, the proposed guidelines are expected to improve the overall quality of the domestic medical device industry and strengthen its global competitiveness.

This study evaluated the effectiveness of the Random Forest (RF) algorithm in classifying walking status using electromyography (sEMG) data. Data were collected from physically healthy men and women in their 20s and were preprocessed by extracting the root mean square (RMS) features in the 6-channel EMG data. The RF model was used to classify the three activities of walking, climbing stairs, and descending stairs, and was trained based on the optimal hyperparameters. As a result of the verification, the average accuracy was 96.48%, and the accuracy in the test data was 96.64%, indicating excellent performance. In particular, the F1 score for each class was analyzed as walking (0.9930), climbing stairs (0.9560), and descending stairs (0.9496). This study proved that the RF algorithm is effective in classifying walking status, and in future studies, we plan to further improve the performance by applying deep learning algorithms such as LSTM and data augmentation techniques. These developments are expected to increase the possibility of application in practical applications such as walking monitoring and rehabilitation training systems for the elderly.

The elastic bands and buttons in patient gowns can affect X-ray image quality depending on their material, potentially reducing diagnostic accuracy. However, many medical institutions prioritize cost and efficiency over material considerations when selecting patient gowns. Moreover, previous studies have primarily focused on fabric, with limited research on elastic bands and buttons. This study quantitatively evaluated the effects of eight types of elastic band materials and four types of synthetic plastic polyester buttons on X-ray image quality. Using a PBU-60 phantom, 270 images were acquired for the elastic band dataset under Abdomen AP, L-Spine AP, and Pelvis AP conditions, while 520 images were obtained for the button dataset under Chest PA, Chest AP, Rib AP, and T-Spine AP conditions. Image analysis was conducted using ImageJ to define regions of interest (ROIs) and measure mean brightness, followed by statistical analysis using SPSS. The results showed that among the elastic band materials, nylon had the least impact on X-ray images, whereas wool had the most significant effect. For buttons, all synthetic plastic polyester materials were found to degrade image quality. In conclusion, nylon is the most suitable material for elastic bands, while wool should be avoided. Additionally, synthetic plastic polyester buttons should be repositioned or removed before imaging, depending on the examination site.