• Journal of the Korean Society for Precision Engineering
• /
• v.2 no.1
• /
• pp.33-40
• /
• 1985

의료의 고도화를 위해서는 각종 생체현상의 계측기술이 중요시된다. 그림1과 같은 생체현상의 계측과 감시를 위한 계통도에서와 같이 생체에서 얻어지는 정보를 바르게 계측하여 평가하기 위해서는 앞에서 기술한 생체의 물성에 관한 지식이 필요하다. 다음에 전극, 변환기등의 각종 새로운 센서의 개발이 중요하며, 그리고서 얻어지는 데이터를 증폭하여 전송하는 기술과 데이터를 처리하여 표시하거나 기록하는 방법도 중요하다. 지금까지는 측정이 불가능하다고 생각되어진 것들을 가능하게 하기 위한 새로운 센서의 개발과 정성적으로만 측정되었던 것들까지도 정량적으로 측정되는 새로운 계측시스템이 고안되어 비관혈계측의 경향으로 연구되고 있다. 이들 센서들 중에는 생체의 활동전위를 검출하는 전극과, 활동전위 이외의 일반생체현상을 변환기(transducer)를 이용하여 전기신호로 변환하여 검출하는 센서가 있다.

• 전기의세계
• /
• v.33 no.7
• /
• pp.412-418
• /
• 1984

의용생체공학의 한분야인 재활공학의 많은 발전으로 상실된 인간의 사지기관의 일부는 거의 자연스런 기능을 갖는 장치로 대치할 수 있는 가능성이 높아지고 있으며, 일한 연구의 결과는 산업용 로보트의 개발에도 기여를 하고 있다. 그중에서도 핵심이 되고 있는 것이 근전도신호를 이용한 보철제어(Prosthesis Control)에 관한 연구이다. 근전도신호가 인공팔제어에 이용된 것은 1950년대 초 소련에서 처음 시도되었고 그후 유럽, 카나다 미국등에서 계속 이에 관한 연구가 성과를 나타내고 있다. 근전도 신호를 제어신호로 사용할 경우 가장 큰 문제점은 근전도신호의 저주파 잡음인데, 실제로 비례제어신호를 얻기위하여는 이 잡음이 제거되어야 한다. 그러므로 여기에서는 근전도신호 처리방법에 대한 개략적인 것을 소개하고, 잡음의 제거방법등을 검토해 보고자 한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.6
• /
• pp.1141-1149
• /
• 2007

This paper describes two major techniques; image processing and gas vent insert and rejection control, for efficient gas vent exchange and holes detecting on the shoes mold. The key idea is to detect holes on the mold to select which holes to insert and to reject automatically guide center of hole's position. This allows us to save labor time while minimizing defective rate of PU shoes mold forming and production costs for gas vent exchange such as insertion and rejection.. Our experimental results have demonstrated that the hole's detection and gasvent exchange mechanism are more efficient and provide accurate mechanism to mitigate risks of vent injection/rejection failures.

• Journal of Biomedical Engineering Research
• /
• v.41 no.6
• /
• pp.219-227
• /
• 2020

In this study, we tried to quantify the actual cross-sectional area inside the bore when scanning by the MRI system with various bore sizes. To this end, a comparative analysis was conducted by both of blueprint of each MRI equipment and actual measurement in the field. As a result of analysis, ACSA(Actual Cross-Sectional Area) in Ingenia CX, Elition X, uMR 780, Omega, Vida, Lumina, Architect, Premier is recorded as 171230, 232150, 242100, 309332, 230760, 230760, 229380 and 235990 ㎟, respectively ACSA% was 60.6, 60.3, 73.0, 70.0, 60.0, 60.0, 59.6, and 61,3%. In addition, DTB (Distance from Table top to Bore top) recorded 400, 407, 445, 495, 405, 405, 405, 403, and 412 mm. Through this study, it was confirmed that there is a difference between the bore size according to each MRI system and the actual cross-sectional area during MRI scanning. Accordingly, if we consider the internal actual area just not bore size at the clinical site, useful diagnostic images can be obtained in the end with better convenience.

• Journal of Biomedical Engineering Research
• /
• v.44 no.4
• /
• pp.255-263
• /
• 2023

Clinical ultrasound (US) is a widely used imaging modality with various clinical applications. However, capturing a large field of view often requires specialized transducers which have limitations for specific clinical scenarios. Panoramic imaging offers an alternative approach by sequentially aligning image sections acquired from freehand sweeps using a standard transducer. To reconstruct a 3D volume from these 2D sections, an external device can be employed to track the transducer's motion accurately. However, the presence of optical or electrical interferences in a clinical setting often leads to incorrect measurements from such sensors. In this paper, we propose a deep learning (DL) framework that enables the prediction of scan trajectories using only US data, eliminating the need for an external tracking device. Our approach incorporates diverse data types, including correlation volume, optical flow, B-mode images, and rawer data (IQ data). We develop a DL network capable of effectively handling these data types and introduce an attention technique to emphasize crucial local areas for precise trajectory prediction. Through extensive experimentation, we demonstrate the superiority of our proposed method over other DL-based approaches in terms of long trajectory prediction performance. Our findings highlight the potential of employing DL techniques for trajectory estimation in clinical ultrasound, offering a promising alternative for panoramic imaging.

• Journal of Biomedical Engineering Research
• /
• v.44 no.6
• /
• pp.384-391
• /
• 2023

Among the elderly, fatal injuries and deaths are significantly attributed to falls. Therefore, a pre-impact fall detection system is necessary for injury prevention. In this study, a robust threshold-based algorithm was proposed for pre-impact fall detection, reducing false positives in highly dynamic daily-living movements. The algorithm was validated using public datasets (KFall and FARSEEING) that include the real-world elderly fall. A 6-axis IMU sensor (Movella Dot, Movella, Netherlands) was attached to S2 of 20 healthy adults (aged 22.0±1.9years, height 164.9±5.9cm, weight 61.4±17.1kg) to measure 14 activities of daily living and 11 fall movements at a sampling frequency of 60Hz. A 5Hz low-pass filter was applied to the IMU data to remove high-frequency noise. Sum vector magnitude of acceleration and angular velocity, roll, pitch, and vertical velocity were extracted as feature vector. The proposed algorithm showed an accuracy 98.3%, a sensitivity 100%, a specificity 97.0%, and an average lead-time 311±99ms with our experimental data. When evaluated using the KFall public dataset, an accuracy in adult data improved to 99.5% compared to recent studies, and for the elderly data, a specificity of 100% was achieved. When evaluated using FARSEEING real-world elderly fall data without separate segmentation, it showed a sensitivity of 71.4% (5/7).

• Journal of Biomedical Engineering Research
• /
• v.40 no.2
• /
• pp.55-61
• /
• 2019

Recently, various researches on materials and equipment have been actively conducted to overcome the limitations of conventional output methods due to the increase of diversity of 3D printing materials and to adopt an output method suitable for the characteristics of each material. As the range applicable to outputable materials is expanded, manufacturing of medical devices applied to patients is in a more rapid growth trend than other fields. In this study, we investigated the suitable materials for fabricating 3D printer using photocurable resin. As a result, one suitable material was selected through biological safety experiment and thermal stability experiment. Next, to optimize the output of the selected materials, we have developed a system that optimizes the equipment according to the characteristics of the material. The results of this study enabled the implementation of personalized medical implants that could not be made from 3D printer dependent materials, thereby overcoming the limitations of existing 3D printer output conditions and dedicated materials.

• Journal of Biomedical Engineering Research
• /
• v.42 no.3
• /
• pp.116-124
• /
• 2021

It is important to differentiate between the target tissue (or organ) and the rest of the tissue before incision during surgery. And when it is necessary to preserve the differentiated tissues, the blood vessels connected to the tissue must be preserved together. Various non-invasive medical imaging methods have been developed for this purpose. We aimed to develop a medical imaging system that can simultaneously apply fluorescence imaging using indocyanine green (ICG) and laser speckle contrast imaging (LSCI) using laser speckle patterns. We designed to collect images directed to the two cameras on a co-axial optical path and to compensate equal optical path length for two optical designs. The light source used for fluorescence and LSCI the same 785 nm wavelength. This system outputs real-time images and is designed to intuitively distinguish target tissues or blood vessels. This system outputs LSCI images up to 37 fps through parallel processing. Fluorescence for ICG and blood flow in animal models were observed throughout the experiment.

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.186-192
• /
• 2021

In this paper, we evaluated prediction accuracy of Euler angle spectrograph classification method using a convolutional neural networks (CNN) for hand gesture recognition in augmented reality (AR) cognitive rehabilitation system based on Leap Motion Controller (LMC). Hand gesture recognition methods using a conventional support vector machine (SVM) show 91.3% accuracy in multiple motions. In this paper, five hand gestures ("Promise", "Bunny", "Close", "Victory", and "Thumb") are selected and measured 100 times for testing the utility of spectral classification techniques. Validation results for the five hand gestures were able to be correctly predicted 100% of the time, indicating superior recognition accuracy than those of conventional SVM methods. The hand motion recognition using CNN meant to be applied more useful to AR cognitive rehabilitation training systems based on LMC than sign language recognition using SVM.

• Journal of the Korean Society of Radiology
• /
• v.83 no.6
• /
• pp.1208-1218
• /
• 2022

In the medical field, artificial intelligence has been used in various ways with many developments. However, most artificial intelligence technologies are developed so that one model can perform only one task, which is a limitation in designing the complex reading process of doctors with artificial intelligence. Multi-task learning is an optimal way to overcome the limitations of single-task learning methods. Multi-task learning can create a model that is efficient and advantageous for generalization by simultaneously integrating various tasks into one model. This study investigated the concepts, types, and similar concepts as multi-task learning, and examined the status and future possibilities of multi-task learning in the medical research.