• 농촌계획
• /
• 제20권2호
• /
• pp.81-90
• /
• 2014

This study was carried out to identify the limitations and problems of organization, as well as present plans to activate the organization through diagnosis on 'My Hometown Keeper' organization that was created for the purpose of growth of agricultural and fishing regions, and environment improvement. Utilizing Weisbord's Six-box Model, an organization diagnosis model useful for diagnosis of 'My Hometown Keeper' organization, 6 areas including organization's objective, structure, relationship, compensation system, leadership, subsidiary device system etc. and 14 survey questions were prepared, and a survey investigation was conducted on the staff at Korea Rural Community Corporation in charge of 'My Hometown Keeper' participating residents and administrative support. Based on the analysis results of survey investigation, the limitations and problems of organization were identified, and as plans to improve these and activate 'My Hometown Keeper' organization, 'Clear establishment of organization's objective and role', 'Preparation of compensation and incentive system', 'Growth of relationship and leadership between constituents' 'Enhancing the utilization of subsidiary device system such as education and information acquisition etc.' etc. were presented.

• 사상체질의학회지
• /
• 제29권1호
• /
• pp.29-39
• /
• 2017

Objectives Facial features can be utilized as an indicator of Korean medical diagnosis. They are often measured by using the diagnostic device for an objective diagnosis. Accordingly, it is necessary to verify the reliability of the features which are obtained from the device for the accurate diagnosis. In this study, we attempt to evaluate the repeatability of facial feature variables using the Sasang Constitutional Analysis Tool(SCAT) for the Sasang Constitutional face diagnosis. Methods Facial pictures of two subjects were taken 24 times respectively for two days according to a standard guideline. In order to evaluate the repeatability, the coefficient of variation was calculated for the facial features extracted from frontal and profile images. Results The coefficient of variation was less than 10% in most of the facial features except the upper lip, trichion, and chins related features. Conclusions It was confirmed that the coefficient of variation was small in most of the features which enables the objective and reliable analysis of face. However, some features showed the low reliability because the location of facial landmarks related to them is ambiguous. In order to solve the problem, a clear basis for the location discussion is required.

• 전기학회논문지
• /
• 제56권4호
• /
• pp.724-729
• /
• 2007

In this paper, we propose a new diagnosis method of DC/DC converter aging. The method is based on variations of the parasitic resistor for the aging process. We apply an on-line diagnosis of the DC/DC converter because the observation is not a device, but a system. This study proposes a method of DC/DC converter diagnosis by analyzing the variations of model on the variations of parasitic resistor.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2012년도 춘계학술대회 논문집
• /
• pp.515-516
• /
• 2012

• 대한임베디드공학회논문지
• /
• 제19권3호
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• 동의생리병리학회지
• /
• 제28권6호
• /
• pp.662-667
• /
• 2014

The purpose of this clinical study is to develop structured clinical trial protocol and guideline for improvement of safety, useful and effective of pulse diagnosis devices. As a first step, papers on pulse diagnosis and pulse diagnosis devices from 2001 and 2013 were systematically reviewed. In the next step, we have collected the opinions from the specialists, companies, and statistician in pulse diagnosis to evaluate the current condition, the state and problem of domestic clinical trial cases of pulse diagnosis device. And we have to created protocol and case report form (CRF) in regards to site condition and characteristics of pulse diagnosis devices, and showed the guideline of eligibility criteria, operation process, investigation items, evaluation items and so on. This clinical protocol will become a basic information for a researcher in designing or performing a clinical study of pulse diagnosis devices, and be used as a useful material during acquisition of good clinical data. Furthermore, we hope to enhance the invigoration of pulse diagnosis clinical trials and the performance improvement of pulse diagnosis devices.

• 동의생리병리학회지
• /
• 제26권5호
• /
• pp.621-629
• /
• 2012

This study aimed to examine the possibility of data from pulse diagnosis device to be used for diagnosis of Sasang constitution. Systematic searches of 5 major Korean medical database were conducted for articles published up to May 2012. Searching key word was "Sasang" or "Constitution". Studies dealt with correlation between Sasang constitution and the pulse wave data from pulse diagnosis machine were included. Totally 2886 studies are searched and 3 studies are added from references of evaluated articles. Among them, 12 studies were met our inclusion criteria (2 Xishu Mac, 2 Self-made pulse diagnosis machine, 8 3D-Mac). Three of the eight 3D-Mac studies intended to develop a formula of constitutional differential diagnosis, 2 studies compared variables by Sasang constitution in healthy group and 3 studies compared variables by Sasang constitution in healthy group and special disease group. They all reported some significant variables, however results are not consistent between studies. The accuracy of the formula of constitutional differential diagnosis using 3D-Mac pulse diagnosis devices is 46.0% by now. Improvements in measuring pulse are required to achieve more accurate result and be used for diagnosis of Sasang constitution. Compensating B.M.I. among Sasang constitutional groups and separating constitutional pulse factors from acquired characteristics are also needed in further study.

• 사상체질의학회지
• /
• 제22권4호
• /
• pp.20-29
• /
• 2010

1. Objectives Our goal is to observe the feasibility of constitution discrimination from computing quantitative roughness index from dynamic friction coefficients and their gradients with the measurement device of skin friction with 3-Axis load cell sensor. 2. Methods In the traditional Korean medicine, skin diagnosis is one of the examination methods to discriminate Sasang constitution since it was known that Tae-eumin has rough skin, and Soyangin has smooth one. It is based on the skin roughness on the back of one's hand for the discrimination. The measurement device of skin friction with 3-axis load cell sensor has been developed in order to provide quantitative skin roughness through dynamic friction coefficients. The effective interval of the coefficients is obtained from the automatic sampling algorithm to use their curvature and slope. Then, Fisher's discriminant function of them makes the discrimination. 3. Results The success rate of extracting the effective interval was about 90% and the discriminant accuracy between Tae-eumin and Soyangin was 70% and 68% for men and women, respectively. The entire methods showed the possibility to distinguish between Tae-eumin and Soyangin by using stochastic properties of roughness index, which can make the entire system to include the measurement, the computation of the roughness index and the discrimination of constitution automatical. 4. Conclusions The measurement device, the automatic sampling algorithm of dynamic friction coefficients and the constitution discrimination algorithm were developed, respectively, and their combination can become the serial and automatic procedure for quantitative and objective skin diagnosis, which mimics the movement of the Oriental medical doctors' skin diagnosis. It can be applied to healthcare as well as the diagnosis of constitution in a u-Health system soon.

• 한국인터넷방송통신학회논문지
• /
• 제18권6호
• /
• pp.187-193
• /
• 2018

국내에서의 전력에 대한 수요는 점진적으로 증가하고 있는 추세이다. 수요에 대응하기 위한 발전소는 기능이 다양해지고 효율이 점차 커져야 한다. 발전소 내의 전력 기기에서 사고가 발생하면 막대한 경제적 손실 및 장애를 초래하게 된다. 사고 발생의 원인 중의 하나로서 절연 성능이 저하 된 케이블이 있다. 케이블 사고를 미연에 방지하기 위하여 절연의 상태를 감시하고 확인하여야 한다. 케이블 사고는 연결 부위인 접속에서 발생하는 사고가 대부분을 차지한다. 본 연구와 관련하여 우리는 접속부 상태를 판별하기 위한 장비를 개발하였고, 한국서부발전(주)의 현장에 설치하여 운용 중이다. 본 논문에서는 현장에서 설치 운용 중인 장비에 대한 설명과 더불어 설치 운용된 결과를 통해 케이블의 수명을 예측할 수 있는 고전압 케이블 접속재의 안정적 사용을 위한 온라인 감시진단기법 중에서 사고가 가장 빈번하게 발생하는 접속부에 대해 안정적인 사용을 위한 진단의 정확성과 신뢰성을 향상시키기 위한 연구를 하였다. 이 논문에서 하드웨어 구성을 위주로 우리가 개발한 장비를 소개한다.

• 대한의용생체공학회:의공학회지
• /
• 제42권3호
• /
• pp.125-142
• /
• 2021

The POCT (point-of-care test) sensing that has been a fast-developing field is expected to be a next generation technology in health care. The POCT sensors for the detection of proteins, small molecules and especially nucleic acids have lately attracted considerable attention. According to the World Health Organization (WHO), the POCT methods are required to follow the ASSURED guidelines (Affordable, Sensitive, Specific, User- friendly, Robust and rapid, Equipment-free, Deliverable to all people who need the test). Recently, several CRISPR (Clustered Regularly Interspaced Short Palindromic Repeats) based diagnostic techniques using the sensitive gene recognition function of CRISPR have been reported. CRISPR/Cas (Cas, CRISPR associated protein) systems based detection technology is the most innovative gene analysis technology that is following the ASSURED guidelines. It is being re-emerged as a powerful diagnostic tool that can detect nucleic acids due to its characteristics that enable rapid, sensitive and specific analyses of nucleic acid. The first CRISPR-based diagnosis begins with the discovery of the additional function of Cas13a. The enzymatic cleavage occurs when the conjugate of Cas protein and CRISPR RNA (crRNA) detect a specific complementary sequence of the target sequence. Enzymatic cleavage occurs on not only the target sequence, but also all surrounding non-target single-stranded RNAs. This discovery was immediately utilized as a biosensor, and numerous sensor studies using CRISPR have been reported since then. In this review, the concept of CRISPR, the characteristics of the Cas protein required for CRISPR diagnosis, the current research trends of CRISPR diagnostic technology, and some aspects to be improved in the future are covered.