• 한국정보처리학회논문지
• /
• 제4권11호
• /
• pp.2711-2720
• /
• 1997

CRAY 에서 멀티/마이크로 태스킹은 다수의 CPU를 이용하여 계산속도를 증가시키는 하나의 방법이다. CRAY-2 에는 4개의 CPU 가 있으므로 적절히 설계된 알고리즘을 가지고 최대 4배의 speedup을 실현할 수 있다. 저자는 이 논문에서 CRAY-2에서 멀티태스킹/마이트로태스킹 라이브러리를 이용한 2가지의 선형시스템의 해의 병렬화를 제시한다. 하나는 조밀행렬에 대한 가우스 소거법이고 다른 하나는 Radicati di Brozolo가 제안한 준비행렬을 이용한 대형이산 행렬의 반복적 해법이다. 첫째 경우에 크기가 600인 행렬에서 2개의 CPU에 멀티태스킹을 이용하여 1.3의 speedup을 얻었으며 두 번째 경우에서는 크기가 8192인 행렬에서 4개의 CPU에 마이크로 태스킹을 사용하여 3이상의 speedup을 얻었다. 첫째 경우에서는 비균일한 벡터길이 때문에 speedup 이 제한되었다. 두 번째 경우에서는 Radicati 의 테크닉을 혼합한 ILU(0) 준비행렬은 4개의 프로세서에서 상당히 높은 speedup을 얻었다.

• 융복합기술연구소 논문집
• /
• 제3권2호
• /
• pp.11-15
• /
• 2013

These days, the quality of goods is required to improve in the process of manufacturing the semiconductor through the short working hours and clean transportation. The non-contact transport device using magnetic levitation can be a solution in the manufacturing process. The non-contact transport device, using electromagnetic actuation, is the system that can actually transport them by only using attraction force from the electromagnetic source without authentic contact. Moreover, the system using electromagnetic force has a substantial number of benefits ranging from unrestricted design to unlimited expansion. Especially, the price is competitive. The non-contact transport device, using electromagnetic force, has another merits in controlling by giving the same amount of attraction force to ferromagnetic body. By controlling the currents given to coil, the operator is able to decide the direction of the transportation. In order to design the optimal system, we implemented five different things such as the presence of the links below the electromagnetic, the electromagnet changes due to coupling method, the change according to the thickness of the links below electromagnet, due to changes in between electromagnetic distance direction, and the size of the current. Through simulations and the optimum design, it seems to control easily and figure out the exact size of power. It might definitely be the non-contact transport that can sharply reduce tiny scratches and particles in the process of manufacturing the semiconductor.

• 반도체디스플레이기술학회지
• /
• 제18권4호
• /
• pp.30-34
• /
• 2019

We analyzed how the features in plasma information based virtual metrology (PI-VM) for SiO₂ etching depth with variation of 5% contribute to the prediction accuracy, which is previously developed by Jang. As a single feature, the explanatory power to the process results is in the order of plasma information about electron energy distribution function (PI_EEDF), equipment, and optical emission spectroscopy (OES) features. In the procedure of stepwise variable selection (SVS), OES features are selected after PI_EEDF. Informative vector for developed PI-VM also shows relatively high correlation between OES features and etching depth. This is because the reaction rate of each chemical species that governs the etching depth can be sensitively monitored when OES features are used with PI_EEDF. Securing PI_EEDF is important for the development of virtual metrology (VM) for prediction of process results. The role of PI_EEDF as an independent feature and the ability to monitor variation of plasma thermal state can make other features in the procedure of SVS more sensitive to the process results. It is expected that fault detection and classification (FDC) can be effectively developed by using the PI-VM.

• 품질경영학회지
• /
• 제49권3호
• /
• pp.327-340
• /
• 2021

Purpose: The purpose of this study is to propose a system predicting whether an electricity distribution system is abnormal by analyzing the temperature of the deteriorated system. Traditional electricity distribution system abnormality diagnosis was mainly limited to post-inspection. This research presents a remote monitoring system for detecting thermal images of the deteriorated electricity distribution system efficiently hereby providing safe and efficient abnormal diagnosis to electricians. Methods: In this study, an object detection algorithm (YOLOv5) is performed using 16,866 thermal images of electricity distribution systems provided by KEPCO(Korea Electric Power Corporation). Abnormality/Normality of the extracted system images from the algorithm are classified via the limit temperature. Each classification model, Random Forest, Support Vector Machine, XGBOOST is performed to explore 463,053 temperature datasets. The process capability index is employed to indicate the quality of the electricity distribution system. Results: This research performs case study with transformers representing the electricity distribution systems. The case study shows the following states: accuracy 100%, precision 100%, recall 100%, F1-score 100%. Also the case study shows the process capability index of the transformers with the following states: steady state 99.47%, caution state 0.16%, and risk state 0.37%. Conclusion: The sum of caution and risk state is 0.53%, which is higher than the actual failure rate. Also most transformer abnormalities can be detected through this monitoring system.

• 한국전자통신학회논문지
• /
• 제16권5호
• /
• pp.845-850
• /
• 2021

본 연구에서는 전기 자동차(EV : Electric Vehicle) 파워트레인의 에너지 변환 특성과 설계를 수행하였다. 그리고 EV 파워트레인의 동력원으로서 영구자석 매입형 동기 모터(IPMSM : Interior Permanent Magnet Synchronous Motor)를 대상으로 하였으며 제어를 수행하였다. IPMSM을 구동하기 위해서는 두 가지 영역인 일정한 토크와 일정한 출력(약계자) 영역이 사용되며, IPMSM을 위한 제어 시스템의 설계는 d-q 레퍼런스 프레임(벡터 제어)을 바탕으로 구성하였다. IPMSM의 두 영역에서 나타나는 모터 토크의 정적 특성을 결정하기 위해 IPMSM의 토크제어 시스템과 d축 전류 제어 시스템을 제안 및 구현하였다. 특성해석을 위해서 Matlab-Simulink 소프트웨어를 사용하였다. 최종적으로 실제 차량 사양을 기준으로 EV 차량 레벨 조건으로 변경하여 파워트레인 모델에 IPMSM을 적용하였으며 제안된 제어 시스템의 시뮬레이션 결과를 수행했고 특성을 분석하였다.

• 대한의용생체공학회:의공학회지
• /
• 제40권2호
• /
• pp.62-67
• /
• 2019

The purpose of this study was to evaluate the performance of deep neural network model in order to determine whether there is a risk factor for coronary artery disease based on the cardiac variation parameter. The study used unidentifiable 297 data to evaluate the performance of the model. Input data consists of heart rate parameters, which are SDNN (standard deviation of the N-N intervals), PSI (physical stress index), TP (total power), VLF (very low frequency), LF (low frequency), HF (high frequency), RMSSD (root mean square of successive difference) APEN (approximate entropy) and SRD (successive R-R interval difference), the age group and sex. Output data are divided into normal and patient groups, and the patient group consists of those diagnosed with diabetes, high blood pressure, and hyperlipidemia among the various risk factors that can cause coronary artery disease. Based on this, a binary classification model was applied using Deep Neural Network of deep learning techniques to classify normal and patient groups efficiently. To evaluate the effectiveness of the model used in this study, Kernel SVM (support vector machine), one of the classification models in machine learning, was compared and evaluated using same data. The results showed that the accuracy of the proposed deep neural network was train set 91.79% and test set 85.56% and the specificity was 87.04% and the sensitivity was 83.33% from the point of diagnosis. These results suggest that deep learning is more efficient when classifying these medical data because the train set accuracy in the deep neural network was 7.73% higher than the comparative model Kernel SVM.

• 전기전자학회논문지
• /
• 제23권2호
• /
• pp.543-551
• /
• 2019

영구자석 동기 전동기는 출력 밀도가 높고 효율이 높다는 장점 때문에 적용 범위가 넓어지고 있다. 자동차나 로봇과 같은 고전력밀도, 고성능 전동기 구동 시스템뿐만 아니라 세탁기, 에어컨, 냉장고와 같은 비용 절감이 매우 중요한 시스템에도 영구자석 동기 전동기가 사용되고 있다. 비용 절감을 위해 회전자 위치 센서를 제거하는 센서리스 제어가 필요한데, 일반적으로 센서리스 제어는 전동기를 기동하는 조건에서는 사용하기 어렵다. 따라서 초기 기동에서는 전류 벡터를 임의의 속도로 회전시키는 I-F 속도 제어를 사용하고, 특정 속도 이상이 되면 센서리스 속도 제어로 절환해야 한다. I-F 속도 제어와 센서리스 속도 제어에서의 속도 제어 성능도 중요하지만 두 제어 기법이 절환되는 과도 상태에서도 속도 제어 성능을 유지해야 한다. 본 논문에서는 영구자석 동기 전동기의 센서리스 속도 제어를 위해 I-F 속도 제어에서 센서리스 속도 제어로의 절환 기법을 제안한다. 제안된 기법의 성능을 확인하기 위해 세탁기 구동 시스템에서 실험을 수행하였다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제43권6호
• /
• pp.503-509
• /
• 2020

This study aims to develop a patient-specific radiation exposure dose prediction model based on anthropometric data that can be easily measurable during CT examination, and to be used as basic data for DRL setting and radiation dose management system in the future. In addition, among the machine learning algorithms, the most suitable model for predicting exposure doses is presented. The data used in this study were chest CT scan data, and a data set was constructed based on the data including the patient's anthropometric data. In the pre-processing and sample selection of the data, out of the total number of samples of 250 samples, only chest CT scans were performed without using a contrast agent, and 110 samples including height and weight variables were extracted. Of the 110 samples extracted, 66% was used as a training set, and the remaining 44% were used as a test set for verification. The exposure dose was predicted through random forest, linear regression analysis, and SVM algorithm using Orange version 3.26.0, an open software as a machine learning algorithm. Results Algorithm model prediction accuracy was R^2 0.840 for random forest, R^2 0.969 for linear regression analysis, and R^2 0.189 for SVM. As a result of verifying the prediction rate of the algorithm model, the random forest is the highest with R^2 0.986 of the random forest, R^2 0.973 of the linear regression analysis, and R^2 of 0.204 of the SVM, indicating that the model has the best predictive power.

• 대한방사선기술학회지:방사선기술과학
• /
• 제45권2호
• /
• pp.111-116
• /
• 2022

In this study, the applicability of machine learning for the development of a simulator for general X-ray examination education is evaluated. To this end, k-nearest neighbor(kNN), support vector machine(SVM) and neural network(NN) classification models are analyzed to present the most suitable model by analyzing the results. Image data was obtained by taking 100 photos each corresponding to Posterior anterior(PA), Posterior anterior oblique(Obl), Lateral(Lat), Fan lateral(Fan lat). 70% of the acquired 400 image data were used as training sets for learning machine learning models and 30% were used as test sets for evaluation. and prediction model was constructed for right-handed PA, Obl, Lat, Fan lat image classification. Based on the data set, after constructing the classification model using the kNN, SVM, and NN models, each model was compared through an error matrix. As a result of the evaluation, the accuracy of kNN was 0.967 area under curve(AUC) was 0.993, and the accuracy of SVM was 0.992 AUC was 1.000. The accuracy of NN was 0.992 and AUC was 0.999, which was slightly lower in kNN, but all three models recorded high accuracy and AUC. In this study, right-handed PA, Obl, Lat, Fan lat images were classified and predicted using the machine learning classification models, kNN, SVM, and NN models. The prediction showed that SVM and NN were the same at 0.992, and AUC was similar at 1.000 and 0.999, indicating that both models showed high predictive power and were applicable to educational simulators.

• 한국산업정보학회논문지
• /
• 제28권5호
• /
• pp.31-39
• /
• 2023

최근 자연어 처리(NLP) 기술, 특히 ChatGPT를 비롯한 거대 언어 모델(LLM)의 발전으로 특정 전문지식에 대한 질의응답(QA) 시스템의 연구개발이 활발하다. 본 논문에서는 거대언어모델과 문서검색 알고리즘을 활용하여 한국원자력연구원(KAERI)의 규정 등 다양한 문서를 이해하고 사용자의 질문에 답변하는 시스템의 동작 원리에 대해서 설명한다. 먼저, 다수의 문서를 검색과 분석이 용이하도록 전처리하고, 문서의 내용을 언어모델에서 처리할 수 있는 길이의 단락으로 나눈다. 각 단락의 내용을 임베딩 모델을 활용하여 벡터로 변환하여 데이터베이스에 저장하고, 사용자의 질문에서 추출한 벡터와 비교하여 질문의 내용과 가장 관련이 있는 내용들을 추출한다. 추출된 단락과 질문을 언어 생성 모델의 입력으로 사용하여 답변을 생성한다. 본 시스템을 내부 규정과 관련된 다양한 질문으로 테스트해본 결과 복잡한 규정에 대하여 질문의 의도를 이해하고, 사용자에게 빠르고 정확하게 답변을 제공할 수 있음을 확인하였다.