http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
박지연(Ji-Yeon Park),서동호(Dong-Ho Seo),남해운(Hae-Woon Nam) 한국전자파학회 2021 한국전자파학회논문지 Vol.32 No.4
본 논문은 convolutional neural network (CNN) 모델에 이미지화 알고리즘을 적용한 자동 변조 분류 기법을 제안한다. 또한 다양한 이미지화 알고리즘을 이용하여 시계열 데이터의 이미지화 작업 후 이를 이용한 CNN 모델의 분류 성능을 비교 및 분석한다. 실험 결과, 원시 데이터를 Markov Transition Field (MTF)를 사용하여 이미지화한 후 CNN을 이용한 분류를 수행했을 시−6 ㏈ 환경에서는 오차율이 34 %에서 30 %로 감소하였으며, 0 ㏈ 환경에서는 오차율이 37 %에서 18 %로 감소하였다. 본 논문은 시계열 데이터의 이미지화가 CNN 기반 변조 분류 성능 개선으로 이어지는 것을 보여줌으로써 이미지화 알고리즘 적용의 유효성을 보여준다. This paper presents an automatic modulation classification method that involves the application of various imaging algorithms to a convolutional neural network (CNN). The effect of time-series data imaging on the performance of CNN-based modulation classification is analyzed. Our experiment suggests that converting raw signal data into image data using Markov transition field can reduce the error rate of CNN classification from 34 % to 30 % in case of −6 ㏈ signal to noise ratio (SNR) and from 37 % to 18 % in case of 0 ㏈ SNR. This study shows that time-series imaging is a viable preprocessing method for improving the performance of CNN-based modulation classification.
진행성 전신경화증 환자에서 식도관련증상과 식도 운동성과의 상호관계
송인성(I S Song),최규완(K W Choi),김정룡(C Y Kim),정영화(Y H Chung),이풍렬(P L Rhee),정현채(H C Jung),송영욱(Y W Song),이효석(H S Lee),윤용범(Y B Yoon) 대한소화기학회 1988 대한소화기학회지 Vol.20 No.3
N/A To investigate the correlation of esophageal symptoms w ith esophageal manometric parameters in patients with progressive systemic sclerosis (PSS) we tested esophageal motility in 10 patients with PSS who were admitted to Seoul National University Hospital from Feb. 1988 to Aug. 1988 and in 5 normal subjects, and we analyzed every parameters. The results were as follows: 1) 4 patients with esophageal symptoms showed marked decrease of lower esophageal sphincter pressure (LESP) (9.I+4.4 mmHg vs 27.9+8.5 mmHg; p< 0.005) while 6 patients having no esophageal symptoms showed normal LESP (29.4+4.0 mmHg vs 27.9+8.5 mmHg). 2) Normally propagating peristaltic waves were not found in the lower esophageal bodies of 4 patients who had esophagea] symptoms. On the other hand, among 6 patients without symptoms, 3 patients showed no propagating peristaltic waves while the other 3 patients showed normally propagating peristaltic waves in the lower esophagus. 3) The amplitudes of contraction waves at upper esophageal body of patients with esophageal symptoms were decreased compared with those of patients who had no esophageal symptom. (29.0+6.1 mmHg vs 21.0+4.4 mmHg; p<0.05) 4) In cases not showing normally propagating peristaltic waves, nonpropagating, hroad-based, low-amplitude contractions were found at the lower esophageal body. In conclusion, LESP is the esophageal manornetric parameter vhich seemed to be the most closely correlated with esophagea) symptoms in patients with PSS. And PSS seems to influence the upper esophageal contraction. Our data also indicates that esophageal manometry may be useful in the early detection of esophageal involvement in patients with PSS.
송인성(I S Song),최규완(K W Choi),김정룡(C Y Kim),정현채(H C Jung),윤용범(Y B Yoon),양석균(S K Yang),임용철(Y C Lim),윤병철(Byung Cheol Kim),노임환(I H Roe),유권(K Yoo) 대한소화기학회 1989 대한소화기학회지 Vol.21 No.4
N/A A total of 486 cases of upper gastrointestinal bleeding admitted to Seoul National University Hospital via emergency room from Jan. 1986 to Jun. 1988 were clinically reviewed and the following results were obtained: 1) The male to female ratio was 4.7:1 and peak incidence was in the 6th and 5th decades. The sex and age had no prognostic value. 2) The causes of bleeding were esophageal varix (35.2%), gastric ulcer (17.7%), duodenal ulcer (13.4%), stomach cancer (6.6%), gastritis (5.15), Mallory-Weiss syndrome (2.7gp), miscellaneous causes (l.0%), and unknown causes (18.3%). Variceal bleeders had the highest mortality rate. 3) There was no past history of bleeding in 61.5% overall, and it had no prognostic value. But variceal bleeders had past history of bleeding in, 50.3% and the first episode of bleeding offered higher mortality rate. 4) Three types of bleeding hefore admission were hematemesis in 27.85, melena in 25.7% and both of them in 46.5%, which had no prognostic value if variceal and nonvariceal bleeders were considered respectively. 5) Systolic blood pressure and pulse rate had some prognostic value, that is, high pulse rate on admission carried higher morthalty rate in variceal bleeders and low systolic blood pressure did in nonvariceal bleeders. 6) The three patterns of bleeding after admission were single bleeding in 63.0%, repeated bleeding in 21.0% and continuous bleeding in 16.0%. The mortality rate of repeated and continuous bleeding was higher than that of single bleeding. 7) The patients who received transfusion were 86.8% and the amount of blood transfused was more than 10 pints in 24.1%. The mortality rate increased as the amount of blood transfused increased. 8) Esophageal varix ivas the cause of the first bleeding in 76.4% of patients with chronic liver disease with esophageal varix. If the cause of the first bleeding was the esophageal varix in patients with chronic liver disease with esophageal varix, the cause of the second bleeding was also esophageal varix in 93.5%.
윤석주(S J Youn),고광철(K C Koh),이동호(D H Lee),윤용범(Y B Youn),송인성(I S Song),최규완(K W Choi),김정룡(C Y Kim) 대한소화기학회 1987 대한소화기학회지 Vol.19 No.1
N/A We have analysed the records of esophageal manometric examinations performed in 22 patients who came to Seoul National University Hospital complaining epigastric discomfort or pain and showed endoscopic picture typical of reflux esophagitis and obtained following results; 1) Of the total 22 patients, 8 patients (36.4%) showed low LESP (<10mmHg) and 9 patients (40.9%) showed abnormality in espophageal body peristalsis and 8 patients (36.4%) showed no abnormality either in LESP or in esophageal body peristalsis. 2) Of the 9 patients who had abnormal body peristalsis, only one patient had low (<40mmHg) peristaltic pressure and 8 patients had frequent aperistalsis pattern. 3) In patient group with more severe esophagitis, higher percentage of patients showed body peristalsis abnormality. (p <0.05) compared to the less severe group. As can be seen from the above results, low LESP and abnormality in esophageal body peristalsis may have important role in the genesis of reflux esophagitis but whether these factors acted as causative mechanism or has resulted from the esophagitis process and what kinds of other factors participate in the pathogenesis of them is not clear yet and still remain to be clarified.
흉부 X-선 영상에서 밝기값 정규화 및 다중 스케일 폐-집중 패치를 사용한 앙상블 딥러닝 모델 기반의 폐렴 자동 분류
김윤조,안진서,홍헬렌 한국정보과학회 2022 정보과학회논문지 Vol.49 No.9
It is difficult to classify normal and pneumonia in pediatric chest X-ray (CXR) images due to irregular intensity values. In addition, deep learning model has a limitation in that it can misclassify CXR by incorrectly focusing on the outer part of the lung. This study proposed an automatic classification of pneumonia based on ensemble deep learning model using three intensity normalizations and multiscale lung-focused patches on CXR images. First, to correct for irregular intensity values in internal lungs, three intensity normalization methods were performed respectively. Second, to focus on internal lungs, regions of interest were extracted by segmenting lung regions. Third, multiscale lung-focused patches were extracted to train the characterization of pneumonia. Finally, ensemble modeling with attention module was performed to improve the classification performance. In the experiment, the method using large patches of CLAHE images showed an accuracy of 92%, which was 5% higher than that of original images. Furthermore, the proposed method using an ensemble of large and middle patches showed the best performance with an accuracy of 93%. 소아 흉부 X-선 영상(CXR)은 밝기값이 불규칙하여 정상과 폐렴을 구분하기 어렵다. 또한 딥러닝 모델은 폐의 외부 영역에 잘못 집중하여 CXR을 오분류할 수 있다는 한계가 있다. 본 논문은 CXR 영상에서 밝기값 정규화 및 다중 스케일 폐-집중 패치를 사용한 앙상블 딥러닝 기반 폐렴 자동 분류 방법을 제안한다. 첫째, 불규칙한 폐 내부 밝기값을 개선하기 위해 세 가지 밝기값 정규화 방법을 각각 수행한다. 둘째, 폐 내부에 집중하여 학습하기 위해 폐 영역을 분할하여 관심 영역을 추출한다. 셋째, 다중 스케일 폐-집중 패치를 사용하여 폐렴의 특징을 학습한다. 마지막으로 분류 성능을 향상시키기 위해 어텐션 모듈을 추가한 앙상블 모델을 사용한다. 실험 결과, CLAHE를 적용한 큰 크기의 패치 사용 시 정확도 92%로 원 영상 대비 5%p 향상된 성능을 보였다. 또한 큰 크기와 중간 크기의 패치를 앙상블한 제안 방법이 정확도 93%로 가장 좋은 성능을 보였다.