http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김영남,김영아,양애리,이복희 한국식품영양과학회 2014 Preventive Nutrition and Food Science Vol.19 No.4
Limited epidemiologic data is available regarding the cardiovascular effects of mercury exposure. The purpose of this study was to determine the relationship between mercury exposure from fish consumption and cardiovascular disease in a nationally representative sample of Korean adults using the Fourth Korea National Health and Nutrition Examination Survey (KNHANES IV 2008∼2009). Survey logistic regression models accounting for the complex sampling were used to estimate the odds ratios (OR) adjusted for fish consumption frequency, age, education, individual annual income, household annual income, body mass index (BMI), waist circumference (WC), alcohol consumption status, and smoking status. The mean blood mercury level in the population was 5.44 ㎍/L. Trends toward increased blood mercury levels were seen for increased education level (P=0.0011), BMI (P<0.0001), WC (P<0.0001), and fish (i.e., anchovy) consumption frequency (P=0.0007). The unadjusted OR for hypertension in the highest blood mercury quartile was 1.450 [95% confidential interval (CI): 1.106∼1.901] times higher than that of the lowest quartile. The fish consumption-adjusted OR for hypertension in the highest blood mercury quartile was 1.550 (95% CI: 1.131∼ 2.123) times higher than that of the lowest quartile, and the OR for myocardial infarction or angina in the highest blood mercury quartile was 3.334 (95% CI: 1.338∼8.308) times higher than that of the lowest quartile. No associations were observed between blood mercury levels and stroke. These findings suggest that mercury in the blood may be associated with an increased risk of hypertension and myocardial infarction or angina in the general Korean population.
교량 구조물 손상탐지를 위한 Open Set Recognition 기반 다중손상 인식 모델 개발
김영남,조준상,김준경,김문현,김진평 대한토목학회 2022 대한토목학회논문집 Vol.42 No.1
Currently, the number of bridge structures in Korea is continuously increasing and enlarged, and the number of old bridges that havebeen in service for more than 30 years is also steadily increasing. Bridge aging is being treated as a serious social problem not only in Korea but also around the world, and the existing manpower-centered inspection method is revealing its limitations. Recently, various bridge damage detection studies using deep learning-based image processing algorithms have been conducted, but due to the limitationsof the bridge damage data set, most of the bridge damage detection studies are mainly limited to one type of crack, which is also based on a close set classification model. As a detection method, when applied to an actual bridge image, a serious misrecognition problem may occur due to input images of an unknown class such as a background or other objects. In this study, five types of bridge damageincluding crack were defined and a data set was built, trained as a deep learning model, and an open set recognition-based bridge multiple damage recognition model applied with OpenMax algorithm was constructed. And after performing classification andrecognition performance evaluation on the open set including untrained images, the results were analyzed.