http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
하계 트레이닝기간중 혈청 철분과 지질 및 운동수행 능력의 변화에 관한 연구
김성주,정일규 고려대학교 스포츠과학연구소 1987 스포츠科學論叢 Vol.1 No.1
The study was done in order to investigate the changes in hematological status related to iron and lipid metabolism, physical work capacity over a six-week period of training for male (N=6) and female (N=6) basketball athletes. The hematological variables and the items of physical work capacity were tested three times (pre, mid, post) for each two week with the beginning of the training. The results of a paired t-Test on this data were summarized as follows; 1. From the test of Basic Hematological Test, all items were not changed in male and female athletes. 2. The iron indices (SeFe^(++), TIBC, %TS) indicated that the stores of iron in the interior of the subject's body had decreased through the summer training. 3. The serum triglyceride decreased more than the total cholesterol, after six-week summer training. 4. In male athletes, the significant changes of All out time, Energy max and 9min-H.R response were observed, but in female athletes only the 3 min-HR response was significantly changed after three and six weeks. 5. VO₂ max, H.R max, 6 min-H.R response, Systolic and Diastolic blood pressure were not changed in both sexes.
김성주,김경범,Kim, Sung Joo,Kim, Gyung Bum 한국반도체디스플레이기술학회 2021 반도체디스플레이기술학회지 Vol.20 No.1
In this paper, a method for improving the defect classification performance in low contrast, ununiformity and featureless steel plate surfaces has been studied based on deep convolution neural network and transfer-learning neural network. The steel plate surface images have low contrast, ununiformity, and featureless, so that the contrast between defect and defect-free regions are not discriminated. These characteristics make it difficult to extract the feature of the surface defect image. A classifier based on a deep convolution neural network is constructed to extract features automatically for effective classification of images with these characteristics. As results of the experiment, AlexNet-based transfer-learning classifier showed excellent classification performance of 99.43% with less than 160 seconds of training time. The proposed classification system showed excellent classification performance for low contrast, ununiformity, and featureless surface images.