http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김경은,김필송,민주연,박수경,신서인,이지은,정해인,조호정,최정원,최정인 이화여자대학교 간호과학대학 2013 이화간호학회지 Vol.- No.47
Purpose: The purpose of this study was to investigate the relationships between the degree of smart phone addiction among adolescents and their depression and anxiety levels. Method: In this study, 379 high school students were selected using the convenient sampling method. The instruments used for this study were smart phone addiction measure, the CES-D (Center for Epidemiological Studies-Depression Scale), and the STAI (State-Trait Anxiety Inventory). Data were analyzed using the SPSS 20.0 program with descriptive statistics, t-test, ANOVA with Scheffe test, and Pearson’s correlation coefficient. Result: The mean score for smart phone addiction was 40.45±17.27, depression was 36.56±9.58, state anxiety was 44.00±9.61, and trait anxiety was 45.70±9.75. There were significant differences between the degree of smart phone addiction and the following variables: gender (t=-4.953, p<.001), hours of smart phone use per day (F=12.259, p<.001), types of frequently used features (F=3.485, p=.008), and satisfaction level for smart phone (F=5.18, p<.001). There were statistically significant relationships (p<.001) among degree of smart phone addiction, depression level, and state and trait anxiety levels. Conclusion: The results of this study suggested that there was a significant relationship between smart phone addiction and mental health, specifically, depression and anxiety among adolescents. Further research is needed to develop nursing strategies to provide care for adolescents who frequently utilize smart phones.
MLP 모델을 위한 Mixup 알고리즘 기반의 Data Augmentation에 관한 연구
현선영 ( Sun-young Hyun ),김필송 ( Pil-song Kim ),황성연 ( Seong-yeon Hwang ),하영국 ( Young-guk Ha ) 한국정보처리학회 2021 한국정보처리학회 학술대회논문집 Vol.28 No.2
본 논문에서는 CNN 모델에서 학습에 사용할 이미지 데이터를 늘리기 위해 사용되는 Mixup 알고리즘을 MLP 모델에 사용하는 데이터셋에 적용하여 data augmentation 효과를 얻을 수 있는 지에 대한 테스트를 수행했다. 테스트 결과 MLP 모델에 사용할 데이터셋에도 Mixup 알고리즘으로 data augmentation 효과를 기대할 수 있음을 보여준다.