http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김지연,김동재,Kim, Jiyeon,Kim, Dongjae 한국데이터정보과학회 2013 한국데이터정보과학회지 Vol.24 No.6
임상시험에서 적당한 크기의 표본 수 결정은 통계적으로 유의한 연구결과의 도출과 연구수행의 효율적인 비용을 산출하기 위해서 중요한 사항 중의 하나이다. 기존의 비열등성 시험에서 표본 수 계산방법에는 t 검정법을 이용한 모수적 방법이 있고, Wilcoxon 순위합 검정을 이용하여 Wang 등 (2003)이 제안한 표본 수 계산방법을 Kim과 Kim (2007)이 비열등성 시험에 확장시켜 적용하여 제시한 비모수적 방법이 있다. 본 논문에서는 Orban과 Wolfe (1982)가 제안한 선형위치통계량의 검정법에 Kim (1994)이 계산한 검정력의 결과를 이용한 표본 수 계산 방법을 제안하고, 그에 따른 표본 수 계산결과를 기존에 제시된 표본 수 계산 결과와 비교하였다. 그 결과 기존의 방법들보다 본 논문에서 제안하는 방법으로 계산한 경우의 표본 수가 가장 작게 나왔다. 따라서 모집단에 대해서 구체적인 분포함수를 가정하기 힘든 경우 모수적 방법을 이용하게 되면 검정력이 떨어지거나 유의수준을 제어하지 못하는 문제점을 보완하고, 모수적 방법에 비해 표본 수가 크게 나와 시간이나 비용 면에서 효율적이지 않았던 Wilcoxon 순위합 검정을 이용한 방법의 단점을 보완할 수 있는 방법으로 본 논문에서 제시한 위치 (placement)를 이용한 표본 수 계산이 이용될 수 있다. In clinical research, sample size determination is one of the most important things. There are parametric method using t-test and non-parametric method suggested by Kim and Kim (2007) based on Wilcoxon's rank sum test for determining sample size in non-inferiority trials. In this paper, we propose sample size calculation method based on placements method suggested by Orban and Wolfe (1982) and using the power calculated by Kim (1994) in non-inferiority trials. We also compare proposed sample size with that using Kim and Kim (2007)'s formula and that of t-test for parametric methods. As the result, sample size calculated by proposed method based on placements is the smallest. Therefore, proposed method based on placements is better than parametric methods in case that it's hard to assume specific distribution function for population and also more efficient in terms of time and cost than method based on Wilcoxon's rank sum test.
심수진,김동재,Sim, Sujin,Kim, Dongjae 한국데이터정보과학회 2013 한국데이터정보과학회지 Vol.24 No.6
반복이 있는 랜덤화 블록 계획법에서 우산형 대립가설을 검정하기 위한 비모수 방법에는 Kim과 Kim (1992)이 제안한 방법이 있다. 본 논문에서는 Orban과 Wolfe (1982)가 제안한 위치와 Kim (1999)이 제안한 대조군과 처리군의 방법을 확장하여 랜덤화 블록 계획법에서 우산형 대립가설에서의 검정법을 제안하였다. 또한 여러 분포에 대한 모의실험 통하여 기존의 방법과의 검정력을 비교하였다. Kim and Kim (1992) proposed typical nonparametric method for umbrella alternative in randomized block design with replications. In this paper, We consider a test procedure for umbrella alternatives in a randomized block design using extension of the two sample placement tests described in Orban and Wolfe (1982) and treatment tests described in Kim (1999). We perform a Monte Carlo study to compare the empirical powers of the test statistics for underlying distributions.
Kim, Dongjae,Hwang, Hongsik,Bae, Sungwoo,Lee, Cheewoo IEEE 2016 IEEE transactions on magnetics Vol.52 No.7
<P>A double-stator flux-switching permanent magnet (DS-FSPM) machine using ferrite is proposed to replace an interior permanent magnet synchronous motor (IPMSM) on hybrid electric vehicles. A conventional FSPM machine is designed, and its torque characteristic is analyzed by a frozen permeability method. It is verified that magnetic saturation causes the reduction of flux linkage generated by PM and leads to the deterioration of electromagnetic torque. A DS-FSPM machine is effective for magnetic saturation because of its unique structure and makes the improvement of efficiency and power density. The proposed DS-FSPM machine achieves distinct performance enhancement compared with an IPMSM, even by utilizing ferrite PM.</P>
SG-Drop: Faster Skip-Gram by Dropping Context Words
( Dongjae Kim ),( Doangjoo Synn ),( Jong-kook Kim ) 한국정보처리학회 2020 한국정보처리학회 학술대회논문집 Vol.27 No.2
Many natural language processing (NLP) models utilize pre-trained word embeddings to leverage latent information. One of the most successful word embedding model is the Skip-gram (SG). In this paper, we propose a Skipgram drop (SG-Drop) model, which is a variation of the SG model. The SG-Drop model is designed to reduce training time efficiently. Furthermore, the SG-Drop allows controlling training time with its hyperparameter. It could train word embedding faster than reducing training epochs while better preserving the quality.
Kim, Sunho,Kim, Bongsung,Im, Inseob,Kim, Dongjae,Lee, Haeseong,Nam, Jaewook,Kyoon Chung, Ho,Lee, Hoo-Jeong,Min Cho, Sung IOP Pub 2017 Nanotechnology Vol.28 No.34
<P>This study proposes a simple method of Au coating on silver nanowires (Ag NWs) transparent conductive films as the anode of organic light emitting diodes (OLED) to increase the work function of the film and thus enhance hole transport. We carefully engineer the process conditions (pretreatment, solution concentrations, and coating number) of the coating using a diluted HAuCl<SUB>4</SUB> solution on the Ag NWs film to minimize etching damage on Ag NWs accompanying the galvanic replacement reaction. Ultraviolet photoelectron spectroscopy and Kelvin probe force microscopy show work function increase of Ag NWs upon Au coating. OLED devices based on Au-coated Ag NWs show a lower turn-on voltage and higher luminance, compared with pristine Ag NWs device. Although the Ag NWs device displays poor efficiencies in the low luminance range due to a high leakage, some of the Au-coated Ag NWs devices showed efficiencies higher than those of the ITO device in a high luminance.</P>
Maximum Tolerated Dose Estimation Applied Biased Coin Design in a Phase I Clinical Trial
Kim, Yu Rim,Kim, Dongjae 한국통계학회 2012 Communications for statistical applications and me Vol.19 No.6
Phase I trials determine the maximum tolerated dose(MTD) and the recommended dose(RD) for subsequent Phase II trials. In this paper, a MTD estimation method applied to a biased coin design is proposed for Phase I Clinical Trials. The suggested MTD estimation method is compared to the SM3 method and the NM method (Lee and Kim, 2012) using a Monte Carlo simulation study.