• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.413-413
• /
• 2019

하천과 호수에서 남조류의 이상 과잉증식 문제(이하 녹조문제)는 담수생태계의 생물다양성을 감소시키며, 음용수의 이취미 원인물질을 발생시켜 물 이용에 장해가 된다. 또한 독소를 생산하는 유해남조류가 대량 증식할 경우에는 가축이나 인간의 건강에 치명적 해를 끼치기도 한다. 그 동안 국내에서 녹조문제는 댐 저수지와 하구호와 같은 정체수역에서 간헐적으로 문제를 일으켰으나, 4대강사업(2010-2011)으로 16개의 보가 설치된 이후 낙동강, 금강, 영산강 등 대하천에서도 광범위하게 발생되고 있어 중요한 사회적 환경적 이슈로 대두되었다. 한편, 대하천에 설치된 보 구간에서 빈번히 발생하는 녹조현상의 원인에 대해서는 전 지구적 기온상승에 따른 기후변화의 영향이라는 주장과 유역으로부터 영양염류의 과도한 유입, 가뭄에 따른 유량감소, 보 설치에 따른 체류시간 증가 등 다양한 의견이 제시되고 있으나, 대상 유역과 수체의 특성에 따라 녹조 발생의 원인이 상이하거나 또는 다양한 요인이 복합적으로 작용하기 때문에 보편적 해석(universal interpretation)이 어려운 것이 현실이다. 따라서 각 수계별, 보별 녹조현상에 대한 정확한 원인분석과 효과적인 대책 마련을 위해서는 집중된 실험자료와 데이터마이닝 기법에 근거로 한 보다 과학적이고 객관적인 접근이 이루어져야 한다. 본 연구에서는 2012년 보 설치 이후 남조류에 의한 녹조현상이 빈번히 발생하고 있는 낙동강 4개보(강정고령보, 달성보, 합천창녕보, 창녕함안보)를 대상으로 집중적인 현장조사와 실험분석을 수행하고, 수집된 기상, 수문, 수질, 조류 자료에 대해 통계분석과 다양한 데이터모델링 기법을 적용하여 보별 남조류 우점 환경조건과 이를 제어하기 위한 주요 조절변수를 규명하는데 있다. 연구대상 보 별 수질과 식물플랑크톤의 정성 및 정량 실험은 2017년 5월부터 2018년 11월까지 2년에 걸쳐 실시하였으며, 남조류 세포수 밀도와 환경요인과의 상관성 분석을 실시하고, 단계적 다중회귀모델(Step-wise Multiple Linear Regressions, SMLR), 랜덤포레스트(Random Forests, RF) 모델과 재귀적 변수 제거 기법(Recursive Feature Elimination using Random Forest, RFE-RF)을 이용한 변수중요도 평가, 의사결정나무(Decision Tree, DT), 주성분분석(Principal Component Analysis, PCA) 기법 등 다양한 모수적 및 비모수적 데이터마이닝 결과를 바탕으로 각 보별 남 조류 우점 환경요인을 종합적으로 해석하였다.

• Journal of Animal Science and Technology
• /
• v.54 no.5
• /
• pp.331-336
• /
• 2012

This study was conducted to estimate genetic parameters for ultrasound and carcass traits in Hanwoo. Heritabilities and genetic and phenotypic correlations were estimated for carcass and ultrasound measurements collected from Hanwoo cows (n=312) born at Hanwoo experiment station. Traits evaluated were eye muscle area (EMA), backfat thickness (BF), marbling score (MS) from carcass, and ultrasound eye muscle area (UEMA), ultrasound backfat (UBF), and ultrasound marbling score (UMS). Parameters were estimated using multi-trait animal models byderivative-free restricted maximum likelihood procedures. Estimated heritabilities for UBF, UEMA and UMS were 0.43, 0.23 and 0.32, while heritabilities for BF, EMA and MS were 0.33, 0.13 and 0.33 in fattened cows, respectively. Genetic correlations between ultrasound and carcass measurements were estimated to -0.19, -0.61, and -0.36 for UBF: UEMA, UBF: UMS, and UEMA: UMS in fattened cows, respectively. Phenotypic correlations between ultrasound and carcass measurements were 0.03, 0.13 and 0.26 for UBF: UEMA, UBF: UMS, and UEMA: UMS in fattened cows, respectively. As for the steer, genetic correlations between ultrasound and carcass measurements were 0.36, -0.80 and 0.27 for UBF: UEMA, UBF: UMS, and UEMA: UMS in steers, respectively. Phenotypic correlations between ultrasound and carcass measurements were 0.13, 0.07 and 0.41 for UBF: UEMA, UBF: UMS, and UEMA: UMS in steers, respectively. In conclusion, this finding would be very useful to implement into Hanwoo breeding program.

• The Korean Journal of Applied Statistics
• /
• v.31 no.3
• /
• pp.383-396
• /
• 2018

Various parallel processing R packages are used for fast processing and the analysis of big data. Parallel processing is used when the work can be decomposed into tasks that are non-interdependent. In some cases, each task decomposed for parallel processing can also be decomposed into non-interdependent subtasks. We have to choose whether to parallelize the decomposed tasks in the first step or to parallelize the subtasks in the second step when facing nested parallelism situations. This choice has a significant impact on the speed of computation; consequently, it is important to understand the nature of the work and decide where to do the parallel processing. In this paper, we provide an idea of how to apply parallel computing effectively to problems by illustrating how to select a parallelism point for the bandwidth selection of nonparametric regression.

• Journal of Radiation Protection and Research
• /
• v.24 no.1
• /
• pp.31-38
• /
• 1999

A real-time dose assessment system(FADAS : Following Accident Dose Assessment System) has been developed for the real-time accident consequence assessment against a nuclear accident. Field tracer experiment near Younggwang nuclear power plant was performed to improve the accuracy of developed system and to parameterize the site-specific parameters into the FADAS. The mean values and turbulent components of wind profile obtained through field experiment have been reflected to FADAS with site-specific conditions. The simulated results of diffusion model agreed well with the measured data through tracer experiment. The developed system is being used as a basic module of emergency preparedness system in Korea. The diffusion model which can be reflected site-specific parameters will be improved through field experiments continuously.

• Journal of Korea Water Resources Association
• /
• v.32 no.3
• /
• pp.265-279
• /
• 1999

In this study, one of the techniques on the extension of low flow series has been developed, in which the daily streamflows were simulated by the Tank model with the input of extended daily rainfall series which were stochastically generated by the Markov chain model. The annual lowest flow serried for each of the given durations were formulated form the simulated daily streamflow sequences. The frequency of the estimated annual lowest flow series was analyzed. The distribution types to be used for the frequency analysis were two-parameter and three-parameter log-normal distribution, two-parameter and three-parameter Gamma distribution, three-parameter log-Gamma distribution, Gumbel distribution, and Weibull distribution, of which parameters were estimated by the moment method and the maximum likelihood method. The goodness-of-fit test for probability distribution is evaluated by the Kolmogorov-Sminrov test. The fitted distribution function for each duration series is applied to frequency analysis for developing duration-low flow-frequency curves at Yongdam Dam station. It was shown that the purposed technique in this study is available to generate the daily streamflow series with fair accuracy and useful to determine the probabilistic low flow in the watersheds having the poor historic records of low flow series.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.993-1000
• /
• 2016

Semi-supervised learning makes it easy to use an unlabeled data in the supervised learning such as classification. Applying the semi-supervised learning on the regression analysis, we propose two methods for a better regression function estimation. The proposed methods have been assumed different marginal densities of independent variables and different smoothing parameters in unlabeled and labeled data. We shows that the overfitted pilot estimator should be used to achieve the fastest convergence rate and unlabeled data may help to improve the convergence rate with well estimated smoothing parameters. We also find the conditions of smoothing parameters to achieve optimal convergence rate.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.670-677
• /
• 2019

As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.

• Communications for Statistical Applications and Methods
• /
• v.15 no.3
• /
• pp.387-402
• /
• 2008

In this thesis we propose a two-stage periodic inspection model for maintaining the reliability of a system in long-term storage. There are two types of tests available; a fallible test and an error-free test. The system is overhauled at detection of failure or when the storage reliability after inspection becomes less than or equal to the prespecified value. The expected cost per unit time until overhaul is derived and a procedure for minimizing the expected cost is suggested. The two-stage periodic inspection model is compared with the one-stage periodic inspection model for various parameters of the cost function when the failure time follows exponential and Weibull distributions. The proposed model is then applied to an existing missile system for comparison with the current inspection policy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.347-351
• /
• 2012

본 연구는 기후변화로 인한 국내 낙동강 유역의 기온, 강수, 상대습도의 변동 경향을 파악하고자, 낙동강 본류의 상, 중, 하류 지역을 연구대상 지역으로 선정하여 분석을 실시하였다. 이를 위하여 기상요소인 평균, 최저, 최고 기온과 상대습도 및 강우 자료를 기상청의 관측 자료를 활용하여 수집하였다. 분석을 실시함에 있어서 연평균, 최고, 최저 기온과 연평균, 최고, 최저 상대습도를 분석하였으며, 강우량 관측 자료를 통해 총 강우량, 강우집중률, 일 최대강우량을 고려하였다. 분석방법은 기후변화로 인한 기상자료의 변동 경향을 파악하기 위하여 비모수적 경향성 검정인 Mann-Kendall Test, Hotelling-Pabst Test, Sen's Test 3가지의 검정방법을 사용하였으며, 표준정규변량의 크기를 통하여 변동 경향의 유의성을 비교해보았다. 또한, 각 요소별 관측 자료의 상위 10개, 하위 10개의 자료를 통하여 최근(1995~2011)과 과거(1973~1994)의 기상요소들을 비교하여 변동 특성을 파악하였다. 연구지역 중 낙동강 중류 지점에 위치하는 구미의 경우, 요소별 자료 중 연평균기온의 상위 9개의 자료가 최근 17년 이내에 포함되어 있으며, 연 최저 및 최고 기온의 6개의 자료가 포함되어 있어 기후온난화가 진행되고 있음을 확인하였다. 연 최저 상대습도의 경우 3가지 경향성 검정 방법을 통하여 과거자료에 비해 하강하는 추세를 보이고 있다. 강우자료 분석 결과 관측이 시작된 이래 연강수량 중 상위 10개의 자료에서 7개가 최근에 발생한 것으로 분석되었고, 일 최대강우량은 9개가 포함되어 있다. 위의 요소별 분석 결과 낙동강 유역의 연강수량 및 강우강도는 대체적으로 증가하고, 기온 또한 증가하는 등 기후 변화로 인한 지구온난화현상이 국내에서도 나타나는 것을 확인 할 수 있었다.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.552-560
• /
• 2021

With the recent development of the art distribution system, interest in art investment is increasing rather than seeing art as an object of aesthetic utility. Unlike stocks and bonds, the price of artworks has a heterogeneous characteristic that is determined by reflecting both objective and subjective factors, so the uncertainty in price prediction is high. In this study, we used LSTM Recurrent Neural Network deep learning model to predict the auction winning price by inputting the artist, physical and sales charateristics of the Korean artist. According to the result, the RMSE value, which explains the difference between the predicted and actual price by model, was 0.064. Painter Lee Dae Won had the highest predictive power, and Lee Joong Seop had the lowest. The results suggest the art market becomes more active as investment goods and demand for auction winning price increases.