http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김유철,홍영규,오세진,오승민,지원현,양재의,김성철 한국토양비료학회 2015 한국토양비료학회지 Vol.48 No.2
Heavy metal pollution has been a critical problem in agricultural field near at the abandoned metal mines and chemical amendments are applied for remediation purpose. However, biological activity can be changed depending on chemical amendments affecting crop productivity. Main purpose of this research was to evaluate biological parameters after applying chemical amendments in heavy metal polluted agricultural field. Result showed that soil respiration (SR) and microbial biomass carbon (MBC) were changed after chemical amendments were applied. Among three different amendments, lime stone (LS), steel slag (SS), and acid mine drainage sludge(AMDS), AMDS had an effect to increase SR in paddy soil. Comparing to control (93.98-170.33 mg kg-1 day-1), average of 30% increased SR was observed. In terms of MBC, SS had an increased effect in paddy soil. However, no significant difference of SR and MBC was observed in upland soil after chemical amendment application. Overall, SR can be used as an indicator of heavy metal remediation in paddy soil.
Predicting Game Results using Machine Learning -MMORPG TERA : Focusing on the Rikanor Arena
김유철,김재민,김명영,이원형 (사)한국컴퓨터게임학회 2018 한국컴퓨터게임학회논문지 Vol.31 No.1
Recently, much attention has been paid to machine learning - especially deep learning. As big companies like Google, Facebook are interested in AI and machine learning, these research is being developed day by day. Machine learning is expected to be used in various industries such as medical, translation, and IT. The game sector is also considered one of the areas where the effects of applying machine learning technology are expected. In this paper, we designed a Neural Network that predicts the win / loss of monsters in MMORPG-Tera’s Game contents. We designed the model through Tensorflow. This model has 1 input layer, 2 hidden layer and 1 output layer. There are 8 nodes in input layer, 16 nodes in each hidden layer and 1 nodes in output layer. For the better results we use Adam for gradient descent, Sigmoid function and Relu function for Activate function. The last part of the prepared dataset was used for the test data and the rest was used for the learning model. This model is able to predict the odds within 5 ~ 10 % error. The lack of datasets is left as an unsatisfactory point, it will be possible to reduce the error further if sufficient data is acquired and more improved model is prepared. And this proposed model will be applied to other games or sports games in the future.