• International Journal of Internet, Broadcasting and Communication
• /
• 제12권3호
• /
• pp.125-130
• /
• 2020

At the end of 1997, the volatility of the exchange rate intensified as the nation's exchange rate system was converted into a free-floating exchange rate system. As a result, managing the exchange rate is becoming a very important task, and the need for forecasting the exchange rate is growing. The exchange rate prediction model using the existing exchange rate prediction method, statistical technique, cannot find a nonlinear pattern of the time series variable, and it is difficult to analyze the time series with the variability cluster phenomenon. And as the number of variables to be analyzed increases, the number of parameters to be estimated increases, and it is not easy to interpret the meaning of the estimated coefficients. Accordingly, the exchange rate prediction model using artificial neural network, rather than statistical technique, is presented. Using DNN, which is the basis of deep learning among artificial neural networks, and LSTM, a recurrent neural network model, the number of hidden layers, neurons, and activation function changes of each model found the optimal exchange rate prediction model. The study found that although there were model differences, LSTM models performed better than DNN models and performed best when the activation function was Tanh.

• Journal of Advanced Research in Ocean Engineering
• /
• 제2권1호
• /
• pp.1-11
• /
• 2016

The objective of this paper is to present an analytical solution in deep water waves and verify the validity of the theory (Shin, 2015). Hence this is a follow-up to Shin (2015). Instead of a variational approach, another approach was considered for a more accurate assessment in this study. The products of two coefficients were not neglected in this study. The two wave profiles from the KFSBC and DFSBC were evaluated at N discrete points on the free-surface, and the combination coefficients were determined for when the two curves pass the discrete points. Thus, the solution satisfies the differential equation (DE), bottom boundary condition (BBC), and the kinematic free surface boundary condition (KFSBC) exactly. The error in the dynamic free surface boundary condition (DFSBC) is less than 0.003%. The wave theory was simplified based on the assumption tanh $D{\approx}1$ in this paper. Unlike the perturbation method, the results are possible for steep waves and can be calculated without iteration. The result is very simple compared to the 5th Stokes' theory. Stokes' breaking-wave criterion has been checked in this study.

• 제어로봇시스템학회지
• /
• 제22권2호
• /
• pp.29-33
• /
• 2016

본 기술 특집호에서는 최근메 강인제어 분야에서 많이 주목받고 있는 사전규정 오차 구속제어기법들메 대해 기본적인 개념과 각 구속제어 기법들이 특징들을 소개한다. 기존의 제어기법들은 안정도 및 일정한 출력성능은 보장하지만 선정된 제어기 게인 값에 따라 추종성능이 민감하게 변하며 안전을 위한 제약이 없는데 반해 이러한 구속제어는 최소한의 게인 선정으로 오버슈트, 정상오차 등에 대해 사전에 규정한 성능범위를 만족하도록 강제로 구속시켜 출력성능 및 안전성이 동시에 보장되도록 한다. 이러한 구속제어는 오버슈트에 크게 영향을 받는 정밀기기 위치제어, 힘 제어에서 안전성을 확보해주며 외란이나 시스템 불확실성에 매우 강인한 특성을 갖는다. 가장 먼저 연구된 구속제어는 funnel 제어로서 시스템의 동적 모델을 포함하지 않는 비모델 기준 제어기법이다. 추종오차의 초기값이 오차에 대한 사전 구속함수로 구성된 funnel (깔데기) 안에 있으면 항상 사전메 규정된 오차범위 내에 머물도록 funnel 제어기가 작동하며 PD 제어와 구조가 유사하다. 다음으로 tanh 함수와 추종오차 변환을 결합한 방법으로서 전통적인 순환적 (recursive) 제어방법인 backstepping 제어와 결합하는 방법이다. 최종적므로 좀더 단순한 오차변환을 통해 오차에 대한 switching을 이용한 기법은 제어기 구조를 단순하게 만들고 기존의 제어기와 편리하게 결합할 수 있다. 이러한 구속제어 기법들은 또한 미지의 시스템에 특성에 대해 관측기나 지능제어를 이용한 근사함수를 요구하지 않는다. 본 특집호에서는 최근까지 연구된 구속제어에 대한 간단한 이론과 적용 결과들을 제시하기로 한다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제10권2호
• /
• pp.25-30
• /
• 2018

This paper is about wine quality classification with multilayer perceptron using the deep neural network. Wine complexity is an issue when predicting the quality. And the deep neural network is considered when using complex dataset. Wine Producers always aim high to get the highest possible quality. They are working on how to achieve the best results with minimum cost and efforts. Deep learning is the possible solution for them. It can help them to understand the pattern and predictions. Although there have been past researchers, which shows how artificial neural network or data mining can be used with different techniques, in this paper, rather not focusing on various techniques, we evaluate how a deep learning model predicts for the quality using two different activation functions. It will help wine producers to decide, how to lead their business with deep learning. Prediction performance could change tremendously with different models and techniques used. There are many factors, which, impact the quality of the wine. Therefore, it is a good idea to use best features for prediction. However, it could also be a good idea to test this dataset without separating these features. It means we use all features so that the system can consider all the feature. In the experiment, due to the limited data set and limited features provided, it was not possible for a system to choose the effective features.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2006년도 International Symposium on GPS/GNSS Vol.2
• /
• pp.101-106
• /
• 2006

The geoidal undulations are needed for determining the orthometric heights from the Global Positioning System GPS-derived ellipsoidal heights. There are several methods for geoidal undulation determination. The paper presents a method employing a simple architecture Two Layer Multiquadric-Biharmonic Artificial Neural Network (TLMB-ANN) to approximate an area of 4200 square kilometres quasigeoid surface with GPS-levelling data. Hardy’s Multiquadric-Biharmonic functions is used as the hidden layer neurons’ activation function and Levenberg-Marquardt algorithm is used to train the artificial neural network. In numerical examples five surfaces were compared: the gravimetric geometry hybrid quasigeoid, Support Vector Machine (SVM) model, Hybrid Fuzzy Neural Network (HFNN) model, Traditional Three Layer Artificial Neural Network (ANN) with tanh activation function and TLMB-ANN surface approximation. The effectiveness of TLMB-ANN surface approximation depends on the number of control points. If the number of well-distributed control points is sufficiently large, the results are similar with those obtained by gravity and geometry hybrid method. Importantly, TLMB-ANN surface approximation model possesses good extrapolation performance with high precision.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제67차 동계학술대회논문집 31권1호
• /
• pp.315-316
• /
• 2023

본 논문에서는 딥러닝을 활용하여 KBO (Korea Baseball Organization)의 다음 시즌 플레이오프 진출 확률을 예측하는 Deep Neural Network (DNN) 시스템을 설계하고 구현하는 방법을 제안한다. 연구 방법으로 KBO 각 시즌별 데이터를 1999년도 데이터부터 수집하여 분석한 결과, 각 시즌 데이터 중 경기당 평균 득점, 타자 OPS, 투수 WHIP 등이 시즌 결과에 유의미한 영향을 끼치는 것을 확인하였다. 모델 설계는 linear, softmax 함수를 사용하는 것보다 relu, tanh, sigmoid 함수를 사용했을 때 더 높은 정확도를 얻을 수 있었다. 실제 2022 시즌 결과를 예측한 결과 88%의 정확도를 도출했다. 폭투의 수, 피홈런 등 가중치가 높은 변수의 값이 우수할 경우 시즌 결과가 좋게 나온다는 것이 증명되었다. 본 논문에서 설계한 이 시스템은 KBO 구단만이 아닌 모든 야구단에서 선수단을 구성하는데 활용 가능하다고 사료된다.

• Journal of Information Processing Systems
• /
• 제19권6호
• /
• pp.842-857
• /
• 2023

Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speech and emoticons without comprehending users' emotional inclinations and grasping moral nuances. This study proposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the model employs a combined stop-word list and word2vec for word vectorization. To mitigate local information loss, the TextCNN model, devoid of pooling layers, is employed for local feature extraction, while BiLSTM is utilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments are categorized using a classification layer. Given the binary classification task at the output layer and the numerous hidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findings demonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a 1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to the individual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9% in precision, recall, and F1 values.

• 한국추진공학회지
• /
• 제3권2호
• /
• pp.10-17
• /
• 1999

후류손실을 가지는 혼합 전단층에 대하여 밀도변화가 없는 유동 및 밀도변화가 있는 유동의 선형 불안정성 해석을 수행하였다. 기본유동의 속도장 및 밀도장은 tanh 함수를 사용하였으며, Gaussian 형태의 해석적 함수를 사용하여 두 유동을 분리시키는 평판 바로 다음에 존재하는 후류 손실 유동을 포함시켰다. 공간적 선형 불안정성 해석을 수행하여 불안정성 모드의 성장률과 파장속도를 주파수의 함수로서 구하였다. 해석 결과로부터 후류 손실을 가지는 혼합층은 sinuous 모드와 varicose 모드의 두 개의 불안정성 모드를 가짐을 알았다. 밀도가 균일한 경우에는 varicose 모드보다 sinuous 모드가 지배적이다. 밀도구배가 존재하나 빠른 자유유동의 밀도가 높은 경우에는 밀도가 균일한 경우와 마찬가지로 sinuous모드가 지배적인 모드가 된다. 그러나 느린 자유 유동의 밀도가 높은 경우에는 밀도장의 두께가 속도장의 두께보다 상대적으로 얇아지면 varicose 모드가 sinuous 모드보다 더욱 불안정하여질 수 있다. varicose 모드와 sinuous 모드의 성장률이 비슷한 밀도장의 두께에서는 두 불안정성 모드가 주파수가 변함에 따라 분지되어지는 경향을 보인다.

• 환경영향평가
• /
• 제18권6호
• /
• pp.461-467
• /
• 2009

This paper provides two case studies of environmental impacts with socio-economic values. The first case is on flood protection levees conducted from 2003 to 2004 in Phu Tan district, An Giang province. The impacts were found by comparing full flood protection levees area (FFPL) to non-full flood protection levees area (NFFPL). Participatory Rural Appraisal (PRA) tools per each group of rich, middle, and poor people were used to list the impacts. Then, major impacts were selected by ranking and interviewing 60 households per site, and assessed by Cost Benefit Analysis (CBA) in rice production from 1996 to 2002 between two areas. The tested research indicated moving system of NFFPL to that of FFPL lost about 11 million VND/ha/year. The second case is on impacts of Penaeid shrimp farming conducted in Duyen Hai District, Tra Vinh Province in 2004-2005. Ninety households and 12 local officials were interviewed. Four PRAs were conducted and 36 water samples were taken inside and outside shrimp pond to measure values of DO, COD, Fe total, TSS, N-$NO_3{^-}$, N-$NH_4{^+}$, P-$PO{_4}^{3-}$, and Chlorophyll-a. Research results showed only 36.7% of the households got profit from shrimp farming. Highest financial efficiency was 0.72 for the semi-intensive system. Tested water indicators showed surface water quality did not match Vietnamese standard for surface water in coastal area (TCVN 5943-1995) and in rain. The water was very muddy and contaminated by organic aluminum. Summarily, the impacts were clarified more obviously via adding socio-economic values to assessment. Importantly, the values were transformed to household's income which is an indicator for policy-makers to consider the impacts obviously. Besides, data of different group of people impacted are cases contributing to consideration of the impacts in an appropriate social level.

• 천문학회지
• /
• 제34권4호
• /
• pp.309-311
• /
• 2001

Strong thermal X-ray emission, called Galactic Ridge X-ray Emission, is observed along the Galactic plane (Koyama et al. 1986). The origin of hot ($\~$7 keV) component of GRXE is not known, while cool ($\~$0.8 keV) one is associated with supernovae (Kaneda et al. 1997, Sugizaki et al. 2001). We propose a possible mechanism to explain the origin; locally strong magnetic fields of $B_{local}\;\~30{\mu}G$ heat interstellar gas to $\~$7 keV via magnetic reconnection (Tanuma et al. 1999). There will be the small-scale (< 10 pc) strong magnetic fields, which can be observed as $(B)_{obs} \;\~3{\mu}G$ by integration of Faraday Rotation Measure, if it is localized by a volume filling factor of f $\~$ 0.1. In order to examine this model, we solved three-dimensional (3D) resistive magnetohydrodynamic (MHD) equations numerically to examine the magnetic reconnect ion triggered by a supernova shock (fig.l). We assume that the magnetic field is Bx = 30tanh(y/20pc) $\mu$G, By = Bz = 0, and the temperature is uniform, at the initial condition. We put a supernova explosion outside the current sheet. The supernova-shock, as a result, triggers the magnetic reconnect ion, and the gas is heatd to > 7 keV. The magnetic reconnect ion heats the interstellar gas to $\~$7 keV in the Galactic plane, if it occurs in the locally strong magnetic fields of $B_{local}\;\~30{\mu}G$. The heated plasma is confined by the magnetic field for $\~10^{5.5} yr$. The required interval of the magnetic reconnect ions (triggered by anything) is $\~$1 - 10 yr. The magnetic reconnect ion will explain the origin of X-rays from the Galactic ridge, furthermore the Galactic halo, and clusters of galaxies.