• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.1
• /
• pp.103-116
• /
• 2021

Analysis of runoff is substantial for effective water management in the watershed. Runoff occurs by reaction of a watershed to the rainfall and has non-linearity and uncertainty due to the complex relation of weather and watershed factors. ANN (Artificial Neural Network), which learns from the data, is one of the machine learning technique known as a proper model to interpret non-linear data. The performance of ANN is affected by the ANN's structure, the number of hidden layer nodes, learning rate, and activation function. Especially, the activation function has a role to deliver the information entered and decides the way of making output. Therefore, It is important to apply appropriate activation functions according to the problem to solve. In this paper, ANN models were constructed to estimate runoff with different activation functions and each model was compared and evaluated. Sigmoid, Hyperbolic tangent, ReLU (Rectified Linear Unit), ELU (Exponential Linear Unit) functions were applied to the hidden layer, and Identity, ReLU, Softplus functions applied to the output layer. The statistical parameters including coefficient of determination, NSE (Nash and Sutcliffe Efficiency), NSEln (modified NSE), and PBIAS (Percent BIAS) were utilized to evaluate the ANN models. From the result, applications of Hyperbolic tangent function and ELU function to the hidden layer and Identity function to the output layer show competent performance rather than other functions which demonstrated the function selection in the ANN structure can affect the performance of ANN.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.25 no.6
• /
• pp.1-11
• /
• 2021

To develop an efficient procedure related to the flamelet library, the machine learning process based on artificial neural network(ANN) is applied for the gaseous hydrogen/liquid oxygen combustor under a supercritical pressure condition. For hidden layers, 25 combinations based on Rectified Linear Unit(ReLU) and hyperbolic tangent are adopted to find an optimum architecture in terms of the computational efficiency and the training performance. For activation functions, the hyperbolic tangent is proper to get the high learning performance for accurate properties. A transformation learning data is proposed to improve the training performance. When the optimal node is arranged for the 4 hidden layers, it is found to be the most efficient in terms of training performance and computational cost. Compared to the interpolation procedure, the ANN procedure reduces computational time and system memory by 37% and 99.98%, respectively.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.5
• /
• pp.445-455
• /
• 2013

A new linearization model for MR dampers is analyzed. The nonlinear hysteretic damping force model of MR damper can be modeled as a hyperbolic tangent function of currents, positions, and velicities, which is an algebraic function with constant parameters. Model parameters can be identified with numerical method using experimental force-velocity-position data obtained from various operating conditions. The nonlinear hysteretic damping force can be linearized with a given slope of damping coefficient if there exist corresponding currents to compensate for the nonlinearity. The corresponding currents can be calculated from the inverse model when the given linear damping force is set equal to the nonlinear hysteretic damping force. The linearization controller is realized in a DSP controller such that the corresponding currents to satisfy a given damping coefficient should be calculated. Experiments show that the current inputs to the MR damper produce linearized damping force with a given slope of the damping coefficient.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.115-122
• /
• 2012

We present here a new class of activation functions for neural networks, which herein will be called CosGauss function. This function is a cosine-modulated gaussian function. In contrast to the sigmoidal-, hyperbolic tangent- and gaussian activation functions, more ridges can be obtained by the CosGauss function. It will be proven that this function can be used to aproximate polynomials and step functions. The CosGauss function was tested with a Cascade-Correlation-Network of the multilayer structure on the Tic-Tac-Toe game and iris plants problems, and results are compared with those obtained with other activation functions.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.4
• /
• pp.462-470
• /
• 1999

In this paper, we proposed a cross-couple controller for compensating nonlinear friction of the X-Y table of CNC machines. Due to the nonlinearity of the frictions, large contour errors, referred to as quadrant glitches, occur when each axis of the X-Y table makes a zero velocity crossing. To reduce the quadrant glitches the friction compensators and nonlinear friction observers for estimating Coulomb frictions are employed in the proposed method. A hyperbolic tangent function is used in reducing the magnitude of quadrant glitches and the CEM (Contour Error Model) is utilized for the estimation of the velocities. The performance of the proposed compensators is evaluated for several trajectories by computer simulations.

• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.625-632
• /
• 2001

Principal component analysis(PCA) is a multivariate technique falling under the general title of factor analysis. The purpose of PCA is to Identify the dependence structure behind a multivariate stochastic observation In order to obtain a compact description of it. In engineering field PCA is utilized mainly (or data compression and restoration. In this paper we propose a new robust Hebbian algorithm for robust PCA. This algorithm is based on a hyperbolic tangent function due to Hampel ef al.(1989) which is known to be robust in Statistics. We do two experiments to investigate the performance of the new robust Hebbian learning algorithm for robust PCA.

• The Bulletin of The Korean Astronomical Society
• /
• v.37 no.1
• /
• pp.85.1-85.1
• /
• 2012

In this study we use three-dimensional magnetohydrodynamic simulations of flux emergence from solar subsurface layer to corona. In order to study the twist parameter of magnetic field we compare the simulations for strongly twisted and weakly twisted cases. Based on the results, we derive a flux expansion factor of selected flux tubes which is a ratio of expanded cross section to the one measured at the footpoint of the flux tube. To understand the effect of flux expansion factor, we make a comparison between magnetic field configuration and the expansion factor. By using a fitting function of hyperbolic tangent we derive noticeable correlations among the strength of the vertical magnetic field, current density and expansion factor. We discuss what these results tell about the relationship between the twist of emerging field and the mechanism for the solar wind.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.11 no.1
• /
• pp.584-596
• /
• 2019

This paper presents a Modified Adaptive Complementary Sliding Mode Control (MACSMC) system for the longitudinal motion control of the Fully-Submerged Hydrofoil Craft (FSHC) in the presence of time varying disturbance and uncertain perturbations. The nonlinear disturbance observer is designed with less conservatism that only boundedness of the derivative of the disturbance is required. Then, a complementary sliding mode control system combined with adaptive law is designed to reduce the bound of stabilization error with fast convergence. In particularly, the modified complementary sliding mode surface which contains the estimation of the disturbance can reduce the switching gain and retain the normal performance of the system. Moreover, a hyperbolic tangent function contained in the control law is utilized to attenuate the chattering of the actuator. The global asymptotic stability of the closed-loop system is demonstrated utilizing the Lyapunov stability theory. Ultimately, the simulation results show the effectiveness of the proposed approach.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.22 no.10
• /
• pp.1020-1023
• /
• 2011

In this paper, we present a symbol remapping method of BRGC M-ary QAM signal by using LLR soft bit decision information which is obtained after iterative decoding process. In order to reconstruct estimated transmitted signal constellation, we have to use exponential or hyperbolic tangent(tanh) function resulting in high implementation complexity. The BRGC mapping rule enables us to use a recursive operation. In addtion, we reduce the implementing complexity by using a curve fitting algorithm.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.363-363
• /
• 2019

활성화 함수(activation function)는 기계학습(machine learning)의 학습과정에 비선형성을 도입하여 심층적인 학습을 용이하게 하고 예측의 정확도를 높이는 중요한 요소 중 하나이다(Roy et al., 2019). 일반적으로 기계학습에서 사용되고 있는 활성화 함수의 종류에는 계단 함수(step function), 시그모이드 함수(sigmoid 함수), 쌍곡 탄젠트 함수(hyperbolic tangent function), ReLU 함수(Rectified Linear Unit function) 등이 있으며, 예측의 정확도 향상을 위하여 다양한 형태의 활성화 함수가 제시되고 있다. 본 연구에서는 기계학습을 통하여 수위예측 시 정확도 향상을 위하여 Hybrid 활성화 함수를 제안하였다. 연구대상지는 조수간만의 영향을 받는 한강을 대상으로 선정하였으며, 2009년 ~ 2018년까지 10년간의 수문자료를 활용하였다. 수위예측 알고리즘은 Python 내 Tensorflow의 RNN (Recurrent Neural Networks) 모델을 이용하였으며, 강수량, 수위, 조위, 댐 방류량, 하천 유량의 수문자료를 학습시켜 3시간 및 6시간 후의 수위를 예측하였다. 예측정확도 향상을 위하여 입력 데이터는 정규화(Normalization)를 시켰으며, 민감도 분석을 통하여 신경망모델의 은닉층 개수, 학습률의 최적 값을 도출하였다. Hybrid 활성화 함수는 쌍곡 탄젠트 함수와 ReLU 함수를 혼합한 형태로 각각의 가중치($w_1,w_2,w_1+w_2=1$)를 변경하여 정확도를 평가하였다. 그 결과 가중치의 비($w_1/w_2$)에 따라서 예측 결과의 RMSE(Roote Mean Square Error)가 최소가 되고 NSE (Nash-Sutcliffe model Efficiency coefficient)가 최대가 되는 지점과 Peak 수위의 예측정확도가 최대가 되는 지점을 확인할 수 있었다. 본 연구는 현재 Data modeling을 통한 수위예측의 정확도 향상을 위해 기초가 되는 연구이나, 향후 다양한 형태의 활성화 함수를 제안하여 정확도를 향상시킨다면 예측 결과를 통하여 침수예보에 대한 의사결정이 가능할 것으로 기대된다.