• Bulletin of the Korean Chemical Society
• /
• v.26 no.12
• /
• pp.2007-2016
• /
• 2005

An artificial neural network (ANN) is successfully presented for prediction acidity constant (pKa) of various benzoic acids and phenols with diverse chemical structures using a nonlinear quantitative structure-property relationship. A three-layered feed forward ANN with back-propagation of error was generated using six molecular descriptors appearing in the multi-parameter linear regression (MLR) model. The polarizability term $(\pi_1)$, most positive charge of acidic hydrogen atom $(q^+)$, molecular weight (MW), most negative charge of the acidic oxygen atom $(q^-)$, the hydrogen-bond accepting ability $(\epsilon_B)$ and partial charge weighted topological electronic (PCWTE) descriptors are inputs and its output is pKa. It was found that properly selected and trained neural network with 205 compounds could fairly represent dependence of the acidity constant on molecular descriptors. For evaluation of the predictive power of the generated ANN, an optimized network was applied for prediction pKa values of 37 compounds in the prediction set, which were not used in the optimization procedure. Squared correlation coefficient $(R^2)$ and root mean square error (RMSE) of 0.9147 and 0.9388 for prediction set by the MLR model should be compared with the values of 0.9939 and 0.2575 by the ANN model. These improvements are due to the fact that acidity constant of benzoic acids and phenols in water shows nonlinear correlations with the molecular descriptors.

• Journal of the Society of Disaster Information
• /
• v.9 no.3
• /
• pp.324-331
• /
• 2013

Epoxy asphalt concrete is used to reduce dead load and to increase durability on long-span steel bridge overlay. The strength development properties of epoxy asphalt concrete are affected by time and temperature because epoxy asphalt is two-phase reactive materials. The strength development of epoxy asphalt concrete should be predicted precisely to decide traffic opening time. Based on this background in mind, the prediction model for traffic opening time for epoxy asphalt pavement was proposed in this research. The developed model using nonlinear curve fitting revealed R2 value of 0.943 while the R2 value of the existing model using chemical kinetics was 0.806. An improved precise prediction result is to be obtained when the prediction model uses accurate temperature data of pavement.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1281-1284
• /
• 1998

This paper proposes an efficient time series prediction of the nonlinear dynamical discrete-time systems using multilayer neural networks of a hybrid learning algorithm. The proposed learning algorithm is a hybrid backpropagation algorithm based on the steepest descent for high-speed optimization and the dynamic tunneling for global optimization. The proposed algorithm has been applied to the y00 samples of 700 sequences to predict the next 100 samples. The simulation results shows that the proposed algorithm has better performances of the convergence and the prediction, in comparision with that using backpropagation algorithm based on the gradient descent for multilayer neural network.

• The KSFM Journal of Fluid Machinery
• /
• v.16 no.2
• /
• pp.42-47
• /
• 2013

Ship stability prediction is very complex in reality. In this paper, risk based approach is applied to predict the probability of a certified ship, which is effected by the forces of sea especially the wave loading. Safety assessment and risk analysis process are also applied for the probabilistic prediction of ship stability. The survival probability of ships encountering with different waves at sea is calculated by the existed statistics data and risk based models. Finally, ship capsizing probability is calculated according to single degree of freedom(SDF) rolling differential equation and basin erosion theory of nonlinear dynamics. Calculation results show that the survival probabilities of ship excited by the forces of the seas, especially in the beam seas status, can be predicted by the risk based method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.157-160
• /
• 1999

A prediction method of conditional event matching pre-diction (EMP) for a purpose of predicting nonlinear phenomena of insulator pollution was proposed in this paper. The EMP was used if the conditional probability for increase of insulator pollution exceeded a threshold value. A performance of the EMP was strongly related to selection of database of events and a closeness function. By use of the prediction of the insulator pollution based on the conditional EMP, reliable decision making for the washing timing of the polluted insulators was e-valuated based on actual data in Kasatsu substation, Japan.

• Journal of the Korean Applied Science and Technology
• /
• v.25 no.4
• /
• pp.438-445
• /
• 2008

For recipe prediction of colorant proportion showing nonlinear behavior, we modeled the effects of colorant proportion of basic colors on the target colors and predicted colorant proportion necessary for making target colors. First, colorant proportion of basic colors and color information indicated by the instrument was applied by a linear model and a multi-layer perceptrons model with back-propagation learning method. However, satisfactory results were not obtained because of nonlinear property of colors. Thus, in this study the neuro-fuzzy model with merit of artificial neural networks and fuzzy systems was presented. The proposed model was trained with test data and colorant proportion was predicted. The effectiveness of the proposed model was verified by evaluation of color difference(${\Delta}E$).

• Environmental Engineering Research
• /
• v.14 no.2
• /
• pp.102-110
• /
• 2009

Application of artificial intelligence (AI) approaches in eco-environmental modeling has gradually increased for the last decade. Comprehensive understanding and evaluation on the applicability of this approach to eco-environmental modeling are needed. In this study, we reviewed the previous studies that used AI-techniques in eco-environmental modeling. Decision Tree (DT) and Artificial Neural Network (ANN) were found to be major AI algorithms preferred by researchers in ecological and environmental modeling areas. When the effect of the size of training data on model prediction accuracy was explored using the data from the previous studies, the prediction accuracy and the size of training data showed nonlinear correlation, which was best-described by hyperbolic saturation function among the tested nonlinear functions including power and logarithmic functions. The hyperbolic saturation equations were proposed to be used as a guideline for optimizing the size of training data set, which is critically important in designing the field experiments required for training AI-based eco-environmental modeling.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.63 no.4
• /
• pp.307-311
• /
• 2014

Due to the increasing of power consumption, it is difficult to construct accurate prediction model for daily peak power demand. It is very important work to know power demand in next day for manager and control power system. In this research, we develop a daily peak power demand prediction method considering of characteristics of day of week. The proposed method is composed of liner model based on AR model and nonlinear model based on ELM to resolve the limitation of a single model. Using data sets between 2006 and 2010 in Korea, the proposed method has been intensively tested. As the prediction results, we confirm that the proposed method makes it possible to effective estimate daily peak power demand than conventional methods.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.4
• /
• pp.62-66
• /
• 2002

An attempt of using SOCMAC neural network for the prediction of a nonlinear sequence, which is generated by Mackey-Glass equation, is reported. The ,report shows the SOCMAC can handle a system with multi-dimensional continuous inputs, which has been considered very difficult, if not impossible, task to be implemented by a CMAC neural network because of a huge amount of memory required. Also, an improved training method based on the variable receptive fields is proposed. The Performance ranged somewhere around those of TDNN and BP neural networks.

• Proceedings of the KIEE Conference
• /
• 1987.07a
• /
• pp.129-134
• /
• 1987

In this paper, "Revised two-level costate prediction method" is developed to optimize the quadratic performance of a class of nonlinear dynamic systems. To show the merit, of this algorithm, the proposed algorithm is compared With "The new prediction method" and "Two-level costate prediction method". Advantages of this algorithm are illustrated by applying it to three examples, turbine generator system, fermentation Process, power control system in nuclear reactor.