• Journal of Information Technology Applications and Management
• /
• v.19 no.1
• /
• pp.1-12
• /
• 2012

Data mining is the process of searching and analyzing large quantities of data for finding out meaningful patterns and rules. Artificial Neural Network (ANN) is one of the tools of data mining which is becoming very popular in forecasting the future values. Some of the areas where it is used are banking, medicine, retailing and fraud detection. In finance, artificial neural network is used in various disciplines including stock market forecasting. In the stock market time series, due to high volatility, it is very important to choose a model which reads volatility and forecasts the future values considering volatility as one of the major attributes for forecasting. In this paper, an attempt is made to develop two models - one using feed forward back propagation Artificial Neural Network and the other using Autoregressive Conditional Heteroskedasticity (ARCH) technique for forecasting stock market returns. Various parameters which are considered for the design of optimal ANN model development are input and output data normalization, transfer function and neuron/s at input, hidden and output layers, number of hidden layers, values with respect to momentum, learning rate and error tolerance. Simulations have been done using prices of daily close of Sensex. Stock market returns are chosen as input data and output is the forecasted return. Simulations of the Model have been done using MATLAB$^{(R)}$ 6.1.0.450 and EViews 4.1. Convergence and performance of models have been evaluated on the basis of the simulation results. Performance evaluation is done on the basis of the errors calculated between the actual and predicted values.

• Structural Engineering and Mechanics
• /
• v.77 no.1
• /
• pp.47-56
• /
• 2021

This paper deals with damage detection using a Gapped Smoothing Method (GSM) combined with deep learning. Convolutional Neural Network (CNN) is a model of deep learning. CNN has an input layer, an output layer, and a number of hidden layers that consist of convolutional layers. The input layer is a tensor with shape (number of images) × (image width) × (image height) × (image depth). An activation function is applied each time to this tensor passing through a hidden layer and the last layer is the fully connected layer. After the fully connected layer, the output layer, which is the final layer, is predicted by CNN. In this paper, a complete machine learning system is introduced. The training data was taken from a Finite Element (FE) model. The input images are the contour plots of curvature gapped smooth damage index. A free-free beam is used as a case study. In the first step, the FE model of the beam was used to generate data. The collected data were then divided into two parts, i.e. 70% for training and 30% for validation. In the second step, the proposed CNN was trained using training data and then validated using available data. Furthermore, a vibration experiment on steel damaged beam in free-free support condition was carried out in the laboratory to test the method. A total number of 15 accelerometers were set up to measure the mode shapes and calculate the curvature gapped smooth of the damaged beam. Two scenarios were introduced with different severities of the damage. The results showed that the trained CNN was successful in detecting the location as well as the severity of the damage in the experimental damaged beam.

• Nuclear Engineering and Technology
• /
• v.38 no.1
• /
• pp.81-92
• /
• 2006

In this study, the core dynamics of a PWR reactor is identified online by a recursive least-squares method. Based on the identified reactor model consisting of the control rod position and the core average coolant temperature, the future average coolant temperature is predicted. A model predictive control method is applied to designing an automatic controller for the thermal power control of PWR reactors. The basic concept of the model predictive control is to solve an optimization problem for a finite future at current time and to implement as the current control input only the first optimal control input among the solutions of the finite time steps. At the next time step, this procedure for solving the optimization problem is repeated. The objectives of the proposed model predictive controller are to minimize both the difference between the predicted core coolant temperature and the desired temperature, as well as minimizing the variation of the control rod positions. In addition, the objectives are subject to the maximum and minimum control rod positions as well as the maximum control rod speed. Therefore, a genetic algorithm that is appropriate for the accomplishment of multiple objectives is utilized in order to optimize the model predictive controller. A three-dimensional nuclear reactor analysis code, MASTER that was developed by the Korea Atomic Energy Research Institute (KAERI) , is used to verify the proposed controller for a nuclear reactor. From the results of a numerical simulation that was carried out in order to verify the performance of the proposed controller with a $5\%/min$ ramp increase or decrease of a desired load and a $10\%$ step increase or decrease (which were design requirements), it was found that the nuclear power level controlled by the proposed controller could track the desired power level very well.

• Journal of Environmental Impact Assessment
• /
• v.14 no.2
• /
• pp.55-62
• /
• 2005

This study applied the Neural Network and Fuzzy theory to show water-purity control and preventive measure in water quality forecasting of the future river. This study picked out NAJU and HAMPYUNG as the subject of investigation and used monthly the water quality and the outflow data of KWANGJU2, NAJU, YOUNGSANNPO and HAMPYUNG from 1995 to 1999 to forecast BOD, COD, T-N, T-P water density. The datum from 1995 to 1999 are used for study and that of 2000 are used for verification. To develop model of water quality forecasting, firstly, this research formed Neural Network model and divided Neural Network model into two case - the case of considering lag and not considering. And this study selected optimal Neural Network model through changing the number of hidden layer based on input layer(n) from n to 3n. Through forecasting result, the case without considering lag showed more precise simulated result. Accordingly, this study intended to compare, analyse that Fuzzy model using the method without considering lag with Neural Network model. As a result, this study found that the model without considering lag in Neural Network Network shows the most excellent outcome. Thus this study examined a forecasting accuracy, analyzed result and verified propriety through appling the method of water quality forecasting using Neural Network and Fuzzy Algorithms to the actual case.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1473-1476
• /
• 1997

This paper presents a scheme for continuous-time fuzzy modelling of nonlinear systems, based on the adjustment technique and the genetic algorithm technque. The fuzzy model is characterized by fuzzy "If-then" rules whcih represent locally linear input-output relations whose consequence part is defined as subsystem of a nonlinear system. To compute the final output and deal with the initialization and unmeasurable signal problems in on-line estimatio of the fuzzy model, a discrete-time model is obtaned. Then the parameters of both the premis and consequence of the fuzzy model are adjusted on-line by a genetic algorithm. A simulation work is carried out to demonstrate the effectiveness of the proposed method.ed method.

• International Journal of Automotive Technology
• /
• v.8 no.3
• /
• pp.351-359
• /
• 2007

In this study, a hierarchical switching control scheme based on robust control theory is proposed for tracking control of vehicle longitudinal acceleration in the presence of large uncertainties. A model set consisting of four multiplicative-uncertainty models is set up, and its corresponding controller set is designed by the LMI approach, which can ensures the robust performance of the closed loop system under arbitray switching. Based on the model set and the controller set, a switching index function by estimating the system gain of the uncertainties between the plant and the nominal model is designed to determine when and which controller should be switched into the closed loop. After theoretical analyses, experiments have also been carried out to validate the proposed control algorithm. The results show that the control system has good performance of robust stability and tracking ability in the presence of large uncertainties. The response time is smaller than 1.5s and the max tracking error is about $0.05\;m/S^2$ with the step input.

• Journal of the Korean Society of Industry Convergence
• /
• v.11 no.2
• /
• pp.71-82
• /
• 2008

In this study, 3 dimensional non-linear race car vehicle model including Chassis, steering and suspension systems were modeled by using Multi-Body Dynamics Simulation Program, DADS 9.5(Dynamic Analysis and Design System),which was used in kinematic and dynamic analysis. A full race car vehicle dynamics model using DADS program was presented and analysis was carried out to estimate the handling characteristics that may be very useful to design a race car in early design stage. The simulation of vehicle handling behavior for step steering input was simulated and compared with different design parameters: torsional stiffness of the front and rear anti roll bars, the motion ratio of the front and rear suspension system, the location of the tie rod joint, in multibody dynamic model. Therefore this simulation model before race car construction in early design step will be helpful for race car designer to save time and limited budget.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.420-423
• /
• 2001

In this paper, the Multi-FNNs(Fuzzy-Neural Networks) architecture is identified and optimized using HCM(Hard C-Means) clustering method and genetic algorithms. The proposed Multi-FNNs architecture uses simplified inference and linear inference as fuzzy inference method and error back propagation algorithm as learning rules. Here, HCM clustering method, which is carried out for the process data preprocessing of system modeling, is utilized to determine the structure of Multi-FNNs according to the divisions of input-output space using I/O process data. Also, the parameters of Multi-FNNs model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is used to achieve a sound balance between approximation and generalization abilities of the model. To evaluate the performance of the proposed model we use the time series data for gas furnace and the NOx emission process data of gas turbine power plant.

• The Journal of Information Systems
• /
• v.8 no.2
• /
• pp.91-110
• /
• 1999

Recently, searching agent systems to help purchase of products between business and customer have been actively studied in Electronic Commerce(EC). However, the most of comparative searching agent systems are only provided customers with searching results by the keyword-based search, and is not support the efficient decision models to be selected products considering the customer's requirements. This paper proposes the decision agent system applied decision model as well as searching functions based on the keyword-input to be selected useful products in EC. The proposed decision agent system is consist of the user interface, provider interface, decision model. Especially, as the example of the decision model, this paper is designed and implemented the prototype of decision agent system which is normalized the searching data and value of customer's preference weight as to each attribute, and orderly provided customers with computed results. This agent system is also carried out sensitive analysis according to the reflection ratio of the each attribute.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.138-138
• /
• 2000

In this paper, a methodology for designing a controller based on inverse dynamics for speed control of DC motors is presented. The proposed controller consists of a prefilter, the inverse dynamic model of a system and a fuzzy logic controller. The prefilter prevents high frequency effects from the inverse dynamic model. The model of the system is characterized by a nonlinear equation with coulomb friction. The fuzzy logic controller regulates the error between the set-point and the system output which may be caused by disturbances and it simultaneously traces the change o( the reference input. The parameters of the model are estimated by a genetic a]gorithm. An experimental work on a DC motor system is carried out to illustrate the performance of the proposed controller