• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2911-2913
• /
• 1999

This paper suggest an optimal identification method to complex and nonlinear system modeling that is based on Fuzzy-Neural Network(FNN). The FNN modeling implements parameter identification using HCM algorithm and optimal identification algorithm structure combined with two types of optimization theories for nonlinear systems, we use a HCM Clustering Algorithm to find initial parameters of membership function. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using optimal identification algorithm. The proposed optimal identification algorithm is carried out using both a genetic algorithm and the improved complex method. Also, an aggregate objective function(performance index) with weighted value is proposed 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, the data of sewage treatment process and traffic route choice process.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.4
• /
• pp.160-166
• /
• 2002

Since conventional mobile robot control with one module has limitation to solve complex problems, there have been a variety of works on combining multiple modules for solving them. Recently, many researchers attempt to develop mobile robot controllers using artificial life techniques. In this paper, we develop a mobile robot controller using cellular automata based neural networks, where complex tasks are divided to simple sub-tasks and optimal neural structure of each sub-task is explored by genetic algorithm. Neural network modules are combined dynamically using the action selection mechanism, where basic behavior modules compete each other by inhibition and cooperation. Khepera mobile robot simulator is used to verify the proposed model. Experimental results show that complex behaviors emerge from the combination of low-level behavior modules.

• Structural Engineering and Mechanics
• /
• v.83 no.5
• /
• pp.671-680
• /
• 2022

The shear capacity of beams is an essential parameter in designing beams carrying shear loads. Precise estimation of the ultimate shear capacity typically requires comprehensive calculation methods. For steel fiber reinforced concrete (SFRC) beams, traditional design methods may not accurately predict the interaction between different parameters affecting ultimate shear capacity. In this study, artificial neural network (ANN) modeling was utilized to predict the ultimate shear capacity of SFRC beams using ten input parameters. The results demonstrated that the ANN with 30 neurons had the best performance based on the values of root mean square error (RMSE) and coefficient of determination (R²) compared to other ANN models with different neurons. Analysis of the ANN model has shown that the clear shear span to depth ratio significantly affects the predicted ultimate shear capacity, followed by the reinforcement steel tensile strength and steel fiber tensile strength. Moreover, a Genetic Algorithm (GA) was used to optimize the ANN model's input parameters, resulting in the least cost for the SFRC beams. Results have shown that SFRC beams' cost increased with the clear span to depth ratio. Increasing the clear span to depth ratio has increased the depth, height, steel, and fiber ratio needed to support the SFRC beams against shear failures. This study approach is considered among the earliest in the field of SFRC.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.33 no.2
• /
• pp.1-16
• /
• 2008

The purpose of this paper is to propose a new binary classification method for predicting corporate failure based on genetic algorithm, and to validate its prediction power through empirical analysis. Establishing virtual companies representing bankrupt companies and non-bankrupt ones respectively, the proposed method measures the similarity between the virtual companies and the subject for prediction, and classifies the subject into either bankrupt or non-bankrupt one. The values of the classification variables of the virtual companies and the weights of the variables are determined by the proper model to maximize the hit ratio of training data set using genetic algorithm. In order to test the validity of the proposed method, we compare its prediction accuracy with ones of other existing methods such as multi-discriminant analysis, logistic regression, decision tree, and artificial neural network, and it is shown that the binary classification method we propose in this paper can serve as a premising alternative to the existing methods for bankruptcy prediction.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2125-2138
• /
• 2023

The printed circuit heat exchanger (PCHE) with airfoil fins has the benefits of high compactness, high efficiency and superior heat transfer performance. A novel multi-objective optimization approach is presented to design the airfoil fin PCHE in this paper. Three optimization design variables (the vertical number, the horizontal number and the staggered number) are obtained by means of dimensionless airfoil fin arrangement parameters. And the optimization objective is to maximize the Nusselt number (Nu) and minimize the Fanning friction factor (f). Firstly, in order to investigate the impact of design variables on the thermal-hydraulic performance, a parametric study via the design of experiments is proposed. Subsequently, the relationships between three optimization design variables and two objective functions (Nu and f) are characterized by an improved particle swarm optimization-backpropagation artificial neural network. Finally, a multi-objective optimization is used to construct the Pareto optimal front, in which the non-dominated sorting genetic algorithm II is used. The comprehensive performance is found to be the best when the airfoil fins are completely staggered arrangement. And the best compromise solution based on the TOPSIS method is identified as the optimal solution, which can achieve the requirement of high heat transfer performance and low flow resistance.

• Journal of computational fluids engineering
• /
• v.19 no.3
• /
• pp.29-36
• /
• 2014

In the present study, an aerodynamic design optimization of UAV rotor blades was conducted using a genetic algorithm(GA) coupled with computational fluid dynamics(CFD). To reduce computational cost in making databases, a function approximation was applied using artificial neural networks(ANN) based on a radial basis function network. Three dimensional Reynolds-Averaged Navier-Stokes(RANS) solver was used to solve the flow around UAV rotor blades. Design directions were specified to maximize thrust coefficient maintaining torque coefficient and minimize torque coefficient maintaining thrust coefficient. Design variables such as twist angle, thickness and chord length were adopted to perform a planform optimization. As a result of an optimization regarding to maximizing thrust coefficient, thrust coefficient was increased about 4.5% than base configuration. In case of an optimization minimizing torque coefficient, torque coefficient was decreased about 7.4% comparing with base configuration.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.10
• /
• pp.9-21
• /
• 2020

The aim of this paper is to predict the Borsa Istanbul (BIST) 30 index movements to determine the most accurate buy and sell decisions using the methods of Artificial Neural Networks (ANN) and Genetic Algorithm (GA). We combined these two methods to obtain a hybrid intelligence method, which we apply. In the financial markets, over 100 technical indicators can be used. However, several of them are preferred by analysts. In this study, we employed nine of these technical indicators. They are moving average convergence divergence (MACD), relative strength index (RSI), commodity channel index (CCI), momentum, directional movement index (DMI), stochastic oscillator, on-balance volume (OBV), average directional movement index (ADX), and simple moving averages (3-day moving average, 5-day moving average, 10-day moving average, 14-day moving average, 20-day moving average, 22-day moving average, 50-day moving average, 100-day moving average, 200-day moving average). In this regard, we combined these two techniques and obtained a hybrid intelligence method. By applying this hybrid model to each of these indicators, we forecast the movements of the Borsa Istanbul (BIST) 30 index. The experimental result indicates that our best proposed hybrid model has a successful forecast rate of 75%, which is higher than the single ANN or GA forecasting models.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.6
• /
• pp.15-26
• /
• 2006

Although numerous investigations have been performed over the years to predict the behavior and bearing capacity of piles, the mechanisms are not yet entirely understood. The prediction of bearing capacity is a difficult task, because large numbers of factors affect the capacity and also have complex relationship one another. Therefore, it is extremely difficult to search the essential factors among many factors, which are related with ground condition, pile type, driving condition and others, and then appropriately consider complicated relationship among the searched factors. The present paper describes the application of Artificial Neural Network (ANN) in predicting the capacity including its components at the tip and along the shaft from dynamic load test of the driven piles. Firstly, the effect of each factor on the value of bearing capacity is investigated on the basis of sensitivity analysis using ANN modeling. Secondly, the authors use the design methodology composed of ANN and genetic algorithm (GA) to find optimal neural network model to predict the bearing capacity. The authors allow this methodology to find the appropriate combination of input parameters, the number of hidden units and the transfer structure among the input, the hidden and the out layers. The results of this study indicate that the neural network model serves as a reliable and simple predictive tool for the bearing capacity of driven piles.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.9
• /
• pp.27-35
• /
• 2021

Artificial life is used in various fields of applied science by evaluating natural life-related systems, their processes, and evolution. Research has been actively conducted to evolve physical body design and behavioral control strategies for the dynamic activities of these artificial life forms. However, since co-evolution of shapes and neural networks is difficult, artificial life with optimized movements has only one movement in one form and most do not consider the environmental conditions around it. In this paper, artificial life that co-evolve bodies and neural networks using predator-prey models have environmental adaptive movements. The predator-prey hierarchy is then extended to the top-level predator, medium predator, prey three stages to determine the stability of the simulation according to initial population density and correlate between body evolution and population dynamics.