• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.726-730
• /
• 1990

In this paper, assuming that local range information is available, a collision-free path planning algorithm for multiple mobile robots is presented by using Hopfield neural optimization network. The energy function of the network is built using the present position and the goal position of each robot as well as its local range information. The proposed algorithm has several advantages such as the effective passing around obstacles with the directional safety distance, the easy implementation of robot motion planning including its rotation, the real-time path planning capability from the totally localized computations of path for each robot, and the adaptivity on arbitrary environment since any special shape of obstacles is not assumed.

• Structural Engineering and Mechanics
• /
• v.65 no.4
• /
• pp.447-452
• /
• 2018

The controlling and prediction of spring back is one of the most important factors in sheet metal forming processes which require high dimensional precision. The relationship between effective parameters and spring back phenomenon is highly nonlinear and complicated. Moreover, the objective function is implicit with regard to the design variables. In this paper, first the influence of some effective factors on spring back in U-die bending process was studied through some experiments and then regarding the robustness of artificial neural network (ANN) approach in predicting objectives in mentioned kind of problems, ANN was used to estimate a prediction model of spring back. Eventually, the spring back angle was optimized using the Imperialist Competitive Algorithm (ICA). The results showed that the employment of ANN provides us with less complicated and time-consuming analytical calculations as well as good results with reasonable accuracy.

• Proceedings of the KIEE Conference
• /
• 1998.07b
• /
• pp.519-521
• /
• 1998

Fuzzy inference systems have found many applications in recent years. The fuzzy inference system design procedure is related to an expert or a skilled human operator in many fields. Various attempts have been made in optimizing its structure using genetic algorithm automated designs. This paper presents a new approach to structurally optimized designs of FNN models. The messy genetic algorithm is used to obtain structurally optimized fuzzy neural network models. Structural optimization is regarded important before neural network based learning is switched into. We have applied the method to the problem of a time series estimation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.297-300
• /
• 2005

In this study, we proposed genetically optimized self-organizing fuzzy polynomial neural network based on information granulation and evolutionary algorithm (gdSOFPNN), develop a comprehensive design methodology involving mechanisms of genetic optimization. The proposed gdSOFPNN gives rise to a structural Iy and parametrically optimized network through an optimal parameters design available within FPN (viz. the number of input variables, the order of the polynomial, input variables, the number of membership functions, and the apexes of membership function). Here, with the aid of the information granulation, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. The performance of the proposed gdSOFPNN is quantified through experimentation that exploits standard data already used in fuzzy modeling.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2004.11a
• /
• pp.179-188
• /
• 2004

Bankruptcy prediction is an important and widely studied topic since it can have significant impact on bank lending decisions and profitability. Recently, support vector machine (SVM) has been applied to the problem of bankruptcy prediction. The SVM-based method has been compared with other methods such as neural network, logistic regression and has shown good results. Genetic algorithm (GA) has been increasingly applied in conjunction with other AI techniques such as neural network, CBR. However, few studies have dealt with integration of GA and SVM, though there is a great potential for useful applications in this area. This study proposes the methods for improving SVM performance in two aspects: feature subset selection and parameter optimization. GA is used to optimize both feature subset and parameters of SVM simultaneously for bankruptcy prediction.

• KIEE International Transaction on Systems and Control
• /
• v.2D no.2
• /
• pp.53-58
• /
• 2002

In this paper, various aspects in magnetoencephalography (MEG) source localization are studied. To minimize the errors in experimental data, an approximation technique using a polynomial function is proposed. The simulation shows that the proposed technique yields more accurate results. To improve the convergence characteristics in the optimization algorithm, a hybrid algorithm of evolution strategy and sensitivity analysis is applied to the neuromagnetic inverse problem. The effectiveness of the hybrid algorithm is verified by comparison with conventional algorithms. In addition, an artificial neural network (ANN) is applied to find an initial source location quickly and accurately. The simulation indicates that the proposed technique yields more accurate results effectively.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.16 no.6
• /
• pp.125-132
• /
• 2017

Generally, in machining operations, the required machining performance can be obtained by properly combining several machining parameters properly. In this research, we construct a simulation model, which that predicts the relationship between the input variables and output variables in the turning operation. Input variables necessary for the turning operation include cutting speed, feed, and depth of cut. Surface roughness and electrical current consumption are used as the output variables. To construct the simulation model, an Artificial Neural Network (ANN) is employed. With theIn ANN, training is necessary to find appropriate weights, and the Ant Colony Optimization (ACO) technique is used as a training tool. EspeciallyIn particular, for the continuous domain, ACOR is adopted and athe related algorithm is developed. Finally, the effects of the algorithm on the results are identified and analyzsed.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.964-967
• /
• 1993

This paper presents an auto tuning method of fuzzy inference using Genetic Algorithm. The determination of membership functions by human experts is a difficult problem. Therefore, some auto-tuning methods have been proposed to reduce the time-consuming operations. However, the convergence of the tuning by the previous methods depends on the initial conditions of the fuzzy model. So, we proposes an auto tuning method for the fuzzy neural network by Genetic Algorithm (ATF system). This paper shows effectiveness of the ATF system by simulations.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.757-759
• /
• 1996

This paper proposes an application of artificial neural networks to the bus-bar separation in a substation for radial network operation. For the effective bus-bar operation, the insecurity index of transmission line load is introduced. For the radial network operation. the constraints of bus-bar switch is formulated in the performance function with the insecurity index. The determination of bus-bar switching is to find the states of 0 or 1 in the circuit breakers. In this paper, it is tested that the bus-bar separation of binary optimization problem can be solved by Hopfield networks with adequate manipulations.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.2
• /
• pp.19-28
• /
• 2019

The purpose of this study is to examine the trends on machine learning and deep learning research in the published journals from the Web of Science Database. To achieve the study purpose, we used the abstracts of 20,664 articles published between 1990 and 2017, which include the word 'machine learning', 'deep learning', and 'artificial neural network' in their titles. Twenty major research topics were identified from topic modeling analysis and they were inclusive of classification accuracy, machine learning, optimization problem, time series model, temperature flow, engine variable, neuron layer, spectrum sample, image feature, strength property, extreme machine learning, control system, energy power, cancer patient, descriptor compound, fault diagnosis, soil map, concentration removal, protein gene, and job problem. The analysis of the time-series linear regression showed that all identified topics in machine learning research were 'hot' ones.