• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.2
• /
• pp.143-148
• /
• 2012

This paper proposes a new method to improve performance of AdaBoost by using a distance weight function to increase the accuracy of its machine learning processes. The proposed distance weight algorithm improves classification in areas where the original binary classifier is weak. This paper derives the new algorithm's optimal solution, and it demonstrates how classifier accuracy can be improved using the proposed Distance Sensitive AdaBoost in a simulation experiment of pedestrian detection.

• Proceedings of the KSME Conference
• /
• 2008.11a
• /
• pp.1236-1239
• /
• 2008

Through the optimization design of the pneumatic components it leads the energy efficiency increasement and resources saving. Also it effects on the high speed operation, low speed operation, low weight, and complexity of pneumatic systems. In this paper the development of the software will be described based on Object-Oriented technology, which will provide function for development of pneumatic system without any deep knowledge about pneumatic system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.8
• /
• pp.854-867
• /
• 2014

This paper deals with the performance comparison of a PSO algorithm inspired in the process of simulating the behavior pattern of the organisms. The PSO algorithm finds the optimal solution (fitness value) of the objective function based on a stochastic process. Generally, the stochastic process, a random function, is used with the expression related to the velocity included in the PSO algorithm. In this case, the random function of the normal distribution (Gaussian) or uniform distribution are mainly used as the random function in a PSO algorithm. However, in this paper, because the probability distribution which is various with 2 shape parameters can be expressed, the performance comparison of a PSO algorithm using the beta probability distribution function, that is a random function which has a high degree of freedom, is introduced. For performance comparison, 3 functions (Rastrigin, Rosenbrock, Schwefel) were selected among the benchmark Set. And the convergence property was compared and analyzed using PSO-FIW to find the optimal solution.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.10
• /
• pp.812-818
• /
• 2001

This paper proposes an optimum design method of structural and control systems, taking a 2-D truss structure as an example. The structure is supposed to be subjected to initial static loads and disturbances. For the structure, a FEM model is formed, and using modal transformation, the equation of motion is transformed into that of modal coordinates in order to reduce the D.O.F. of the FEM model. The structure is controlled by an output feedback $H^$\infty$$ controller to suppress the effect of the disturbances. The design variables of the simultaneous optimal design of control-structure systems are the cross sectional areas of truss members. The structural objective function is the structural weight. The control objective function is the $H^$\infty$$ norm, that is, the performance index of control. The second structural objective function is the energy of the response related to the initial state, which is derived from the time integration of the quadratic form of the state in the closed-loop system. In a numerical example, simulations have been carried out. Through the consideration of structural weight and $H^$\infty$$ norm, an advantage of the simultaneous optimum design of structural and control systems is shown. Moreover, while the optimized performance index of control is almost kept, we can acquire better design of structural strength.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.22 no.2
• /
• pp.1-12
• /
• 2019

Open space planners and designers should consider scientific and quantified functions of trees when they have to locate where to plant the tree. However, until now, most planners and designers could not consider them because of lack of tool for considering scientific and quantitative tree functions. This study introduces a tree location supporting tool which focuses on the multi-objective including scientific function using ACO (Ant colony optimization). We choose shading effect (scientific function), shielding, and openness as objectives for test application. The results show that when the user give a high weight to a particular objective, they can obtain the optimal results with high value of that objective. When we allocate higher weight for the shading effect, the tree plans provide larger shadow value. Even when compared with current tree plan, the study result has a larger shading effect plan. This result will reduce incident radiation to the ground and make thermal friendly open space in the summer. If planners and designers utilize this tool and control the objectives, they would get diverse optimal tree plans and it will allow them to make use of the many environmental benefits from trees.

• International Journal of Advanced Culture Technology
• /
• v.5 no.2
• /
• pp.82-89
• /
• 2017

The range of problems that can be handled by the activation of big data and the development of hardware has been rapidly expanded and machine learning such as deep learning has become a very versatile technology. In this paper, mnist data set is used as experimental data, and the Cross Entropy function is used as a loss model for evaluating the efficiency of machine learning, and the value of the loss function in the steepest descent method is We applied the GradientDescentOptimize algorithm to minimize and updated weight and bias via backpropagation. In this way we analyze optimal reliability value corresponding to the number of exercises and optimal reliability value without overfitting. And comparing the overfitting time according to the number of data changes based on the number of training times, when the training frequency was 1110 times, we obtained the result of 92%, which is the optimal reliability value without overfitting.

• Journal of Sensor Science and Technology
• /
• v.25 no.6
• /
• pp.431-434
• /
• 2016

Currently, the radial basis function network (RBFN) and various other neural networks are employed to classify gases using chemical sensors arrays, and their performance is steadily improving. In particular, the identification performance of the RBFN algorithm is being improved by optimizing parameters such as the center, width, and weight, and improved algorithms such as the radial basis function network-stochastic gradient (RBFN-SG) and radial basis function network-normalized stochastic gradient (RBFN-NSG) have been announced. In this study, we optimized the number of centers, which is one of the parameters of the RBFN-NSG algorithm, and observed the change in the identification performance. For the experiment, repeated measurement data of 8 samples were used, and the elbow method was applied to determine the optimal number of centers for each sample of input data. The experiment was carried out in two cases(the only one center per sample and the optimal number of centers obtained by elbow method), and the experimental results were compared using the mean square error (MSE). From the results of the experiments, we observed that the case having an optimal number of centers, obtained using the elbow method, showed a better identification performance than that without any optimization.

• Journal of Korea Water Resources Association
• /
• v.31 no.5
• /
• pp.599-612
• /
• 1998

Numerical analysis of convection-dominated transport problems are challenging because of dual characteristics of the governing equation. In the finite element method, a strategy is to modify the test function to weight more in the upwind direction. This is called as the Petrov-Galerkin method. In this paper, both N+1 and N+2 Petrov-Galerkin methods are applied to transport problems at high grid Peclet number. Frequency fitting algorithm is used to obtain optimal levels of N+2 upwinding, and the results are discussed. Also, a new Petrov-Galerkin method, named as "Optimal Test Function Petrov-Galerkin Method," is proposed in this paper. The test function of this numerical method changes its shape depending upon relative strength of the convection to the diffusion. A numerical experiment is carried out to demonstrate the performance of the proposed method.

• International Journal of Aeronautical and Space Sciences
• /
• v.11 no.1
• /
• pp.19-25
• /
• 2010

A computational study for the optimal design of heat exchangers (HX) used in a high temperature and high pressure system is presented. Two types of air to air HX are considered in this study. One is a single-pass cross-flow type with straight plain tubes and the other is a two-pass cross-counter flow type with plain U-tubes. These two types of HX have the staggered arrangement of tubes. The design models are formulated using the number of transfer units ($\varepsilon$-NTU method) and optimized using a genetic algorithm. In order to design compact light weight HX with the minimum pressure loss and the maximum heat exchange rate, the weight of HX core is chosen as the object function. Dimensions and tube pitch ratio of a HX are used as design variables. Demanded performance such as the pressure loss (${\Delta}P$) and the temperature drop (${\Delta}T$) are used as constraints. The performance of HX is discussed and their optimal designs are presented with an investigation of the effect of design variables and constraints.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.96-101
• /
• 2007

A new metallic sandwich panel with a quasi-Kagome truss core subjected to bending load has been analyzed. First, equations of the failure loads corresponding to the eight failure modes are presented. Then, non-dimensional forms of the equations are derived as functions of three geometric variables, one material parameter (yield strain), one load index and one weight index. Failure maps are presented for a given weight index. By using the dimensionless forms of equations as the design constraints, two kinds of optimization are performed. One is based on the weight, that is, the objective function, namely, the dimensionless load is to be maximized for a given weight. Another is based on the load, that is, the dimensionless weight is to be minimized for a given load. The results of the two optimization processes are found to agree each other. The optimized geometric variables are derived as a function of given weights or failure loads. The performance of the quasi-Kagome truss as the core of a sandwich panel is evaluated by comparison with those of honeycomb cored and octet truss cored panels