• East Asian mathematical journal
• /
• v.34 no.1
• /
• pp.1-16
• /
• 2018

We study an optimization problem for hyperbolic absolute risk aversion (HARA) utility function under two-factor Heston's stochastic volatility model. It is not possible to obtain an explicit solution because our financial market model is complicated. However, by using asymptotic analysis technique, we find the explicit forms of the approximations of the optimal value function and the optimal strategy for HARA utility function.

• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.4
• /
• pp.259-275
• /
• 2021

This study explored the usefulness and implications of the Bayesian hyperparameter optimization in developing species distribution models (SDMs). A variety of machine learning (ML) algorithms, namely, support vector machine (SVM), random forest (RF), boosted regression tree (BRT), XGBoost (XGB), and Multilayer perceptron (MLP) were used for predicting the occurrence of four benthic macroinvertebrate species. The Bayesian optimization method successfully tuned model hyperparameters, with all ML models resulting an area under the curve (AUC) > 0.7. Also, hyperparameter search ranges that generally clustered around the optimal values suggest the efficiency of the Bayesian optimization in finding optimal sets of hyperparameters. Tree based ensemble algorithms (BRT, RF, and XGB) tended to show higher performances than SVM and MLP. Important hyperparameters and optimal values differed by species and ML model, indicating the necessity of hyperparameter tuning for improving individual model performances. The optimization results demonstrate that for all macroinvertebrate species SVM and RF required fewer numbers of trials until obtaining optimal hyperparameter sets, leading to reduced computational cost compared to other ML algorithms. The results of this study suggest that the Bayesian optimization is an efficient method for hyperparameter optimization of machine learning algorithms.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.656-657
• /
• 2015

Recently, Multi-Objective Optimization of design elements is an important issue in building design. Design variables that considering the specificities of the different environments should use the appropriate algorithm on optimization process. The purpose of this study is to compare and analyze the optimal solution using three evolutionary algorithms and energy modeling simulation. This paper consists of three steps: i)Developing three evolutionary algorithm model for optimization of design elements ; ii) Conducting Multi-Objective Optimization based on the developed model ; iii) Conducting comparative analysis of the optimal solution from each of the algorithms. Including Non-dominated Sorted Genetic Algorithm (NSGA-II), Multi-Objective Particle Swarm Optimization (MOPSO) and Random Search were used for optimization. Each algorithm showed similar range of result data. However, the execution speed of the optimization using the algorithm was shown a difference. NSGA-II showed the fastest execution speed. Moreover, the most optimal solution distribution is derived from NSGA-II.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.187-188
• /
• 2011

This paper proposes the hybrid Complex-PSO algorithm based on the complex search method and particle swarm optimization (PSO) for unconstrained optimization. This hybridization intends to produce faster and more accurate convergence to the optimum value. These hybrid will concentrate on determining the dynamic load model parameters, the ZIP model and induction motor model parameters. Measurement-based parameter estimation, which employs measurement data to derive load model parameters, is used. The theoretical foundation of the measurement-based approach is system identification. The main objective of this paper is to demonstrate how the standard particle swarm optimization and complex method can be improved through hybridization of the two methods and the results will be compared with that of their original forms.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.523-528
• /
• 2002

Topology optimization is widely accepted as a conceptual design tool for the product design. Since the resulted layout of the topology optimization is a kind of digital images represented by the density distribution, the seamless process is required to transform digital images to the CAD model for the practical use. In this paper, the general process to construct a CAD model is developed to apply for topology images based on elements. The node density and the morphology technique is adopted to extract boundary contour of the shape and remove the noise of images through erosion and dilation operation. The proposed method automatically generates point data sets of the geometric model. The process is integrated with Pro/Engineer, so that the engineer in practice can directly handle with curves or surface form digital images.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.19 no.9
• /
• pp.884-891
• /
• 2009

This study investigates some of swarm intelligence algorithms to tackle a traditional damage detection problem having stiffness degradation or damage in mechanical structures. Particle swarm(PSO) and ant colony optimization(ACO) methods have been exploited for localizing and estimating the location and extent damages in a structure. Both PSO and ACO are population-based, stochastic algorithms that have been developed from the underlying concept of swarm intelligence and search heuristic. A finite element (FE) model updating is implemented to minimize the difference in a set of natural frequencies between measured and baseline vibration data. Stiffness loss of certain elements is considered to simulate structural damages in the FE model. It is numerically shown that PSO and ACO algorithms successfully completed the optimization process of model updating in locating unknown damages in a truss structure.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.1023-1028
• /
• 2004

A micro-pressure wave is generated by the high-speed train which enters a tunnel, and it causes explosive noise and vibration at the exit. It is known that train speed, train-tunnel area ratio, nose slenderness and nose shape mainly influence on generating micro-pressure wave. So it is required to minimize it by searching optimal values of such train shape factors and tunnel condition. In this study, response surface model, one of approximation models, is used to perform optimization effectively and analyze sensitivity of design variables. Owen's randomized orthogonal array and D-optimal Design are used to construct response surface model. In order to increase accuracy of model, stepwise regression is selected. Finally SQP(Sequential Quadratic Programming) optimization algorithm is used to minimize the maximum micro-pressure wave by using built approximation model.

• Proceedings of the KSME Conference
• /
• 2008.11b
• /
• pp.2440-2443
• /
• 2008

This paper presents a three dimensional shape optimization procedure for a low-speed axial flow fan blade with a weighted average surrogate model. Reynolds-averaged Navier-Stokes equations with shear stress transport turbulence model are discretized by finite volume approximations. Six variables from airfoil profile and lean are selected as design variables. 3D RANS solver is used to evaluate the objective functions of total pressure efficiency. Surrogate approximation models for optimization have been employed to find the optimal design of fan blade. A search algorithm is used to find the optimal design in the design space from the constructed surrogate models for the objective function. The total pressure efficiency is increased by 0.31% with the weighted average surrogate model.

• Water for future
• /
• v.27 no.3
• /
• pp.135-143
• /
• 1994

This paper presents a model for the optimal design of dendritic water distribution systems using linear progranning technique. The optimization model was formulated and applied to a coastal region reclamation project site located in Hae-Ham, Jun-Nam province. The water distribution systems in the region had aleady been designed using a hydraulic simulator(BRANCH). The optimization model developed in this research utilized the data given in the report of the project. The comparison between the systems designed by the simulator and by the optimization model shows that the optimization model provides better results and can be utilized more efficiently in the design of dendritic water distribution systems.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.54 no.2
• /
• pp.53-59
• /
• 2005

In this paper, optimum shape design of permanent magnet in slotted type Permanent Magnet Linear Synchronous Motor(PMLSM) is progressed for minimization of detent force owing to structure of slot-teeth and thrust ripple by harmonic magnetic flux of permanent magnet. In order to reduce remodeling time as changing design parameter for Permanent Magnet shape optimization, the moving model node technique was applied. The characteristics of thrust and detent force computed by finite element analysis are acquired equal effect both skewed basic model and optimum model which is optimization of permanent magnet shape. In addition to, thrust per unit volume is improved 4.l2[%] in optimum model.