• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.16 no.1
• /
• pp.105-111
• /
• 2003

Wheel for passenger car support the car weight with tires, and they transmit rolling and braking power into the ground. Whittling away at wheel weight is more effective to boost fuel economy than lighting vehicle body structure. A shape of hole in disk is optimized for minimizing the weight of steel wheel. Pro/ENGINEER program is used for formulating the design model, and ANSYS package is selected for analyzing the design model. It has difficulties to interface these commercial software directly. For Combining both programs, response surface methodology is applied to construct approximation functions for maximum stresses and maximum displacements are obtained by full factorial design of five levels. This steel wheel is modeled in 14-inch diameter of rim, and wide parameter of hole in disk is only selected as design variable for reducing the weight of steel whee. PLBA(Pshenichny-Lim-Belegundu-Arora) algorithm, which used the second-order information in the direction finding problem and uses the active set strategy, is used for solving optimization problems.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.7 no.4
• /
• pp.750-769
• /
• 2015

The geometry of engineering systems affects their performances. For this reason, the shape of engineering systems needs to be optimized in the initial design stage. However, engineering system design problems consist of multi-objective optimization and the performance analysis using commercial code or numerical analysis is generally time-consuming. To solve these problems, many engineers perform the optimization using the approximation model (response surface). The Response Surface Method (RSM) is generally used to predict the system performance in engineering research field, but RSM presents some prediction errors for highly nonlinear systems. The major objective of this research is to establish an optimal design method for multi-objective problems and confirm its applicability. The proposed process is composed of three parts: definition of geometry, generation of response surface, and optimization process. To reduce the time for performance analysis and minimize the prediction errors, the approximation model is generated using the Backpropagation Artificial Neural Network (BPANN) which is considered as Neuro-Response Surface Method (NRSM). The optimization is done for the generated response surface by non-dominated sorting genetic algorithm-II (NSGA-II). Through case studies of marine system and ship structure (substructure of floating offshore wind turbine considering hydrodynamics performances and bulk carrier bottom stiffened panels considering structure performance), we have confirmed the applicability of the proposed method for multi-objective side constraint optimization problems.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.12
• /
• pp.219-225
• /
• 2014

A Gompertz modeling, sigmoid in shape, is a widely used application for social science, natural science, engineering, and medical research to allow confident approximation and accurate analysis and has been applied to estimate an elderly population on aging of population. Due to the high toxicity of currently available drug delivery vehicles, various efforts have been made to reduce side-effects in clinical fields, but its application to preclinical and clinical studies is limited and there are some difficulties to optimize the parameters of Gompertz modeling applicable to preclinical studies. Therefore, in this study, we demonstrated the ability of sickle red blood cells loaded by hypotonic dialysis then photosensitized and light-activated ex vivo for controlled release and simultaneously optimized Gompertz function to evaluate controlled drug release properties of photosensitized sickle red blood cells to reduce pain-related treatments in cancer patients.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.4
• /
• pp.423-434
• /
• 2004

In this paper, we introduce a new topology of Self-Organizing Polynomial Neural Networks (SOPNN) based on genetically optimized Multi-Layer Perceptron (MLP) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. Let us recall that the design of the 'conventional' SOPNN uses the extended Group Method of Data Handling (GMDH) technique to exploit polynomials as well as to consider a fixed number of input nodes at polynomial neurons (or nodes) located in each layer. However, this design process does not guarantee that the conventional SOPNN generated through learning results in optimal network architecture. The design procedure applied in the construction of each layer of the SOPNN deals with its structural optimization involving the selection of preferred nodes (or PNs) with specific local characteristics (such as the number of input variables, the order of the polynomials, and input variables) and addresses specific aspects of parametric optimization. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between the approximation and generalization (predictive) abilities of the model. To evaluate the performance of the GA-based SOPNN, the model is experimented using pH neutralization process data as well as sewage treatment process data. A comparative analysis indicates that the proposed SOPNN is the model having higher accuracy as well as more superb predictive capability than other intelligent models presented previously.reviously.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.7
• /
• pp.75-84
• /
• 2003

To reduce the effects of the uncertainties due to the modeling error and aerodynamic coefficients, a nonlinear adaptive control system based on neural networks is proposed . Neural networks parameters are adjusted by using an adaptive law. The sliding mode control scheme is used to compensate for the effect of the approximation error of neural networks. Control parameters and neural networks structures are optimized to obtain better performance by using the genetic algorithm. By introducing the concept of multi-groups of populations, the genetic algorithm is modified so that individuals and groups can be simultaneously evolved . To verify the performance of the pro posed algorithm, the optimized neural networks control system is applied to an aircraft longitudinal dynamics.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1158-1165
• /
• 2021

This paper proposes a CNN accelerator which is optimized Pooling layer operation incorporated in Multiplication And Accumulation(MAC) to reduce the memory size. For optimizing memory and data path circuit, the quantized 8bit integer weights are used instead of 32bit floating-point weights for pre-training of MNIST data set. To reduce chip area, the proposed CNN model is reduced by a convolutional layer, a 4*4 Max Pooling, and two fully connected layers. And all the operations use specific MAC with approximation adders and multipliers. 94% of internal memory size reduction is achieved by simultaneously performing the convolution and the pooling operation in the proposed architecture. The proposed accelerator chip is designed by using TSMC65nmGP CMOS process. That has about half size of our previous paper, 0.8*0.9 = 0.72mm². The presented CNN accelerator chip achieves 94% accuracy and 77us inference time per an MNIST image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.8C
• /
• pp.1086-1103
• /
• 2004

Most research efforts on the OCDMA technology assume single-bit-per-symbol transmission techniques such as on-off keying. However, achieving high spectral efficiency with such transmission techniques is likely to be a challenging task due to the "unipolar" nature of optical signals. In this paper, an M-ary transmission technique using more than two equally-weighted codes is proposed for OCDMA local area networks, and ie BER performance and spectral efficiency are analyzed. Poison frame arrival and randomly generated codes are assumed for the BER analysis, and the probability of incorrect symbol detection is analytically derived. From the approximation, it is found that there exists an optimal code weight that minimizes the BER, and its physical interpretation is drawn in an intuitive and simple statement. Under the assumption of this optimized code weight and sufficiently large code dimension, it is also shown that the spectral efficiency of OCDMA networks can be significantly improved by increasing the number (M) of symbols used. Since the cost of OCDMA transceivers is expected to increase with the code dimension, we finally provide a guideline to determine the optimal number of symbols for a given code dimension and traffic load.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.14 no.4
• /
• pp.505-513
• /
• 2001

In this study, an optimum design algorithm using efficient reanalysis is proposed for seismic design of Reinforced Concrete (RC) piers. The proposed algorithm for optimization of RC piers is based on efficient reanalysis technique. Considering structural behavior of RC piers, the other approximation technique such as artificial constraint deletion is introduced to increase the efficiency of optimization. The efficiency and robustness of the proposed algorithm including the proposed reanalysis technique is demonstrated by comparing it with a conventional optimization algorithm. A few of design examples are optimized to show the applicability of the proposed algorithm.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.9 no.2
• /
• pp.41-50
• /
• 2010

In this paper, a multi-band antenna with novel structure for mobile communications is designed and fabricated. The proposed antenna has the Multi-band antenna characteristics by two common-grounded slots with different size and angle. In order to reduce size and to enhance the gain of the antenna, a reflector is consisted of chokes on the three sides. It is optimized by using the CST Microwave Studio commercial software based on the FIA(Finite Integration Algorithm) and PBA(Perfect Boundary Approximation), and then the fabricating and measuring is practiced. As a result of measurement, the reflection coefficient is less than -11 dB(VSWR < 1.8) and the gain of antenna is more than 6dBi at 824~894MHz and 1885-2500MHz.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.13 no.4
• /
• pp.351-358
• /
• 2002

To determine a scattering performance of a rectangular waveguide with two skewed conducting posts in approximation by the mode matching method and the generalized scattering method is presented in this paper. We determined the optimized result from effective analysis to select the adequate eigenmode number in mode matching method for the skewed two conducting posts. And we obtained the scattering performance of the junction of the waveguide to coaxial line with two skewed conducting posts by application of above method. By this result, it can be seen that the transmission performance at output port of waveguide to coaxial line is 3 ㏈ at the angle, 50°And we obtained the reflection performance to decrease linearly along the skewed angle at input port.