• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2005년도 추계 학술대회논문집(수송기계편)
• /
• pp.194-199
• /
• 2005

Body-on-frame type vehicle has a set of frame bushes which are installed between body and frame fur vibration Isolation. Such frame bushes are important vibration transmission paths to passenger space. In order to reduce the vibration level of passenger space, therefore, the change of complex stiffness of the frame bushes is more efficient than modification of other parts of the vehicle such as body, frame and suspension. The purpose of this study is to reduce the vibration level for ride comfort by optimization of complex stiffness of frame bushes. In order to do this end, simple finite element vehicle model was constructed and the complex stiffness of frame bushes was set to be design variable. Objective function was defined to reflect passenger ride comfort and genetic algorithm and sub-structure synthesis were applied for minimization of the objective function.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권10호
• /
• 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.

• 한국지능시스템학회논문지
• /
• 제18권6호
• /
• pp.871-875
• /
• 2008

본 논문은 개체 변환 유전자 알고리즘을 (GAVaPS) 이용하여 k-nearest neighbor (k-NN) 분류기에서 사용되는 특징들을 선정하는 방법을 제시한다. 우리는 다수의 k-NN 분류기들을 사용하기 때문에 사용되는 특징들을 선정하는 문제는 매우 탐색 영역이 크고 해결하기 어려운 문제이다. 따라서 우리는 효과적인 특징득의 선정을 위해 일반적인 유전자 알고리즘 (GA) 보다 효율적이라고 알려진 개체군 변환 유전자 알고리즘을 사용한다. 또한 다수 k-NN 분류기를 개체군 변환 유전자 알고리즘으로 효과적으로 결합하는 방법을 제시한다. 제안하는 알고리즘의 우수성을 여러 실험을 통해 보여준다.

• 유체기계공업학회:학술대회논문집
• /
• 유체기계공업학회 2003년도 유체기계 연구개발 발표회 논문집
• /
• pp.397-403
• /
• 2003

In an attempt to solve multiobjective optimization problems, weighted sum method is most widely used for the advantage that a designer can consider the relative significance of each object functions by weight values but it can be highly sensitive to weight vector and occasionally yield a deviated optimum from the relative weighting values designer designated because the multiobjective function has the form of simple sum of the product of the weighting values and the object functions in traditional approach. To search the design solution well agree to the designer's weighting values, we proposed new multiobjective function which is the functional of each normalized objective functions and considered to find the design solution comparing the distance between the characteristic line and the ideal optimum. In this study, proposed multiobjective function was applied to design high efficiency and low noise axial flow fan and the result shows this approach will be effective for the case that the qualify of the design can be highly affected by the designer's subjectiveness represented as weighting values in multiobjective design optimization process.

• 한국소음진동공학회논문집
• /
• 제16권6호
• /
• pp.619-626
• /
• 2006

Body-on-frame type vehicle has a set of frame bushes between body and frame for vibration isolation. Such frame bushes are important vibration transmission paths to passenger space for excitations during driving. In order to reduce the vibration level of passenger space, therefore, change of complex stiffness of the frame bushes is more efficient than modification of other parts of the vehicle such as body, frame and suspension. The purpose of this study is to reduce the vibration level for ride comfort by optimization of complex stiffness of frame bushes. In order to do this, a simple finite element vehicle model was constructed and complex stiffness of the frame bushes was set to be design variables. The objective function was defined to reflect frequency dependence of passenger ride comfort. Genetic algorithm and sub-structure synthesis were applied for minimization of the objective function. After optimization level at a position of interest on the car body was reduced by about 43.7 % in RMS value. Causes for optimization results are discussed.

• Steel and Composite Structures
• /
• 제32권4호
• /
• pp.455-466
• /
• 2019

Despite the rapid advancement in computing resources, many real-life design and optimization problems in structural engineering involve huge computation costs. To counter such challenges, approximate models are often used as surrogates for the highly accurate but time intensive finite element models. In this paper, surrogates for first-order shear deformation based finite element models are built using a polynomial regression approach. Using statistical techniques like Box-Cox transformation and ANOVA, the effectiveness of the surrogates is enhanced. The accuracy of the surrogate models is evaluated using statistical metrics like $R^2$, $R^2{_{adj}}$, $R^2{_{pred}}$ and $Q^2{_{F3}}$. By combining these surrogates with nature-inspired multi-criteria decision-making algorithms, namely multi-objective genetic algorithm (MOGA) and multi-objective particle swarm optimization (MOPSO), the optimal combination of various design variables to simultaneously maximize fundamental frequency and frequency separation is predicted. It is seen that the proposed approach is simple, effective and good at inexpensively producing a host of optimal solutions.

• 한국기계기술학회지
• /
• 제20권6호
• /
• pp.809-817
• /
• 2018

The model predictive controller performance of the mobile robot is set to an arbitrary value because it is difficult to select an accurate value with respect to the controller parameter. The general model predictive control uses a quadratic cost function to minimize the difference between the reference tracking error and the predicted trajectory error of the actual robot. In this study, we construct a predictive controller by transforming it into a quadratic programming problem considering velocity and acceleration constraints. The control parameters of the predictive controller, which determines the control performance of the mobile robot, are used a simple weighting matrix Q, R without the reference model matrix $A_r$ by applying a quadratic cost function from which the reference tracking error vector is removed. Therefore, we designed the predictive controller 1 and 2 of the mobile robot considering the constraints, and optimized the controller parameters of the predictive controller using a genetic algorithm with excellent optimization capability.

• 한국지반공학회논문집
• /
• 제25권8호
• /
• pp.23-32
• /
• 2009

본 연구에서는 모래 다짐말뚝 공법의 설계 및 시공단계에서 침하거동 예측에 활용될 수 있는 합리적이고 간편한 해석기법을 제안하였으며, 모델 계수값들은 유전자 알고리즘에 근거한 최적화 과정을 통하여 구할 수 있다. 제안된 기법의 검증을 위하여 0(무치환), 20, 36 및 56%의 다양한 모래 치환율에 대한 SCP 복합지반의 침하거동에 관한 실내압밀실험이 수행되었다. 제안된 모델은 각 치환율에 대하여 간극비-대수응력 관계 및 시간-압축 관계에서 계측값과 매우 일치되는 경향성을 보였다.

• 한국지능시스템학회논문지
• /
• 제16권2호
• /
• pp.222-227
• /
• 2006

현재 막대한 병렬성을 갖는 DNA 컴퓨팅을 이용하여 Traveling Salesman Problem (TSP)를 해결하기 위한 연구가 진행되고 있다. 하지만 기존의 방법은 그래프 문제의 표현에서 DNA의 특성을 고려하지 않아, 실제 생물학적 실험 결과와의 차이가 발생하고 있다. 따라서 DNA의 특성을 반영하고 생물학적 실험 오류를 줄일 수 있는 DNA 서열 생성 알고리즘이 필요하다. 본 논문에서는 DNA 컴퓨팅에 진화 모델의 하나인 DNA 코딩 방법을 적용한 DNA 서열 생성 알고리즘을 제안한다. 제안한 알고리즘은 TSP에 적용하여 기존에 단순 유전자 알고리즘과 비교하였다. 그 결과 제안한 알고리즘은 오류를 최소화한 우수한 서열을 생성하고 생물학적 실험 오류율도 줄일 수 있었다.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2017년도 9th Asian Crop Science Association conference
• /
• pp.57-57
• /
• 2017

Chrysanthemum is one of the most important floral crop in Korea produced about 7 billion dollars (1 billion for pot and 6 billion for cutting) in 2013. However, it is difficult to breed and to do genetic study because 1) it is highly self-incompatible, 2) it is outcrossing crop having heterozygotes, and 3) commercial cultvars are hexaploid (2n = 6x = 54). Although low-density genetic map and QTL study were reported, it is not enough to apply for the marker assisted selection and other genetic studies. Therefore, we are trying to make high-density genetic mapping using GBS with about 100 $F_1s$ of C. boreale that is oHohhfd diploid (2n = 2x = 18, about 2.8Gb) instead of commercial culitvars. Since Chrysanthemum is outcrossing, two-way pseudo-testcross model would be used to construct genetic map. Also, genotype-by-sequencing (GBS) would be utilized to generate sufficient number of markers and to maximize genomic representation in a cost effective manner. Those completed sequences would be analyzed with TASSEL-GBS pipeline. In order to reduce sequence error, only first 64 sequences, which have almost zero percent error, would be incorporated in the pipeline for the analysis. In addition, to reduce errors that is common in heterozygotes crops caused by low coverage, two rare cutters (NsiI and MseI) were used to increase sequence depth. Maskov algorithm would also used to deal with missing data. Further, sparsely placed markers on the physical map would be used as anchors to overcome problems caused by low coverage. For this purpose, were generated from transcriptome of Chrysanthemum using MISA program. Among those, 10 simple sequence repeat (SSR) markers, which are evenly distributed along each chromosome and polymorphic between two parents, would be selected.