• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제2권1호
• /
• pp.1-6
• /
• 2013

소프트웨어의 결함 경향 모듈 예측을 위해 SVM 분류기가 우수한 성능을 보인다는 연구들이 많지만, SVM에서 필요한 파라미터 선정 시 매 커널마다 다르게 선정해야 하고, 파라미터의 변경에 따른 결과예측을 위해 알고리즘을 반복적으로 수행해야 하는 불편함이 있다. 따라서 본 논문에서는 SVM의 파라미터 선정 시 유전알고리즘을 이용하여 스스로 찾게 하는 GA-SVM 모델을 구현하였다. 그리고 분류 성능 비교를 위해 신경망의 역전파알고리즘을 이용하여 분류했던 기존 논문과 비교 분석한 결과, GA-SVM 모델의 성능이 더 우수함을 확인하였다.

• 한국재료학회지
• /
• 제11권8호
• /
• pp.655-660
• /
• 2001

Metalorganic chemical vapor deposition (MOCVD)으로 성장한 $In_{0.5}$ ($Gal_{1-x}$ $Al_{x}$ )0.5P/GaAS 이중 이종접합 구조의 특성을 표면 광전압 (surface Photovoltage ; SPV) 측정으로 연구하였다. $In_{0.5}$($Gal_{1-x}$ $Al_{x}$ )0.5P/GaAS 이중 이종접합 구조의 SPV 측정값을 Lorentzian 피팅한 띠 간격에너지 ($E_{0}$ ) 값과 조성비 (x)로 구한 이론 값이 잘 일치하였다. 그리고 변조 주파수 의존성을 측정한 결과 SPV 신호의 형태는 변하지 않고, 신호의 크기만이 변하는 것은 광 조사에 따른 전기적 상태의 과도 현상에 따른 것이고, GaAs와 InGaAlP의 특성시간의 차이는 광 캐리어의 수명의 차이로 분석된다. 그리고 온도 의존성 측정으로 $In_{0.5}$ /($Gal_{1-x}$ $Al_{x}$ )0.5P/GaAS 이중 이종 접합 시료의 균일한 변형분포와 계면상태가 양호함을 알 수 있었다.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2008년도 International Meeting on Information Display
• /
• pp.831-833
• /
• 2008

150 nm thick Ga-doped ZnO thin film, which was deposited by a sputtering process, was wet-chemically etched by using various organic acids such as oxalic, citric and formic acid. Wet etch parameters including etchant concentration and temperature are investigated for each etchant, and their effects on the etch rate and the feature of edge line are compared.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.222-222
• /
• 2000

The general dicing process cuts a semiconductor wafer to lengthwise and crosswise direction by using a rotating circular diamond blade. But inferior goods are made under the influence of several parameters in dicing such as blade, wafer, cutting water and cutting conditions. Moreover we can not applicable this dicing method to GaN wafer, because the GaN wafer is harder than the other wafer as GaAs. In older to overcome this problem, a new dicing process is necessary. This paper describes a new machine using scriber and precision servo mechanism in order to dice a semiconductor wafer.

• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1996년도 춘계학술발표회논문집(1)
• /
• pp.380-385
• /
• 1996

The genetic algorithm(GA) is applied to the design of the nuclear power control system. The reactor control system model is described in the LQR configuration. The LQR system order is increased to make the tracking system. The key parameters of the design are weighting matrices, and these are usually determined through numerous simulations in the conventional design. To determine the more objective and optimal weightings, the improved GA is applied. The results show that the weightings determined by the GA yield the better system responses than those obtained by tile conventional design method.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.114-116
• /
• 2015

This paper presents a Stochastic Time-Cost Tradeoff analysis system (STCT) that identifies optimal construction methods for activities, hence reducing the project completion time and cost simultaneously. It makes use of schedule information obtained from critical path method (CPM), applies alternative construction methods data obtained from estimators to respective activities, computes an optimal set of genetic algorithm (GA) parameters, executes simulation based GA experiments, and identifies near optimal solution(s). A test case verifies the usability of STCT.

• 한국진공학회지
• /
• 제19권5호
• /
• pp.353-359
• /
• 2010

Metal-organic chemical vapour deposition (MOCVD) 법으로 성장된 $In_{0.49}Ga_{0.51}P$/GaAs 이종접합 구조의 특성을 표면 광전압(surface photovoltage; SPV) 분광법으로 조사하였다. SPV 측정은 입사광의 세기, 변조 주파수, 온도의 함수로 수행하였다. 상온에서 시료의 띠간격 에너지(band gap energy)는 GaAs와 $In_{0.49}Ga_{0.51}P$는 각각 1.400 및 1.893 eV이었다. 광세기를 증가시킴에 따라 SPV 크기는 증가하는 반면에, 변조 주파수를 증가시킴에 따라 SPV 크기는 감소하였다. 그리고 SPV 스펙트럼의 온도 의존성으로부터 GaAs와 $In_{0.49}Ga_{0.51}P$의 띠간격 에너지의 변화를 Varshni 및 Bose-Einstein 표현에 의해 분석하였다.

• 한국물환경학회지
• /
• 제23권5호
• /
• pp.697-704
• /
• 2007

This study proposes an integrated technique of Genetic Algorishim (GA) and Geographic Information System (GIS) for designing the water quality monitoring networks. To develop solution scheme of the integrated system, fitness functions are defined by the linear combination of five criteria which stand for the operation objectives of water quality monitoring stations. The criteria include representativeness of a river system, compliance with water quality standards, supervision of water use, surveillance of pollution sources and examination of water quality changes. The fitness level is obtained through calculations of the fitness functions and input data from GIS. To find the most appropriate parameters for the problems, the sensitivity analysis is performed for four parameters such as number of generations, population sizes, probability of crossover, and probability of mutation. Using the parameters resulted from the sensitivity analysis, the developed system proposed 110 water quality monitoring stations in the Nakdong River. This study demonstrates that the integrated technique of GA and GIS can be utilized as a decision supporting tool in optimized design for a water quality monitoring network.

• Computers and Concrete
• /
• 제6권4호
• /
• pp.343-356
• /
• 2009

Experiments were designed to investigate the flow behavior of portland cement paste and concrete incorporating superplasticizers. The paste and concrete mixtures were subjected to prolonged mixing for up to 110 min at high temperature. The yield stress values of concrete and that of the corresponding cement paste were measured using a rotating rheometer and viscometer, respectively. The results reveal a weak linear correlation between the yield stress of concrete mixtures and that of the corresponding cement pastes. Results also indicate that the yield stress of concrete varies in a linear fashion with the elapsed time, while its variations with the temperature and superplasticizer dosage follow power and inverse power functions, respectively. In this study, the genetic algorithms (GA) technique was used to predict the yield stress of concrete considering various parameters, such as the mixing time, ambient temperature, and superplasticizer dosage. A sensitivity study was conducted to evaluate the ability of the GA equations thus developed to capture the effects of test parameters on the yield stress of concrete. It was found that the GA equations were sensitive to the effects of test parameters and provided yield stress predictions that compared well with corresponding experimental data.

• 소성∙가공
• /
• 제30권3호
• /
• pp.125-133
• /
• 2021

In this study, response surface method (RSM), back propagation neural network (BPNN), and genetic algorithm (GA) were used for modeling and multi-objective optimization of the parameters of AA5052-H32 in incremental sheet forming (ISF). The goal of optimization is to determine the maximum forming angle and minimum surface roughness, while varying the production process parameters, such as tool diameter, tool spindle speed, step depth, and tool feed rate. A Box-Behnken experimental design (BBD) was used to develop an RSM model and BPNN model to model the variations in the forming angle and surface roughness based on variations in process parameters. Subsequently, the RSM model was used as the fitness function for multi-objective optimization of the ISF process the GA. The results showed that RSM and BPNN can be effectively used to control the forming angle and surface roughness. The optimized Pareto front produced by the GA can be utilized as a rational design guide for practical applications of AA5052 in the ISF process