• The Journal of the Korea Contents Association
• /
• v.11 no.6
• /
• pp.1-7
• /
• 2011

The methodology of KOSPI forecast has been considered as one of the most difficult problem to develop accurately since short-term KOSPI is correlated with various factors including politics and economics. In this paper, we presents a methodology for forecasting short-term trends of stock price for five days using the feature selection method based on a neural network with weighted fuzzy membership functions (NEWFM). The distributed non-overlap area measurement method selects the minimized number of input features by removing the worst input features one by one. A technical indicator are selected for preprocessing KOSPI data in the first step. In the second step, thirty-nine numbers of input features are produced by wavelet transforms. Twelve numbers of input features are selected as the minimized numbers of input features from thirty-nine numbers of input features using the non-overlap area distribution measurement method. The proposed method shows that sensitivity, specificity, and accuracy rates are 72.79%, 74.76%, and 73.84%, respectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.206-211
• /
• 2009

This paper presents a methodology to 1-day-forecast stock index using the automatic feature extraction method based on the neural network with weighted fuzzy membership functions (NEWFM). The distributed non-overlap area measurement method selects the minimized number of input features by automatically removing the worst input features one by one. CPP$_{n,m}$(Current Price Position of the day n: a percentage of the difference between the price of the day n and the moving average from the day n-1 to the day n-m) and the 2 wavelet transformed coefficients from the recent 32 days of CPP$_{n,m}$ are selected as minimized features using bounded sum of weighted fuzzy membership functions (BSWFMs). For the data sets, from 1989 to 1998, the proposed method shows that the forecast rate is 60.93%.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.500-500
• /
• 2022

「물환경보전법」은 2007년의 「수질 및 수생태계 보전에 관한 법률」에서 개정된 법률로 그 목적이 수질과 수생태계로 국한되어 왔다. 하지만 통합물관리 도입으로 인하여 제정된 「물관리기본법」에서는 "국가와 지방자치단체가 물과 관련된 정책을 수립, 시행할 때에는 물순환 과정의 전주기를 고려하여야 한다"고 명시되어 있으며 「물환경보전법」의 물순환관리지표는 수량이 제외되어 물순환 왜곡으로 인한 문제점이 충분히 포함되지 않은 실정이다. 따라서 본 연구에서는 국민들의 안전을 도모하기 위하여 물순환관리지표에 도시유역의 물순환 왜곡으로 인한 수재해 현황을 추가적으로 고려하고자 한다. 수재해 현황은 행정안전부의 자연재해로 인한 최근 10년간 인명피해와 피해액 조사를 바탕으로 가장 심각한 피해를 불러일으킨 폭염과 태풍 및 호우를 고려대상으로 선정하였다. 그 중 도시유역에서의 폭염피해란 불투수면적률이 증가함에 따라 증발산량이 감소하며 발생하는 도심의 열섬현상과 깊은 관계가 있고, 태풍 및 호우피해는 첨두유량의 증가와 도시배수의 연결성에 의하여 발생하는 침수와 깊은 관계가 있기에 이를 본 연구에서의 수량의 대표인자로 결정하였다. 수계 단위의 물순환관리지표와 행정구역 단위의 수재해 현황을 공간적으로 비교하기 위해 면적가중평균법을 이용하여 물순환율과 불투수면적률을 행정구역별로 재척도화를 하였다. 그리고 고려할 요소를 판단하기 위해 행정구역 별 물순환관리지표와 열섬현상, 도시침수를 측정하는 지표의 순위를 매겨 등위상관계수를 계산하였다. 도시침수와 열섬현상을 대표하는 지표 중 물순환율과 상관계수가 낮은 지표부터 물순환관리지표에 포함시켜야 할 요소라고 판단하였으며, 이를 바탕으로 보다 개선된 물순환관리지표를 제안하였다. 기후변화에 따라 현재 수재해 위험성이 더욱 커지고 그의 패턴도 달라지고 있기에 본 연구의 결과를 바탕으로 물순환관리지표가 좀 더 국민들에게 실효성이 있는 평가지표로 개선되기를 기대한다.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.9 no.5
• /
• pp.590-597
• /
• 1985

A recursive geometric adaptive control method to compensate for machining straightness error in the finished surface due to tool deflection and guideway error generated by end milling process is developed. The relationship between the tool deflection and the feedrate is modeled by a modified Taylor's tool life equation. Without a priori knowledge on the variations off cutting parameters, time varying parameters are then estimated by an exponentially windowed recursive least squares method with only post-process measurements of the straightness error. The location error is controlled by shifting the milling bed in the direction perpendicular to the finished surface and adding a certain amount of feedrate with respect to the tool deflection model before cutting. The waviness error is compensated by adjusting the feedrate during machining. Experimental results show that location error is controlled within a range of fixturing error of the bed on the guideway and that about 60% reduction in the waviness error can be achieved within a few steps of parameter adaption under wide operating ranges of cutting conditions even if the parameters do not converge to fixed values.

• Journal of the Korean Society for Advanced Composite Structures
• /
• v.1 no.2
• /
• pp.29-35
• /
• 2010

In addition to the Young's modulus, the Poisson's ratio is also at the center of attention in the field stochastic finite element analysis since the parameters play an important role in determining structural behavior. Accordingly, the sole effect of this parameter on the response variability is of importance from the perspective of estimation of uncertain response. To this end, a formulation to determine the response variability in laminate composite plates due to the spatial randomness of Poisson's ratio is suggested. The independent contributions of random Poisson's ratiocan be captured in terms of sub-matrices which include the effect of the random parameter in the same order, which can be attained by using the Taylor's series expansion about the mean of the parameter. In order to validate the adequacy of the proposed formulation, several example analyses are performed, and then the results are compared with Monte Carlo simulation (MCS). A good agreement between the suggested scheme and MCS is observed showing the adequacy of the scheme.

• The Journal of Engineering Geology
• /
• v.3 no.1
• /
• pp.1-20
• /
• 1993

In this study, laboratory direct shear tests on 37 core specimens of gneiss were performed to examine the characteristics of shear behavior on fractures by using a portable direct shear box. The multi-stage shear testing method was used and normal stress applied to specimens ranges from 5.60 to $25.67kg/\textrm{cm}^2$. On the basis of test results, the empirical equations for the shear strength on fractures were suggested. The methanical parameters that can influence the shear behavior were derived and compared between each parameter. The values of shear stiffness have a trend showing rapid increase with the increase of normal stress and joint roughness coeffident, and the average value of secant shear stiffness for all specimens is about $110.68kg/\textrm{cm}^3$ under the range of normal stress applied in this test In addition, the relationship between the length of specimen and shear stiffness is inversely correlated due to the size effect. Therefore, even the specimens with the same joint roughness coeffident show the trend of decreasing shear stiffness in case of the specimens being the longer length.

• Journal of the Korean Solar Energy Society
• /
• v.33 no.1
• /
• pp.79-88
• /
• 2013

This study set out to evaluate the economy, environmentality, and complexity (economy+environmentality) of fire station buildings of public service facilities and propose ways to apply the optimization of renewable energy system to fire station buildings. As for economy according to life cycle costs, economy increased when the application percentage of the geothermal and solar heat system increased over the three renewable energy system types (geothermal, solar heat, and solar photovoltaic). On the other hand, economy decreased when the application percentage of the solar photovoltaic system increased. As for environmentality according to tons of carbon dioxide, environmentality decreased when the application percentage of the geothermal and solar heat system increased. Environmentality increased when the application percentage of the solar photovoltaic system increased. As for complexity (economy+environmentality) according to the weighted coefficient method, complexity increased when the application percentage of the geothermal system increased. It was highest at the combination of the solar heat system (20%) and geothermal system (80%). On the other hand, complexity decreased when the application percentage of the solar photovoltaic system increased. It was lowest at the combination of the solar photovoltaic system (80%) and geothermal system (20%).

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.3 no.2
• /
• pp.96-104
• /
• 2001

Usage of ecosystem models has been extended to landscape scales for understanding the effects of environmental factors on natural and agro-ecosystems and for serving as their management decision tools. Accurate prediction of spatial variation in daily temperature is required for most ecosystem models to be applied to landscape scales. There are relatively few empirical evaluations of landscape-scale temperature prediction techniques in mountainous terrain such as Korean Peninsula. We derived a periodic function of seasonal lapse rate fluctuation from analysis of elevation effects on daily temperatures. Observed daily maximum and minimum temperature data at 63 standard stations in 1999 were regressed to the latitude, longitude, distance from the nearest coastline and altitude of the stations, and the optimum models with $r^2$ of 0.65 and above were selected. Partial regression coefficients for the altitude variable were plotted against day of year, and a numerical formula was determined for simulating the seasonal trend of daily lapse rate, i.e., partial regression coefficients. The formula in conjunction with an inverse distance weighted interpolation scheme was applied to predict daily temperatures at 267 sites, where observation data are available, on randomly selected dates for winter, spring and summer in 2000. The estimation errors were smaller and more consistent than the inverse distance weighting plus mean annual lapse rate scheme. We conclude that this method is simple and accurate enough to be used as an operational temperature interpolation scheme at landscape scale in Korea and should be applicable to elsewhere.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.381-381
• /
• 2018

우리나라에서는 지속적인 자연재해로 각기 다른 필요성과 목적에 따라 다양한 형태의 홍수 침수 관련 지도가 작성되어 왔다. 연구 성과로 작성된 계획 빈도 및 상위 2개 빈도의 호우피해예상도를 실측 강우와 연계하여 재난관리단계별 대응단계에 활용하기 위해 실시간 피해위험구역을 표출하고자 한다. 본 연구는 실시간으로 피해위험구역을 표출하기 위해 실측 강우와 연계된 호우피해예상도에 공간 보간 알고리즘을 적용하고자 한다. 호우피해예상도란 돌발호우나 태풍으로 인하여 홍수가 발생하면 인명 및 재산피해를 최소화하기 위해 홍수지역을 미리 예측 가능하도록 제작된 지도이다. 지형자료(DEM), 하천 중심선(Stream Centerline), 하천 횡단면(Cross-Section Line), 제방고(Bank), 수문기상 자료(Hydrological Data), 조도계수(Roughness) 등을 사용하여 하천법 제 21조와 하천법시행령 제 17조를 근거로 작성된다. 본 연구에서는 호우피해예상도에 IDW(Inverse Distance Weighted, 역거리가중법) 보간, TIN(Triangulated Irregular Network system, 불규칙삼각망) 보간, Kriging 보간 방법 적용 알고리즘을 제시하고자 하였다. 호우피해예상도에 보간 알고리즘을 적용하기 위해 보간 방법에 따른 적용사례를 분석하였으며 그 결과, 보간 알고리즘을 적용한 호우피해예상도 보간을 통하여 계획빈도 및 상위 2개 빈도 이외의 빈도(하위빈도-계획빈도, 계획빈도-상위빈도 구간)에 대한 호우피해예상도의 피해위험구역 구현 방안을 제시하였다. 호우피해예상도에 IDW, TIN, Kriging 보간 알고리즘을 적용하여 계획빈도 및 상위빈도 이외의 빈도에 대한 피해위험구역을 표출 할 수 있다. 표출된 계획빈도 및 상위빈도 이외의 빈도를 지점확률강우량-빈도에 대한 Matching table을 통하여 실측 강우와 연계 가능하다. 본 연구 결과는 추후 풍수해피해예측시스템에 활용하여 재난관리단계별 예방 및 대응 단계에 활용 할 수 있을 것으로 판단된다.

• Journal of the Korean Geotechnical Society
• /
• v.16 no.3
• /
• pp.163-172
• /
• 2000

최종침하 예측기법들은 분석상 간단명료하고 경제적인 기법이라 현장에서 널리 이용되고 있지만, 현장계측상의 문제들이 다분히 있는 실측치에 크게 의존함으로써 설계단계에서 침하량예측에 분석가의 주관적 판단이 큰 변수로 작용할 수 있으므로 객관성이 결여되는 결점을 안고 있다. 그 중 쌍곡선법(Hypervolic Method)이 가장 널리 쓰이고 있지만, 현장 계측치에 따라 가정 기본식의 선형성이 다소 뚜렷하지 않아 분석가에 따라 해석결과가 다르게 나타날 수 있으므로, 기술 적용상의 어려움과 경제적 비용을 더욱 가중시키는 결과를 초래할 수 있다. 따라서, 본 연구에서는 현장 계측자료 분석에 있어서 대표적으로 널리 적용되고 있는 쌍곡선법의 기본 가정식의 선형성 문제에 주안점을 두어 기본 가정식의 선형성을 확보하고, 그 선형구간을 확장한 새로운 침하예측기법을 제안하였다. 성토완료 직후의 현장 자료를 배수재가 설치된 지역과 배수재가 설치되지 않은 지역으로 구분하여 최종 1차 압밀침하량, 수직압밀계수 등을 기존예측기법 및 현장계측자료와 비교 검토하여 제안된 침하예측기법의 적용성을 검증하였다.