• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.156-161
• /
• 2003

It is an interest problem to predict substance distributions in three-dimensional space. Recently, a research field as Geostatistics is advanced. It is a kind of inter- or extrapolation mathematically. Some useful means for the inter- and extrapolation are known, in which slide window method with neural networks is hopeful one. We propose multi-dimensional extrapolation using multi-layer neural networks and the slide-window method. The multi-dimensional extrapolation is not similar to one-dimension. It has plural algorithms. We researched line predictors and local-plain predictors I two-dimensional space. The both predictors are equivalent; however, in multi-dimensional extrapolation, it is very important to find the direction of predictions. Especially, since the slide window method requires information to predict the future in sampling data, if they are not ordered appropriately in the direction, the predictor cannot operate. We tested the extrapolation for typical two-dimensional functions, and found an excellent character of slide-window method based on local-plain. By using the method, we can extrapolate the function until twice-outer regions of the definitions.

• Geomechanics and Engineering
• /
• 제12권5호
• /
• pp.863-870
• /
• 2017

With the increasing interest in using bacterial biofilms in geo-engineering practices, such as soil improvement, sealing leakage in earth structures, and hydraulic barrier installation, understanding of the contribution of bacterial biofilm formation to mechanical and hydraulic behavior of soils is important. While mechanical properties of soft gel-like biofilms need to be identified for appropriate modeling and prediction of behaviors of biofilm-associated soils, elastic properties of biofilms remain poorly understood. Therefore, this study investigated the microscale Young's modulus of biofilms produced by Shewanella oneidensis MR-1 in a liquid phase. The indentation test was performed on a biofilm sample using the atomic force microscopy (AFM) with a spherical indentor, and the force-indentation responses were obtained during approach and retraction traces. Young's modulus of biofilms was estimated to be ~33-38 kPa from these force-indentation curves and Hertzian contact theory. It appears that the AFM indentation result captures the microscale local characteristics of biofilms and its stiffness is relatively large compared to the other methods, including rheometer and hydrodynamic shear tests, which reflect the average macro-scale behaviors. While modeling of mechanical behaviors of biofilm-associated soils requires the properties of each component, the obtained results provide information on the mechanical properties of biofilms that can be considered as cementing, gluing, or filling materials in soils.

• 대한기계학회논문집A
• /
• 제30권4호
• /
• pp.465-472
• /
• 2006

Recently, the regulations of the government and the concerns of people have rise to the interest in noise pollution levels as compared to other vehicles. In this area, many researchers have studied to reduce this noise in the field of automotive engineering. This paper proposes an optimal design scheme to reduce the noise of the intake system by adapting Kriging with two meta-heuristic techniques. For this, as a measuring tool for the performance of the intake system, the performance prediction software, was used. Then, the length and radius of each component of the current intake system are selected as input variables and the orthogonal arrays is adapted as a space-filling design. With these simulated data, we can estimate a correlation parameter in Kriging by solving the nonlinear problem with a genetic algorithm and find an optimal level for the intake system by optimizing Kriging estimated with simulated annealing. We notice that this optimal design scheme gives noticeable results and is a preferable way to analyze the intake system. Therefore, an optimal design for the intake system is proposed by reducing the noise of its system.

• 한국생산제조학회지
• /
• 제22권4호
• /
• pp.693-699
• /
• 2013

Environmental issues are attracting increasing interest worldwide, and accordingly, environmental regulations for vehicles are being made more stringent. As a result, the car industry is conducting studies focusing on fuel efficiency and lightweight vehicles. To manufacture lightweight vehicles, existing steel parts are replaced by composite materials and lightweight metals. In this study, the fatigue life of a new material for manufacturing lightweight car door hinges was predicted using a finite-element analysis program. The existing steel material was replaced by carbon-fiber-reinforced plastic (CFRP) and aluminum alloy 6061, and the test results were analyzed. The maximum stress decreased by approximately three times, whereas the fatigue life and safety factor increased. When only CFRP was used, its allowable stress, safety factor, and fatigue life were excellent, but the sagging of the product exceeded the allowable value, which posed a limitation in use. Therefore, it seems desirable to use an appropriate combination of steel, AA6061, and CFRP for this product.

• 인터넷정보학회논문지
• /
• 제11권6호
• /
• pp.1-11
• /
• 2010

특정 기능을 중심으로 연구 개발되었던 LBS는 GPS 기능이 탑재된 스마트폰의 급속한 보급에 의해 개인을 위한 솔루션으로 점차 변모하고 있다. 이에 본 논문에서는 협업 필터링 기술에 기반한 추천 시스템을 개인용 LBS에 적용하여 위치기반 콘텐츠 제공 시스템의 개인화 방안을 제안하고자 한다. 제안하는 개인화 LBS 시스템은 사용자의 현재 위치를 중심으로 사용자가 설정한 반경 거리 안에 공유된 위치기반 콘텐츠의 선호도를 예측하여 사용자가 관심을 보일 것이라 예상되는 콘텐츠를 추천한다. 제안하는 시스템의 성능을 평가하기 위해 실지 구현한 프로토타입을 바탕으로 다양한 조건에서 선호도 예측 정확도를 관찰한 결과, 협업 필터링 기술과 LBS의 융합이 LBS의 개인화를 위한 측면에서 유효함을 확인할 수 있었다.

• 한국정밀공학회지
• /
• 제32권8호
• /
• pp.693-698
• /
• 2015

Recently, the quality of products after the corresponding machining processes were scrutinized in the interest of maintaining a high product-quality standard. The structure and stability of machine tools are important for the prediction of product quality. A structural analysis needs to be carried out to achieve the stable design of machine tools before the initial design stage in the manufacturing process of a precision product. In this study, a structural analysis was carried out using a finite element analysis (FEA) simulation to obtain the design stability of the main parts of a grinding machine. The sizes and locations of both the maximum stress and deformation in consideration of the cutting force of the chuck, tail stock, and bearing of the grinding machine were analyzed. Finally the grinding machine was successfully developed.

• 응용통계연구
• /
• 제28권3호
• /
• pp.457-465
• /
• 2015

경기침체가 장기화되고 세계적으로 저성장이 지속되면서 미래의 경기동향에 대한 예측의 중요성이 증폭되었다. 정부의 정책이 계획되면서부터 효과가 나타나기까지에는 시차가 존재하므로, 정책목표와 선행적 상관관계를 가지면서 목표의 미래 상황을 예측할 수 있는 유용한 지표의 개발에 관심이 모아진다. 본 연구에서는 통계청이 실시한 소비자 전망조사 결과가 미래의 실질성장에 유용한 선행적 정보를 제공했는지 평가해 보았다. 소비자들의 기대심리를 나타내는 체감지표를 사용하여 예측을 유발하는 통계모형을 설정한 후 미래의 실질성장에 대해 유의한 예측력을 갖는지 추정하였다. 소비자기대심리의 예측력은 먼 미래로 갈수록 정확도가 높아져 미래의 실질성장에 대해 선행적 정보를 주는 변수로 활용할 수 있는 것으로 판별된다.

• 한국전자파학회논문지
• /
• 제8권3호
• /
• pp.310-317
• /
• 1997

현재 통신시스템들은 주파수의 부족으로 인하여 통일주파수대역을 공용하고 있다. 따라서 이들 시스템간의 안전한 운용을 위해서는 이들간에 일어나는 간섭을 어느 정도 정확하게 예측하여야만 한다. 통신시스템간의 간섭은 기후, 주파수, 고려되는 시간율, 경로 거리 및 지형 동 여러 요인에 의존하고 있으며 GHz대 주파수에 특히 중요한 간섭원으로 작용하는 것이 강우산란에 의한 간섭이다. ITU-R에서는 많은 연구결과들을 종합하여 강우산란에 의한 간섭평가를 위한 전송손실 모델을 제공하고 있다. 본 논문에서는 ITU-R에서 제공하는 강우산란 모텔을 이용하여 관련식을 유도한 후 강우산란에 의한 전송손실을 예측해 보고 이를 실측 데이타와 비교하여 보았다.

• 대한안전경영과학회지
• /
• 제6권2호
• /
• pp.211-229
• /
• 2004

The basis of cyber trading has been sufficiently developed with innovative advancement of Internet Technology and the tendency of stock market investment has changed from long-term investment, which estimates the value of enterprises, to short-term investment, which focuses on getting short-term stock trading margin. Hence, this research shows a Short-term Stock Price Forecasting System on Learning Agent System using DTA(Decision Tree Algorithm) ; it collects real-time information of interest and favorite issues using Agent Technology through the Internet, and forms a decision tree, and creates a Rule-Base Database. Through this procedure the Short-term Stock Price Forecasting System provides customers with the prediction of the fluctuation of stock prices for each issue in near future and a point of sales and purchases. A Human being has the limitation of analytic ability and so through taking a look into and analyzing the fluctuation of stock prices, the Agent enables man to trace out the external factors of fluctuation of stock market on real-time. Therefore, we can check out the ups and downs of several issues at the same time and figure out the relationship and interrelation among many issues using the Agent. The SPFA (Stock Price Forecasting System) has such basic four phases as Data Collection, Data Processing, Learning, and Forecasting and Feedback.

• 한국전기전자재료학회논문지
• /
• 제23권11호
• /
• pp.831-836
• /
• 2010

In this paper, Plasma Enhanced Chemical Vapor Deposition (PECVD) $SiO_2$ film properties are modeled using statistical analysis and neural networks. For systemic analysis, Box-Behnken's 3 factor design of experiments (DOE) with response surface method are used. For characterization, deposited film thickness and film stress are considered as film properties and three process input factors including plasma RF power, flow rate of $N_2O$ gas, and flow rate of 5% $SiH_4$ gas contained at $N_2$ gas are considered for modeling. For film thickness characterization, regression based model showed only 0.71% of root mean squared (RMS) error. Also, for film stress model case, both regression model and neural prediction model showed acceptable RMS error. For sensitivity analysis, compare to conventional fixed mid point based analysis, proposed sensitivity analysis for entire range of interest support more process information to optimize process recipes to satisfy specific film characteristic requirements.