• 전자공학회논문지B
• /
• 제28B권10호
• /
• pp.831-841
• /
• 1991

A combined model of probabilistic and MLP(multi layer perceptron) model is proposed for the pattern classification of EMG( electromyogram) signals. The MLP model has a problem of not guaranteeing the global minima of error and different quality of approximations to Bayesian probabilities. The probabilistic model is, however, closely related to the estimation error of model parameters and the fidelity of assumptions. A proper combination of these will reduce the effects of the problems and be robust to input variations. Proposed model is able to get the MAP(maximum a posteriori probability) in the probabilistic model by estimating a priori probability distribution using the MLP model adaptively. This method minimize the error probability of the probabilistic model as long as the realization of the MLP model is optimal, and this is a good combination of the probabilistic model and the MLP model for the usage of MLP model reliability. Simulation results show the benefit of the proposed model compared to use the Mlp and the probabilistic model seperately and the average calculation time fro classification is about 50ms in the case of combined motion using an IBM PC 25 MHz 386model.

• 통합자연과학논문집
• /
• 제10권4호
• /
• pp.209-215
• /
• 2017

CXC chemokine receptor 2 (CXCR2) is a prominent chemokine receptor on neutrophils. CXCR2 antagonist may reduce the neutrophil chemotaxis and alter the inflammatory response because the neutrophilic inflammation in the lung diseases is found to be largely regulated through CXCR2 receptor. Hence, in the present study, Topomer based Comparative Molecular Field Analysis (Topomer CoMFA) was performed on a series of CXCR2 antagonist named pyrimidine-5-carbonitrile-6-alkyl derivatives. The best Topomer COMFA model was obtained with significant cross-validated correlation coefficient ($q^2$ = 0.487) and non cross-validated correlation coefficients ($r^2$ = 0.980). The model was evaluated with six external test compounds and its $r^2{_{pred}}$ was found to be 0.616. The steric and electrostatic contribution map show that presence of bulkier and electropositive group around cyclopropyl ring may contribute more for improving the biological activities of these compounds. The generated Topomer CoMFA model could be helpful for future design of novel and structurally related CXCR2 antagonists.

• 디지털융복합연구
• /
• 제15권6호
• /
• pp.229-236
• /
• 2017

효율적인 빈발 패턴 알고리즘은 연관 규칙 마이닝이나 융복합을 위한 마이닝 과정에서 필수적인 요소이며 많은 활용성을 가지고 있다. 패턴 마이닝을 위한 많은 모델들이 빈발 패턴에 관한 정보를 추출하여 FP-트리를 이용하여 저장하고 있다. 본 논문에서는 항목들의 무게중심을 이용한 새로운 빈발 패턴 알고리즘(CAWFP-Growth)을 제안하여 항목들이 가지는 가중치와 빈도수를 같이 고려하여 항목간의 중심을 계산하여 기존의 FP-Growth 알고리즘의 효율성을 향상시킨다. 제안한 방법은 하향 폐쇄의 성질을 유지하기 위한 기존의 전역적 최대치 가중치 지지도를 필요로 하지 않기 때문에 자연히 빈발 패턴의 탐색시간이 줄어들고 정보의 손실을 줄일 수 있다. 실험결과를 통하여 제안된 알고리즘이 기존의 동적가중치를 이용하는 다른 방법과 비교해볼 때, 항목들의 무게중심이 빈발패턴의 정확한 정보를 유지하고 FP-트리의 처리시간을 줄여주기 때문에 제안한 방법의 중요성을 보이고 있다 또한 가상 분산모드에서 맵리듀스 프레임을 기반으로 빅데이터를 모델링하고 향후 완전분산 모드에서 제안한 알고리즘의 모델링이 필요하다.

• 한국측량학회지
• /
• 제26권6호
• /
• pp.583-590
• /
• 2008

도로, 철도 및 운하 등을 비롯한 각종 건설공사를 위해서는 건설공사의 설계과정에서 건설예정지에 대한 지형측량을 실시하고 이를 기초로 종 횡단면도의 제작이 필수적인 요소이다. 본 연구에서는 건설예정지에 대한 프로파일제작에 있어 NGIS구축사업에 의해 제작된 수치지형도의 지형정보를 이용하여 정밀 3차원지형모델을 구축하고, 이로부터 자동 프로파일을 생성하여 종 횡단면도로 활용할 수 있는 방안을 검토하고자 하였다. 이를 위해 수치지형도로부터 표고 및 주요시설물의 레이어를 각각 추출하고 이를 이용하여 정밀 3차원 지형모델을 구축하는 한편, 3차원 지형모델로부터 자동 프로파일을 생성하여 종 횡단면도를 제작하였다. 그리고 생성된 프로파일의 경로에 대하여 지형측량을 실시하여 상호 분석함으로써 자동 생성된 프로파일의 정확도가 현지측량 정확도를 만족시킬 수 있는지의 여부를 검토하였다. 본 연구의 결과는 건설공사를 위해 실시되는 설계과정에서 설계기간의 단축, 설계비용의 감소와 설계업무의 효율화를 꾀할 수 있는 새로운 개념의 프로파일 생성기법으로 제안할 수 있을 것으로 사료된다.

• 한국지형학회지
• /
• 제24권1호
• /
• pp.77-91
• /
• 2017

Many debris landforms in the mountains of Korea have formed in the periglacial environment during the last glacial stage when the generation of sediments was active. Because these landforms are generally located on steep slopes and mostly covered by vegetation, however, it is difficult to observe and access them through field investigation. A scientific method is required to reduce the survey range before performing field investigation and to save time and cost. For this purpose, the use of remote sensing and GIS technologies is essential. This study has extracted the potential area of debris landform formation using a fuzzy set model as a mathematical data integration method. The first step was to obtain information about the location of debris landforms and their related factors. This information was verified through field observation and then used to build a database. In the second step, we conducted the fuzzy set modeling to generate a map, which classified the study area based on the possibility of debris formation. We then applied a cross-validation technique in order to evaluate the map. For a quantitative analysis, the calculated potential rate of debris formation was evaluated by plotting SRC(Success Rate Curve) and calculating AUC(Area Under the Curve). The prediction accuracy of the model was found to be 83.1%. We posit that the model is accurate and reliable enough to contribute to efficient field investigation and debris landform management.

• 지질공학
• /
• 제21권4호
• /
• pp.393-402
• /
• 2011

석면은 강한 독성이 있는 물질로 폐암 및 폐와 관련된 질환에 치명적이다. 최근 자연 상태의 석면이 함유된 지역에 대한 정확한 정보의 부재로 석면이 함유된 지역을 효율적으로 관리할 필요가 있다. 본 연구의 목적은 효율적인 석면관리를 위해서 석면위험지역을 지역적으로 등급화 할 수 있는 자연 상태의 석면 노출위험도를 제작하는 것이다. 이를 위해서는 먼저 석면 위험지역을 평가할 수 있는 주제를 발굴하고 필요에 따라 현지조사를 통해 공간적으로 매핑 할 수 있는 주제도를 작성한다. 또한 석면 데이터에 대한 분석 표현 및 프로세스들을 정리하여 석면 지식베이스 구축을 하고 석면노출위험을 위한 평가모델을 마련한다. 석면 노출위험도 작성을 위한 공간분석은 문헌 및 전문가의 의견에 기반을 둔 가중치 분석과 불확실한 데이터에 사용하는 퍼지 연산자들을 이용한 공간 중첩분석을 수행한다. 가중치 및 퍼지 연산에 따라 작성된 석면 노출 위험도는 지역을 계층적 관리함으로써 석면 안전 및 보상에 활용할 수 있을 것으로 판단된다.

• 대한산업공학회지
• /
• 제39권3호
• /
• pp.163-171
• /
• 2013

Various web browsers offer mouse gesture functions because they are convenient input methods. Mouse gestures enable users to move to the previous page or tab without clicking its relevant icon or menu of the web browser. To maximize the efficiency of mouse gestures, they should be designed to match users' mental models. Mental models of human beings are used to make accurate predictions and reactions when certain information has been recognized by humans. This means providing users with appropriate information about mental models will lead to fast understanding and response. A cognitive response test was performed in order to evaluate whether the mouse gestures easily associate with their respective functional meanings or not. After extracting mouse gestures which needed improvement, those were redesigned to reduce cognitive load via sketch maps. The methods presented in this study will be of help for evaluating and designing mouse gestures.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.36.4-36
• /
• 2001

A robust and reliable path recognition system is one necessary component for the autonomous navigation of a mobile robot to help determining its current position in its navigation map. This paper describes a computer visual path-recognition system using on-board video camera as vision-based driving assistance for an autonomous navigation mobile robot. The common problem for a visual system is that its reliability was often influenced by different lighting conditions. Here, two different image processing methods for the path detection were developed to reduce the effect of the luminance: one is based on the RGB color model and features of the path, another is based on the HSV color model in the absence of luminance.

• 도시과학
• /
• 제7권1호
• /
• pp.29-38
• /
• 2018

The cadastral rehabilitation project, which has been implemented since 2012, is a project to re-examine the national land that is not in conformity with the cadastral map, There is a lot of trouble in securing financial resources for business execution. This study examines the utility of UAS(Unmanned Aerial System) image - based cadastral demarcation as an alternative to budget reduction in the current state of cadastral rehabilitation, reasonable boundary adjustment, UAV(Unmanned Aerial Vehicles) is used to create 3D models and orthoimages of business districts, and to check accuracy by superimposing and comparing with digital maps of NGII(National Geographic Information Institute). As a result of the study, the accuracy of the 3D model and the orthoimage through the SfM(Structure-from-Motion) - based image interpretation of the digital map of the NGII were derived. In particular, we confirmed the similarity of UAS-based orthoimage with the cadastral boundaries affirmation, It is anticipated that the cost saving effect of current survey and boundary survey can be expected. In addition, it is easy to prepare a report to reduce civil complaints, which is a problematic element of the adjustment.

• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 2003년도 공동 춘계학술대회 논문집
• /
• pp.100-100
• /
• 2003

The purpose of this study is to reveals spatial relationships between landslides and geospatial data set, map the landslide susceptibility using the relationships and verify the landslide susceptibility using the landslide occurrence data in Bosun area in 1998. Landslide locations were detected from aerial photography and field survey and topography, soil, forest, and land use data sets were constructed as a spatial database using GIS. As the landslide occurrence factors, slope, aspect, curvature and type of topography, texture, material, drainage and effective thickness of soil, type, age, diameter and density of wood and land use were used. Is extract the relationship between landslides and geospatial database, Bayesian probability methods, likelihood ratio and weight of evidence, were applied and the ratio and contrast value that is W$\^$＋/- W$\^$-/ were calculated. The landslide susceptibility index was calculated by summation of the likelihood ratio and contrast value and the landslide susceptibility maps were generated using the index. As a result, it is expected that spatial relationships between landslides and geospatial database is helpful to explain the characteristics of landslide and the landslide susceptibility map is used to reduce associated hazards, and to plan land use and construction.