• 정보과학회 논문지
• /
• 제44권11호
• /
• pp.1149-1155
• /
• 2017

최근 통신 기술의 발달로 공간 내 환경 자극을 나타내는 다양한 센서 데이터 수집이 가능해졌다. 베이지안 네트워크는 추론 근거를 확률적으로 고려함으로써 센서 데이터의 불확실하고 불완전한 특성을 보완할 수 있다. 본 논문은 환경 자극의 심리적 영향력을 고려하여 설계된 모듈형 베이지안 네트워크 기반 대중 감성 예측 시스템을 제안한다. 또한 단일 베이지안 네트워크를 모듈화하여 공간 내 환경 자극 변동의 유연한 대응 및 효율적 추론을 수행하였다. 시스템의 성능 검증을 위해 유치원 공간에서 수집된 조도, 음량, 온도, 습도, 색 온도, 음향, 향기, 대중 감성 데이터를 기반으로 대중 감성을 예측하였다. 실험 결과, 제안하는 방법의 예측 정확도는 85%로 여타 분류 기법보다 높은 성능을 나타내었다. 정량적, 정성적 분석을 통해 대중 감성 예측을 위한 확률 기반 방법론의 가능성 및 한계를 분석하였다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제6권3호
• /
• pp.155-160
• /
• 2017

최근 컴퓨터를 이용한 다양한 인식 문제를 해결하기 위해 딥 러닝을 적용하는 사례가 늘어나고 있다. 딥 러닝은 학습에 필요한 요소를 학습데이터를 통해 스스로 도출해내기 때문에, 수작업(hand-craft)을 통해 특징을 도출하던 기존의 기계학습 방법보다 더 많은 장점을 갖는다. 행동인식을 위한 기존의 심층 신경망은 비디오 데이터를 일정 프레임의 이미지로 분할한 후, 분할된 각 이미지 사이의 시간적 연계성 분석을 통해 행동을 분류한다. 그러나 이러한 신경망은 소규모 행동 클래스를 갖는 분류 문제에서 학습 데이터의 부족 문제 및 과적합(overfitting) 문제로 인해 이를 실제 문제에 적용하기 어려운 경우가 많다. 이에 본 논문에서는 5가지의 소규모 행동 클래스를 정의하고, 기존 행동 인식 신경망의 최적화를 통해 이를 분류하였다. 700개의 비디오데이터를 통해 행동 데이터베이스를 구성하였고, 약 74.00%의 분류 정확도를 얻을 수 있었다.

• 대한공간정보학회지
• /
• 제13권1호
• /
• pp.63-69
• /
• 2005

InSAR(Interferometric Synthetic Aperture Radar)는 급속히 발진하고 있는 기술이며 지표면의 수치지형모델 제작과 토지이용 분류뿐만 아니라, 지진, 화신, 지반침하와 빙하흐름의 모니터링과 같은 다양한 응용분야 적용은 그것의 장점을 강화시켜 주고 있다. InSAR는 원격탐측 기술의 한 부류이므로, 위성위치와 자세, 대기, 그리고 기타 요소에 의한 다양한 오차원인을 가지고 있으므로, 이 시스템의 정확도 검증, 특별히 SAR 영상으로부터 제작된 수치지형모델에 대해서는 중요하다. 본 연구에서는 RTK GPS와 Kinematic GPS 측위가 InSAR 기술로 제작된 수치지형모델의검증 도구로 이용되었다. 그 결과로서, Kinematic GPS는 실험지역에서 RTK GPS보다 많은 관측값을 얻을 수 있었지만, 안테나 주위 나무 등에 의한 위성추적 문제와 통신거리에 따른 기준국과 이동국사이의 자료전송 문제 등이 여전히 시급히 해결해야 할 과제로 나타났다.

• 한국콘텐츠학회논문지
• /
• 제10권4호
• /
• pp.84-90
• /
• 2010

데이터베이스 시스템의 응용분야가 데이터웨어하우징에서 전자상거래에 이르기까지 광범위해지면서 데이터베이스 시스템이 대형화되었다. 이로 인해 데이터베이스 시스템의 성능 향상을 위한 튜닝이 중요한 논점이 되었다. 데이터베이스 시스템의 튜닝은 워크로드 특성을 고려하여 수행할 필요가 있다. 그러나 복합적인 데이터베이스 환경에서 워크로드를 식별하기는 어려우므로 자동적인 식별 방법이 요구된다. 본 논문에서는 데이터베이스 워크로드를 자동적으로 식별하는 SVM 워크로드 분류기를 제안한다. TPC-C와 TPC-W 성능 평가에서 자원할당 파라미터 변경에 따른 워크로드 데이터를 수집하여 SVM을 통해 분류 한다. SVM의 커널별 커널 파라미터와 오류 허용 임계치 값인 C의 조정을 통하여 최적의 SVM 워크로드 분류기를 선택한다. 제안한 SVM 워크로드 분류기와 Decision Tree, Naive Bayes, Multilayer Perceptron, K-NN 분류기의 분류 성능을 비교한 결과, SVM 워크로드 분류기가 다른 기계 학습 분류기보다 9% 이상 향상된 분류 성능을 보였다.

• Journal of Biosystems Engineering
• /
• 제36권1호
• /
• pp.40-47
• /
• 2011

Image analysis algorithm for the quality evaluation of ginseng seedling was investigated. The images of ginseng seedling were acquired with a color CCD camera and processed with the image analysis methods, such as binary conversion, labeling, and thinning. The processed images were used to calculate the length and weight of ginseng seedlings. The length and weight of the samples could be predicted with standard errors of 0.343 mm, and 0.0214 g respectively, $R^2$ values of 0.8738 and 0.9835 respectively. For the evaluation of the three quality grades of Gab, Eul, and abnormal ginseng seedlings, features from the processed images were extracted. The features combined with the ratio of the lengths and areas of the ginseng seedlings efficiently differentiate the abnormal shapes from the normal ones of the samples. The grade levels were evaluated with an efficient pattern recognition method of support vector machine analysis. The quality grade of ginseng seedling could be evaluated with an accuracy of 95% and 97% for training and validation, respectively. The result indicates that color image analysis with support vector machine algorithm has good potential to be used for the development of an automatic sorting system for ginseng seedling.

• 농촌계획
• /
• 제15권4호
• /
• pp.213-220
• /
• 2009

Farmland spatial data are needed as a basic information in conducting rational use of farmlands in regional scale. This study develops a method that can be used to make up such farmland spatial data in a simple way and to develop a technique to manage them in a unitary way, and examines the effectiveness of the technique by applying it to the case area. A method that Web-Service Raster Image and Digital Cadastal Map can be utilized as a base map was devised. It was designed applying the vector system, in which one lot of farmland is area unit. Raster image and field survey data were combined to increase the accuracy of data. The lot boundaries of the existing boundary map were adjusted to the shapes of actual farmlands using GIS edition function. A proper farmland use classification system to the area characteristics was established and data obtained from the field survey were coded. Usually it is very difficult to identify the size of one lot of actual farmland in the existing space data, based on the results of the case study, the result map showed actual topography very realistically. Also the frequently occurring lot divisions and the serious topographical modifications by natural disasters frequently have made it impossible to survey farmlands on the catastral map in the field. But the final map had a great usefulness in that it may solve such problems by expressing the filed survey results graphically.

• Ecology and Resilient Infrastructure
• /
• 제5권2호
• /
• pp.59-71
• /
• 2018

Lake Enriquillo, the largest lake in the Dominican Republic, recently has undergone unusual water area changes since 2001 thus it has been affected seriously by local community's livelihood. Earthquakes and seismic activities of Hispaniola plate tectonic coupled with human activities and climate change are addressed as factors causing the increasing. Thus, a thorough study on relationship between lake area changing, and those factors is needed urgently. To do so, this study applied MESMA on MODIS data to extract water area of Lake Enriquillo during 2001 and 2012 bimonthly, with six issues 12-year. MODIS provides high temporal resolution, and its coarse spatial resolution is compensated by MESMA fraction map. The increase in water area was $142.2km^2$, and the maximum lake area was $338.0km^2$ (in 2012). Water areas extracted by two Landsat scenes at two different times with three image classification approaches (ISODATA, MNDWI, and TCW) were used to assess accuracy of MODIS and MESMA results; it indicated that MESMA water areas are same as ISODATA's, less than 0.4%, while the highest difference is between MESMA and TCW, 2.4%. A number of previously formulated hypotheses of lake area change were investigated based on the outcomes of the present study, though none of them could fully explain the changes.

• Progress in Superconductivity
• /
• 제8권1호
• /
• pp.46-53
• /
• 2006

Magnetocardiography(MCG) has been proposed as a novel and non-invasive diagnostic tool for the detection of cardiac electrical abnormality associated with myocardial ischemia. In our previous study, we have proposed a new classification method of MCG parameters, based on the different populations of the parameters between coronary artery disease(CAD) patients, symptomatic patients and healthy volunteers. We used four parameters, representing the directional changes of the electrical activity in the period of an R-ST-T interval. In patients with chest pain and without ST-segment elevation, who were selected consecutively from all patients admitted to the hospital in 2004, the patients with CAD could be classified with a higher sensitivity than conventional methods, showing that the proposed method can be useful for the diagnosis of CAD with MCG. In this study, we examined the validity of the algorithm with the prior probability distribution in diagnosis of new patients admitted to the hospital in 2005. In the results, presence of CAD could be found with sensitivity and specificity of 81.3% and 71.4%, respectively, in patients with chest pain and non-diagnostic ECG findings.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2011년도 춘계학술대회 논문집
• /
• pp.618-626
• /
• 2011

Recent development of related technologies and efficient utilization of the entire country for the purpose of railway construction, and plans are being accelerated. the railway noise has been improved by increasing the high speed railway station, and accelerating the existing trains. Nord2000 which is an overseas noise prediction equation could not be applied directly to the domestic railway vehicles. So the specific vehicles in the Nordic countries which is a similar specification to domestic trains should be selected. Nord2000's accuracy was compared to Schall03, CRN's. Prediction of Ground impedance and Roughness class were carried out at different. In this paper, the result of selected vehicles for Nord2000 was as follows. S-1aX2 was for express trains, N-$^*2c$-3b was for Mugunghwa, S-Pass/wood was for Saemaul, N-4a was for freight trains, N-3a was for subway, the calculation time for Nord2000 took longer than others, in addition, Ground absorption was indispensable to calculate a noise map for Nord2000. As a result, CRN's prediction noise levels at Wonju-si was closest to the measurements. However, the predicted noise levels of Nord2000 was the most accurate.

• 한국농공학회지
• /
• 제45권4호
• /
• pp.78-88
• /
• 2003

The land use changes from non-urban areas to urban areas lead to the increased impervious areas, consequently increased direct runoff and higher peak runoff. Urban areas have also been recognized as significant sources of Nonpoint Source (NPS) pollution, while agricultural activities have been known as the primary sources of NPS pollution. Many features of the L-THIA/NPS GIS, L-THIA/NPS WWW system have been enhanced to provide easy-to-use system. The L-THIA model was applied to the Little Eagle Creek (LEC) watershed in Indiana to evaluate the accuracy of the model. The L-THIA/NPS GIS estimated yearly direct runoff values match the direct runoff separated from U.S. Geological Survey stream flow data reasonably. The $R^2$ and Nash-Sutcliffe values are 0.67 and 0.60, respectively. The L-THIA estimated runoff volume and total nitrogen loading for each land use classification in the LEC watershed were computed. The estimated runoff volume and total nitrogen loading in the LEC watershed increased by 180% and 270% for the 20 years. Urbanized areas -"Commercial", "High Density Residential", and "Low Density Residential"- of the LEC watershed made up around 68% of the 1991 total land areas, however contributed more than 92% of average annual runoff and 86% of total nitrogen loading. Therefore, it is essential to consider the impacts of land use change on hydrology and water quality in land use planning of urbanizing watershed.nning of urbanizing watershed.