• Journal of Broadcast Engineering
• /
• v.22 no.4
• /
• pp.496-508
• /
• 2017

In this paper, we propose a Tone Mapping Operator (TMO) that preserves global contrast and precisely preserves boundary information. In order to reconstruct a High Dynamic Range (HDR) image to a Low Dynamic Range (LDR) display by using Threshold value vs. Intensity value (TVI) based on Human Visual System (HVS) and contrast value. As a result, the global contrast of the image can be preserved. In addition, by combining the boundary information detected using Guided Image Filtering (GIF) and the detected boundary information using the spatial masking of the Just Noticeable Difference (JND) model, And improved the perceived image quality of the output image. The conventional TMOs are classified into Global Tone Mapping (GTM) and Local Tone Mapping (LTM). GTM preserves global contrast, has the advantages of simple implementation and fast execution time, but it has a disadvantage in that the boundary information of the image is lost and the regional contrast is not preserved. On the other hand, the LTM preserves the local contrast and boundary information of the image well, but some areas are expressed unnatural like the occurrence of the halo artifact phenomenon in the boundary region, and the calculation complexity is higher than that of GTM. In this paper, we propose TMO which preserves global contrast and combines the merits of GTM and LTM to preserve boundary information of images. Experimental results show that the proposed tone mapping technique has superior performance in terms of cognitive quality.

• Journal of the Korean earth science society
• /
• v.30 no.1
• /
• pp.111-126
• /
• 2009

The purpose of this study was to derive the criterions of each type of mental models on the plate boundaries and to investigate high school students' mental models on these concepts. The 11th grade student participants were requested to draw the collisional, convergent, and divergent boundaries and were interviewed individually. The drawings and the data gathered through the interviews were analyzed qualitatively. The mental models on the plate boundaries were classified as 'naive model', 'unstable model', 'causal model', and 'conceptual model'. The criterions for analyzing the mental models were the differentiations of the lithospheric plates and the mantle, the explanations of the motion of the plates and lower mantle, the demonstrations of topographical features of the plate boundaries and the causal relationships between the mantle convection and the topographical features. The findings revealed that the students holding 'the naive model' and 'the unstable model' were unable to relate the mantle convection and the three boundaries. In contrast, the students holding 'the causal model' and 'the conceptual model' were able to explain that the mantle convection causes the three boundaries. Also, the types of epistemological belief were different depending on their mental models. Students holding the naive model and the unstable model tended to rely upon the external authorities.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.217-217
• /
• 2019

해안과 하천이 위치해 있는 낙동강하구의 담 염수 경계면 추적 연구에서 담 염수 경계면의 담수기원특성을 분석하기 위해서는 담 염수 경계면을 이루는 담수의 기원이 하천 혹은 지하수 인지를 규명하는 것이 매우 중요하다. 담 염수 경계면에 있는 담수는 일반적으로 하천과 지하수에 의한 것으로, 낙동강하구 일원을 대상으로 지하수공 내 해수침투 여부 파악을 위해 화학적(유기물) 분석을 실시하였다. 이와 아울러 낙동강하구 일원에서 담 염수 경계면에서 채취한 수질시료의 담수기원을 분석하기 위하여 K-water연구원 수질안전센터에 지하수공 7개지점(BH-1~7호공)의 심도별 물시료 2~4개지점(총 23개 지점), 하천(1개 지점), 해수 및 해안유출수(각 1개 지점)를 포함한 26개 시료를 LC-OCD(Liquid Chromatography-Organic Carbon Detector)로 분석하였다. LC-OCD 분석결과 특성은 기본적으로 유기물질이 물에서 유래한 aquagenic 혹은 토양층에서 유래한 pedogenic 유기물질 인지에 달려있다. 댐 또는 하천에서 pedogenic 유기물의 농도는 일반적으로 유역분지의 수문 또는 수리지질학적 경로에 의존한다. pedogenic 유기물들은 주로 상대적으로 작은 분자량을 갖는 친수성, 높은 사슬밀도 및 내화성 분자특성을 갖는 펄빅산으로 구성된다. aquagenic 유기물질은 수생 식물성 생물이나 플랑크톤의 분해 산물로서 세포벽에서 유래된 peptidoglycans와 고분자량의 polysaccharides 등을 포함한다(Chio & Jung, 2008; Buffle, 1988). 담 염수 경계면 추적을 위한 7개 관측공의 심도별 수질시료는 하천, 해수, 그리고 해안유출수의 용존유기탄소를 분석하기 위하여 LC-OCD로 정밀분석하였다. 그 결과, humic, 휴믹물질의 산화물질인 building blocks, 생물고분자 물질(bio-polymers), neutrals, acids로 분석되었으며, 일반적인 자연유기물질의 기원은 pedogenic과 aquagenic 유기물질로 분류된다. IHSS 표준물질 분석 등을 통한 SUVA 값으로부터 자연유기물질의 기원정보를 제공하는 HS-Diagram으로 도시한 결과, 2018년 11월 2일 조사한 26개의 원수시료 전체는 pedogenic fulvic acid〉aquagenic fulvic acid으로 하천의 기원이 우세한 것으로 분석되었다. BH-1호공과 BH-6호공의 특정 1개구간 GL.-6m를 제외한 모든 구간에서 aquagenic FA의 지하수 기원으로 분석되었으며, 나머지 지하수공(BH-2, 3, 4, 5, 7)과 하천 및 해안유출수는 유역분지 수문학적 경로인 pedogenic FA의 하천 기원의 담수인 것으로 분석된다.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.77-86
• /
• 2022

The Republic of Korea is a country in which coastal surveillance is an imperative national task as it is surrounded by seas on three sides under the confrontation between South and North Korea. However, due to Defense Reform 2.0, the number of R/D (Radar) operating personnel has decreased, and the period of service has also been shortened. Moreover, there is always a possibility that a human error will occur. This paper presents specific guidelines for developing an AI learning model for the intelligent coastal surveillance system. We present a three-step strategy to realize the guidelines. The first stage is a typical stage of building an AI learning model, including data collection, storage, filtering, purification, and data transformation. In the second stage, R/D signal analysis is first performed. Subsequently, AI learning model development for classifying real and false images, coastal area analysis, and vulnerable area/time analysis are performed. In the final stage, validation, visualization, and demonstration of the AI learning model are performed. Through this research, the first achievement of making the existing weapon system intelligent by applying the application of AI technology was achieved.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.10
• /
• pp.2028-2042
• /
• 1994

Properly defining signal and noise in a self-organizing system like ART(Adaptive Resonance Theory) neural network model raises a number of subtle issues. Pattern context must enter the definition so that input features, treated as irrelevant noise when they are embedded in a given input pattern, may be treated as informative signals when they are embedded in a different input pattern. The ATR automatically self-scales their computational units to embody context and learning dependent definitions of a signal and noise and there is no problem in categorizing input pattern that have features similar in nature. However, when we have imput patterns that have features that are different in size and nature, the use of only one vigilance parameter is not enough to differentiate a signal from noise for a good categorization. For example, if the value fo vigilance parameter is large, then noise may be processed as an informative signal and unnecessary categories are generated: and if the value of vigilance parameter is small, an informative signal may be ignored and treated as noise. Hence it is no easy to achieve a good pattern categorization. To overcome such problems, a Coupled-ART neural network capable of modularized categorization of patterns is proposed. The Coupled-ART has two layer of tightly coupled modules. the upper and the lower. The lower layer processes the global features of a pattern and the structural features, separately in parallel. The upper layer combines the categorized outputs from the lower layer and categorizes the combined output, Hence, due to the modularized categorization of patterns, the Coupled-ART classifies patterns more efficiently than the ART1 model.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.2
• /
• pp.21-35
• /
• 2020

Vegetation information is a very important factor used in various fields such as urban planning, landscaping, water resources, and the environment. Vegetation varies according to canopy density or chlorophyll content, but vegetation vitality is not considered when classifying vegetation areas in previous studies. In this study, in order to satisfy various applied studies, a study was conducted to set a threshold value of vegetation index considering vegetation vitality. First, an eBee fixed-wing drone was equipped with a multi-spectral camera to construct optical and near-infrared orthomosaic images. Then, GIS calculation was performed for each orthomosaic image to calculate the NDVI, GNDVI, SAVI, and MSAVI vegetation index. In addition, the vegetation position of the target site was investigated through VRS survey, and the accuracy of each vegetation index was evaluated using vegetation vitality. As a result, the scenario in which the vegetation vitality point was selected as the vegetation area was higher in the classification accuracy of the vegetation index than the scenario in which the vegetation vitality point was slightly insufficient. In addition, the Kappa coefficient for each vegetation index calculated by overlapping with each site survey point was used to select the best threshold value of vegetation index for classifying vegetation by scenario. Therefore, the evaluation of vegetation index accuracy considering the vegetation vitality suggested in this study is expected to provide useful information for decision-making support in various business fields such as city planning in the future.

• Journal of Korea Water Resources Association
• /
• v.49 no.7
• /
• pp.635-644
• /
• 2016

This study investigates variation of flow characteristics due to variation of branch channel width and discharge ratio at bifurcation channel using 2D numerical model. The calculated result considering secondary flow is more accurate and stable than without considering one. The diversion flow rate ($Q_3/Q_1$) is reduced by flow stagnation effect according to the interaction of the secondary flow and flow separation zone in branch channel. The less upstream inflow or the lower upstream velocity, the bigger variation of diversion flow rate by changing branch channel width. At uniform downstream boundary condition, the rate of change in Froude number of downstream of main channel($Fr_2$)-diversion flow rate ($Q_3/Q_1$) relations is similar about -2.4843~-2.6675 when branch channel width ratio (b/B) is decreased. At uniform diversion flow rate ($Q_3/Q_1$) condition, the width of recirculation zone in branch channel is decreased when branch channel width ratio (b/B) is decreased. The less upstream inflow in the case of increasing branch channel width or the narrower branch channel width in the case of increasing upstream inflow, the bigger reduction ratio of recirculation zone width. At uniform inflow discharge ($Q_1$) condition, diversion flow rate, the width and length of recirculation zone in branch channel are decreased when branch channel width ratio (b/B) is decreased.

• Journal of Intelligence and Information Systems
• /
• v.14 no.2
• /
• pp.193-206
• /
• 2008

Medical diagnosis can be considered a classification task which classifies disease types from patient's condition data represented by a set of pre-defined attributes. This study proposes a hybrid genetic algorithm based classification method to develop classifiers for multidimensional pattern classification problems related with medical decision making. The classification problem can be solved by identifying separation boundaries which distinguish the various classes in the data pattern. The proposed method fits a finite number of regional agents to the data pattern by combining genetic algorithms and local adaptive operations. The local adaptive operations of an agent include expansion, avoidance and relocation, one of which is performed according to the agent's fitness value. The classifier system has been tested with well-known medical data sets from the UCI machine learning database, showing superior performance to other methods such as the nearest neighbor, decision tree, and neural networks.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.71-89
• /
• 2003

Although many studies demonstrate that one technique outperforms the others for a given data set, there is often no way to tell a priori which of these techniques will be most effective in the classification problems. Alternatively, it has been suggested that a better approach to classification problem might be to integrate several different forecasting techniques. This study proposes the linearly combining methodology of different classification techniques. The methodology is developed to find the optimal combining weight and compute the weighted-average of different techniques' outputs. The proposed methodology is represented as the form of mixed integer programming. The objective function of proposed combining methodology is to minimize total misclassification cost which is the weighted-sum of two types of misclassification. To simplify the problem solving process, cutoff value is fixed and threshold function is removed. The form of mixed integer programming is solved with the branch and bound methods. The result showed that proposed methodology classified more accurately than any of techniques individually did. It is confirmed that Proposed methodology Predicts significantly better than individual techniques and the other combining methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.2
• /
• pp.517-524
• /
• 2010

Recently, the size of online texts and textual information is increasing explosively, and the automated classification has a great potential for handling data such as news materials and images. Text classification system is based on supervised learning which needs laborous work by human expert. The main goal of this paper is to reduce the manual intervention, required for the task. The other goal is to increase accuracy to be high. Most of the documents have high complexity in contents and the high similarities in their described style. So, the classification results are not satisfactory. This paper shows the implementation of classification system based on ETOM+RPost algorithm and classification progress using SPAM data. In experiments, we verified our system with right-training documents and wrong-training documents. The experimental results show that our system has high accuracy and stability in all situation as 16% improvement in accuracy.