• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.240-242
• /
• 2019

본 논문에서는 대한민국 국토에 대한 토지피복지도를 인공위성 영상으로부터 생성하는 기술을 제안한다. 제안하는 방법은 먼저 합성곱 신경망을 이용하여 인공위성 영상의 각 패치를 4 종류의 토지 용도로 분류한다. 이후 인공위성 영상과 토지 용도 분류 결과를 조건부 랜덤 필드에 적용하여 픽셀 단위로 색상과 질감이 유사한 영역을 같은 토지 용도로 분류될 수 있도록 하여 정확한 토지피복지도를 생성한다. 현재 대한민국 국토에 대한 토지피복지도 생성을 위해 구축된 데이터 세트가 없기 때문에 본 연구에서는 합성곱 신경망 학습을 위한 데이터 세트를 직접 구축하였다. 이를 위해 환경공간정보 서비스 웹사이트로부터 인공위성 영상을 취득하고, 각 영상을 패치 단위로 나누어 토지 용도를 직접 분류하였다. 실험 결과를 통해 제안하는 토지 용도 분류 합성곱 신경망의 성능을 평가하였으며, 최종 생성된 토지피복지도는 제안하는 방법이 효과적으로 토지 용도를 분류할 수 있음을 나타낸다.

• Journal of the Korean earth science society
• /
• v.35 no.1
• /
• pp.69-87
• /
• 2014

This paper suggests a conditional simulation framework based on multiple data transformations for geostatistical simulation of compositional data. First, log-ratio transformation is applied to original compositional data in order to apply conventional statistical methodologies. As for the next transformations that follow, minimum/maximum autocorrelation factors (MAF) and indicator transformations are sequentially applied. MAF transformation is applied to generate independent new variables and as a result, an independent simulation of individual variables can be applied. Indicator transformation is also applied to non-parametric conditional cumulative distribution function modeling of variables that do not follow multi-Gaussian random function models. Finally, inverse transformations are applied in the reverse order of those transformations that are applied. A case study with surface sediment compositions in tidal flats is carried out to illustrate the applicability of the presented simulation framework. All simulation results satisfied the constraints of compositional data and reproduced well the statistical characteristics of the sample data. Through surface sediment classification based on multiple simulation results of compositions, the probabilistic evaluation of classification results was possible, an evaluation unavailable in a conventional kriging approach. Therefore, it is expected that the presented simulation framework can be effectively applied to geostatistical simulation of various compositional data.

• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.81-92
• /
• 2003

Generalized LR parsing is one of the enhanced LR parsing methods so that it overcome the limit of one-way linear stack of the traditional LR parser using graph-structured stack, and it has been playing an important role of a firm starting point to generate other variations for NL parsing equipped with various mechanisms. In this paper, we propose a conditional Action Model that can solve the problems of conventional probabilistic GLR methods. Previous probabilistic GLR parsers have used relatively limited contextual information for disambiguation due to the high complexity of internal GLR stack. Our proposed model uses Surface Phrasal Types representing the structural characteristics of the parse for its additional contextual information, so that more specified structural preferences can be reflected into the parser. Experimental results show that our GLR parser with the proposed Conditional Action Model outperforms the previous methods by about 6-7% without any lexical information, and our model can utilize the rich stack information for syntactic disambiguation of probabilistic LR parser.

• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.1-12
• /
• 2020

In the medical field, numerical imbalance of data due to differences in disease prevalence is a common problem. It reduces the performance of a artificial intelligence network, leading to difficulties in learning a network with good performance. Recently, generative adversarial network (GAN) technology has been introduced as a way to address this problem, and its ability has been demonstrated by successful applications in various fields. However, it is still difficult to achieve good results in solving problems with performance degraded by numerical imbalances because the image resolution of the previous studies is not yet good enough and the structure in the image is modeled locally. In this paper, we propose a multi-scale conditional generative adversarial network based on attention mechanism, which can produce high resolution images to solve the numerical imbalance problem of chest X-ray image data. The network was able to produce images for various diseases by controlling condition variables with only one network. It's efficient and effective in that the network don't need to be learned independently for all disease classes and solves the problem of long distance dependency in image generation with self-attention mechanism.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.1
• /
• pp.27-35
• /
• 2017

This research was to elucidate the generation method of daily precipitation data from monthly data. We applied a combined method of Markov chain and gamma distribution function using 4 specific parameters of ${\alpha}$, ${\beta}$, p(W/W) and p(W/D) for generation of daily rainfall data using daily precipitation data for the past 30 years which were collected from the country's 23 meteorological offices. Four parameters, applied to use for the combination method, were calculated by maximum likelihood method in location of 23 sites. There are high correlations of 0.99, 0.98 and 0.98 in rainfall days, rainfall probability and mean amount of daily rainfall between measured and simulated data in case of those parameters. In case of using parameters estimated from monthly precipitation, correlation coefficients in rainfall days, rainfall probability and mean amount of daily rainfall are 0.84, 0.83 and 0.96, respectively. We concluded that a combination method with parameter estimation from monthly precipitation data can be applied, in practical purpose such as assessment of climate change in agriculture and water resources, to get daily precipitation data in Korea.

• Korean Journal of Cognitive Science
• /
• v.6 no.3
• /
• pp.25-40
• /
• 1995

This paper proposes a generating method of fuzzy rules by genetic and descent method (GAGDM),and its applied to classification problems.The number of inference rules and the shapes of membership function in the antecedent part are detemined by applying the genetic algorithm,and the real numbers of the consequent parts are derived by using the descent method.The aim of the proposed method is to generation a minmun set of fuzzy rules that can correctly classify all training patterns,and fiteness function of GA defined by the aim of th proposed method.Finally,in order to demonstrate the effectiveness of the present method,simulation results are shown.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2006.11a
• /
• pp.313-316
• /
• 2006

디지털 핑거프린팅(Digital Fingerprinting)은 기 밀 정보를 디지털 콘텐츠에 삽입하는 측면에서는 디지털 워터마킹과 동일 하다고 볼 수 있으나 저작권자나 판매자의 정보가 아닌 콘텐츠를 구매한 사용자의 정보를 삽입함으로써 콘텐츠 불법 배포자를 추적할 수 있도록 한다는 점에서 워터마킹과 차별화된 기술이다. 이러한 핑거프린팅 기술은 소유권에 대한 인증뿐만 아니라 개인 식별 기능까지 제공해야 하므로 기존의 워터마킹이 갖추어야 할 요구사항인 비가시성, 견고성, 유일성과 더불어 공모허용, 비대칭성, 익명성, 조건부 추적성 등이 부가적으로 필요하다. 본 논문에서는 행렬의 한 열을 선택 후 쉬프팅 기법을 사용 하서 사용자 정보로 조합하여 핑거프린트를 생성하였다. 이렇게 생성된 핑거프린트 정보를 2레벨 웨이블릿 변환 영역 중 LH2, HL2, HH2 부대역에 삽입하였다. 쉬프팅 정보와 도메인 개념을 사용하여 보다 많은 사용자에게 핑거프린트 정보를 삽입할 수 있으며, 공모공격과 JPEG 압축에서도 최소한 1명 이상의 공모자를 검출할 수 있는 핑거프린팅의 기본 조건을 만족하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.577-579
• /
• 2004

인터넷을 통한 정보 제공이 늘어남에 따라서 사용자가 원하는 정보를 손쉽게 얻기 위한 .연구가 활발히 진행되고 있으며. 이러한 연구 중 하나가 대화형 에이전트이다. 최근 대화형 에이전트에서 사용자 질의의 주제 추론을 위하여 베이지안 네트워크가 적용되었다 하지만 베이지안 네트워크의 설계는 많은 시간이 소요되며, 스크립트(대화를 위한 데이터베이스)의 추가 변경시에는 베이지안 네트워크도 같이 수정해야 하는 번거로움이 있어 대화형 에이전트의 확장성을 저해하고 있다. 본 논문에서는 스크립트로부터 베이지안 네트워크를 자동으로 생성하여 베이지안 네트워크를 이용한 대화형 에이전트의 확장성을 높이는 방법을 제안하다. 제안하는 방법은 베이지안 네트워크의 구성 노드를 계층적으로 설계하고. Noisy-OR gate를 사용하여 베이지안 네트워크의 조건부 확률 테이블을 계산한다. 피험자 10명이 대화형 에이전트를 위한 베이지안 네트워크를 수동 설계한 것과 비교하여 제안하는 방법의 유용성을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.764-767
• /
• 2021

While Generative Adversarial Networks (GANs) have seen huge success in image synthesis tasks, synthesizing high-quality images from text descriptions is a challenging problem in computer vision. This paper proposes a method named Text-to-Face Generation Using Multi-Scale Gradients for Conditional Generative Adversarial Networks (T2F-MSGGANs) that combines GANs and a natural language processing model to create human faces has features found in the input text. The proposed method addresses two problems of GANs: model collapse and training instability by investigating how gradients at multiple scales can be used to generate high-resolution images. We show that T2F-MSGGANs converge stably and generate good-quality images.

• Economic and Environmental Geology
• /
• v.54 no.1
• /
• pp.77-89
• /
• 2021

In this study, a method has been proposed to improve the performance of hydraulic property estimation model developed by Jeong et al. (2020). In their study, low-dimensional features of the annual groundwater level (GWL) fluctuation patterns extracted based on a Denoising autoencoder (DAE) was used to develop a regression model for predicting hydraulic properties of an aquifer. However, low-dimensional features of the DAE are highly dependent on the precipitation pattern even if the GWL is monitored at the same location, causing uncertainty in hydraulic property estimation of the regression model. To solve the above problem, a process for generating the GWL fluctuation pattern for conditioning the precipitation is proposed based on a conditional variational autoencoder (CVAE). The CVAE trains a statistical relationship between GWL fluctuation and precipitation pattern. The actual GWL and precipitation data monitored on a total of 71 monitoring stations over 10 years in South Korea was applied to validate the effect of using CVAE. As a result, the trained CVAE model reasonably generated GWL fluctuation pattern with the conditioning of various precipitation patterns for all the monitoring locations. Based on the trained CVAE model, the low-dimensional features of the GWL fluctuation pattern without interference of different precipitation patterns were extracted for all monitoring stations, and they were compared to the features extracted based on the DAE. Consequently, it can be confirmed that the statistical consistency of the features extracted using CVAE is improved compared to DAE. Thus, we conclude that the proposed method may be useful in extracting a more accurate feature of GWL fluctuation pattern affected solely by hydraulic characteristics of the aquifer, which would be followed by the improved performance of the previously developed regression model.