• 대한원격탐사학회지
• /
• 제38권1호
• /
• pp.111-126
• /
• 2022

Land use and land cover (LULC) mapping is an important factor in geospatial analysis. Although highly precise ground-based LULC monitoring is possible, it is time consuming and costly. Conversely, because the synthetic aperture radar (SAR) sensor is an all-weather sensor with high resolution, it could replace field-based LULC monitoring systems with low cost and less time requirement. Thus, LULC is one of the major areas in SAR applications. We developed a LULC model using only KOMPSAT-5 single co-polarized data and digital elevation model (DEM) data. Twelve HH-polarized images and 18 VV-polarized images were collected, and two HH-polarized images and four VV-polarized images were selected for the model testing. To train the LULC model, we applied the conditional generative adversarial network (cGAN) method. We used U-Net combined with the residual unit (ResUNet) model to generate the cGAN method. When analyzing the training history at 1732 epochs, the ResUNet model showed a maximum overall accuracy (OA) of 93.89 and a Kappa coefficient of 0.91. The model exhibited high performance in the test datasets with an OA greater than 90. The model accurately distinguished water body areas and showed lower accuracy in wetlands than in the other LULC types. The effect of the DEM on the accuracy of LULC was analyzed. When assessing the accuracy with respect to the incidence angle, owing to the radar shadow caused by the side-looking system of the SAR sensor, the OA tended to decrease as the incidence angle increased. This study is the first to use only KOMPSAT-5 single co-polarized data and deep learning methods to demonstrate the possibility of high-performance LULC monitoring. This study contributes to Earth surface monitoring and the development of deep learning approaches using the KOMPSAT-5 data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권4호
• /
• pp.1486-1501
• /
• 2021

The removal of accessories from the face is one of the essential pre-processing stages in the field of face recognition. However, despite its importance, a robust solution has not yet been provided. This paper proposes a network and dataset construction methodology to remove only the glasses from facial images effectively. To obtain an image with the glasses removed from an image with glasses by the supervised learning method, a network that converts them and a set of paired data for training is required. To this end, we created a large number of synthetic images of glasses being worn using facial attribute transformation networks. We adopted the conditional GAN (cGAN) frameworks for training. The trained network converts the in-the-wild face image with glasses into an image without glasses and operates stably even in situations wherein the faces are of diverse races and ages and having different styles of glasses.

• 한국재료학회:학술대회논문집
• /
• 한국재료학회 1998년도 IUMRS-ICEM ABSTRACT BOOK
• /
• pp.93.4-93
• /
• 1998

• 한국재료학회:학술대회논문집
• /
• 한국재료학회 1998년도 IUMRS-ICEM ABSTRACT BOOK
• /
• pp.94.4-94
• /
• 1998

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.369-372
• /
• 2018

본 논문은 매핑 되지 않은 입력 음성과 목표음성 사이에 음성 변환하는 비 병렬 음성 변환 네트워크를 제안한다. 기존 음성 변환 연구에서는 변환 전후 스펙트로그램의 거리 오차를 최소화하는 방법을 주로 학습 한다. 이러한 방법은 MSE의 이미지를 평균 내는 특징으로 인하여 생성된 스펙트로그램의 해상도가 저하되는 문제점이 있었다. 또한, 병렬 데이터를 사용해 연구를 진행했기 때문에 데이터를 수집하는 것에도 어려움이 많았다. 본 논문에서는 입력 음성의 발음 PPGs를 사용하여 비 병렬 데이터 간 학습을 진행 하며, GAN 학습을 통해 더욱 선명한 음성을 생성하는 방법을 사용하였다. 제안한 방법의 유효성을 검증하기 위해서 기존 음성 변환 시스템에서 많이 사용하는 GMM 기반 모델과 MOS 테스트를 진행하였으며 기존 모델에 비하여 성능이 향상되는 결과를 얻었다.

• 한국재료학회:학술대회논문집
• /
• 한국재료학회 1998년도 IUMRS-ICEM ABSTRACT BOOK
• /
• pp.111.3-111
• /
• 1998

• Bulletin of the Korean Chemical Society
• /
• 제33권1호
• /
• pp.171-176
• /
• 2012

A novel chemiluminescence (CL) system was established for the determination of cytosine arabinoside (Ara-C) in pharmaceutical preparations. It was showed that a clear CL signal was observed when Eosin Y mixed with Fenton reagent. The CL intensity was decreased significantly when Ara-C was added to the reaction system and partially scavenged the hydroxyl radicals in the solution. The extent of decrease in the CL intensity had a good stoichiometrical relationship with the Ara-C concentration. Based on this, we developed a new method for the determination of Ara-C using a flow injection analysis (FIA) technique with CL detection. Under the optimal conditions, the linear range of Ara-C concentration was $6.0{\times}10^{-9}\sim1.0{\times}10^{-7}mol/L$ (R = 0.9982) with a detection limit of $7.6{\times}10^{-10}mol/L$ (S/N=3), the RSD was 5.6% for $6.0{\times}10^{-8}mol/L$ Ara-C (n = 11). The method was successfully applied to the determination of Ara-C in injection samples. The possible chemiluminescence reaction mechanism was discussed.

• 천문학회지
• /
• 제29권spc1호
• /
• pp.295-298
• /
• 1996

Non-LTE calculations, with the non-thermal ionization effects included, indicated that for electron bombardment, the H$\alpha$ line is widely broadened and shows a strong central reversal. Significant enhancements at the line wings of Ly$\alpha$ and Ly$\beta$ are also predicted at the beginning of the impulsive phase of flares. For the proton bombardment, no strong broadening and no large central reversal are expected. However, due to proton-hydrogen charge exchange, the enhancements at the red wings of Ly$\alpha$ and Ly$\beta$ lines at the early impulsive phase of flares are significant. Our results show that the electron beam can also in some cases generate visible and UV continuum emission in white-light flares. However, at the onset phase, a negative flare may appear within several seconds, due to the increase of the H- opacity. Another spectroscopic signature of energetic particles, i.e. the impact polarization of atomic lines, is also mentioned.

• 한국통신학회논문지
• /
• 제36권6C호
• /
• pp.384-390
• /
• 2011

The paper derives formulas for the mean-squared error distortion and resulting signal-to-noise (SNR) ratio of a fixed-rate scalar quantizer designed optimally in the minimum mean-squared error sense for a Gaussian density with the standard deviation ${\sigma}_q$ when it is mismatched to a Laplacian density with the standard deviation ${\sigma}_q$. The SNR formulas, based on the key parameter and Bennett's integral, are found accurate for a wide range of $p\({\equiv}\frac{\sigma_p}{\sigma_q}\){\geqq}0.25$. Also an upper bound to the SNR is derived, which becomes tighter with increasing rate R and indicates that the SNR behaves asymptotically as $\frac{20\sqrt{3{\ln}2}}{{\rho}{\ln}10}\;{\sqrt{R}}$ dB.

• Mycobiology
• /
• 제39권3호
• /
• pp.143-150
• /
• 2011

The basidiomycete fungus Cryptococcus neoformans is an important pathogen of immunocompromised people. The ability of the fungus to sense its environment is critical for proliferation and the generation of infectious propagules, as well as for adaptation to the mammalian host during infection. The conserved cAMP/protein kinase A pathway makes an important contribution to sensing, as demonstrated by the phenotypes of mutants with pathway defects. These phenotypes include loss of the ability to mate and to elaborate the key virulence factors capsule and melanin. This review summarizes recent work that reveals new targets of the pathway, new phenotypic consequences of signaling defects, and a more detailed understanding of connections with other aspects of cryptococcal biology including iron regulation, pH sensing, and stress.