• Korean Journal of Remote Sensing
• /
• v.20 no.1
• /
• pp.39-46
• /
• 2004

The generalized Rayleigh-Gans (GRG) approximation is usually used to compute the scattering amplitudes of leaves smaller or comparable to a wavelength, while the physical optics (PO) approach with the resistive sheet approximation is commonly used for leaves larger or comparable to the wavelength. In this paper, the scattering amplitudes of an elliptical leaf are computed using those theoretical scattering models (GRG and PO) at different frequencies. The accuracies of the analytical models for microwave scattering from deciduous leaves are investigated by comparison with the precise estimation by the method of moment (MoM). It was found that both the PO approach and the GRG approximation can be used alternatively for computing the scattering matrices of natural deciduous leaves at P-, L-, C- and X-band frequencies.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.105-108
• /
• 2021

Generative adversarial networks (GANs) have reached a great result at creating the synthesis image, especially in the face generation task. Unlike other deep learning tasks, the input of GANs is usually the random vector sampled by a probability distribution, which leads to unstable training and unpredictable output. One way to solve those problems is to employ the label condition in both the generator and discriminator. CelebA and FFHQ are the two most famous datasets for face image generation. While CelebA contains attribute annotations for more than 200,000 images, FFHQ does not have attribute annotations. Thus, in this work, we introduce a method to learn the attributes from CelebA then predict both soft and hard labels for FFHQ. The evaluated result from our model achieves 0.7611 points of the metric is the area under the receiver operating characteristic curve.

• Journal of Internet of Things and Convergence
• /
• v.4 no.2
• /
• pp.1-6
• /
• 2018

Techniques for generating new sample data from higher dimensional data such as images have been utilized variously for speech synthesis, image conversion and image restoration. This paper adopts Progressive Growing of Generative Adversarial Networks(PG-GANs) as an implementation model to generate high-resolution images and to enhance variation of the generated images, and applied it to fashion image data. PG-GANs allows the generator and discriminator to progressively learn at the same time, continuously adding new layers from low-resolution images to result high-resolution images. We also proposed a Mini-batch Discrimination method to increase the diversity of generated data, and proposed a Sliced Wasserstein Distance(SWD) evaluation method instead of the existing MS-SSIM to evaluate the GAN model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.416-416
• /
• 2020

우리나라의 계절 특성상 여름철 집중호우가 쏟아지는 현상이 빈번하게 발생하는데 이러한 돌발홍수가 예고 없이 일어나 상습적으로 침수 피해를 입는 지역이 증가하고 있다. 본 연구에서 2009년 ~ 2019년 동안 서울시 침수 피해 사건 중심의 인터넷 기사를 기반으로 실제 침수 사례를 조사해본 결과, 침수가 가장 많이 발생한 순으로 반포동(26건), 대치동(25건), 잠실동(21건)으로 집계되었다. 침수피해가 가장 많은 반포동을 연구지역으로 선정하고 그 중 잠수교의 수위를 예측하는 연구를 진행하였다. 기존 연구에서는 수치모형에 비해 신속한 결과를 도출할 수 있는 자료 기반 모형 중 LSTM 기법을 많이 사용하였다. 그러나 이는 선행 시간이 길어질수록 첨두수위에서 과소추정된 것으로 분석된 취약점이 존재하였다(정성호 외, 2018). 본 연구에서는 이러한 단점을 보완하기 위해 GANs(Generative Adversarial Networks)를 이용하였다. GANs는 생성자와 감별자가 나뉘어 생성자가 실제 자료인 첨두수위에서의 잠수교의 수위를 학습하고 실제와 근접한 가상데이터를 결과로 생성하여 감별자는 그 생성된 미래의 잠수교의 수위가 실제인지 가상인지 판별하도록 학습시키는 신경망 구조이다. 사용한 수문자료는 한강홍수통제소, 기상청, 국립해양조사원에서 제공하는 최근 15년간의 (2005년~2019년) 수위, 방류량, 강수량, 조위 자료를 수집하였고 t-test와 상관성분석을 통해 사용한 인자 간의 유의미성 판단과 상관성을 분석했다. 또한, 민감도 분석 결과 시퀀스길이(5), 반복횟수(1000), 은닉층(10), 학습률(0.005)로 최적값을 선정하였다. 또한 학습구간(2005년~2014년)과 검증구간(2015~2019년)으로 나누어 상대적으로 높은 수위가 관측되는 홍수기의 3, 6, 9시간 후의 수위를 예측하고 오차 지표를 이용해 평가하였다. LSTM 기법으로 예측된 수위와 GANs로 예측된 수위를 비교한 결과 GANs으로 예측된 첨두수위에서의 정확도가 5% 정도로 향상되었다. 향후에는 다양한 영향인자와 다른 기법과의 결합을 고려한다면 보다 정확하게 수위를 예측하여 하천 주변 사회기반시설의 침수 피해를 감소시킬 것으로 판단된다.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.1
• /
• pp.49-59
• /
• 2019

Generative adversarial networks(GANs) have received great attention in the machine learning field for their capacity to model high-dimensional and complex data distribution implicitly and generate new data samples from the model distribution. This paper investigates the model training methodology, architecture, and various applications of generative adversarial networks. Experimental evaluation is also conducted for generating synthetic image dataset for defense using two types of GANs. The first one is for military image generation utilizing the deep convolutional generative adversarial networks(DCGAN). The other is for visible-to-infrared image translation utilizing the cycle-consistent generative adversarial networks(CycleGAN). Each model can yield a great diversity of high-fidelity synthetic images compared to training ones. This result opens up the possibility of using inexpensive synthetic images for training neural networks while avoiding the enormous expense of collecting large amounts of hand-annotated real dataset.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.157-159
• /
• 2019

Hologram technology has been actively developed in terms of generation, transmission, and reproduction of 3D objects, but it is currently in a state of rest because of various limitations. Beyond VR and AR, the pseudo-hologram market is growing at an intermediate stage to meet the needs of new technologies. The key to the technology of hologram is to generate vast 3 dimensional data in the form of a point cloud, transmit the vast amount of data through the communication network in real time, and reproduce it like the original at the destination. In this paper, we propose a method to transmit massive 3 - D data in real - time and transmit the minutiae points of 3 - dimensional object information to reproduce the object as similar to original.

• Smart Media Journal
• /
• v.8 no.2
• /
• pp.46-57
• /
• 2019

In recent research, deep learning-based methods have achieved state-of-the-art performance in various computer vision tasks. However, these methods are commonly supervised, and require huge amounts of annotated data to train. Acquisition of data demands an additional costly effort, particularly for the tasks where it becomes challenging to obtain large amounts of data considering the time constraints and the requirement of professional human diligence. In this paper, we present a data level synthetic sampling solution to learn from small and imbalanced data sets using Generative Adversarial Networks (GANs). The reason for using GANs are the challenges posed in various fields to manage with the small datasets and fluctuating amounts of samples per class. As a result, we present an approach that can improve learning with respect to data distributions, reducing the partiality introduced by class imbalance and hence shifting the classification decision boundary towards more accurate results. Our novel method is demonstrated on a small dataset of 2789 tomato plant disease images, highly corrupted with class imbalance in 9 disease categories. Moreover, we evaluate our results in terms of different metrics and compare the quality of these results for distinct classes.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.437-450
• /
• 2022

Generative adversarial networks(GANs) have demonstrated remarkable success in image synthesis. However, since GANs show instability in the training stage on large datasets, it is difficult to apply to various application fields. A single image GAN is a field that generates various images by learning the internal distribution of a single image. In this paper, we investigate five Single Image GAN: SinGAN, ConSinGAN, InGAN, DeepSIM, and One-Shot GAN. We compare the performance of each model and analyze the pros and cons of a single image GAN.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.316-318
• /
• 2003

An eigen-analysis of the coherency matrix provides the polarimetric scattering mechanisms with the matrix characterizing parameters. In this paper, the coherency matrices of deciduous and coniferous vegetation are calculated using the analytical method. The Generalized Rayleigh-Gans approximation is used to model backscattering from distributed coniferous and deciduous leaves. The characteristics of eigen-parameters of simulated coherency matrix for deciduous and coniferous leaves with respect to the leaf shapes and orientations are illustrated.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.404-408
• /
• 2019

비지도 학습 모델인 GAN은 학습 데이터 구축이 어려운 여러 분야에 활용되고 있으며, 알려진 문제점들을 보완하기 위해 다양한 모델 결합 및 변형으로 발전하고 있다. 하지만 문장을 생성하는 GAN은 풀어야 할 문제가 많다. 그중에서도 문제가 되는 것은 완성도가 높은 문장을 생성하는데 어려움이 있다는 것이다. 본 논문에서는 단어 그래프를 구성하여 GAN의 학습에 도움을 주며 완성도가 높은 문장을 생성하는 방법을 제안한다.