• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.177-185
• /
• 2022

A method of restoring the occluded area was proposed by referring to images taken with the same types of sensors on high-resolution optical satellite images through deep learning. For the natural continuity of the simulated image with the occlusion region and the surrounding image while maintaining the pixel distribution of the original image as much as possible in the patch segmentation image, CycleGAN (Cycle Generative Adversarial Network) method with ConvNeXt block applied was used to analyze three experimental regions. In addition, We compared the experimental results of a training patch size of 512*512 pixels and a 1024*1024 pixel size that was doubled. As a result of experimenting with three regions with different characteristics,the ConvNeXt CycleGAN methodology showed an improved R² value compared to the existing CycleGAN-applied image and histogram matching image. For the experiment by patch size used for training, an R² value of about 0.98 was generated for a patch of 1024*1024 pixels. Furthermore, As a result of comparing the pixel distribution for each image band, the simulation result trained with a large patch size showed a more similar histogram distribution to the original image. Therefore, by using ConvNeXt CycleGAN, which is more advanced than the image applied with the existing CycleGAN method and the histogram-matching image, it is possible to derive simulation results similar to the original image and perform a successful simulation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5427-5445
• /
• 2019

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.33-43
• /
• 2022

This study presents a method to restore an optical satellite image with distortion and occlusion due to fog, haze, and clouds to one that minimizes degradation factors by referring to the same type of peripheral image. Specifically, the time and cost of re-photographing were reduced by partially occluding a region. To maintain the original image's pixel value as much as possible and to maintain restored and unrestored area continuity, a simulation restoration technique modified with the Cycle Generative Adversarial Network (CycleGAN) method was developed. The accuracy of the simulated image was analyzed by comparing CycleGAN and histogram matching, as well as the pixel value distribution, with the original image. The results show that for Site 1 (out of three sites), the root mean square error and R² of CycleGAN were 169.36 and 0.9917, respectively, showing lower errors than those for histogram matching (170.43 and 0.9896, respectively). Further, comparison of the mean and standard deviation values of images simulated by CycleGAN and histogram matching with the ground truth pixel values confirmed the CycleGAN methodology as being closer to the ground truth value. Even for the histogram distribution of the simulated images, CycleGAN was closer to the ground truth than histogram matching.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.867-871
• /
• 2022

Amid the recent rapid trend change, the change in design has a great impact on the sales of fashion companies, so it is inevitable to be careful in choosing new designs. With the recent development of the artificial intelligence field, various machine learning is being used a lot in the fashion market to increase consumers' preferences. To contribute to increasing reliability in the development of new products by quantifying abstract concepts such as preferences, we generate new images that do not exist through three adversarial generative neural networks (GANs) and numerically compare abstract concepts of preferences using pre-trained convolution neural networks (CNNs). Deep convolutional generative adversarial networks (DCGAN), Progressive growing adversarial networks (PGGAN), and Dual Discriminator generative adversarial networks (DANs), which were trained to produce comparative, high-level, and high-level images. The degree of similarity measured was considered as a preference, and the experimental results showed that D2GAN showed a relatively high similarity compared to DCGAN and PGGAN.

• Journal of Oriental Neuropsychiatry
• /
• v.23 no.1
• /
• pp.59-82
• /
• 2012

Objectives : We purposed to objectify the pattern diagnosis of Tic disorders through factor and reliability analysis regarding a pattern identification questionnaire concerning Tic disorders in children. Methods : We chose and studied 144 children who were pattern-diagnosed out of 200 tic disordered children who visited H hospital in Seoul from January 2006 to April 2011. Results : 1. TTD (50%) was the most common type and the occurrence rate in male children was higher(4.76:1). Also, the rate of hospital visits was highest at the age 8(23.6%). 2. In results concering pattern diagnosis, Gan-poong-nae-dong was most frequently diagnosed in 53 patients (36.8%), and Dam-hwa-yo-sin (42 patients), Gan-sin-um-her (30 patients), and Bee-her-gan-wang (6 patients). 3. In an attempt to verify the reliability of the questionnaire, the coefficient regarding the whole questions (Cronbach ${\alpha}$) came to 0.909. Moreover, the reliability coefficient foreach sub factor was 0.687 in Ganpoong-nae-dong, 0.817 in Dam-hwa-yo-sin, 0.851 in Bee-her-gan-wang, and 0.726 in Gan-sin-um-her, respectively. Thus, their consistency was ensured. 4. In exploratory factor analysis concerning the most common five questions in the questionnaire, the questions of Dam-hwa-yo-sin and Gan-poong-nae-dong appeared to be part of different factors. While, Gan-sin-um-her and Bee-her-gan-wang questions showed that they belong to the same factors. 5. In factor analysis excluding both Gan-sin-um-her and Bee-her-gan-wang questions, both showed significant results; however, the one excluding Gan-sin-um-her showed improved results. Conclusions : From the above results concerning the Pattern Identification Questionnaire for Tic Disordered children, three separated patterns of Bee-her-gan-wang, Dam-hwa-yo-sin, Gan-poong-nae-dong are thought to be available for clinical use. However, further validity studies are needed.

• The Journal of Internal Korean Medicine
• /
• v.20 no.1
• /
• pp.263-273
• /
• 1999

Cheung-Gan-Haeju tang has been used on 3 cases of alcoholic liver disease patients complicated with ascites, clinical symptom(fatigue. jaundice, urine dark, indigestion, anorexia. ascites etc), liver function (AST, ALT, ${\gamma}$-GT, ALP, total bilirubin), and index of nutritional state (total protein, albumin, cholesterol) were improved after the adminstration. Although the exact mechanism involved in the effects of Cheung-Gan-haeju tang on these disease is still unknown, it is possibly suspected that Cheung-Gan-Haeju tang is non-toxic to liver and has beneficial effects on treating alcoholic liver disease complicated ascites. Further reports with many case, however, will be needed.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.63-69
• /
• 2020

Image-image translation is a technology that creates a target image through input images, and has recently shown high performance in creating a more realistic image by utilizing GAN, which is a non-map learning structure. Therefore, there are various studies on image-to-image translation using GAN. At this point, most image-to-image translations basically target one attribute translation. But the data used and obtainable in real life consist of a variety of features that are hard to explain with one feature. Therefore, if you aim to change multiple attributes that can divide the image creation process by attributes to take advantage of the various attributes, you will be able to play a better role in image-to-image translation. In this paper, we propose Multi CycleGAN, a dual attribute transformation structure, by utilizing CycleGAN, which showed high performance among image-image translation structures using GAN. This structure implements a dual transformation structure in which three domains conduct two-way learning to learn about the two properties of an input domain. Experiments have shown that images through the new structure maintain the properties of the input area and show high performance with the target properties applied. Using this structure, it is possible to create more diverse images in the future, so we can expect to utilize image generation in more diverse areas.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.44-46
• /
• 2022

Various object recognition using artificial intelligence basically shows planar results. It is based on classifying objects or identifying what objects are on the image. However, the original object has a three-dimensional shape, not a plane, and although the perception to obtain only simple results from the image does not matter, there is a lot of information that is insufficient when used in various fields. In this paper, checks the method of generating data in various fields of objects and whether it is meaningful by utilizing the characteristics of Layer that generates intermediate results with respect to image generation based on the GAN algorithm. It solves some of the problems in the hardware and collection process for generating existing multi-faceted data, and confirms that it can be utilized after data generation on several limited objects.

• 대한상한금궤의학회지
• /
• v.4 no.1
• /
• pp.1-12
• /
• 2012

Objective : The purpose of this study is to find out the effectiveness of Ling-Gui-Gan-Zao-Tang for patients of panic disorder. Method : To achieve the purpose of this study, Ling-Gui-Gan-Zao-Tang was prescribed for three months to two different patients of panic disorder. They were diagnosed as panic disorder in department of neuropsychiatry, and had no other prescribed decoction or psychotherapy. Results : 1. The BAI score for anxiety were decreased in both patients, and they got improved overall symptoms. 2. In panic attack, patients are in dominant state of sympathetic nerve, so they have palpitaion and get nervous. Fu-Ling(茯笭) can treate this kind of situation. 3. Based on and , urgent situation, over-tension of muscles, hot flash can be treated Gancao(甘草), Dazao(大棗), Guizhi(桂枝) respectively. Conclusions : When panic disorder attaks, the sympathetic nerves are dominant in patient's body. So they feel palpitating, sweating, suffocating. Ling-Gui-Gan-Zao-Tang can treat this series of symptoms.

• Journal of Internet of Things and Convergence
• /
• v.9 no.1
• /
• pp.131-138
• /
• 2023

This paper is related to performance improvement of Image-to-Image translation using Relativistic Average Patch GAN and Residual in Residual Dense Block. The purpose of this paper is to improve performance through technical improvements in three aspects to compensate for the shortcomings of the previous pix2pix, a type of Image-to-Image translation. First, unlike the previous pix2pix constructor, it enables deeper learning by using Residual in Residual Block in the part of encoding the input image. Second, since we use a loss function based on Relativistic Average Patch GAN to predict how real the original image is compared to the generated image, both of these images affect adversarial generative learning. Finally, the generator is pre-trained to prevent the discriminator from being learned prematurely. According to the proposed method, it was possible to generate images superior to the previous pix2pix by more than 13% on average at the aspect of FID.