• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.351-358
• /
• 2022

Recently, Generative Adversarial Networks (GAN) and Variational AutoEncoders (VAE) have been applied to voice conversion that can make use of non-parallel training data. Especially, Conditional Cycle-Consistent Generative Adversarial Networks (CC-GAN) and Cycle-Consistent Variational AutoEncoders (CycleVAE) show promising results in many-to-many voice conversion among multiple speakers. However, the number of speakers has been relatively small in the conventional voice conversion studies using the CC-GANs and the CycleVAEs. In this paper, we extend the number of speakers to 100, and analyze the performances of the many-to-many voice conversion methods experimentally. It has been found through the experiments that the CC-GAN shows 4.5 % less Mel-Cepstral Distortion (MCD) for a small number of speakers, whereas the CycleVAE shows 12.7 % less MCD in a limited training time for a large number of speakers.

• 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.

• Journal of Haehwa Medicine
• /
• v.16 no.1
• /
• pp.199-206
• /
• 2007

Objective : The purpose of this study is to report treated case about patient with diplopia caused by stroke. Methods : The improvement of diplopia was observed as he was treated with acupuncture therapy and herb medicine named Bo-gan-san(保肝散). Results : Diplopia improved and disappeared gradually with acupuncture therapy and herb medicine named Bo-gan-san(保肝散). The patient was discharged with favorable recovery. Conclusion : In traditional Korean medicine, diplopia is caused by disorder of JungKi(精氣), intrusion of PoongSa(風邪) into Neoi(腦), and hollowness of Gan(肝), Shin(腎). Treating it is by expelling PoongSa(風邪) or strengthening Gan(肝), Shin(腎). The patient was diagnosed as cerebral infarction according to Brain MRI. Diplopia was improved after acupunctural therapy and intaking Bo-gan-san(保肝散), herbal prescription selected from DongYiBoGam(東醫寶鑑).

• The Journal of Pediatrics of Korean Medicine
• /
• v.24 no.2
• /
• pp.22-30
• /
• 2010

Objectives The purpose of this study is to report two cases of epileptic children who were diagnosed as Sik-Gan(食癎) and were treated by oriental medical treatment. Methods We diagnosed the patients as Sik-Gan(食癎) and treated them with herbal medicine, acupuncture, moxa and oriental physical therapy. We observed the improvement of patient's disease by checking seizure frequency and clinical progression of gastrointestinal symptoms. Results Oriental medical treatment reduced patients' the number of seizures, and improved gastrointestinal symptoms. Conclusions This study showed that the oriental medicine can be a meaningful treatment for epileptic children who were diagnosed as Sik-Gan(食癎), but more relevant studies on epileptic children diagnosed as Sik-Gan(食癎) are needed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.77-79
• /
• 2022

A large amount of related images are required to detect images with variable shapes. Therefore, in this paper, fire images among images with variable shapes are multiplied through GAN algorithms, and detection rates when AI learning is performed using this image are compared to analyze whether the multiplied images are suitable for learning data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.145-147
• /
• 2022

본 논문에서는 훼손되어 식별할 수 없는 탑 이미지를 비롯해 낮은 해상도의 탑 이미지를 개선하기 위해 우리는 탑 이미지의 화질 개선을 인공지능을 이용하여 빠르게 개선을 해 보고자 한다. 최근에 Generative Adversarial Networks(GANS) 알고리즘에서 SrGAN 알고리즘이 나오면서 이미지 생성, 이미지 복원, 해상도 변화 분야가 지속해서 발전하고 있다. 이에 본 연구에서는 다양한 GAN 알고리즘을 화질 개선에 적용해 보았다. 탑 이미지에 GAN 알고리즘 중 SrGan을 적용하였으며 실험한 결과 Srgan 알고리즘은 학습이 진행되었으며, 낮은 해상도의 탑 이미지가 높은 해상도, 초고해상도 이미지가 생성되는 것을 확인했다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.567-569
• /
• 2023

GAN은 이미지 생성모델로서 이미지 공간에서 좋은 결과를 보여왔다. 우리는 이러한 GAN의 능력을 더욱 향상하기 위하여 본 연구에서 주파수 영역에서 이미지를 학습하고 생성하는 새로운 방법을 제안한다. 이를 위하여 먼저 학습데이터를 2D FFT로 주파수 영역으로 변환한 후 변환된 학습데이터를 GAN이 학습하게 한다. 학습 후에 GAN은 새로운 이미지를 생성하며 생성된 이미지를 2D IFFT하여 이미지 공간으로 변환한다. 이렇게 주파수 영역에서 이미지를 생성하는 방법은 이미지 공간에서 생성하는 방법보다 다양한 장점이 있다. 생성된 이미지의 품질을 평가하기 위하여 4개 데이터 셋에 4개의 평가지표를 사용하여 평가한 결과 주파수 영역에서 생성한 이미지가 IS, P&R, D&C 측면에서 더 좋은 것으로 평가되었다.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.241-248
• /
• 2023

GAN (Generative Adversarial Networks) creates highly sophisticated counterfeit products by learning real images or text and inferring commonalities. Therefore, it can be useful in fields that require the creation of large-scale images or graphics. In this paper, we implement GAN-based game character creation AI that can dramatically reduce illustration design work costs by providing expansion and automation of game character image creation. This is very efficient in game development as it allows mass production of various character images at low cost.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.904-905
• /
• 2023

본 논문에서는 의료 영상 생성을 위한 Med-StyleGAN2를 제안한다. 생성적 적대 신경망은 이미지 생성에는 효과적이지만, 의료 영상 생성에는 한계점을 가지고 있다. 따라서 본 연구에서는 의료 영상 생성에 특화된 StyleGAN 기반 학습 모델을 제안한다. 이는 다양한 의료 영상 어플리케이션에 활용할 수 있으며, 생성된 의료 영상에 대한 정량적, 정성적 평가를 수행함으로써 의료 영상 생성 분야의 발전 가능성에 대해 연구한다.

• Journal of Ocean Engineering and Technology
• /
• v.36 no.1
• /
• pp.32-40
• /
• 2022

Underwater optical images face various limitations that degrade the image quality compared with optical images taken in our atmosphere. Attenuation according to the wavelength of light and reflection by very small floating objects cause low contrast, blurry clarity, and color degradation in underwater images. We constructed an image data of the Korean sea and enhanced it by learning the characteristics of underwater images using the deep learning techniques of CycleGAN (cycle-consistent adversarial network), UGAN (underwater GAN), FUnIE-GAN (fast underwater image enhancement GAN). In addition, the underwater optical image was enhanced using the image processing technique of Image Fusion. For a quantitative performance comparison, UIQM (underwater image quality measure), which evaluates the performance of the enhancement in terms of colorfulness, sharpness, and contrast, and UCIQE (underwater color image quality evaluation), which evaluates the performance in terms of chroma, luminance, and saturation were calculated. For 100 underwater images taken in Korean seas, the average UIQMs of CycleGAN, UGAN, and FUnIE-GAN were 3.91, 3.42, and 2.66, respectively, and the average UCIQEs were measured to be 29.9, 26.77, and 22.88, respectively. The average UIQM and UCIQE of Image Fusion were 3.63 and 23.59, respectively. CycleGAN and UGAN qualitatively and quantitatively improved the image quality in various underwater environments, and FUnIE-GAN had performance differences depending on the underwater environment. Image Fusion showed good performance in terms of color correction and sharpness enhancement. It is expected that this method can be used for monitoring underwater works and the autonomous operation of unmanned vehicles by improving the visibility of underwater situations more accurately.