• 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.

• The Journal of the Korea Contents Association
• /
• v.12 no.4
• /
• pp.476-484
• /
• 2012

Family member network of kings in Chosun dynasty shows scale free network properties as if most social networks do. One of distinct topological properties of the network is relatively high diameter that reflects dataset composed of the one generation continuously falling to next one. When k-core algorithm as a useful tool for obtaining a core network from the complex family member network was employed, it is possible to obtain hidden and valuable information from a complex network. Unfortunately, it is found that k-core algorithm is not useful tool for applying narrow and deep structural network. The family member network is composed of kings, queens, princes, and princesses. It is possible to separate sub-family members and to construct sub-family member networks such as queen-centered, prince-centered, and princess-centered networks. Sub-family member networks provide an useful and hidden information. These results provide new insight that is analyzed by network-based approaches for the family member of the kings in the Chosun dynasty.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 1999.05a
• /
• pp.97-105
• /
• 1999

An important task for any software project manager is to be able to predict and control project size. Unfortunately, there is comparatively little work that deals with the problem of building estimation methods for software size in fourth-generation languages systems. In this paper, we propose a new estimation method for estimating for software size based on minimum relative error(MRE) criterion. The characteristic of the proposed method is insensitive to the extreme values of the observed measures which can be obtained early in the development life cycle. In order to verify the performance of the proposed estimation method for software size in terms of both quality of fit and predictive quality, the experiments has been conducted for the dataset I and II, respectively. For the data set I and II, our proposed estimation method was shown to be superior to the traditional method LS and RLS in terms of both the quality of fit and predictive quality when applied to data obtained from actual software development projects.

• Publications of The Korean Astronomical Society
• /
• v.20 no.1 s.24
• /
• pp.55-62
• /
• 2005

The First Generation Digitized Sky Survey (DSS-I) is a collection of digitized photographic atlases of the night sky taken from the Palomar Observatory (northen sky) and the Anglo-Australian Observatory (southern sky). DSS-I is widely used by the astronomical community for a number of applications including object cross-identification and astrometry. However, accessing and retrieving the actual images are nontrivial owing to the huge size (> 60 GB) of the dataset. To facilitate retrieval process of DSS-I data for the public, Korean Astronomical Data Center (KADC) developed a web application that provides not only data retrieval but also visualization functions. The web application consists of several modules developed using Java Applet, Jave Servlet, and JaveServer Pages (JSP) technologies. It allows users to retrieve images efficiently in various formats such as FITS, JPEG, GIF, and TIFF, and also offers an interactive visulization tool, ImgViewer, for displaying/analyzing FITS images. To use the web application, users require a Java-enabled web browser.

• Journal of Welding and Joining
• /
• v.31 no.5
• /
• pp.35-40
• /
• 2013

In this paper, we propose the Tangible Virtual Reality Representation Method to using haptic device and feature to morphology of created bead from Flux Cored Arc Welding. The virtual reality was started to rising for reduce to consumable materials and welding training risk. And, we will expected maximize virtual reality from virtual welding training. In this paper proposed method is get the database to changing the input factor such as work angle, travelling angle, speed, CTWD. And, it is visualization to bead from extract to optimal morphological feature information to using the Neural Network algorithm. The database was building without error to extract data from automatic robot welder. Also, the Neural Network algorithm was set a dataset of the highest accuracy from verification process in many times. The bead was created in virtual reality from extract to morphological feature information. We were implementation to final shape of bead and overlapped in process by time to using bead generation algorithm and calibration algorithm for generate to same bead shape to real database in process of generating bead. The best advantage of virtual welding training, it can be get the many data to training evaluation. In this paper, we were representation bead to similar shape from generated bead to Flux Cored Arc Welding. Therefore, we were reduce the gap to virtual welding training and real welding training. In addition, we were confirmed be able to maximize the performance of education from more effective evaluation system.

• Journal of Digital Convergence
• /
• v.15 no.12
• /
• pp.293-301
• /
• 2017

Most new products not only suddenly disappear in the market but also quickly cannibalize older products. Under such a circumstance, retailers may have too much stock, and customers may be faced with difficulties discovering products suitable to their preferences among short life cycle products. To address these problems, recommender systems are good solutions. However, most previous recommender systems had difficulty in reflecting changes in customer preferences because the systems employ static customer preferences. In this paper, we propose a recommendation methodology that considers dynamic customer preferences. The proposed methodology consists of dynamic customer profile creation, neighborhood formation, and recommendation list generation. For the experiments, we employ a mobile image transaction dataset that has a short product life cycle. Our experimental results demonstrate that the proposed methodology has a higher quality of recommendation than a typical collaborative filtering-based system. From these results, we conclude that the proposed methodology is effective under conditions where most new products have short life cycles. The proposed methodology need to be verified in the physical environment at a future time.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.2
• /
• pp.11-19
• /
• 2020

When a character's pose changes, its center of mass(COM) also changes. The change of COM has distinctive patterns corresponding to various motion types like walking, running or sitting. Thus the motion type can be predicted by using COM movement. We propose a motion generator that uses character's center of mass information. This generator can generate various motions without annotated action type labels. Thus dataset for training and running can be generated full-automatically. Our neural network model takes the motion history of the character and its center of mass information as inputs and generates a full-body pose for the current frame, and is trained using simple Convolutional Neural Network(CNN) that performs 1D convolution to deal with time-series motion data.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.9-18
• /
• 2021

Although Generative Adversarial Networks (GANs) have gained great popularity in computer vision and related fields, generating audio signals independently has yet to be presented. Unlike images, an audio signal is a sampled signal consisting of discrete samples, so it is not easy to learn the signals using CNN architectures, which is widely used in image generation tasks. In order to overcome this difficulty, GAN researchers proposed a strategy of applying time-frequency representations of audio to existing image-generating GANs. Following this strategy, we propose an improved method for increasing the fidelity of synthesized audio signals generated by using GANs. Our method is demonstrated on a public speech dataset, and evaluated by Fréchet Inception Distance (FID). When employing our method, the FID showed 10.504, but 11.973 as for the existing state of the art method (lower FID indicates better fidelity).

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1403-1410
• /
• 2020

Recently, as interest in non-face-to-face experiences and services increases, the demand for web video contents that can be easily consumed using mobile devices such as smartphones or tablets is rapidly increasing. To cope with these requirements, in this paper we propose a technique to efficiently produce video contents that can provide experience of visiting famous places (i.e., stage tour) in animation or movies. To this end, an image dataset was established by collecting images of stage areas using Google Maps and Google Street View APIs. Afterwards, a deep learning-based style transfer method to apply the unique style of animation videos to the collected street view images and generate the video contents from the style-transferred images was presented. Finally, we showed that the proposed method could produce more interesting stage-tour video contents through various experiments.

• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.176-185
• /
• 2022

Data augmentation is general approach to solve overfitting of machine learning models by applying various data transformations and distortions to dataset. However, when data augmentation is applied in GAN-based model, which is deep learning image generation model, data transformation and distortion are reflected in the generated image, then the generated image quality decrease. To prevent this problem called augmentation leak, we propose a scheme that can prevent augmentation leak regardless of the type and number of augmentations. Specifically, we analyze the conditions of augmentation leak occurrence by type and implement auxiliary augmentation task classifier that can prevent augmentation leak. Through experiments, we show that the proposed technique prevents augmentation leak in the GAN model, and as a result improves the quality of the generated image. We also demonstrate the superiority of the proposed scheme through ablation study and comparison with other representative augmentation leak prevention technique.