• Journal of information and communication convergence engineering
• /
• v.19 no.4
• /
• pp.228-233
• /
• 2021

In this study, we analyze the credit information (loan, delinquency information, etc.) of individual business owners to generate voluminous training data to establish a bankruptcy prediction model through a partial synthetic training technique. Furthermore, we evaluate the prediction performance of the newly generated data compared to the actual data. When using conditional tabular generative adversarial networks (CTGAN)-based training data generated by the experimental results (a logistic regression task), the recall is improved by 1.75 times compared to that obtained using the actual data. The probability that both the actual and generated data are sampled over an identical distribution is verified to be much higher than 80%. Providing artificial intelligence training data through data synthesis in the fields of credit rating and default risk prediction of individual businesses, which have not been relatively active in research, promotes further in-depth research efforts focused on utilizing such methods.

• Journal of IKEEE
• /
• v.25 no.1
• /
• pp.76-82
• /
• 2021

In this paper, the compressed sensing basic pursuit denoise algorithm adopted to synthetic aperture radar imaging is investigated to improve the object recognition. From the incomplete data sets for image processing, the compressed sensing algorithm had been integrated to recover the data before the conventional back- projection algorithm was involved to obtain the synthetic aperture radar images. This method can lead to the reduction of measurement events while scanning the objects. An ultra-wideband radar scheme using a stripmap synthetic aperture radar algorithm was utilized to detect objects hidden behind the box. The Ultra-Wideband radar system with 3.1~4.8 GHz broadband and UWB antenna were implemented to transmit and receive signal data of two conductive cylinders located inside the paper box. The results confirmed that the images can be reconstructed by using a 30% randomly selected dataset without noticeable distortion compared to the images generated by full data using the conventional back-projection algorithm.

• The Korean Journal of Applied Statistics
• /
• v.36 no.2
• /
• pp.141-166
• /
• 2023

This paper investigates synthetic data generation methods and their evaluation measures. There have been increasing demands for releasing various types of data to the public for different purposes. At the same time, there are also unavoidable concerns about leaking critical or sensitive information. Many synthetic data generation methods have been proposed over the years in order to address these concerns and implemented in some countries, including Korea. The current study aims to introduce and compare three representative synthetic data generation approaches: Sequential regression, nonparametric Bayesian multiple imputations, and deep generative models. Several evaluation metrics that measure the utility and disclosure risk of synthetic data are also reviewed. We provide empirical comparisons of the three synthetic data generation approaches with respect to various evaluation measures. The findings of this work will help practitioners to have a better understanding of the advantages and disadvantages of those synthetic data methods.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.1-16
• /
• 2023

Synthetic data generation is generally used in performance evaluation and function tests in data-intensive applications, as well as in various areas of data analytics, such as privacy-preserving data publishing (PPDP) and statistical disclosure limit/control. A significant amount of research has been conducted on tools and languages for data generation. However, existing tools and languages have been developed for specific purposes and are unsuitable for other domains. In this article, we propose a regular expression-based data generation language (DGL) for flexible big data generation. To achieve a general-purpose and powerful DGL, we enhanced the standard regular expressions to support the data domain, type/format inference, sequence and random generation, probability distributions, and resource reference. To efficiently implement the proposed language, we propose caching techniques for both the intermediate and database queries. We evaluated the proposed improvement experimentally.

• MALSORI
• /
• no.64
• /
• pp.1-14
• /
• 2007

The purpose of this study was to examine the acoustic perception different by formants change for profoundly hearing impaired children with cochlear implants. The subjects were 10 children after 15 months of experience with the implant and mean of their chronological age was 8.4 years and Standard deviation was 2.9 years. The ability of auditory perception was assessed using acoustic-synthetic vowels. The acoustic-synthetic vowel was combined with F1, F2, and F3 into a vowel and produced 42 synthetic sound, using Speech GUI(Graphic User Interface) program. The data was deal with clustering analysis and on-line analytical processing for perception ability of acoustic synthetic vowel. The results showed that auditory perception scores of acoustic-synthetic vowels for cochlear implanted children were increased in F2 synthetic vowels compaire to those of F1. And it was found that they perceived the differences of vowels in terms of distance rates between F1 and F2 in specific vowel.

• Smart Media Journal
• /
• v.8 no.4
• /
• pp.33-37
• /
• 2019

Because the ECG signals are time-series data acquired as time elapses, it is important to obtain comparative data the same in size as the enrolled data every time. This paper suggests a network model of GAN (Generative Adversarial Networks) based on an auxiliary classifier to generate synthetic ECG signals which may address the different data size issues. The Cosine similarity and Cross-correlation are used to examine the similarity of synthetic ECG signals. The analysis shows that the Average Cosine similarity was 0.991 and the Average Euclidean distance similarity based on cross-correlation was 0.25: such results indicate that data size difference issue can be resolved while the generated synthetic ECG signals, similar to real ECG signals, can create synthetic data even when the registered data are not the same as the comparative data in size.

• Journal of architectural history
• /
• v.15 no.1 s.45
• /
• pp.41-60
• /
• 2006

Preservation of wooden architecture by means of synthetic resin, is physical and chemical work. Synthetic resins are using for consolidation and restoration of decayed members. Since 1978, synthetic resin became useful preservation of architectural heritage in Korea. The first object was Chimgyeru of Songgwang-temple in Suncheon city. In the 1980s, have begun the care of materials for conservation on the architectural heritage, it was influenced according to authenticity of UNESCO Venice charter's principle, in 1964. In Korea, preservation of wooden architecture by means of synthetic resin that is sing many kinds of epoxies. Among the specific types of epoxies are araldite XN1023, SV427, etc. The use of synthetic resin have merits and demerits in the restoration for architectural heritage. The merit is that it is more smaller change with new members during preservation work. But the demerit is an irreversibility of the epoxy resin. In 1999, 'ICOMOS International Wood Committee' recommend contemporary materials and techniques, should be chosen and used with the greatest caution. And preservation work should reversible, as possible as technically. Therefore, should be data continous for preservation of wooden architecture by synthetic resin. Because data is very important work about a preservation of wooden architecture by synthetic resin. And should be try to think about new materials and techniques instead of synthetic resin, in the long view.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.2
• /
• pp.89-96
• /
• 2015

In this paper, time-frequency analysis algorithms, empirical mode decomposition and local mean decomposition, are reviewed and their applications to nonlinear and nonstationary real-world data are discussed. In addition, their generic extensions to complex domain are addressed for the analysis of multichannel data. Simulations of these algorithms on synthetic data illustrate the fundamental structure of the algorithms and how they are designed for the analysis of nonlinear and nonstationary data. Applications of the complex version of the algorithms to the synthetic data also demonstrate the benefit of the algorithms for the accurate frequency decomposition of multichannel data.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.5
• /
• pp.476-486
• /
• 2022

Synthetic dynamic infrared image generation from the given virtual environment is being the primary goal to simulate the output of the infra-red(IR) camera installed on a vehicle to evaluate the control algorithm for various search & reconnaissance missions. Due to the difficulty to obtain actual IR data in complex environments, Artificial intelligence(AI) has been used recently in the field of image data generation. In this paper, CycleGAN technique is applied to obtain a more realistic synthetic IR image. We added the Structural Similarity Index Measure(SSIM) loss function to the L1 loss function to generate a more realistic synthetic IR image when the CycleGAN image is generated. From the simulation, it is applicable to the guided-missile flight simulation tests by using the synthetic infrared image generated by the proposed technique.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.147-155
• /
• 2024

Based on the recently developed deep learning technology, many studies have been conducted on deep learning networks that simultaneously detect and classify targets of interest in synthetic aperture radar(SAR) images. Although numerous research results have been derived mainly with the open SAR ship datasets, there is a lack of work carried out on the deep learning network aimed at detecting and classifying SAR ground targets and trained with the synthetic dataset generated from electromagnetic scattering simulations. In this respect, this paper presents the deep learning network trained with the synthetic dataset and applies it to detecting and classifying real SAR ground targets. With experiment results, this paper also analyzes the network performance according to the composition ratio between the real measured data and the synthetic data involved in network training. Finally, the summary and limitations are discussed to give information on the future research direction.