• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.639-641
• /
• 2023

이미지 기반 폐기물 처리시스템에서 품목별 상이한 수집 난이도로 인해 발생하는 데이터 불균형으로 분류 모델 학습에 어려움이 따른다. 따라서 본 논문에서는 폐기물 분류 모델의 성능 비교를 통해 적합한 이미지 생성 모델을 탐색한다. 데이터의 불균형을 해결할 수 있도록 VAE(Variational Auto-Encoder), GAN(Generative Adversarial Networks) 및 Diffusion Model을 이용하여 이미지를 생성한다. 이후 각각의 생성 방법에 따라 학습데이터와 병합하여 객체 분류를 진행하였다. 정확도는 VAE가 84.41%로 3.3%의 성능 향상을, F1-점수는 Diffusion Model이 91.94%로 6.14%의 성능 향상을 이루었다. 이를 통해, 데이터 수집에서 나타나는 데이터 불균형을 해결하여 실 사용환경에 알맞은 시스템을 구축이 가능함을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.731-732
• /
• 2023

언리얼 엔진 기반의 메타버스나 실시간 게임 환경에서 캐릭터의 맞춤형 동작이 필요한 경우가 있다. 본 논문은 모션 디퓨전 모델을 활용하여 특정 동작을 자동 생성하는 기능을 제공하는 언리얼 엔진 플러그인을 제시한다. 특히 사용자가 텍스트로 신체 동작이나 감정 표현을 기술해 입력값으로 제공하면 서버에서 모션 디퓨전 모델로 애니메이션을 실시간으로 생성한 후, 언리얼엔진 클라이언트에서 후처리하여 사용자의 캐릭터에 실시간으로 적용하는 방식으로 구현했다.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.523-528
• /
• 2004

This study proposed an anisotropic diffusion restoration fer image classification. The anisotropic diffusion restoration uses a probabilistic model based on Markov random field, which represents geographical connectedness existing in many remotely sensed images, and restores them through an iterative diffusion processing. In every iteration, the bonding-strength coefficient associated with the spatial connectedness is adaptively estimated as a function of brightness gradient. This study made experiments on the satellite images remotely sensed on the Korean peninsula. The experimental results show that the proposed approach is also very effective on image classification in remote sensing.

• Journal of Internet Computing and Services
• /
• v.20 no.3
• /
• pp.111-117
• /
• 2019

We categorize the model of simple payment into Magnetic Secure Transmission, Near Filed Communication, and App Card based on the Focus Group Interview. We also define the key drivers for the diffusion of simple payment services based on the literature review with the experts. Through Analytic Hierarchy Process our finding suggests that the degree of acceptance at the stores is the most critical factor which decides the diffusion of simple payment service model. Security is also the important driver but due to the fact that service providers should follow the information security rule and supervisory guidance, it actually did not make a big difference in terms of assessing competence of each model.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.21 no.6
• /
• pp.17-26
• /
• 1984

A computer program (DIFSIM: Diffusion SIMulator) was written to calculate the impurity profile, specifically boron and phosphorus, due to three different diffusion processes-predeposition, drive-in in inert ambient, and drive-in in oxidizing ambient. The vacancy mechanism including Fair and Tsai's theory for phosphDrus diffusion was widely incorporated for modeling various diffusion processes. The concentrationtependent oxidation rate was also explained using the vacancy model, while the oxidation - enhanced diffusion was mo dolled using catkins replacement mochanlsm . The simulation results using DIFSIM showed a fairly good agreement with the experimental data by adjusting some of the empirical parameters in the program. The results obtained using DIFSIM were compared with the results from SUPREM II.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.677-688
• /
• 2017

In order to solve the undetected probability of multiple targets in ultra-wideband (UWB) through-the-wall radar imaging (TWRI), a time-delay and amplitude modified back projection (BP) algorithm is proposed. The refraction point is found by Fermat's principle in the presence of a wall, and the time-delay is correctly compensated. On this basis, transmission loss of the electromagnetic wave, the absorption loss of the refraction wave, and the diffusion loss of the spherical wave are analyzed in detail. Amplitude compensation is deduced and tested on a model with a single-layer wall. The simulating results by finite difference time domain (FDTD) show that it is effective in increasing the scattering intensity of the targets behind the wall. Compensation for the diffusion loss in the spherical wave also plays a main role. Additionally, the two-layer wall model is simulated. Then, the calculating time and the imaging quality are compared between a single-layer wall model and a two-layer wall model. The results illustrate the performance of the time-delay and amplitude-modified BP algorithm with multiple targets and multiple-layer walls of UWB TWRI.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37A no.11
• /
• pp.961-971
• /
• 2012

This article is concerned with effective numerical techniques for partial differential equation (PDE)-based image restoration. Numerical realizations of most PDE-based denoising models show a common drawback: loss of fine structures. In order to overcome the drawback, the article introduces a new time-stepping procedure, called the method of nonflat time evolution (MONTE), in which the timestep size is determined based on local image characteristics such as the curvature or the diffusion magnitude. The MONTE provides PDE-based restoration models with an effective mechanism for the equalization of the net diffusion over a wide range of image frequency components. It can be easily applied to diverse evolutionary PDE-based restoration models and their spatial and temporal discretizations. It has been numerically verified that the MONTE results in a significant reduction in numerical dissipation and preserves fine structures such as edges and textures satisfactorily, while it removes the noise with an improved efficiency. Various numerical results are shown to confirm the claim.

• Journal of the Korean Institute of Telematics and Electronics D
• /
• v.36D no.1
• /
• pp.83-89
• /
• 1999

A Unified model for the alpha-particle-induced charge collection has been developed. By accounting for funneling and diffusion charges separately, new model accurately describes the dependence of collected charge on junction size, junction bias, injection energy, injection angle, injection point, and trench oxide depth.

• Journal of Information Technology Applications and Management
• /
• v.24 no.2
• /
• pp.81-96
• /
• 2017

Forecasting long-term mobile service demand is inevitable to establish an effective frequency management policy despite the lack of reliability of forecast results. The statistical forecasting method has limitations in analyzing how the forecasting result changes when the scenario for various drivers such as consumer usage pattern or market structure for mobile communication service is changed. In this study, we propose a dynamic model of the mobile communication service market using system dynamics technique and forecast the future demand for long-term mobile communication subscriber based on the dynamic model, and also experiment on the change pattern of subscriber demand under various scenarios.

• Management & Information Systems Review
• /
• v.36 no.2
• /
• pp.239-260
• /
• 2017

This study is to explore the factors that may affect the social adoption diffusion of innovative technology, focusing on smart mobility. It reviewed the literature on theory of social acceptance-diffusion and technology adoption model of innovative products, set up structural equation model that includes the causes and effects of perceived usefulness(the nexus among influences, perceived usefulness and purchase intention) and empirically tested the relationship. The survey, covering 534 non-users, was conducted from August 1, 2016 through August 12, 2016. The results show that compatibility and relative advantage significantly positively affect adoption intention through perceived usefulness, and that communication significantly negatively affect. However, complexity and service quality do not have significant positive effects on perceived intention and purchase intention. Some implications to promote social acceptance of smart mobility based on the results of the study are offered.