• 한국컴퓨터그래픽스학회논문지
• /
• 제13권3호
• /
• pp.11-18
• /
• 2007

자연스러운 얼굴 애니메이션 생성은 캐릭터 애니메이션 분야에서 중요한 문제이다. 지금까지 얼굴 애니메이션은 3차원 모델링 프로그램을 이용한 전문 애니메이터들의 수작업을 통해 생성되거나, 필요한 움직임 데이터를 직접 동작 캡쳐함으로써 만들어 왔다. 그러나 이러한 방식은 일반 사용자가 쉽게 접근 할 수 없으며 많은 시간과 비용을 요구한다는 단점이 있다. 본 연구에서는 실제에 가깝고 자연스러운 얼굴애니메이션을 만들기 위해, 누구나 쉽게 사용할 수 있는 직관적인 방식의 스케치 인터페이스를 이용하고자 한다. 이를 통해 키-프레임을 생성하는 시스템을 구축하고, 얼굴 캡쳐를 통하여 얻은 데이터로부터 추출한 얼굴 표정간의 전이 정보를 이용하여 키-프레임을 보간하는 방식을 제안한다. 본 시스템은 전문 애니메이터가 아닌 일반 사용자도 쉽고 빠르게 다양한 감점을 표출하며, 동시에 말하는 얼굴 애니메이션을 만들 수 있도록 한다.

• 한국가스학회지
• /
• 제24권1호
• /
• pp.66-75
• /
• 2020

시추는 석유자원 탐사와 개발에서 가장 중요하며 많은 비용이 소요되는 필수 작업이다. 그래서 시추의 효율 향상을 위한 굴진율 연구가 지속적으로 진행되어왔다. 근래에는 전통적인 수학적 모델의 단점을 극복하기 위하여 새로운 방식의 자료기반 모델이 다양한 연구자들에 의해 개발되고 있다. 자료기반 모델은 알고리즘과 매개변수의 선택이 매우 중요하다. 또한 개발된 모델의 성능향상을 위하여 실시간으로 모델을 재훈련하여 연속적인 시추작업을 실현해야한다. 이 논문에서는 최신 연구들을 조사하여 시추 최적화에서 사용된 알고리즘, 시추 매개변수, 모델 재훈련 간격에 대한 정보를 제공하고자 한다.

• 대한임베디드공학회논문지
• /
• 제8권6호
• /
• pp.339-345
• /
• 2013

This paper addresses the system lifetime maximization algorithm in multi-hop sensor network system. A multi-hop sensor network consists of many battery-driven sensor nodes that collaborate with each other to gather, process, and communicate information using wireless communications. As sensor-driven applications become increasingly integrated into our lives, we propose a energy-aware scheme where each sensor node transmits informative data with adaptive data rate to minimize system energy consumption. We show the optimal data rate to maximize the system lifetime in terms of remaining system energy. Furthermore, the proposed algorithm experimentally shows longer system lifetime in comparison with greedy algorithm.

• 한국정보통신학회논문지
• /
• 제16권7호
• /
• pp.1406-1415
• /
• 2012

WiMedia는 다른 WPAN 기술에 비해 빠른 전송률을 제공하지만 전송 범위가 10미터로 제한되어 있어 그 이상의 거리에 존재하는 디바이스와의 통신은 불가능하다. 따라서 본 논문에서는 WiMedia 네트워크에서 제한된 전송 범위를 극복하여 실시간(Real-Time) 데이터를 전송하기 위한 멀티홉 QoS 라우팅 프로토콜을 제안하였다. 제안된 라우팅 프로토콜은 Table-Driven 라우팅 알고리즘과 On-Demand 라우팅 알고리즘이 결합된 하이브리드 형 라우팅 프로토콜로 2홉 이내의 거리에 존재하는 디바이스에 대한 경로는 주기적으로 전송되는 이웃 디바이스의 정보를 수집한 후 Table-Driven 라우팅 알고리즘을 사용하여 생성하며 3홉 이상의 거리에 존재하는 디바이스에 대한 경로는 On-Demand 라우팅 알고리즘을 사용하여 생성한다. 그리고 ns-2 시뮬레이션을 통해 제안된 라우팅 프로토콜과 AODV, 그리고 DSDV간의 성능을 비교하였으며, 그 결과 처리율과 지연시간에 있어 우수한 성능을 보였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 추계학술대회 논문집
• /
• pp.1084-1087
• /
• 1997

In this paper, we developed the micro NCT system for punching the thin plates, which is driven is driven by the standalone type microprocessor. In order to adjust the alignment between the punch and die in-situ punching procedures, the non-contact type laser sensor for measuring the burr and micro-driving system for punching die with using the differential screw are developed. The height of burr in four directions in the punched hole of test specimen are measured, and the measured data are transferred to the personal computer by RS232C serial communication technology. In the personal computer, by using the graphic user interface type monitoring program and data handling procedures which includes the filtering algorithms, the direction and length of movement of the die position is decided and these data are transferred back to the microprocessor. The microprocessor drives the micro positioning stage based on these data. Even if this method is not a perfect solution for the in-situ alignment in micro punching, but this alignment methodology is accomplished in the same stage just after the punching that we hope to solve the alignment problem in the punching system based on this technology.

• 시스템엔지니어링학술지
• /
• 제16권2호
• /
• pp.67-77
• /
• 2020

Traditionally nuclear thermal hydraulic and nuclear safety has relied on numerical simulations to predict the system response of a nuclear power plant either under normal operation or accident condition. However, this approach may sometimes be rather time consuming particularly for design and optimization problems. To expedite the decision-making process data-driven models can be used to deduce the statistical relationships between inputs and outputs rather than solving physics-based models. Compared to the traditional approach, data driven models can provide a fast and cost-effective framework to predict the behavior of highly complex and non-linear systems where otherwise great computational efforts would be required. The objective of this work is to develop an AI algorithm to predict the peak fuel cladding temperature as a metric for the successful implementation of FLEX strategies under extended station black out. To achieve this, the model requires to be conditioned using pre-existing database created using the thermal-hydraulic analysis code, MARS-KS. In the development stage, the model hyper-parameters are tuned and optimized using the talos tool.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권2호
• /
• 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.

• 한국세라믹학회지
• /
• 제56권6호
• /
• pp.596-600
• /
• 2019

Artificial intelligence with a sufficient amount of realistic big data in certain applications has been demonstrated to play an important role in designing new materials or in manufacturing high-quality products. To reduce cracks in ceramic products using machine learning, it is desirable to utilize big data in recently developed data-driven optimization schemes. However, there is insufficient big data for ceramic processes. Therefore, we developed a numerical algorithm to make "virtual" manufacturing data sets using indirect methods such as computer simulations and image processing. In this study, a numerical algorithm based on the random walk was demonstrated to generate images of cracks by adjusting the conditions of the random walk process such as the number of steps, changes in direction, and the number of cracks.

• Interaction and multiscale mechanics
• /
• 제1권3호
• /
• pp.369-379
• /
• 2008

A combined stochastic diffusion and mean-field model is developed for a systematic study of the grain growth in a pure single-phase polycrystalline material. A corresponding Fokker-Planck continuity equation is formulated, and the interplay/competition of stochastic and curvature-driven mechanisms is investigated. Finite difference results show that the stochastic diffusion coefficient has a strong effect on the growth of small grains in the early stage in both two-dimensional columnar and three-dimensional grain systems, and the corresponding growth exponents are ~0.33 and ~0.25, respectively. With the increase in grain size, the deterministic curvature-driven mechanism becomes dominant and the growth exponent is close to 0.5. The transition ranges between these two mechanisms are about 2-26 and 2-15 nm with boundary energy of 0.01-1 J $m^{-2}$ in two- and three-dimensional systems, respectively. The grain size distribution of a three-dimensional system changes dramatically with increasing time, while it changes a little in a two-dimensional system. The grain size distribution from the combined model is consistent with experimental data available.

• Smart Structures and Systems
• /
• 제32권6호
• /
• pp.359-369
• /
• 2023

Servo-motor driven uniaxial shake tables have been widely used for education and research purposes in earthquake engineering. These shake tables are mostly displacement-controlled by a digital proportional-integral-derivative (PID) controller; however, accurate reproduction of acceleration time histories is not guaranteed. In this study, a control strategy is proposed and verified for uniaxial shake tables driven by a servo-motor. This strategy incorporates a deep-learning algorithm named Long Short-Term Memory (LSTM) network into a displacement PID feedback controller. The LSTM controller is trained by using a large number of experimental data of a self-made servo-motor driven uniaxial shake table. After the training is completed, the LSTM controller is implemented for directly generating the command voltage for the servo motor to drive the shake table. Meanwhile, a displacement PID controller is tuned and implemented close to the LSTM controller to prevent the shake table from permanent drift. The control strategy is named the LSTM-PID control scheme. Experimental results demonstrate that the proposed LSTM-PID improves the acceleration tracking performance of the uniaxial shake table for both bare condition and loaded condition with a slender specimen.