• Journal of KIISE:Software and Applications
• /
• v.37 no.1
• /
• pp.80-84
• /
• 2010

Tracking hands is an essential technique for hand gesture recognition which is an efficient way in Human Computer Interaction (HCI). Recently, many researchers have focused on hands tracking using a 3D hand model and showed robust tracking results compared to using 2D hand models. In this paper, we propose a novel 3D hand tracking method based on a coupled particle filter. This provides robust and fast tracking results by estimating each part of global hand poses and local finger motions separately and then utilizing the estimated results as a prior for each other. Furthermore, in order to improve the robustness, we apply a multi-cue based method by integrating a color-based area matching method and an edge-based distance matching method. In our experiments, the proposed method showed robust tracking results for complex hand motions in a cluttered background.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.8
• /
• pp.1901-1907
• /
• 2015

Today's smartphones and user devices are equipped with multiple radio interfaces increasingly. Aggregating theses multiple radio interfaces and using them concurrently will increase a user's communication speed immediately, but at the expense of increased power consumption. In this paper, we develop a mathematical performance model of an adaptive radio activation scheme by which a radio interface is activated only when needed for performance increase and deactivated otherwise. The developed model shows that the adaptive scheme reduces delay significantly and almost halves power consumption below a certain level of traffic input.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.14 no.1
• /
• pp.75-83
• /
• 1989

In this paper, applying the REC model which characterizes the coupling between the radiating edges to two coupled rectangular microstrip patch antenna, we obtain scattering parameters $\mid$ $S_{11}$ $\mid$ and $\mid$ $S_{12}$ $\mid$for the various coupling separations, Se=0.5mm, 1.0mm, 1.5mm, and 2.0mm, The calculated values are compared with the measured values. For the rectangular microstrip patch antenna with a parasitic element which is gap-coupled to the radiating edges of the rectangular patch, calculated return losses using the REC model are compared with measrued values. Here, the each microstrip antenna is fed by a 50 microstrip line. The purpose of the paper is to compare a 50$\Omega$ microstrip line fed case with a coaxial fed case treated in Ref.

• Proceedings of the CALSEC Conference
• /
• 2002.01a
• /
• pp.474-478
• /
• 2002

컴포넌트 기반 개발(CBD :Component Based Development)의 확신에 따른 컴포넌트 측정 모델의 구축 컴포넌트 기반 개발과 기존 객체 지향 기반 개발 간의 연관성과 상호 보완성 파악 컴포넌트의 이점 극대화를 위한 컴포넌트 측정 모델의 구축(중략)

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.2
• /
• pp.69-76
• /
• 2018

Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a new deep neural network model for referring expression comprehension. The proposed model finds out the region of the referred object in the given image by making use of the rich information about the referred object itself, the context object, and the relationship with the context object mentioned in the referring expression. In the proposed model, the object matching score and the relationship matching score are combined to compute the fitness score of each candidate region according to the structure of the referring expression sentence. Therefore, the proposed model consists of four different sub-networks: Language Representation Network(LRN), Object Matching Network (OMN), Relationship Matching Network(RMN), and Weighted Composition Network(WCN). We demonstrate that our model achieves state-of-the-art results for comprehension on three referring expression datasets.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.13 no.1
• /
• pp.75-85
• /
• 2000

When applying a system identification technique, which incorporates an experimental model to a corresponding finite element model of a structure, one of the major problems is the large difference in the numbers of degrees of freedom (dof) between the two models. While there are large number of dofs in a finite element model, the number of measurement points is practically limited. So it is very difficult to incorporate them. Especially rotational dofs are hard to measure. In this study a method is presented for estimating structural dynamic responses at unmeasurable locations in frequency domain. The proposed method is tested numerically and the feasibility for practical application has been demonstrated through an example structure under moving loads, where translational and rotational dofs of beam at a center point are estimated from the partial measurements of responses at accessible points.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2003.05a
• /
• pp.87-91
• /
• 2003

It has well known that MUSIC and ESPRIT algorithms estimate angle of arrival(AOA) with high resolution by eigenvalue decomposition of the covariance matrix which were obtained from the array antennas. However, the disadvantage of MUSIC and ESPRIT is that they are computationally ineffective, and then they are difficult to implement in real time. The other problem of MUSIC and ESRPIT is to require calibrated antennas with uniform features, and are sensitive to the manufacturing facult and other physical uncertainties. To overcome these disadvantages, several method using neural model have been study. For multiple signals, those require huge training data prior to AOA estimation. This paper proposes the algorithm for AOA estimation by interconnected hopfield neural model. Computer simulations show the validity of the proposed algorithm. The proposed method does not require huge training procedure and only assigns interconnected coefficients to the neural network prior to AOA estimation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.374-377
• /
• 2007

본 논문은 Takagi-Sugeno (T-S) 퍼지 모델을 이용하여 이산 시간에서의 비선형 상호 결합 시스템에 대한 분산 동적 출력 궤한 제어기를 제시한다. 이산시간 비선형 상호 결합 시스템의 각 하위 시스템에 대한 T-S 퍼지 모델링을 한 후, 각각에 대해 동적 출력 궤한 제어기를 설계한다. 제어가 된 폐루프 하위 시스템들로 전체 시스템의 평형점이 안정화되는 선형 행렬 부등식 (LMI)을 구하고, 부등식을 이용하여 동적 출력 궤한 제어기의 이득값을 구한다. 마지막으로 모의실험을 통해 분산 동적 출력 궤한 제어기의 효용성을 확인한다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.27-30
• /
• 2000

본 논문은 HMM(Hidden Markov Model)을 이용하여 인식을 수행할 경우의 오류를 최소화 할 수 있는 후 처리 과정으로 신경망을 결합시켜 HMM 단독으로 사용하였을 때 보다 높은 인식률을 얻을 수 있는 HMM과 신경망의 하이브리드시스템을 제안한다. HMM을 이용하여 학습한 후 학습에 참여하지 않은 데이터를 인식하였을 때 오인식 데이터를 정인식으로 인식하도록 HMM의 출력으로 얻은 각 출력확률을 후 처리에 사용될 MLP(Multilayer Perceptrons)의 학습용으로 사용하여 MLP를 학습하여 HMM과 MLP을 결합한 하이브리드 모델을 만든다. 이와 같은 HMM과 신경망을 결합한 하이브리드 모델을 사용하여 단독 숫자음과 4연 숫자음 데이터에서 실험한 결과 HMM 단독으로 사용하였을 때 보다 각각 약 $4.5\%$, $1.3\%$의 인식률 향상이 있었다. 기존의 하이브리드 시스템이 갖는 많은 학습시간이 소요되는 문제점과 실시간 음성인식시스템을 구현할 때의 학습데이터의 부족으로 인한 인식률 저하를 해결할 수 있는 방법임을 확인할 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.309-312
• /
• 2011

본 논문에서는 유무선 통신환경의 클라이언트-서버 모델에서 바이오정보를 이용해 비밀 키 또는 비밀 정보를 실시간 공유할 수 있는 신뢰구간 기반의 바이오-암호 기법을 설계하고 분석한다. 제안하는 바이오-암호 기법은 키 결합 방식의 바이오-암호 기법의 대표적인 기법의 하나인 퍼지볼트 기법을 기본 모델로 두고 있으나, 퍼지볼트 기법의 주요 이슈인 거짓 볼트 수의 증가에 따른 인식률 저하, 고차 다항식 복원 시간의 실용성 여부, 상관 공격에의 취약을 해결하기 위하여 T-검정 기반 신뢰구간을 적용한 키 결합 방식으로 설계하였다. 실험결과는 거짓 볼트 수의 증가와 상관없이 항상 비밀 키를 획득해 보안성과 정확성이 향상되고, 이때의 수행시간도 사용자가 인지하기 힘든 작은 값으로 실시간 사용의 가능성을 높이고, 유사 바이오정보로 비밀 키를 획득할 수 없어 상관 공격에도 강인함을 확인하였다.