• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.5
• /
• pp.1162-1170
• /
• 2014

In this paper, an accurate remote gaze tracking method with two cameras is presented using a modified Starburst algorithm and honography normalization. Starburst algorithm, which was originally developed for head-mounted systems, often fails in detecting accurate pupil centers in remote tracking systems with a larger field of view due to lots of noises. A region of interest area for pupil is found using template matching, and then only within this area Starburst algorithm is applied to yield pupil boundary candidate points. These are used in improved RANSAC ellipse fitting to produce the pupil center. For gaze estimation robust to head movement, an improved homography normalization using four LEDs and calibration based on high order polynomials is proposed. Finally, it is shown that accuracy and robustness of the system is improved using two cameras rather than one camera.

• Journal of Internet Computing and Services
• /
• v.17 no.1
• /
• pp.47-53
• /
• 2016

A type of workflow affiliation network is one of the specialized social network types, which represents the associative relation between actors and activities. There are many methods on a workflow affiliation network measuring centralities such as degree centrality, closeness centrality, betweenness centrality, eigenvector centrality. In particular, we are interested in the closeness centrality measurements on a workflow affiliation network discovered from enterprise workflow models, and we know that the time complexity problem is raised according to increasing the size of the workflow affiliation network. This paper proposes an estimated ranking algorithm and analyzes the accuracy and average computation time of the proposed algorithm. As a result, we show that the accuracy improves 47.5%, 29.44% in the sizes of network and the rates of samples, respectively. Also the estimated ranking algorithm's average computation time improves more than 82.40%, comparison with the original algorithm, when the network size is 2400, sampling rate is 30%.

• Journal of Korean Society of Steel Construction
• /
• v.17 no.6 s.79
• /
• pp.661-672
• /
• 2005

For the efficient stochastic optimization of steel structures for which a large number of analyses is required, artificial neural networks,which have emerged as a powerful tool that could have been used to replace time-consuming procedures in many scientific or engineering applications, are applied. They are utilized for the solution of the equilibrium equations resulting from the application of the finite element method in connection with the reanalysis type of problem, for which a large number of finite element analyses are required in this study. As such, the use of artificial neural networks to predict finite element analysis outputs simplifies and facilitates the performance of the stochastic optimal design of structural systems where a trained neural network is used to replace the structural reanalysis phase. Moreover, to improve efficiency of used artificial neural networks, genetic algorithm is utilized. The stochastic optimizer used in this study is an algorithm based on the evolution theory. The efficiency of the proposed procedure is examined in problems with both volume (weight) functions and real-world cost functions

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.588-593
• /
• 2006

자연하천은 일반적으로 만곡수로나 사행수로 형태를 보이고 있으며, 직선수로에서와 달리 원심력에 기인한 이차류 영향을 받게 된다. 이차류에 의해서 수면에서는 만곡부 바깥쪽으로, 하상에서는 만곡부 안쪽으로의 흐름특성을 보이게 된다. 만곡부 안쪽으로 가해지는 하상 전단응력에 기인하여 하상에서의 입자가 만곡부 안쪽으로 이송되며, 결과적으로 만곡부 안쪽에는 점사주가, 바깥쪽에는 소(pool)가 생성된다. 또한 지형경사의 생성으로 입자에 가해지는 중력효과도 변화된다. 따라서 이와 같은 자연하천의 흐름과 하상변동을 수치모의 하기 위해서는 만곡부 이차류 특성을 고려한 모형이 필요하다. 본 연구에서는 수심 적분된 흐름방정식과 하상토 보존방정식 (Exner equation)을 이용한 하상변동을 위한 비연계 수치모형을 위해서 하상토 보존방정식의 유한요소 알고리즘을 개발하였다. 하상토 보존방정식은 흐름 특성에 따른 평형 유사량의 공간변화율을 이용하여 일정 기간 동안의 하상 변화량을 계산한다. 이 때 이차류에 의한 하상 전단응력의 편각 및 지형경사 변화에 따른 실제 입자의 이송방향을 보정하여 평형 유사량이 계산된다. 이러한 보정식을 적용시키기 위해서는 유속성분의 공간변화량 및 지형경사의 공간성분이 필요하다. 유한요소법은 연속성 변수를 이산화시켜 근사해를 구하는 수치기법의 일종이기 때문에, 요소망이 불규칙적으로 구성되었을 경우 임의의 절점에서 연속성을 지닌 변수의 공간변화율을 계산하는데 어려움이 있다. 따라서 본 연구에서는 평형 유사량 계산 시에 절점이 아닌 요소 내부에서 평형 유사량을 계산하는, 하상토 보존방정식의 새로운 유한요소 알고리즘을 개발하고, 새로운 알고리즘을 적용시킨 수치모형의 검증을 행하였다. 경계조건 알고리즘의 검증으로 위해서 Soni 등 (1980)이 행한 상류 유입 유사량에 따른 하상변동을 수치 모의하고 실험치와 비교하였으며, Sutmuller와 Glerum (1980)이 수행한 만곡수로에서의 하상변동을 모의하고 실험과 비교하였다. 새로운 알고리즘을 적용시킨 하상토 보존방정식의 유한요소 수치모형의 결과는 매우 안정적이며, 실험과 매우 유사한 결과를 얻을 수 있었다. 본 수치모델은 현재 균일한 입자의 하상토만을 고려하므로, 입자분급이나 하상 장갑화 현상 등은 무시한다.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.39 no.1
• /
• pp.16-23
• /
• 2002

In this paper, we propose the growing and pruning algorithm to design the optimal structure of modular wavelet neural network(MWNN) with F-projection and geometric growing criterion. Geometric growing criterion consists of estimated error criterion considering local error and angle criterion which attempts to assign wavelet function that is nearly orthogonal to all other existing wavelet functions. These criteria provide a methodology which a network designer can construct MWNN according to one's intention. The proposed growing algorithm increases in number of module or the size of modules of MWNN. Also, the pruning algorithm eliminates unnecessary node of module or module from constructed MWNN to overcome the problem due to localized characteristic of wavelet neural network which is used to modules of MWNN. We apply the proposed constructing algorithm of the optimal structure of MWNN to approximation problems of 1-D function and 2-D function, and evaluate the effectiveness of the proposed algorithm.

• Journal of Navigation and Port Research
• /
• v.28 no.3
• /
• pp.221-225
• /
• 2004

This paper deals with a nonlinear system modelling using neural network and genetic algorithm Application q{ neural network to control and identification is actively studied because of their approximating ability of nonlinear function. It is important to design the neural network with optimal structure for minimum error and fast response time. Genetic algorithm is getting more popular nowadays because of their simplicity and robustness. in this paper, we optimize a neural network structure using genetic algorithm The genetic algorithm uses binary coding for neural network structure and searches for an optimal neural network structure of minimum error and fast response time. Through an extensive simulation, the optimal neural network structure is shown to be effective for identification of nonlinear system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37A no.10
• /
• pp.841-849
• /
• 2012

This paper proposes an low-complexity soft-output multiple-input multiple-output (soft-MIMO) detection algorithm for achieving soft-output maximum-likelihood (soft-ML) performance under max-log approximation. The proposed algorithm is based on a parallel tree-search (PTS) applying a channel ordering by a sorted-QR decomposition (SQRD) with altered sort order. The empty-set problem that can occur in calculation of log-likelihood ratio (LLR) for each bit is solved by inserting additional nodes at each search level. Since only the closest node is inserted among nodes with opposite bit value to a selected node, the proposed node insertion scheme is very efficient in the perspective of computational complexity. The computational complexity of the proposed algorithm is approximately 37-74% of that of existing algorithms, and from simulation results for a $4{\times}4$ system, the proposed algorithm shows a performance degradation of less than 0.1dB.

• Proceedings of the KOR-KST Conference
• /
• 2002.02a
• /
• pp.17-42
• /
• 2002

전통적인 OD조사에 의한 OD추정의 여러 문제점들로 인해 링크관측교통량과 기존OD를 결합해 OD를 추정하고자 하는 연구들이 제시되고 있다. Yang(1995)은 일반화최소자승법을 풀기 위한 IEA와 SAB 알고리즘을 제시하였다. 그러나 두 알고리즘의 문제점은 첫째 실제 OD를 알기가 어렵기 때문에 기존 OD를 중요한 추정기준으로 설정한다는 것으로, 이러한 추정의 종속성으로 인해, 기존 OD와 실제 OD의 차이가 큰 경우 정확한 해를 도출하지 못한다. 두 번째 문제는 통행패턴 추정시 선형근사화를 가정하기 때문에 게임이론적 측면에서 전제로 설정한 완전한 Stackelberg 상황을 구현하지 못한다는 것이다. 이러한 문제점을 피하기 위해서는 기존 OD나 관측교통량의 오차에 일관적인 해도출 기법이 필요하다. OD추정 문제는 본질적으로 비선형이고 비볼록하여 전역해 탐색기법이 필요하기 때문에 전역최적화가 가능한 유전알고리즘을 이용한 OD추정모형(GAM)을 개발하였다. 사례네트워크 분석결과, GAM은 기존 OD의 오차에 대해 크게 종속적이지 않으며 OD구조가 변하는 경우에도 추정이 가능하여, 일반적으로 실제 OD를 알 수 없는(기존OD의 오차가 어느 정도인지를 알 수 없는) 도시부 네트워크에서 신뢰성있는 추정력을 보였다. 또한 기존 OD 추정모형은 비교적 용이하게 차종별로 관측할 수 있는 링크교통량을 차종구분 없이 단일차종으로 이용함으로써, 정보의 손실을 초래하여 결과적으로 모형의 추정력을 저하시켰다. 그렇지만 다차종 링크관측교통량으로부터 다차종 OD 추정연구는 거의 없었으며, 그 결과가 단일차종에 대한 추정결과와 어떻게 다른지에 대한 연구도 전무하였다. 본 연구에서는 유전알고리즘을 이용한 OD 추정모형을 다수단 OD 추정모형(GAMUC)으로 확대하였다. 사례 분석 결과 단일차종 OD추정기법은 심각한 추정오류를 범할 수 있으며, 그 적용성도 낮다는 것을 보였다. 다차종 OD 추정기법이 단일차종 OD 추정기법보다 양호한 추정력을 보였으며, 다차종 기법 중에서는 GAMUC가 IEAMUC보다 우수한 추정력을 보였다.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.11
• /
• pp.69-75
• /
• 2013

This paper introduces a touch recognition method for touch screen systems based on the SIFT(Scale Invariant Feature Transform) algorithm for stable touch recognition under strong noises. This method provides strong robustness against the noises and makes it possible to effectively extract the various size of touches due to the SIFT algorithm. In order to verify our algorithm we simulate it on the Matlab with the channel data obtained from a real touch screen. It was found from the simulations that our method could stably recognize the touches without regard to the size and direction of the touches. But, our algorithm implemented on a real touch screen system does not support the realtime feature because the DoG(Difference of Gaussian) of the SIFT algorithm needs too many computations. We solved the problem using the DoM(Difference of Mean) which is a fast approximation method of DoG.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.12
• /
• pp.85-98
• /
• 1998

This paper proposes a new design method of neuro-FLC by the Lamarckian co-adaptation scheme that incorporates the backpropagation learning into the GA evolution in an attempt to find optimal design parameters (fuzzy rule base and membership functions) of application-specific FLC. The design parameters are determined by evolution and learning in a way that the evolution performs the global search and makes inter-FLC parameter adjustments in order to obtain both the optimal rule base having high covering value and small number of useful fuzzy rules and the optimal membership functions having small approximation error and good control performance while the learning performs the local search and makes intra-FLC parameter adjustments by interacting each FLC with its environment. The proposed co-adaptive design method produces better approximation ability because it includes the backpropagation learning in every generation of GA evolution, shows better control performance because the used COG defuzzifier computes the crisp value accurately, and requires small workspace because the optimization procedure of fuzzy rule base and membership functions is performed concurrently by an integrated fitness function on the same fuzzy partition. Simulation results show that the Lamarckian co-adapted FLC produces the most superior one among the differently generated FLCs in all aspects such as the number of fuzzy rules, the approximation ability, and the control performance.