• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1034-1038
• /
• 2005

This paper presents a novel method to speed up neural network (NN) based face detection systems. NN-based face detection can be viewed as a classification and search problem. The proposed method formulates the search problem as an integer nonlinear optimization problem (INLP) and develops an improved genetic algorithm (IGA) to solve it. Each individual in the IGA represents a subwindow in an input image. The subwindows are evaluated by how well they match a NN-based face filter. A face is indicated when the filter response of the best particle is above a given threshold. Experimental results show that the proposed method leads to a speedup of 83 on $320{\times}240$ images compared to the traditional exhaustive search method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 학술대회 논문집 전문대학교육위원
• /
• pp.104-106
• /
• 2000

This paper presents an algorithm for optimal reactive power dispatch problem based on Improved Genetic Algorithm(IGA). Optimal Reactive Power Dispatch (ORPD) is particularized to the minimization of transmission line losses by suitable selection of generator reactive power outputs and transformer tap setting. For the objective, in this paper, Loss Re-Distribution Algorithm(LRDA) is new applied to the equality constraint of ORPD. The proposed method has been evaluated on the IEEE 30 bus system. Results of the application of the method are compared with a base case.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.403-410
• /
• 1998

An immune system has powerful abilities such as memory recognition and learning how to respond to invading antigens, and has been applied to many engineering algorithms in recent year. In this paper, the combined optimization algorithm (Immune-Genetic Algorithm: IGA) is proposed for multi-optimization problems by introduction the capability of the immune system that controls the proliferation of clones to the genetic algorithm. The new combined algorithm is applied to minimize the total weight of the rotor shaft and the transmitted forces at the bearings in order to demonstrate the merit of the combined algorithm. The inner diameter of the shaft and the bearing stiffness are chosen as the design variables. the results show that the combined algorithm can reduce both the weight of the shaft and the transmitted forces at the bearing with dynamic constraints.

• Steel and Composite Structures
• /
• 제21권6호
• /
• pp.1389-1410
• /
• 2016

This paper proposes a hybrid of topological derivative-based level set method (LSM) and isogeometric analysis (IGA) for structural topology optimization. In topology optimization a significant drawback of the conventional LSM is that it cannot create new holes in the design domain. In this study, the topological derivative approach is used to create new holes in appropriate places of the design domain, and alleviate the strong dependency of the optimal topology on the initial design. Furthermore, the values of the gradient vector in Hamilton-Jacobi equation in the conventional LSM are replaced with a Delta function. In the topology optimization procedure IGA based on Non-Uniform Rational B-Spline (NURBS) functions is utilized to overcome the drawbacks in the conventional finite element method (FEM) based topology optimization approaches. Several numerical examples are provided to confirm the computational efficiency and robustness of the proposed method in comparison with derivative-based LSM and FEM.

• Structural Engineering and Mechanics
• /
• 제70권2호
• /
• pp.209-219
• /
• 2019

By normalizing the internal hysteresis variable and eliminating the redundant parameter, the normalized Bouc-Wen model is considered to be an improved and more reasonable form of the Bouc-Wen model. In order to facilitate application and further research of the normalized Bouc-Wen model, some key aspects of the model need to be uncovered. In this paper, hysteresis characterization of the normalized Bouc-Wen model is first studied with respect to the model parameters, which reveals the influence of each model parameter to the shape of the hysteresis loops. The parameter identification scheme is then proposed based on an improved genetic algorithm (IGA), and verified by experimental test data. It is proved that the proposed method can be an efficacious tool for identification of the model parameters by matching the reconstructed hysteresis loops with the target hysteresis loops. Meanwhile, the IGA is shown to outperform the standard GA. Finally, a simplified identification method is proposed based on parameter sensitivity, which indicates that the efficiency of the identification process can be greatly enhanced while maintaining comparable accuracy if the low-sensitivity parameters are reasonably restricted to narrower ranges.

• 한국응용약물학회:학술대회논문집
• /
• 한국응용약물학회 2001년도 추계학술대회 및 정기총회
• /
• pp.37-40
• /
• 2001

• 대한약학회:학술대회논문집
• /
• 대한약학회 2001년도 Proceedings of International Convention of the Pharmaceutical Society of Korea
• /
• pp.319.2-320
• /
• 2001

• 디지털융복합연구
• /
• 제13권8호
• /
• pp.431-438
• /
• 2015

스마트폰이 대중화되고 모바일광고 산업이 많이 발전되었고 모바일광고의 종류도 많이 생겨나고 있다. 모바일게임에서도 많은 개발자가 무료게임을 출시하고 광고를 서비스하는 서비스 업체의 SDK를 이용하여 광고 수익을 내고 있다. 모바일 IGA는 배너, 전면광고, 전면 비디오광고 3가지의 형태로 광고를 사용하고 있으며 각각의 광고는 장단점을 가지고 있다. 현재 많은 게임이 전면광고와 전면 비디오광고를 이용하지만 이러한 광고 수익모델 방식은 유저들의 게임플레이 시간을 일부 사용하는 광고 방식이다. 이러한 방식의 단점을 개선하기 위해서 많이 사용했던 3가지의 광고 수익모델을 분석하여 해당 요소를 찾고, 선행연구들의 연구결과를 이용하여 새로운 광고의 융복합 수익모델을 제안하였다.

• 디지털콘텐츠학회 논문지
• /
• 제8권4호
• /
• pp.491-497
• /
• 2007

무선 홈 응용을 실현하는데 있어서 근거리 네트워킹 기술의 중요성은 증가하고 있다. 예를 들어, 블루투스와 IEEE 802.11b 표준은 무선 홈 응용 구축을 위한 가장 일반적으로 사용되고 있는 기술들이다. 하지만 두 표준은 동일한 무허가 ISM(Industrial, Scientific, Medical) 무선 스펙트럼 대역을 공유하기 때문에 심각한 간섭을 피할 수 없으며, 두 기술을 사용하는 이종 디바이스가 아주 근접하여 있을 경우에 시스템 성능은 심각하게 손상을 받는다. 본 논문에서 연구한 가우시안 FSK 블루투스 시스템은 전자기기 사이의 무선 연결성을 위한 근거리 무선통신 기술의 표준이다. 본 논문에서는 가우시안 FSK 블루투스 시스템에서 동일채널간섭의 영향을 분석하였다. 본 연구에서 사용한 성능 평가 요소는 무선 채널에서의 SIR, 간섭 지수 $\rho$, 그리고 BER 등이며 이를 기반으로 성능을 평가하였다. 가우시안 FSK 블루투스 시스템의 성능 평가에서 다양한 소스로 부터의 동일채널간섭의 영향은 IGA(Impulsive Gaussian Approximation) 방식을 이용하여 분석하였고 다양한 채널상태를 나타내기 위하여 Eb/No, $\rho$와 SIR 값에 따라서 블루투스 시스템의 성능을 분석하여 결과 그래프에 나타내었다.

• Steel and Composite Structures
• /
• 제34권2호
• /
• pp.261-277
• /
• 2020

The main objective of this research paper is to consider vibration analysis of vacancy defected graphene sheet as a nonisotropic structure via molecular dynamic and continuum approaches. The influence of structural defects on the vibration of graphene sheets is considered by applying the mechanical properties of defected graphene sheets. Molecular dynamic simulations have been performed to estimate the mechanical properties of graphene as a nonisotropic structure with single- and double- vacancy defects using open source well-known software i.e., large-scale atomic/molecular massively parallel simulator (LAMMPS). The interactions between the carbon atoms are modelled using Adaptive Intermolecular Reactive Empirical Bond Order (AIREBO) potential. An isogeometric analysis (IGA) based upon non-uniform rational B-spline (NURBS) is employed for approximation of single-layered graphene sheets deflection field and the governing equations are derived using nonlocal elasticity theory. The dependence of small-scale effects, chirality and different defect types on vibrational characteristic of graphene sheets is investigated in this comprehensive research work. In addition, numerical results are validated and compared with those achieved using other analysis, where an excellent agreement is found. The interesting results indicate that increasing the number of missing atoms can lead to decrease the natural frequencies of graphene sheets. It is seen that the degree of the detrimental effects differ with defect type. The Young's and shear modulus of the graphene with SV defects are much smaller than graphene with DV defects. It is also observed that Single Vacancy (SV) clusters cause more reduction in the natural frequencies of SLGS than Double Vacancy (DV) clusters. The effectiveness and the accuracy of the present IGA approach have been demonstrated and it is shown that the IGA is efficient, robust and accurate in terms of nanoplate problems.