• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1334-1337
• /
• 2004

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 expands the basic particle swarm optimization (PSO) to solve it. PSO works with a population of particles, each representing 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. To achieve better performance, the influence of PSO parameter settings on the search performance was investigated. Experiments show that with fine-adjusted parameters, the proposed method leads to a speedup of 94 on 320${\times}$240 images compared to the traditional exhaustive search method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1380-1382
• /
• 1996

In this paper, a motion estimation module is made with ADSP-21020 based on MPEG-2 which is an international standard for moving picture compression. And, the block matching algorithm used as motion estimation method is easy for an hardware implementation. The ADSP-21020 of Analog Device is used for a main control processor. We used three block matching method (exhaustive search method, 2D-logarithmic search method, three step search method) for software simulation and implemented the three step search method to hardware. For the test of the estimation module, we used ping pong image sequences and mobile and calendar image sequences.

• 한국CDE학회논문집
• /
• 제14권6호
• /
• pp.404-414
• /
• 2009

In the computational molecular analysis, 3D structural comparison for protein searching plays a very important role. As protein databases have been grown rapidly in size, exhaustive search methods cannot provide satisfactory performance. Because exhaustive search methods try to handle the structure of protein by using sphere set which is converted from atoms set, the similarity calculation about two sphere sets is very expensive. Instead, the filter-and-refine paradigm offers an efficient alternative to database search without compromising the accuracy of the answers. In recent, a very fast algorithm based on the inter-atomic distance has been suggested by Ballester and Richard. Since they adopted the moments of distribution with inter-atomic distance between atoms which are rotational invariant, they can eliminate the structure alignment and orientation fix process and perform the searching faster than previous methods. In this paper, we propose a new 3D shape descriptor. It has properties of the general shape distribution and useful property in screening the molecular database. We show some experimental results for the validity of our method.

• 한국CDE학회논문집
• /
• 제20권4호
• /
• pp.321-327
• /
• 2015

In the protein database search, 3D structural shape comparison for protein screening plays a important role. Protein databases have big size and have been grown rapidly. Exhaustive search methods cannot provide a satisfactory performance. As protein is composed of a set of spheres, the similarity calculation of two set of spheres is very expensive. Thus, a reasonable filtering method could be an answer for the speedup of protein screening. In this paper, we suggest a speedup method for protein screening with atom number and bounding sphere. We also show some experimental results for the validity of our method.

• 전자공학회논문지
• /
• 제52권3호
• /
• pp.19-24
• /
• 2015

본 논문에서는 massive multiple-input multiple-output (MIMO) 기반의 wireless powered communication network (WPCN)에서 에너지 효율을 향상시키기 위한 기지국 안테나 수 최적화 기법을 제안한다. 제안하는 기법은 massive MIMO 시스템의 채널 hardening 특성을 이용하여 채널 이득을 안테나 수에 대한 식으로 근사한다. 그리고 근사화 된 최적화 문제에 편미분을 적용한 후 Lambert-W 함수를 이용하여 최적해를 closed form으로 찾는다. 모의실험을 통해 제안하는 기법의 근사 과정과 최적화 문제를 해결하는 방법이 적절함을 보이고, closed form 해가 exhaustive search 방법으로 찾은 해와 오차가 크지 않음을 확인한다.

• 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.

• 전자공학회논문지CI
• /
• 제43권1호
• /
• pp.53-66
• /
• 2006

본 논문에서는 전체 차원으로 데이터베이스 내의 모든 영상에 대해 순차적인 검색을 했을 때의 상세 검색 결과와 동일한 적합성을 유지하면서 검색 속도를 훨씬 더 향상시킬 수 있는 통합 검색 시스템을 제안한다. 통합 검색 시스템은 적합성을 유지하는 서로 다른 두 독립적인 시스템이 병합되어 있다. 하나는 특징 벡터 차원 축약을 이용한 2단계 검색 시스템이고 나머지 하나는 이진 트리 클러스터링을 이용한 2단계 검색 시스템이다. 각각의 방법은 1단계에서 상세 검색에서의 검색 결과를 항상 포함하는 후보 영상들을 추출하고, 추출된 후보 영상들을 대상으로 2단계 검색에서 전체 차원으로 재 검색을 한다 그러므로 각 방법과 통합 검색 방법은 모두 상세 검색을 수행했을 때와 동일한 검색 결과를 얻게 된다. 특징 벡터 차원 축약을 이용한 2단계 검색 방법은 Cauchy- Schwartz 부등식의 성질을 이용하여 특징 벡터를 차원 축약하여 검색에 사용하는 방법이다. 이때 전체 검색 시간을 최소로 하는 최적 차원 축약율이 존재하게 되고, 이를 후보 영상 추출을 위한 1차 검색에 적용하게 된다. 이진 트리 클러스터링을 이용한 2단계 검색 방법은 재귀적인 2-means 클러스터링을 통해 각 클러스터의 반경이 동일하게 동적으로 분할하는 방법이다. 동일한 적합성 유지를 위해 유사도 기준이 보정된 질의를 통해 1단계 검색에서 후보 클러스터를 추출하고, 2단계 검색에서 후보 클러스터 내의 영상을 대상으로 최종 결과 영상들을 얻게 된다. 통합 검색 방법은 위의 두 검색 방법을 통합한 것으로 서로 독립적인 두 방법을 동시에 적용함으로써 검색 시스템의 성능을 훨씬 더 향상시킬 수 있다 제안하는 방법은 상세 검색의 적합성을 유지하면서도 검색 속도를 훨씬 더 향상시킬 수 있음이 실험을 통해 입증되었다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• pp.1515-1518
• /
• 2003

This paper suggests the condensed two-stage retrieval method for fast image retrieval in the content-based image retrieval system, and proves the validity of the performance. The condensed two-stage retrieval method reduces the overall response time remarkably while it maintains relevance with the conventional exhaustive search method. It is explained by properties of the Cauchy-Schwartz inequality. In experimental result, it turns out that there is an optimal value of condensation ratio which minimizes the overall response time. We analyze the optimal condensation ratio by modeling a similarity computation time mathematically.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1995년도 추계학술대회 논문집 학회본부
• /
• pp.569-571
• /
• 1995

This paper compares the simulated annealing and the Hopfield neural network method for an optimal routing in a multistage interconnection network(MIN). The MIN provides a multiple number of paths for ATM cells to avoid cell conflict. Exhaustive search always finds the optimal path, but with heavy computation. Although greedy method sets up a path quickly, the path found need not be optimal. The simulated annealing can find an sub optimal path in time comparable with the greedy method.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 1994년도 가을 학술발표회 논문집
• /
• pp.267-272
• /
• 1994

This work presents a method of optimum design for reinforced concrete building frames with rectangular cross sections. The optimization techniques used is based on the principle of divided parameters. The design variable parameters are divided into two groups, external and internal, and the optimization is also divided into external and internal procedure. This principle overcomes difficulties arising from the presence of two materials in one element, the property peculiar to reinforced concrete. Several search algorithms are tested to verify their accuracy for the external optimization. Among them pattern search algorithms has been found consistent. This work proposes a new method, modified pattern search, and a number of sample problems prove its accuracy and usefulness. Exhaustive search for all local minima in the design spaces for two sample problems has been carried out to understand the nature of the problem. The number of local minima identified is quite more than expected and it has become understood that the researcher's task in this field is to find a better local minimum if not global. The designs produced by the method preposed have been found better than those from other method, and they are in full accord with ACI Building Code Requirments(ACI 318-89).