• 제목/요약/키워드: heuristics

검색결과 519건 처리시간 0.021초

A Method for Caption Segmentation using Minimum Spanning Tree

  • Chun, Byung-Tae;Kim, Kyuheon;Lee, Jae-Yeon
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2000년도 ITC-CSCC -2
    • /
    • pp.906-909
    • /
    • 2000
  • Conventional caption extraction methods use the difference between frames or color segmentation methods from the whole image. Because these methods depend heavily on heuristics, we should have a priori knowledge of the captions to be extracted. Also they are difficult to implement. In this paper, we propose a method that uses little heuristics and simplified algorithm. We use topographical features of characters to extract the character points and use KMST(Kruskal minimum spanning tree) to extract the candidate regions for captions. Character regions are determined by testing several conditions and verifying those candidate regions. Experimental results show that the candidate region extraction rate is 100%, and the character region extraction rate is 98.2%. And then we can see the results that caption area in complex images is well extracted.

  • PDF

A High Quality Solution Constructive Heuristic for No-Wait Flow Shop Scheduling Problem

  • Nagano, Marcelo Seido;Miyata, Hugo Hissashi
    • Industrial Engineering and Management Systems
    • /
    • 제15권3호
    • /
    • pp.206-214
    • /
    • 2016
  • This paper deals with the no-wait flow shop scheduling problem in order to minimize the total time to complete the schedule or makespan. It is introduced a constructive heuristic which builds the production schedule from job partial sequences by using an appropriate mechanism of insertion. An extensive computational experiment has been performed to evaluate the performance of proposed heuristic. Experimental results have clearly shown that the presented heuristic provides better solutions than those from the best heuristics existing.

유전알고리즘에서 적응적 연산자들의 비교연구 (Comparison of Adaptive Operators in Genetic Algorithms)

  • Yun, Young-Su;Seo, Seoun-Lock
    • 지능정보연구
    • /
    • 제8권2호
    • /
    • pp.189-203
    • /
    • 2002
  • 이 논문에서 우리는 유전알고리즘의 적응적 연산자에 대한 수행도를 비교한다. 이러한 적응적 연산자를 위해서, 유전알고리즘의 교차변이와 돌연변이 연산자가 고려되어 지며, 이 논문에서 개발된 하나의 퍼지로직 제어기와 기존연구에서 사용된 두개의 휴리스틱 기법이 제시되어진다. 이러한 퍼지로직 제어기와 두개의 기존 휴리스틱 기법들은 유전 탐색과정 동안에 그 연산자의 비율들을 적응적으로 조절한다. 이 논문에서 제시된 모든 알고리즘들은 수치예제에서 분석되어 지며, 결론적으로 이들 알고리즘 중에서 최적의 알고리즘이 추천된다.

  • PDF

퍼지 논리를 이용한 전문가 PID 자기 동조 제어기에 관한 연구 (A Study on the Expert PID Autotuner Using Fuzzy Logic)

  • 김영상;최한호;정명진;안태영
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1993년도 하계학술대회 논문집 A
    • /
    • pp.366-368
    • /
    • 1993
  • In this paper, we present an approach to automatically tune and adapt PID parameters by using Fuzzy Logic. PID controllers are well-known and found in many industries. Although the potentials of PID controllers, PID controllers are often poorly tuned and their capabilities are not fully used. We can think that the tuning of PID parameters is based on heuristics and some rule of thumbs. This is the reason we come to use Fuzzy Logic. We show that by imbedding heuristics and some rule of thumbs in PID controllers, reperesented by Fuzzy Logic. we can make PID controllers be robust to uncertainties such as load variations and adapt parameter changes.

  • PDF

자동화제조시스템에서 다수목표를 위한 물류관리 (Logistics for multiple objectives in automated manufacturing system)

  • 최정상;장길상
    • 한국국방경영분석학회지
    • /
    • 제27권2호
    • /
    • pp.25-36
    • /
    • 2001
  • In this paper a new heuristic algorithm has been developed and presented for logistics for multiple objectives in an automated manufacturing systems. We proposed Simallest Processing and Average setup time Ratio First(SPARF) algorithm for multiple criteria under sequence setup time. The heuristic algorithm is implemented on the various problem cases by number of jobs and machines. The proposed algorithm provided smaller than the previously documented heuristics. The results obtained show a superior solution by the new heuristic over previous heuristics on all problem sizes. we perform analyses of variance to fortify the above results of comparison with the previous algorithms to the four cases using Statistical Analysis System(SAS) package. The results show that the larger is the number of groups or cells, the bigger is the amount of improvement by the proposed algorithms. It suggests that the algorithms proposed is strongly influenced by the number of cells, groups and interaction of these factors.

  • PDF

Synthesis of four-bar linkage motion generation using optimization algorithms

  • Phukaokaew, Wisanu;Sleesongsom, Suwin;Panagant, Natee;Bureerat, Sujin
    • Advances in Computational Design
    • /
    • 제4권3호
    • /
    • pp.197-210
    • /
    • 2019
  • Motion generation of a four-bar linkage is a type of mechanism synthesis that has a wide range of applications such as a pick-and-place operation in manufacturing. In this research, the use of meta-heuristics for motion generation of a four-bar linkage is demonstrated. Three problems of motion generation were posed as a constrained optimization probably using the weighted sum technique to handle two types of tracking errors. A simple penalty function technique was used to deal with design constraints while three meta-heuristics including differential evolution (DE), self-adaptive differential evolution (JADE) and teaching learning based optimization (TLBO) were employed to solve the problems. Comparative results and the effect of the constraint handling technique are illustrated and discussed.

Optimal distribution of metallic energy dissipation devices in multi-story buildings via local search heuristics

  • Zongjing, Li;Ganping, Shu;Zhen, Huang;Jing, Cao
    • Earthquakes and Structures
    • /
    • 제23권5호
    • /
    • pp.419-430
    • /
    • 2022
  • The metallic energy dissipation device (EDD) has been widely accepted as a useful tool for passive control of buildings against earthquakes. The distribution of metallic EDDs in a multi-story building may have significant influence on its seismic performance, which can be greatly enhanced if the distribution scheme is properly designed. This paper addresses the optimal distribution problem in the aim of achieving a desired level of performance using the minimum number of metallic EDDs. Five local search heuristic algorithms are proposed to solve the problem. Four base structures are presented as numerical examples to verify the proposed algorithms. It is indicated that the performance of different algorithms may vary when applied in different situations. Based on the results of the numerical verification, the recommended guidelines are finally proposed for choosing the appropriate algorithm in different occasions.

On Removing Ambiguity in Text Understanding

  • Li, Simin;Itoh, Yukihiro
    • 한국언어정보학회:학술대회논문집
    • /
    • 한국언어정보학회 1998년도 Language, Information and Computation = Selected Papers from the 12th Pacific Asia Conference on Language, Information and Computation, Singapore
    • /
    • pp.271-282
    • /
    • 1998
  • PDF