• Asian Pacific Journal of Cancer Prevention
• /
• 제17권7호
• /
• pp.3651-3658
• /
• 2016

Computer-aided diagnosis of breast cancer is an important medical approach. In this research paper, we focus on combining two major methodologies, namely fuzzy base systems and the evolutionary genetic algorithms and on applying them to the Saudi Arabian breast cancer diagnosis database, to aid physicians in obtaining an early-computerized diagnosis and hence prevent the development of cancer through identification and removal or treatment of premalignant abnormalities; early detection can also improve survival and decrease mortality by detecting cancer at an early stage when treatment is more effective. Our hybrid algorithm, the genetic-fuzzy algorithm, has produced optimized systems that attain high classification performance, with simple and readily interpreted rules and with a good degree of confidence.

• 한국경영과학회지
• /
• 제27권2호
• /
• pp.33-49
• /
• 2002

CBM (Condition-Based Maintenance) has increasingly drawn attention in industry because of its many benefits. CBM Problem Is characterized as a state-dependent scheduling model that demands simultaneous maintenance actions, each for an attribute that influences on machine condition. This problem is very hard to solve within conventional Markov decision process framework. In this paper, we present an intelligent machine maintenance scheduler, for which a new incremental decision tree learning method as evolutionary system identification model and shortest path problem as schedule generation model are developed. Although our approach does not guarantee an optimal scheduling policy in mathematical viewpoint, we verified through simulation based experiment that the intelligent scheduler is capable of providing good scheduling policy that can be used in practice.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 가을 학술발표논문집 Vol.32 No.2 (2)
• /
• pp.691-693
• /
• 2005

송신자 개시 부하 균등 알고리즘에서는 전체 시스템이 과부하일 때 송신자(과부하 프로세서)가 부하를 이전하기 위해 수신자(저부하 프로세서)를 발견할 때까지 불필요한 이전 요청 메시지를 계속 보낸다. 따라서 이같은 상황에서는 저부하 상태인 수신자 프로세서로부터 승인 메시지를 받기까지 불필요한 프로세서간 통신으로 인하여 프로세서의 이용률이 저하되고 또한 태스크의 처리율이 낮아지는 문제점이 발생한다. 본 논문에서는 이질형 분산 시스템에서의 동적 부하 균등을 위해 진화알고리즘을 기반으로 하는 접근 방법을 제안한다.

• 디자인학연구
• /
• 제2권1호
• /
• pp.99-106
• /
• 1989

Environmental designers face a wide range of problems to be solved in their day-to-day works. The scale and number of problems and so enormous that designers should be a way out to meet these complex situation. Lately, environmental design process based on systems a.pproach is chosen for design methodology. It is a very complicated procedure with many alternatives. It is a evolutionary process that establishes the solution of a series of problems. This study attempt to tell the designer how to find design solution to problems and how to organize form as solution problems. The model of this design process is largely composed of three phases; Phase I : Problem definition and existing system analysis. Phase II : design goals and objectives, design criteria Phase III : creative process of design form.

• Wind and Structures
• /
• 제18권1호
• /
• pp.21-35
• /
• 2014

The latest developments in topology optimization are integrated with Computational Fluid Dynamics (CFD) for the conceptual design of building structures. The wind load on a building is simulated using CFD, and the structural response of the building is obtained from finite element analysis under the wind load obtained. Multiple wind directions are simulated within a single fluid domain by simply expanding the simulation domain. The bi-directional evolutionary structural optimization (BESO) algorithm with a scheme of material interpolation is extended for an automatic building topology optimization considering multiple wind loading cases. The proposed approach is demonstrated by a series of examples of optimum topology design of perimeter bracing systems of high-rise building structures.

• 한국시뮬레이션학회논문지
• /
• 제12권1호
• /
• pp.73-83
• /
• 2003

This paper presents armed vehicle BAttle Group Simulation model(called BAGSim) which is an object-oriented simulation system for representing battle group engagement consisting of tanks and helicopters. BAGSim is designed in the evolutionary software life cycle approach with the Unified Software Development Process, and implemented with C++ language. BAGSim consists of a preprocessor for engagement scenario definition and simulation data set up, a main processor for triggering engagement event and advancing simulation clock, and a post processor to record simulation histories. Application scenario covers several type of engagement among command tanks, fight tanks, scout helicopters, attack helicopters, anti-tank guided missiles, and decoys. Thus, BAGSim can be effectively used as an analytic tool to examine some operational concepts and tactics, further experimentally fine tune tank design options.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 추계학술대회 및 정기총회
• /
• pp.482-487
• /
• 2002

본 논문에서는 사용자 개개인에 최적화된 아바타를 생성하기 위해 대화형 진화 연산(Interactive Genetic Algorithm, IGA)을 적용하는 방법을 제안하고 있다. IGA는 사용자의 선택을 적합도 평가에 사용하는 방법이기 때문에, 사용자의 개인적인 취향을 아바타 생성 과정에 반영할 수 있다. 본 연구에서는 기존의 IGA가 가지고 있는 단점을 극복하기 위해 'hidden population' , 'primitive avatar' , 'simplified genotype' 기법을 제안한다. 이러한 방법들은 단시간 내에 최적화된 결과물을 생성하도록 유도함으로써 IGA 시스템의 최대 문제점인 사용자의 피로도를 최소화한다. 마지막으로, 제안하고 있는 알고리즘의 우수성을 증명하기 위해 사용자의 만족도나 신뢰도를 측정할 수 있는 독자적인 평가 방법을 소개하고 있다.

• Structural Engineering and Mechanics
• /
• 제51권5호
• /
• pp.707-725
• /
• 2014

In order to improve the crane-hook's performance and service life, we formulate a multi-criteria shape design problem considering practical conditions. The structural weight, the displacement at specified points and the induced matrix norm of stiffness matrix are adopted as the evaluation items to be minimized. The heights and widths of cross-section are chosen as the design variables. The design variables are expressed in terms of shape functions based on the Gaussian function. For this multi-objective optimization problem with three items, we utilize a multi-objective evolutionary algorithm, that is, the multi-objective Particle Swarm Optimization (MOPSO). As a common feature of obtained solutions, the side views are tapered shapes similar to those of actual crane-hook designs. The evaluation item values of the obtained designs demonstrate importance of the present optimization as well as the feasibility of the proposed optimal design approach.

• 한국자동차공학회논문집
• /
• 제13권4호
• /
• pp.32-38
• /
• 2005

Two No Spin Differential(NSD) models were benchmarked for a project of Dual-Use Technology The Axiomatic approach was utilized to evaluate two models and to derive an evolutionary design from the evaluated results. Test methodology is developed and used to evaluate the mobility, steerability, durability and noise of the newly developed sample. The test results of NSD sample on the test methodology are very positive regarding functional performances.

• ETRI Journal
• /
• 제44권2호
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.