• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2003년도 가을 학술발표논문집 Vol.30 No.2 (2)
• /
• pp.769-771
• /
• 2003

PromSearch는 DNA 염기서열 상에서 프로모터의 위치를 예측하는 프로그램이다. 다루는 대상은 인간 DNA의 프로모터이며, 프로모터의 TSS(transcription start site, 전사시작지점)를 예측하는 것을 목표로 한다. 프로모터 영역을 세분하여 각 영역에 대한 프로파일을 PWM(position weight matrix)을 이용해 작성하며, 임의의 염기서열이 입력으로 주어지면 세분한 영역의 점수를 신경망을 이용해 통합하여 프로모터 여부와 TSS의 위치를 결정한다. 프로모터 영역의 분할은 코어 프로모터의 구성 요소인 TATA-box와 Inr, DPE(downstream promoter element), 그리고 코어 프로모터의 위쪽으로 150bp 크기의 영역 등으로 4분할하였다. Fickett의 데이터를 이용한 평가 결과 sensitivity 43%, specificity 88fp(1/376bp)의 성능을 보였다.

• Steel and Composite Structures
• /
• 제17권5호
• /
• pp.705-719
• /
• 2014

Composite steel-concrete box girders are frequently used in bridge construction for their economic and structural advantages. An integrated metaheuristic based optimization procedure is proposed for discrete size optimization of straight multi-span steel box girders with the objective of minimizing the self-weight of girder. The metaheuristic algorithm of choice is the Cuckoo Search (CS) algorithm. The optimum design of a box girder is characterized by geometry, serviceability and ultimate limit states specified by the American Association of State Highway and Transportation Officials (AASHTO). Size optimization of a practical design example investigates the efficiency of this optimization approach and leads to around 15% of saving in material.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.116-126
• /
• 2019

In this paper, an improved one-against-one support vector machine algorithm is used to classify multiple power quality disturbances. To solve the problem of parameter selection, an improved particle swarm optimization algorithm is proposed to optimize the parameters of the support vector machine. By proposing a new inertia weight expression, the particle swarm optimization algorithm can effectively conduct a global search at the outset and effectively search locally later in a study, which improves the overall classification accuracy. The experimental results show that the improved particle swarm optimization method is more accurate than a grid search algorithm optimization and other improved particle swarm optimizations with regard to its classification of multiple power quality disturbances. Furthermore, the number of support vectors is reduced.

• 복식
• /
• 제63권8호
• /
• pp.156-170
• /
• 2013

The purpose of this research is to scrutinize the cyclist's consumer behavior by analyzing the eWOM information search behavior of cycle-wear according to benefits sought and involvement. The research was conducted through an online survey and the respondents were 291 men who wore cycle-wear and searched information via online. The results of this research are as following. First, the benefits sought from wearing cycle apparel are composed of five sub-factors such as, ideal body figure, brand ostentation, comfort ease, personality, and economic feasibility. In addition, the cycle-wear involvement consisted of two sub-factors: cycling involvement and fashion involvement. Second, the eWOM information search behavior of cyclists was different depending on the benefits sought by the cyclists. When the cyclists pursued ideal body figure they searched more information of design and color, while cyclists put more weight on the information of design, color, and brand when they sought brand ostentation. Moreover, the valence and the type of the information were dissimilar depending on the benefits sought. Third, the sub-factors of eWOM information search behavior affected the eWOM effect distinctively. The price information was the only factor that influenced the eWOM effect among the contents of the information. The valence of the information influenced the eWOM effect, and the effect of positive information was stronger than negative information. Additionally, the subjective information also affected the eWOM effect. Lastly, the effect of the benefits sought influencing the eWOM information search behavior varied by the difference of the cycle-wear involvement. For example, when they are both high in the involvement there were various benefits sought affecting the eWOM information search behavior. However, when only the cycling involvement was high, and they pursued personality, the price information was not important to them.

• 대한조선학회논문집
• /
• 제52권1호
• /
• pp.1-7
• /
• 2015

The weight estimation of floating offshore structures such as FPSO, TLP, semi-Submersibles, Floating Offshore Wind Turbines etc. in the preliminary design, is one of direct measures of both construction cost and basic performance. Through both literature investigation and internet search, the weight data of floating offshore structures such as FPSO and TLP was collected. In this study, the weight estimation model with the genetic programming was suggested for FPSO. The weight estimation model using genetic programming was established by fixing the independent variables based on this data. In addition, the correlation analysis was performed to make up for the weak points of genetic programming; it is apt to induce over-fitting when the number of data is relatively smaller than that of independent variables. That is, by reducing the number of variables through the analysis of the correlation between the independent variables, the increasing effect in the number of weight data can be expected. The reliability of the developed weight estimation model was within 2% of error rate.

• ETRI Journal
• /
• 제29권3호
• /
• pp.336-352
• /
• 2007

Sequential pattern mining has become an essential task with broad applications. Most sequential pattern mining algorithms use a minimum support threshold to prune the combinatorial search space. This strategy provides basic pruning; however, it cannot mine correlated sequential patterns with similar support and/or weight levels. If the minimum support is low, many spurious patterns having items with different support levels are found; if the minimum support is high, meaningful sequential patterns with low support levels may be missed. We present a new algorithm, weighted interesting sequential (WIS) pattern mining based on a pattern growth method in which new measures, sequential s-confidence and w-confidence, are suggested. Using these measures, weighted interesting sequential patterns with similar levels of support and/or weight are mined. The WIS algorithm gives a balance between the measures of support and weight, and considers correlation between items within sequential patterns. A performance analysis shows that WIS is efficient and scalable in weighted sequential pattern mining.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 춘계학술대회 학술발표 논문집
• /
• pp.259-262
• /
• 1997

This paper presents a visual servoing of RV-M2 robot manipulators to track and grasp moving object, using pruned dynamic recurrent neural networks(DRNN). The object is stationary in the robot work space and the robot is tracking and grasping the object by using CCD camera mounted on the end-effector. In order to optimize the structure of DRNN, we decide the node whether delete or add, by mutation probability, first in case of delete node, the node which have minimum sum of input weight is actually deleted, and then in case of add node, the weight is connected according to the number of case which added node can reach the other nodes. Using evolutionary programming(EP) that search the struture and weight of the DRNN, and evolution strategies(ES) which train the weight of neuron, we pruned the net structure of DRNN. We applied the DRNN to the Visual Servoing of a robot manipulators to control position and orientation of end-effector, and the validity and effectiveness of the pro osed control scheme will be verified by computer simulations.

• 한국해양공학회지
• /
• 제17권6호
• /
• pp.38-46
• /
• 2003

Aim of this article is to propose Micro-Genetic Simulated Annealing (${\mu}GSA$) as a hybrid metaheuristics approach to find the global optimum of nonlinear optimisation problems. This approach combines the features of modern metaheuristics such as micro-genetic algorithm (${\mu}GAs$) and simulated annealing (SA) with the general robustness of parallel exploration and asymptotic convergence, respectively. Therefore, ${\mu}GSA$ approach can help in avoiding the premature convergence and can search for better global solution, because of its wide spread applicability, global perspective and inherent parallelism. For the superior performance of the ${\mu}GSA$, the five well-know benchmark test functions that were tested and compared with the two global optimisation approaches: scatter search (SS) and hybrid scatter genetic tabu (HSGT) approach. A practical application to structural sandwich panel is also examined by optimism the weight function. From the simulation results, it has been concluded that the proposed ${\mu}GSA$ approach is an effective optimisation tool for soloing continuous nonlinear global optimisation problems in suitable computational time frame.

• 지식경영연구
• /
• 제16권4호
• /
• pp.1-16
• /
• 2015

This paper aims to explore the small and medium sized enterprises'(SMEs') technological innovation through an open innovative strategy. Researchers have identified open innovation as external search 'breadth' and 'depth'. Although an open innovation strategy is well known as an effective way for SMEs' innovation, this stream of research examines differences between pursuing breadth of external knowledge and depth of external knowledge for SEMs' innovation. The sample comprises a total of 1106 SMEs included in the Korean Innovation Survey, and logistic regression analysis and odds ratio comparison were used to evaluate the relationship between external knowledge search and innovation outcomes. The results show that both 'breadth' and 'depth' positively affect the SMEs' innovation. When SMEs are simultaneously pursuing external searching for breadth and depth, however, a negative result on innovation outcome followed because of the lack of their internal resources and capacities. Despite these contributions, we have certain limitations that can be regarded as means of future research. Even though breadth and depth are adopted to measure the way of how a firm sources the external knowledge, companies may place the different weight on each source of knowledge. And also, it is difficult to understand how the knowledge gained through external search contributes to a firm's incremental and radical innovation, respectively.

• 한국산업융합학회 논문집
• /
• 제24권6_2호
• /
• pp.891-897
• /
• 2021

In this paper, we propose a destination optimal route algorithm for providing route finding service for the transportation handicapped by using the multi-criteria decision-making technique and the modified A-STAR optimal route search algorithm. This is a method to set the route to the destination centering on safety by replacing the distance cost of the existing A-STAR optimal route search algorithm with the safety cost calculated through AHP/TOPSIS analysis. To this end, 10 factors such as road damage, curb, and road hole were first classified as poor road factors that hinder road driving, and then pairwise comparison of AHP was analyzed and then defined as the weight of TOPSIS. Afterwards, the degree of driving safety was quantified for a certain road section in Busan through TOPSIS analysis, and the development of an optimal route search algorithm for the transportation handicapped that replaces the distance cost with safety in the finally modified A-STAR optimal route algorithm was completed.