• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.1-9
• /
• 2002

Evolutionary artificial neural networks (EANNs) are towards the near optimal ANN using the global search of evolutionary instead of trial-and-error process. However, many real-world problems are too hard to be solved by only one ANN. Recently there has been plenty of interest on combining ANNs in the last generation to improve the performance and reliability. This paper proposes a new approach of constructing multiple ANNs which complement each other by speciation. Also, we develop a multiple ANN to combine the results in abstract, rank, and measurement levels. The experimental results on Australian credit approval data from UCI benchmark data set have shown that combining of the speciated EANNs have better recognition ability than EANNs which are not speciated, and the average error rate of 0.105 proves the superiority of the proposed EANNs.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.3
• /
• pp.1-14
• /
• 2008

Mass transit information should contribute many benefits to users. Especially transportation information technology is developing highly with information technology in Korea recently. Hereafter it is expected to provide customized transportation information to users individually with the advent of ubiquitous age in earnest. This public transportation information service can be realized by path finding algorithms in public transportation networks including travel and transfer attributes. In this research, multi objectives such as travel time, transfer time, and number of transfer and so on are constructed with the primary facts influencing users. Moreover, the method reducing user's path finding alternatives arbitrarily is proposed by selecting the best alternative which provides maximum utility to users among non dominated paths. Therefore, the ultimate goal of this study proposes a multi objective shortest paths finding algorithm which can take into account multiple user classes in a transit network with multiple travel modes. The proposed algorithm is demonstrated based on the two case studies - a small toy network and the large-scaled Seoul Metropolitan subway network.

• Journal of Internet Computing and Services
• /
• v.10 no.3
• /
• pp.131-140
• /
• 2009

Recently, the information visualization research community has given significant attention to graph visualization, especially visualization of social networks. However, visualization of information flows in a very large social network has not been studied in depth. However, information flows are tightly related to the structure of social networks and it shows dynamic behavior of interactions between members of social networks. Thus, we can get much useful information about social networks from information flows. In this paper, we present our research result that enables users to navigate a very large social network in Google Maps' method and to take a look at information flows on the network. To this end, we devise three techniques; (i) mapping a very large social network to a 2-dimensional graph layout, (ii) exploring the graph to all directions with zooming it in/out, and (iii) building an efficient query processing framework. With these methods, we can visualize very large social networks and information flows in a limited display area with a limited computing resources.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.2
• /
• pp.1-14
• /
• 2024

The most optimal route-search algorithm thus far has introduced a method of applying node labels and link labels. Node labels consider two nodes simultaneously in the optimal route-search process, while link labels consider two links simultaneously. This study proposes a turn-label-based optimal route-search technique that considers two turns simultaneously in the process. Turn-label-based optimal route search guarantees the optimal solution of dynamic programming based on Bellman's principle as it considers a two-turn search process. Turn-label-based optimal route search can accommodate the advantages of applying link labels because the concept of approaching the limit of link labels is applied equally. Therefore, it is possible to reflect rational cyclic traffic where nodes allow multiple visits without expanding the network, while links do not allow visits. In particular, it reflects the additional cost structure that appears in two consecutive turns, making it possible to express the structure of the travel-cost function more flexibly. A case study was conducted on the metropolitan urban railway network consisting of transportation card terminal readers, aiming to examine the scalability of the research by introducing parameters that reflect psychological resistance in travel with continuous pedestrian transfers into turn label optimal path search. Simulation results showed that it is possible to avoid conservative transfers even if the travel time and distance increase as the psychological resistance value for continuous turns increases, confirming the need to reflect the cost structure of turn labels. Nevertheless, further research is needed to secure diversity in the travel-cost functions of road and public-transportation networks.

• Journal of Labour Economics
• /
• v.25 no.1
• /
• pp.1-21
• /
• 2002

This study presents an empirical analysis of job search behaviors by using the 3rd Korean Labor and Income Panel Study (KLIPS) data. The first finding of the study is that specific job search methods, respectively categorized as the indirect and the formal pattern, show the contrasting consequences of causality, as given job searchers'personal attributes and other social factors. Secondly, this analysis confirms that job searchers' education level is the most important factor that influences their behavioral patterns in a consistent manner. Moreover, it is evident in this exploratory study that job searchers' social network (particularly whether to have close ties with relatives of high social rank) is a statistically important factor to influence the extent of job search methods in use, while their fathers' education level also significantly affects the choice of job search patterns.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11b
• /
• pp.713-716
• /
• 2003

현재 국내 LBS 가 중요한 서비스로 널리 확산되기 위해서는 서비스간의 상호운용성이 제공되어야 한다. 본 논문에서는 LBS 서비스간 상호운용성을 제공하는 개방형 LBS 를 위한 경로탐색 서비스에 대한 설계 및 구현기법을 제시한다. 최단경로문제(Shortest Path Problem)는 통신망 및 교통망의 분석, 생산라인의 품질 관리 등의 다양한 분야 등의 네트워크 흐름 최적화 문제 중에서 가장 많이 연구되고 있는 문제다. 도로 교통망에서는 교차로상에서의 회전 제약 문제 등의 제한조건이 존재한다. 본 논문에서 경로탐색은 듀얼 그래프(dual graph)를 이용하여 회전제약조건을 만족하는 경로를 구할 수 있었고, 사용자 경로탐색 기준에 따른 탐색기법도 제시한다. 또한, 구현된 서비스는OpenLS의 표준화된 인터페이스를 구현하여 상호운용성(interoperability)을 지원하며, 자바를 이용한 웹서비스로 구현되어 이식성, 운영체제 및 프로그래밍 언어 독립성을 제공할 수 있는 장점이 있다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11b
• /
• pp.1031-1034
• /
• 2003

향후 무선인터넷 망이 완전히 개방되면 다양한 포털, 컨텐츠 사업자가 등장할 것이다. 이는 사용자에게는 다양한 서비스를 받을 수 있는 장점이 있지만 현재 휴대폰에서의 모바일 인터넷 컨텐츠 탐색 시 발생하는 사용성 문자를 한층 더 증대 시킬 것으로 예상된다. 기존의 연구들은 단일 포털 업체만을 대상으로 연구를 하였기 때문에 여러 포털 업체에서 제공하고 있는 컨텐츠들을 적절히 탐색할 수 있는 기법에 대해서는 아직 연구가 부족하다. 본 논문에서는 시멘틱 웹 구현 기법 중 하나인 토픽맵을 이용하여 효율적으로 모바일 인터넷 컨텐츠를 탐색하고 관리할 수 있는 기법을 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.51-53
• /
• 2000

기존의 진화 연산의 한계를 극복하기 위해서 탐색점 분포 학습 알고리즘(Estimation of Distribution Algorithm)이 부각되고 있다. 탐색점 분포 학습 알고리즘은 데이터의 분포를 파악하고, 파악된 분포를 이용해서 새로운 학습 데이터를 생성하는 일련의 과정을 통하여 최적화 문제를 해결하는 방법이다. 그런데, 기존의 탐색점 분포 학습 알고리즘들은 대부분 이진 벡터값을 가지는 최적화 문제들만을 대상으로 하고 있다. 본 논문에서는 비감독 확률 신경망 모델인 헬름홀츠 머신을 이용해서 데이터의 분포를 학습하여 연속 함수 최적화 문제를 해결하는 방법을 개발하였다. 테스트 함수들에 대해서 실수 표현형을 사용한 유전자 알고리즘과 결과를 비교하여 제안하는 방법의 우수성을 검증하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.1330-1331
• /
• 2009

본 연구에서는 GERAN (GSM EDGE Radio Access Network) 망에서 다양한 무선환경에 따른 셀 재탐색을 연구하였으며, 시계열분석을 통하여 재탐색 이후의 RSS (Received Signal Strength)를 예측하여 개선된 재탐색 알고리즘을 연구하였다. Field 데이터를 통해 제안된 알고리즘을 분석하였으며, 이를 통하여 다양한 조건에 적합한 기법을 제안코저 한다.

• Journal of the Korea Convergence Society
• /
• v.10 no.10
• /
• pp.173-183
• /
• 2019

The purpose of research is to explore the direction of building a collaborative supply chain, which may enhance the competitiveness of firms and their project-based supply chain. Large-scale plants or large-scale buildings construction is referred to as a EPC project. To identify a collaboration mechanism in the project-based supply chain, the empirical research was conducted on the interrelationship between the absorption capacity of firms participating in the EPC project, the incentive norms, the goal congruence with supply chain, and the ability of respond to changes of the task of supply chain. PLS-SEM was used as an analysis method to verify the research model. It is expected that the results will help inform the need for SCM, the importance of the incentive norms and the goal congruence in the supply chain of EPC project.