• Journal of KIISE:Databases
• /
• v.30 no.5
• /
• pp.464-475
• /
• 2003

few sample objects and compressed histogram information of image databases. The histogram information is used to estimate the selectivity of spherical range queries and a small number of sample objects is used to compensate the selectivity error due to the difference of the similarity measures between meta server and local image databases. An extensive experiment on a large number of image data demonstrates that our proposed method performs well in the distributed heterogeneous environment.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.145-155
• /
• 2002

In content-based image retrieval (CBIR), most conventional approaches assume a linear relationship between different features and require users themselves to assign the appropriate weights to each feature. However, the linear relationship assumed between the features is too restricted to accurately represent high-level concepts and the intricacies of human perception. In this paper, a neural network-based image retrieval (NNIR) model is proposed. It has been developed based on a human-computer interaction approach to CBIR using a radial basis function network (RBFN). By using the RBFN, this approach determines the nonlinear relationship between features and it allows the user to select an initial query image and search incrementally the target images via relevance feedback so that more accurate similarity comparison between images can be supported. The experiment was performed to calculate the level of recall and precision based on a database that contains 1,015 images and consists of 145 classes. The experimental results showed that the recall and level of the proposed approach were 93.45% and 80.61% respectively, which is superior than precision the existing approaches such as the linearly combining approach, the rank-based method, and the backpropagation algorithm-based method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.6
• /
• pp.81-96
• /
• 2021

This study examines the importance of factors that influence the online platform selection decision to support operational optimization strategies. For the research purpose, we first reviewed previous studies on service encounters and identified those factors that have been proven important for using online platforms. Second, this study analyzed the factors that customers perceived as important based on analytical hierarchy process (AHP) of the data we collected from 10 mobile or computer-based Internet users. The study results revealed that the important factors for the online platform selection were in the following order: product diversity (27.4%), ease of use (21.5%), brand credibility (18.1%), interactions with the service provider (17.7%), and ease of accessibility (15.3%). The study provides useful insights to online platform service providers in developing strategies for customer-focused value creation.

• The KIPS Transactions:PartB
• /
• v.17B no.5
• /
• pp.399-404
• /
• 2010

In this paper, we propose a method for precision improvement based on core clusters and term proximity. The method is composed by three steps. The initial retrieval documents are clustered based on query term combination, which occurred in the document. Core clusters are selected by using proximity between query terms. Then, the documents in core clusters are reranked based on context information of query. On TREC AP test collection, experimental results in precision at the top documents(P@100) show that the proposed method improved 11.2% over the language model.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.51-55
• /
• 2016

본 논문에서는 임상 의사 결정 지원을 위한 UMLS와 위키피디아를 이용하여 지식 정보를 추출하고 질병 중심 문서 클러스터와 단어 의미 표현을 이용하여 질의 확장 및 문서를 재순위화하는 방법을 제안한다. 질의로는 해당 환자가 겪고 있는 증상들이 주어진다. UMLS와 위키피디아를 사용하여 병명과 병과 관련된 증상, 검사 방법, 치료 방법 정보를 추출하고 의학 인과 관계를 구축한다. 또한, 위키피디아에 나타나는 의학 용어들에 대하여 단어의 효율적인 의미 추정 기법을 이용하여 질병 어휘의 의미 표현 벡터를 구축하고 임상 인과 관계를 이용하여 질병 중심 문서 클러스터를 구축한다. 추출한 의학 정보를 이용하여 질의와 관련된 병명을 추출한다. 이후 질의와 관련된 병명과 단어 의미 표현을 이용하여 확장 질의를 선택한다. 또한, 질병 중심 문서 클러스터를 이용하여 문서 재순위화를 진행한다. 제안 방법의 유효성을 검증하기 위해 TREC Clinical Decision Support(CDS) 2014, 2015 테스트 컬렉션에 대해 비교 평가한다.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.8
• /
• pp.9-15
• /
• 2013

As the resources of cloud computing are essentially heterogeneous and jobs have various characteristics, resource allocation to jobs is one of important problems. We define this issue as a multi-criteria decision-making problem. This paper proposes a priority-based job scheduling algorithm based on analytic hierarchy process (AHP). On the first step, jobs are classified based on their preferences. On the second step, response time, system utilization, and load becomes decision criteria based on the AHP algorithm. Jobs are allocated to adequate resources through their priorities that are calculated by the AHP algorithm. Through analysis and experiment of the proposed algorithm, we are to confirm that the scheme can schedule jobs as well as utilize its resource efficiently.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.753-756
• /
• 2004

유비쿼터스 컴퓨팅 환경에서 추천시스템은 무수히 많은 정보들에 대하여 사람들이 적절한 선택을 할 수 있도록 도와준다. 사용자에게 필요한 정보를 찾아주고, 정보들의 우선순위를 결정해주는 추천시스템에 있어서 사용자의 위치는 보다 가치있는 정보를 제공할 수 있는 도구가 된다. 위치기반 추천시스템은 사용자가 아이템들로부터 얼마나 멀리 떨어져있는가를 고려하여 상위 리스트들을 제공할 수 있어야 한다. 하지만 일반적인 추천시스템에서 주로 사용되고 있는 기존의 사용자 기반 협업필터링 기법은 사용자의 자발적인 정보 입력에 의존함으로써 일정한 수의 사용자 정보가 축적되어 있지 않으면 정확한 추천이 불가능한 단점이 있다. 본 논문에서는 아이템에 기반한 협업 필터링 기법을 확률적으로 분석하고, 아이템의 위치에따라 랭킹을 부여하는 방법과 사용자의 위치정보를 추천알고리즘에 적용시켜 보다 정확하고 효율적인 추천방법을 제안하였다.

• International Journal of Highway Engineering
• /
• v.14 no.3
• /
• pp.151-162
• /
• 2012

It is not surprising to hear news about irresistible natural disasters all over the world due to climate change. Korean Government has focused on developing a variety of green technologies to reduce green house gasses, in particular, carbon dioxide. This study suggested 18 technology divisions for achieving green highway technology development in six different sub-sectors considering life-cycle of roadway and surveyed 29 highway and/or transportation professionals of three institutes using AHP(Analytical Hierarchy Process) analysis to construct "Green Highway"and realize carbon emission reductions and energy use efficiency in a road sector in Korea. Expert Choice Software was used to rank 18 technology divisions weighted by two-level choices. Transport Operating Infrastructure Improvement, Roadway Policy Implementation, Green Transportation(such as Pedestrian and Bicycle) were highly ranked by respondents according to results of the AHP modeling. Among the 18 divisions, technology policy for supporting R&D investments from development to commercialization was ranked as the most significant one to be focused. Green Transportation Facility Design/Construction/Operation and Eco-Friendly Roadway Plan were followed as expected since professionals have thought that the planning/design step of the life-cycle is a starting point to reduce carbon dioxide from roads more and more. Additionally, comparing the results with the Government investment trend 2006-2011 for the roads, it can be interpreted that the Government should invest to the R&D area more widely than before to promote element and core technology development for Green Highway Construction. Above all, small and mid-sized businesses have to be invested as well as encouraged to undertake green highwayrelated objects to accomplish the divisions which ranked high.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2006.06a
• /
• pp.381-384
• /
• 2006

인터넷과 IT 인프라의 증가는 인터넷 기반의 전자상거래 시스템의 성장을 주도하였고, 이와 관련된 새로운 형태의 서비스가 나타나는 계기가 되었다. 그러나, 현재 전자상거래 서비스는 구매자가 웹에 접속하여 인터넷 쇼핑몰에 보이는 상품을 선택하여 결제 및 상품을 수신하는 방식으로 이루어진다. 또한 구매 판단을 결정할 때 최저가격 외에 신속한 배송, 부가 서비스 등의 다양한 의사결정 요소가 있음에도 불구하고, 인터넷 쇼핑몰에서 제시한 최저가의 판단요소에 의존함으로 구매자가 수동적인 입장이 된다. 따라서, 본 논문에서는 이러한 문제점을 해결하기 위해 상호간에 의견교환 및 사용자가 정한 우선순위에 따른 판단을 효과적으로 할 수 있는 서비스인 게임이론 기반의 지능모델을 제시한다 게임이론은 전통적으로 경제문제 협상과 정치문제 협상, 워 게임 등에 적용되었다. 본 연구에서는 이 점에 착안하여 게임이론 알고리듬을 이용하여 e-Commerce를 위한 지능모델에 적용하여, 기존의 수동적이고 사용자의 취향에 따라 다양한 의사결정 요소를 선택 할 수 없었던 문제를 해결한다.

• Journal of Korea Multimedia Society
• /
• v.14 no.3
• /
• pp.378-391
• /
• 2011

In this paper, we suggest a novel method of selecting visual information based on bottom-up visual attention of human. We propose a new model that improve accuracy of detecting attention region by using depth information in addition to low-level spatial features such as color, lightness, orientation, form and temporal feature such as motion. Motion is important cue when we derive temporal saliency. But noise obtained during the input and computation process deteriorates accuracy of temporal saliency Our system exploited the result of psychological studies in order to remove the noise from motion information. Although typical systems get problems in determining the saliency if several salient regions are partially occluded and/or have almost equal saliency, our system is able to separate the regions with high accuracy. Spatiotemporally separated prominent regions in the first stage are prioritized using depth value one by one in the second stage. Experiment result shows that our system can describe the salient regions with higher accuracy than the previous approaches do.