• Journal of the Korean association of regional geographers
• /
• v.21 no.3
• /
• pp.569-582
• /
• 2015

This study deals with six spa touristy places to analyze the similarity in image and selection factor recognition through multidimensional scaling method. The result is as following. First, as a result of analysis in the similarity in Image of the 6 touristy Spa places, each "Asan and Onyang" and "Suanbo and Ducksan" form different similar image groups. However, Yoosung does not share the similarity in Image that other Spa places own. Second, as a result of analysis of selection factors in the six touristy spa places, it is found out that there is no big difference in selection factors such as 'spa facility', 'a fee to use', and 'quality of service' in the six spa places. Yet, Onyang, Yoosung, Ducksan, and Suanbo spa reflect high selection factor as 'a recognized spa place' different from Asan and Dogo where the reflection of selection factor is low. Onyang, Yoosung, and Dogo regions reflect high selection factor as a 'Touristy destination' while Asan reflects low selection factor.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.197-200
• /
• 2010

단백질의 서열 정보와 기능 정보의 양이 증가함에 따라 컴퓨터 실험을 통한 단백질의 기능 예측이 가능해졌으며 정확성이 높은 예측 시스템을 개발하려는 여러 연구가 시도되고 있다. 대표적인 방법으로 서열 유사도를 기반으로 기능 예측을 하는 시스템이 제안되었으나 단백질 중에는 서열이 유사하지만 기능이 다르거나 또는 서열은 다름에도 불구하고 기능이 같은 단백질이 존재하기 때문에 서열의 유사도 만을 이용해서는 단백질의 기능 예측을 어렵다. 이러한 유사도 방법의 단점을 극복하기 위해 단백질 서열로부터 추출한 특징을 기반으로 분류하는 방법도 제안되었다. 본 논문에서는 이러한 기존 방법들의 장점을 얻기 위하여 서열 유사도 방법과 특징 기반 방법을 융합한 단백질 기능 예측 시스템을 제안하고 예측 정확성 분석을 위한 실험을 실시하였다. 실험의 결과에 따르면 제안된 융합시스템이 서열 유사도만을 이용한 방법과 특징 기반 방법보다 좋은 예측 정확률을 갖는 것으로 분석되었다.

• Smart Media Journal
• /
• v.8 no.4
• /
• pp.25-32
• /
• 2019

While the development of the Internet has made information more accessible, this also has provided a variety of intrusion paths for malicious programs. Traditional Signature-based malware-detectors cannot identify new malware. Although Dynamic Analysis may analyze new malware that the Signature cannot do, it still is inefficient for detecting variants while most of the behaviors are similar. In this paper, we propose a detection method using behavioral similarity with existing malicious codes, assuming that they have parallel patterns. The proposed method is to extract the behavior targets common to variants and detect programs that have similar targets. Here, we verified behavioral similarities between variants through the conducted experiments with 1,000 malicious codes.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10a
• /
• pp.7-9
• /
• 2003

최근 인터넷을 대상으로 하는 정보검색의 방법 중 하이퍼링크 정보를 이용한 방법이 각광받고 있다. 그리고 하이퍼링크 정보이외에 문서내에 존재하는 다양한 정보를 이용하여 검색 성능을 향상시키고자 하는 시도가 지속적으로 이루어지고 있다. 본 연구에서는 문서와 문서 사이의 유사도를 이용하여 하이퍼링크의 가중치를 부설하여 검색 성능을 향상시킨 방법을 개선하여 문서내의 주제정보를 추출하고 주제 단위의 유사도를 이용하여 하이퍼링크의 가중치를 새롭게 부여하여 링크분석 알고리즘에 적용하였다. 본 연구에서 제안한 방법이 문서사이의 유사도를 이용한 방법보다 뛰어난 성능을 나타내고 있음이 입증되었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.6
• /
• pp.119-121
• /
• 1998

For a fuzzy system modeled by a fuzzy hypergraph, two fuzzy similarity measures are proposed:one for the fuzzy similarity between fuzzy sets and the other between elements in fuzzy sets. The proposed measures can represent the realistic similarities which can not be given by the existing measures. With an example, it is shown that it can be used in the system analysis.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.2
• /
• pp.181-188
• /
• 2018

In this paper, we propose an analysis scheme of customer spending pattern using text mining. In proposed consumption pattern analysis scheme, first we analyze user's rating similarity using Pearson correlation, second we analyze user's review similarity using TF-IDF cosine similarity, third we analyze the consistency of the rating and review using Sendiwordnet. And we select the nearest neighbors using rating similarity and review similarity, and provide the recommended list that is proper with consumption pattern. The precision of recommended list are 0.79 for the Pearson correlation, 0.73 for the TF-IDF, and 0.82 for the proposed consumption pattern. That is, the proposed consumption pattern analysis scheme can more accurately analyze consumption pattern because it uses both quantitative rating and qualitative reviews of consumers.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.808-809
• /
• 2017

유사도 검색은 전통적으로 데이터베이스 그리고 웹검색 분야의 핵심이었으나, 대용량 데이터의 등장으로 검색의 정확도뿐만이 아니라 효율성 측면에서의 요구가 증가하며 여전히 다양한 분야에서 활발히 연구되고 있다. 아이템간의 유사도를 측정하기 위한 방법론 중 코사인 유사도 방법론은 고차원공간에서의 활용이 유리하다는 이점 때문에 가장 널리 활용되고 있는 방법론으로, 정보검색, 장바구니 분석, 생물정보학 등 다양한 분야에서 활용되고 있다. 본 논문에서는 코사인 유사도를 소개하고, 연관성 분석 측면에서 코사인 유사도를 사용한 기존의 연구들을 소개한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.5
• /
• pp.1013-1021
• /
• 2014

For efficient investments of government budgets, It is important to analyze the similarities of R&D projects. So, existing studies have proposed a techniques for analyzing similarities using keywords or segments. However, the techniques have low accuracy. We propose a technique for similarities of projects using patent information. To achieve our goal, we suggest three metrics that are based some mathematic theories; set theory and probability theory. In order to validate our technique, we perform case studies that have 156 R&D projects and 160,218 patent informations.

• Journal of Korea Spatial Information System Society
• /
• v.9 no.1
• /
• pp.59-77
• /
• 2007

Advances in mobile techknowledges and supporting techniques require an effective representation and analysis of moving objects. Similarity search of moving object trajectories is an active research area in data mining. In this paper, we propose a trajectory search algorithm for spatio-temporal similarity of moving objects on road network. For this, we define spatio-temporal distance between two trajectories of moving objects on road networks, and propose a new method to measure spatio-temporal similarity based on the real road network distance. In addition, we propose a similar trajectory search algorithm that retrieves spatio-temporal similar trajectories in the road network. The algorithm uses a signature file in order to retrieve candidate trajectories efficiently. Finally, we provide performance analysis to show the efficiency of the proposed algorithm.

• KIISE Transactions on Computing Practices
• /
• v.24 no.3
• /
• pp.145-150
• /
• 2018

Forwarding in opportunistic networks shows low performance because there may be no connecting paths between the source and the destination nodes due to the intermittent connectivity. Currently, social network analysis has been researched. Specifically, similarity is one of methods of social networks analysis. In this paper, we propose forwarding schemes based on representative similarities, and evaluate how much the forwarding performance increases. As a result, since the forwarding schemes are based on similarities, these schemes only forward messages to nodes with higher similarity as relay nodes, toward the destination node. These schemes have low network traffic and hop count while having stable transmission delay.