• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.952-959
• /
• 2018

Clustering is one of the most fundamental algorithms in machine learning. The performance of clustering is affected by the distribution of data, and when there are more data or more dimensions, the performance is degraded. For this reason, we use a stacked auto encoder, one of the deep learning algorithms, to reduce the dimension of data which generate a feature vector that best represents the input data. We use k-means, which is a famous algorithm, as a clustering. Sine the feature vector which reduced dimensions are also multi dimensional, we use the Euclidean distance as well as the cosine similarity to increase the performance which calculating the similarity between the center of the cluster and the data as a vector. A deep clustering networks combining a stacked auto encoder and k-means re-trains the networks when the k-means result changes. When re-training the networks, the loss function of the stacked auto encoder and the loss function of the k-means are combined to improve the performance and the stability of the network. Experiments of benchmark image ad document dataset empirically validated the power of the proposed algorithm.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.637-641
• /
• 2006

To use multimedia contents in restricted resources, any management method of MPEG-7 documents is needed. At this time, some XML clustering methods can be used. But, to improve the performance efficiency better, new clustering method which uses the characteristics of MPEG-7 documents is needed. In this paper, we suggest a new clustering method to manage MPEG-7 documents efficiently, which uses some semantic relationships among elements of MPEG-7 documents. And also we compare it to the existed clustering methods.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.06a
• /
• pp.393-398
• /
• 2001

특정 영역에 대해 사용자에게 관련 정보를 제공해 주는 서비스를 하는 정보 에이전트를 개발 중이다. 정보 에이전트는 사용자 질의 처리를 달은 Agent Manager와 지식베이스를 관리하는 KB Manager, 그리고 Web으로부터 해당 영역의 관련 문서를 끌어오는 Web Manager로 구성되어 있다. Web Manager는 방문할 URL을 수집하고, 이들 문서에 대한 관련 평가와 Indexing을 수행한다. Web Manager는 검색 엔진을 이용하거나, 방문한 문서의 link를 이용하여 URL을 수집하는데 이러한 URL수집기법은 많은 관련 문서를 놓치는 문제점이 있다. 이 문제점을 해결하기 위해서 해당 영역과 관련된 Site들을 대상으로 Link를 이용해 문서들을 모아와, 문서들을 TAG들의 패턴으로 얻어낸 문서 형식을 이용해 Clustering하며 관련 문서들의 Group을 찾아내는 적극적 문서 수집 기법을 제안한다. 실험 결과, Link와 Clustering을 이용할 경우 기존보다 효과적으로 관련 문서를 많이 수집할 수 있음을 알 수 있다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.3
• /
• pp.231-237
• /
• 2008

This research proposes a modified version of single pass algorithm specialized for text clustering. Encoding documents into numerical vectors for using the traditional version of single pass algorithm causes the two main problems: huge dimensionality and sparse distribution. Therefore, in order to address the two problems, this research modifies the single pass algorithm into its version where documents are encoded into not numerical vectors but other forms. In the proposed version, documents are mapped into tables and the operation on two tables is defined for using the single pass algorithm. The goal of this research is to improve the performance of single pass algorithm for text clustering by modifying it into the specialized version.

• Journal of the Korean Society for Library and Information Science
• /
• v.41 no.1
• /
• pp.345-372
• /
• 2007

In this study, the intellectual structure of Records Management & Archival Science in Korea was analyzed using document clustering, a widely used method of text mining, and document similarity network analysis. The data used in this study were 145 articles written on the subject of Records Management & Archival Science selected from five major representative journals in the field of Library & Information Science in Korea, published from 2001 to 2006. The results of cluster analysis show that the core subject areas are "electronic records management and digital Preservation," "records management policy and institution," "records description and catalogues." and "records management domain and education." The results of document analysis, which is more detailed than cluster analysis, show that "digital archiving," a specialized subject in digital preservation, plays a central role. The results of serial analysis, which proceeds according to a timeline, show the emergence of "archival services" as a new subject area.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.535-540
• /
• 2021

Multi-document refers to a document consisting of various topics, not a single topic, and a typical example is online reviews. There have been several attempts to summarize online reviews because of their vast amounts of information. However, collective summarization of reviews through existing summary models creates a problem of losing the various topics that make up the reviews. Therefore, in this paper, we present method to summarize the review with minimal loss of the topic. The proposed method classify reviews through processes such as preprocessing, importance evaluation, embedding substitution using BERT, and embedding clustering. Furthermore, the classified sentences generate the final summary using the trained Transformer summary model. The performance evaluation of the proposed model was compared by evaluating the existing summary model, seq2seq model, and the cosine similarity with the ROUGE score, and performed a high performance summary compared to the existing summary model.

• The Journal of the Korea Contents Association
• /
• v.9 no.12
• /
• pp.19-30
• /
• 2009

The service that has recently come into the spotlight utilizes the map to first approach the map and then provide various mash-up formed results through the interface. This service can provide precise information to the users but the map is barely reusable. The sketch-map system of this paper, unlike the existing large map system, uses the method of presenting the specific spot and route in XML document and then clustering among sketch-maps. The map service system is designed to show the optimum route to the destination in a simple outline map. It is done by renovating the spot presented by the map into optimum contents. This service system, through the process of analyzing, splitting and clustering of the sketch-map's XML document input, creates a valid form of a sketch-map. It uses the LCS(Longest Common Subsequence) algorithm for splitting and merging sketch-map in the process of query. In addition, the simulation of this system's expected effects is provided. It shows how the maps that share information and knowledge assemble to form a large map and thus presents the system's ability and role as a new research portal.

• The KIPS Transactions:PartB
• /
• v.15B no.5
• /
• pp.493-500
• /
• 2008

Although modern day people gather many data from the network, the users want only the information needed. Using this technology, the users can extract on the data that satisfy the query. As the previous studies use the single data in the document, frequency of the data for example, it cannot be considered as the effective data clustering method. What is needed is the effective clustering technology that can process the electronic network documents such as the e-mail or XML that contain the tags of various formats. This paper describes the study of extracting the information from the user query based on the multi-attributes. It proposes a method of extracting the data such as the sender, text type, time limit syntax in the text, and title from the e-mail and using such data for filtering. It also describes the experiment to verify that the multi-attribute based clustering method is more accurate than the existing clustering methods using only the word frequency.

• Journal of KIISE:Databases
• /
• v.34 no.3
• /
• pp.261-269
• /
• 2007

As a basic research to integrate and to retrieve XML documents efficiently, this paper proposes a clustering method by structures of XML documents. We apply an algorithm processing the many transaction data to the clustering of XML documents, which is a quite different method from the previous algorithms measuring structure similarity. Our method performs the clustering of XML documents not only using the cluster histograms that represent the distribution of items in clusters but also considering the global cluster cohesion. We compare the proposed method with the existing techniques by performing experiments. Experiments show that our method not only creates good quality clusters but also improves the processing time.

• Proceedings of the Korean Society for Information Management Conference
• /
• 1999.08a
• /
• pp.25-28
• /
• 1999

자동분류나 정보검색에 주로 이용되는 문헌 클러스터링에서는 문헌간의 유사성을 측정하기 위해 다양한 유사계수를 이용하는데, 모든 유사계수가 동일한 클러스터링 결과를 가져오는 것은 아니다. 본고에서는 50건의 신문기사를 대상으로 SPSS 통계 패키지를 이용하여 다양한 유사계수에 각각 달라지는 문헌 클러스터링의 결과를 살펴본 후, 유사계수간의 연관성을 측정하였다.