• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.92-96
• /
• 2004

The researches of the emotions are currently great interest in speech processing as well as in human-machine interaction domain. In the recent years, more and more of researches relating to emotion synthesis or emotion recognition are developed for the different purposes. Each approach uses its methods and its various parameters measured on the speech signal. In this paper, we proposed using a short-time parameter: MFCC coefficients (Mel­Frequency Cepstrum Coefficients) and a simple but efficient classifying method: Vector Quantification (VQ) for speaker-dependent emotion recognition. Many other features: energy, pitch, zero crossing, phonetic rate, LPC... and their derivatives are also tested and combined with MFCC coefficients in order to find the best combination. The other models: GMM and HMM (Discrete and Continuous Hidden Markov Model) are studied as well in the hope that the usage of continuous distribution and the temporal behaviour of this set of features will improve the quality of emotion recognition. The maximum accuracy recognizing five different emotions exceeds $88\%$ by using only MFCC coefficients with VQ model. This is a simple but efficient approach, the result is even much better than those obtained with the same database in human evaluation by listening and judging without returning permission nor comparison between sentences [8]; And this result is positively comparable with the other approaches.

• Journal of the Korean Society for Library and Information Science
• /
• v.49 no.2
• /
• pp.291-311
• /
• 2015

This paper demonstrates the comparative analysis of the similarity and difference between Medical Subject Headings (MeSH) and social tags. Both types of metadata have the same purpose - that is, succinctly abstracting content of a given document - but are created from heterogeneous viewpoints. The former MeSH terms show the aspects of publication related professionals, whereas the latter social tags are from the perspectives of general readers. When both types of metadata are assigned to the same publications, do they consist of different nomenclatures reflecting the heterogeneous viewpoints or are they similar, since both metadata types describe the same publications? Social tags are also compared with family terms of MeSH terms in the given MeSH hierarchy, so as to understand the specificity of social tags, related to MeSH terms. Lastly, given the fact that readers assign social tags in casual ways without any restricted vocabulary, we tested how many social tags contain consumer health terms, which are familiar to laypeople. Through these comparisons, we ultimately aim to examine how much the highly controlled publication index reflects general readers' cognitive understandings and stress the necessity of general readers' involvement in the publication indexing process.

• Journal of the Korea Society of Computer and Information
• /
• v.6 no.4
• /
• pp.85-93
• /
• 2001

As progressing rapidly to the information society and increasing greatly the amount of information, many researchers have been made utilizing XML to store and retrieval the information effectively. But, many other existing method could not support various structured retrieval method for specific parent, children and sibling nodes. In this paper, we propose (1)an effective method of representation for structured information and of indexing mechanism using OETID(Ordered Element Type ID) for effective management and structured retrieval of the XML documents. Also it contains another proposal that is (2) a documents integration mechanism for retrieval result and storing technique to store structural information of the XML documents. With our methods, we could effectively represent structural information of XML documents, and could directly access the specific elements and process various queries by simple operations.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.63-77
• /
• 2011

The World Wide Web is a very large distributed digital information space. From its origins in 1991, the web has grown to encompass diverse information resources as personal home pasges, online digital libraries and virtual museums. Some estimates suggest that the web currently includes over 500 billion pages in the deep web. The ability to search and retrieve information from the web efficiently and effectively is an enabling technology for realizing its full potential. With powerful workstations and parallel processing technology, efficiency is not a bottleneck. In fact, some existing search tools sift through gigabyte.syze precompiled web indexes in a fraction of a second. But retrieval effectiveness is a different matter. Current search tools retrieve too many documents, of which only a small fraction are relevant to the user query. Furthermore, the most relevant documents do not nessarily appear at the top of the query output order. Also, current search tools can not retrieve the documents related with retrieved document from gigantic amount of documents. The most important problem for lots of current searching systems is to increase the quality of search. It means to provide related documents or decrease the number of unrelated documents as low as possible in the results of search. For this problem, CiteSeer proposed the ACI (Autonomous Citation Indexing) of the articles on the World Wide Web. A "citation index" indexes the links between articles that researchers make when they cite other articles. Citation indexes are very useful for a number of purposes, including literature search and analysis of the academic literature. For details of this work, references contained in academic articles are used to give credit to previous work in the literature and provide a link between the "citing" and "cited" articles. A citation index indexes the citations that an article makes, linking the articleswith the cited works. Citation indexes were originally designed mainly for information retrieval. The citation links allow navigating the literature in unique ways. Papers can be located independent of language, and words in thetitle, keywords or document. A citation index allows navigation backward in time (the list of cited articles) and forwardin time (which subsequent articles cite the current article?) But CiteSeer can not indexes the links between articles that researchers doesn't make. Because it indexes the links between articles that only researchers make when they cite other articles. Also, CiteSeer is not easy to scalability. Because CiteSeer can not indexes the links between articles that researchers doesn't make. All these problems make us orient for designing more effective search system. This paper shows a method that extracts subject and predicate per each sentence in documents. A document will be changed into the tabular form that extracted predicate checked value of possible subject and object. We make a hierarchical graph of a document using the table and then integrate graphs of documents. The graph of entire documents calculates the area of document as compared with integrated documents. We mark relation among the documents as compared with the area of documents. Also it proposes a method for structural integration of documents that retrieves documents from the graph. It makes that the user can find information easier. We compared the performance of the proposed approaches with lucene search engine using the formulas for ranking. As a result, the F.measure is about 60% and it is better as about 15%.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.648-653
• /
• 2008

With development of mobile communications terminal and expansion of mobile Internet, a large number of users can use mobile web contents at anytime and anywhere and will demand service of greater contents. Due to such demand, many studies are being carried out on transcoding contents so that wired web contents can be used in mobile web. However, transcoding and creation of mobile web contents involve difficulties because specifications available from telecommunications companies and mobile terminals have not been standardized. Especially, in order for serving dynamic object of wired web page contents to dynamically change according to time or user, it is required not only to program scripts to suit each terminal, but also to transcode the resources used in advance. For solution to this problem, this study uses the hierarchy structure of DOM (document object model) to display structural characteristics of wired web page. In other words, this study proposes the following technique Wired web pages are analyzed and the results are established as data structure. Then, dynamic object is extracted and the domain is indexed so that, when serving mobile web page, information can be extracted at the indexed position to create mobile web contents for service on real-time basis.

• The KIPS Transactions:PartD
• /
• v.14D no.3 s.113
• /
• pp.355-362
• /
• 2007

With development of mobile communications terminal and expansion of mobile Internet, a large number of users can use mobile web contents at anytime and anywhere and will demand service of greater contents. Due to such demand, many studies are being carried out on transcoding contents so that wired web contents can be used in mobile web. However, transcoding and creation of mobile web contents involve difficulties because specifications available from telecommunications companies and mobile terminals have not been standardized. Especially, in order for serving dynamic object of wired web page contents to dynamically change according to time or user, it is required not only to program scripts to suit each terminal, but also to transcode the resources used in advance. for solution to this problem, this study uses the hierarchy structure of DOM (document object model) to display structural characteristics of wired web page. In other words, this study proposes the following technique. Wired web pages are analyzed and the results are established as data structure. Then, dynamic object is extracted and the domain is indexed so that, when serving mobile web page, information can be extracted at the indexed position to create mobile web contents for service on real-time basis. Also, this study aims at developing an editing device to edit mobile web contents and mobile web service server to service the edited contents by applying the above technique.

• Journal of KIISE:Databases
• /
• v.31 no.5
• /
• pp.553-566
• /
• 2004

Some of the current main research areas involving techniques related to XML consist of storing XML documents, optimizing the query, and indexing. As such we may focus on the set of documents that are composed of various structures, but that are not shared with common structure such as the same DTD or XML Schema. In the case, it is essential to analyze structural similarities and differences among many documents. For example, when the documents from the Web or EDMS (Electronic Document Management System) are required to be merged or classified, it is very important to find the common structure for the process of handling documents. In this paper, we transformed sequential pattern mining algorithms(1) to extract maximal similar paths between two XML documents. Experiments with XML documents show that our transformed sequential pattern mining algorithms can exactly find common structures and maximal similar paths between them. For analyzing experimental results, similarity metrics based on maximal similar paths can exactly classify the types of XML documents.

• Journal of Korea Multimedia Society
• /
• v.7 no.10
• /
• pp.1452-1463
• /
• 2004

The requirement of automatic video summary is increasing as bi-directional broadcasting contents and various user requests and preferences for the bi -directional broadcast environment are increasing. Automatic video summary is needed for an efficient management and usage of many contents in service provider as well. In this paper, we propose a method to generate a content-based summary of linguistic educational videos automatically. First, shot-boundaries and keyframes are generated from linguistic educational video and then multiple(low-level) visual features are extracted. Next, the semantic parts (Explanation part, Dialog part, Text-based part) of the linguistic educational video are generated using extracted visual features. Lastly the XMI- document describing summary information is made based on HieraTchical Summary architecture oi MPEG-7 MDS (Multimedia I)escription Scheme). Experimental results show that our proposed algorithm provides reasonable performance for automatic summary of linguistic educational videos. We verified that the proposed method is useful ior video summary system to provide various services as well as management of educational contents.

• Journal of the Korean Society for information Management
• /
• v.25 no.1
• /
• pp.191-210
• /
• 2008

We would generally use subject terms such as subject indexing for searching and accessing documents. So then, there must be any relationship between document's full-text and its subject terms. This study is started in this question. Master's theses in field of science and technology are worked with because full-text is relatively formatted. This study is to study locations of subject term on Thesis, distribution patterns of subject terms on content of full-text; 'Contents', 'Introduction', 'Theory', 'Main subject', 'Conclusion' and 'References'. Thesis were averagely composed of 1226.3 terms. And Subject terms were averagely compose of $12{\sim}13$ terms. As a result, 'Contents' and 'Introduction' have had the most frequency of subject.

• Journal of Information Management
• /
• v.23 no.1
• /
• pp.39-62
• /
• 1992

In this paper about 60 auxiliary words and 320 stopwords are selected from analysis of sample data, four types of stop word are classified left, right and - auxiliary word truncation & normal. And a keyword extraction system is suggested which undertakes efficient truncation of auxiliary word from words, conversion of Chinese word to Korean and exclusion of stopword. The selected keyeords in this system show 92.2% of accordance ratio compared with manually selected keywords by expert. And then compound words consist of $4{\sim}6$ character generate twice of additional new words and 58.8% words of those are useful as keyword.