• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2612-2633
• /
• 2020

Due to the explosive growth of multimedia speech data, how to protect the privacy of speech data and how to efficiently retrieve speech data have become a hot spot for researchers in recent years. In this paper, we proposed an encrypted speech retrieval scheme based on long short-term memory (LSTM) neural network and deep hashing. This scheme not only achieves efficient retrieval of massive speech in cloud environment, but also effectively avoids the risk of sensitive information leakage. Firstly, a novel speech encryption algorithm based on 4D quadratic autonomous hyperchaotic system is proposed to realize the privacy and security of speech data in the cloud. Secondly, the integrated LSTM network model and deep hashing algorithm are used to extract high-level features of speech data. It is used to solve the high dimensional and temporality problems of speech data, and increase the retrieval efficiency and retrieval accuracy of the proposed scheme. Finally, the normalized Hamming distance algorithm is used to achieve matching. Compared with the existing algorithms, the proposed scheme has good discrimination and robustness and it has high recall, precision and retrieval efficiency under various content preserving operations. Meanwhile, the proposed speech encryption algorithm has high key space and can effectively resist exhaustive attacks.

• Journal of Korean Library and Information Science Society
• /
• 제30권3호
• /
• pp.405-426
• /
• 1999

Academic societies in the field of science and technology are major producers of domestic research information. These information are very important sources to researchers, students and so on. KORDIC built an integrated information system which facilitates the progress of building databases and promotes users easy access to databases. In order to build efficient society research information system, we investigated former cases and analyzed requirement of each society. We identified principal information sources and built an integrated information service system using internet homepage and information retrieval system(KRISTAL-II). In the future we will expand participating societies and focus on text-based information.

• Journal of radiological science and technology
• /
• 제28권1호
• /
• pp.19-24
• /
• 2005

The purpose of this study was to design and implement a useful annotation-based Radiological image retrieval system to accurately determine on education and image information for Radiological technologists. For better retrieval performance based on large image databases, we presented an indexing technique that integrated $B^+-tree$ proposed by Bayer for indexing simple attributes and inverted file structure for text medical keywords acquired from additional description information about Radiological images. In our results, we implemented proposed retrieval system with Delphi under Windows XP environment. End users, Radiological technologists, are able to store simple attributes information such as doctor name, operator name, body parts, disease and so on, additional text-based description information, and Radiological image itself as well as to retrieve wanted results by using simple attributes and text keywords from large image databases by graphic user interface. Consequently proposed system can be used for effective clinical decision on Radiological image, reduction of education time by organizing the knowledge, and well organized education in the clinical fields. In addition, It can be expected to develop as decision support system by constructing web-based integrated imaging system included general image and special contrast image for the future.

• Journal of the Korea Society of Computer and Information
• /
• 제10권4호
• /
• pp.155-164
• /
• 2005

WThe education information have been increased. Accordingly, the necessary of developing on education information metadata standards has been increased. By the reason, the Korea Education & Research Information Service developed KEM(Korea Educational Metadata) 2.0. And MPEG-7 was developed to describe metadata of multimedia data. In this paper, we developed a education information image retrieval system. This system used XML schema to accept education information image metadata. We integrated contents-based retrieval and a semantic-based retrieval to overcome there problems that content-based retrieval system can not support semantic-based retrieval and a semantic-based retrieval can not support content-based retrieval. As a results, we expect to handle metadata more efficiently.

• Korean Journal of Oriental Medicine
• /
• 제11권2호
• /
• pp.35-52
• /
• 2005

This study is to design a Semantic Navigation Retrieval System for Oriental Medicine Articles based on a XTM so that people can search and use them more effectively than before. Keywords extracted from articles are categorized 4 topics : herbs, prescription, disease, and action. Keywords analysis Ontology is modeled based on 4 topics and their relations, and then represented Topic maps. Next, Article analysis Ontology is consist of title, author, keywords, abstracts and organization Topics from metadata. Keywords and Article analysis Ontology were integrated through Keywords Topic. Korean Medical Article Retrieval System is optimistic in terms on search results supporting semantic navigation in the information service aspects and easier accessibility because all related information are semantically connected with each different DBs.

• Proceedings of the Korea Society for Simulation Conference
• /
• 한국시뮬레이션학회 2001년도 The Seoul International Simulation Conference
• /
• pp.141-146
• /
• 2001

An Information Retrieval System offers the integrated view of SCM(Supply Chain Management) information to the enterprise by making it possible to exchange data between regionally distributed heterogeneous computers and also to enable these computers to access various types of databases. The Information Retrieval System is modeled using Data Registry Model based on X3.285. We only verify the MetaData Registry Manager(MDR Manager) among the core parts using SMV(Symbolic Model Verifier) in order to verify whether our model satisfies the requirements under the given assumptions.

• The Journal of Society for e-Business Studies
• /
• 제14권3호
• /
• pp.15-37
• /
• 2009

This study presents a new retrieval system developed to consider various preferential requirements for buyers in the real estate market. The paper analyses essential factors affecting the price of real estate and then a set of factors are classified by region-related factor and individual-related factor. After endowing the buyer's selected factors with weights in the retrieval system, the optimal solutions have been drawn by comparing with the others through an entropy measure of Multi-attribute Decision Making. This retrieval system is applied to the Busan real estate market to estimate the solutions of retrieval. Evaluation results indicate that the retrieval system can provide useful information to analyse the price determination factors of real estate, as well as to save the searching cost of the buyers.

• The KIPS Transactions:PartD
• /
• 제11D권4호
• /
• pp.755-764
• /
• 2004

Recently, the rapid development of biotechnology brings the explosion of biological data and biological data host. Moreover, these data are highly distributed and heterogeneous, reflecting the distribution and heterogeneity of the Molecular Biology research community. As a consequence, the integration and interoperability of molecular biology databases are issue of considerable importance. But, up to now, most of the integrated systems such as link based system, data warehouse based system have many problems which are keeping the data up to date when the schema and data of the data source are changed. For this reason, the integrated system using web service technology that allow biological data to be fully exploited have been proposed. In this paper, we built the integrated system if the bio sequence information bated on the web service technology. The developed system allows users to get data with many format such as BSML, GenBank, Fasta to traverse disparate data resources. Also, it has better retrieval performance because the retrieval modules of the external database proceed in parallel.

• Journal of KIISE:Software and Applications
• /
• 제31권11호
• /
• pp.1505-1518
• /
• 2004

We propose an extremely light DDXMI approach for semi-automated integration of both structurally and semantically heterogeneous distributed XML documents. In the proposed prototype, a DDXMI(Distributed Documents XML Metadata Interface) is defined and a user interface generator is developed. The prototype takes sources' DTDs as inputs and generates a friendly graphical user interface for the application users. The user can easily describe the semantic mapping between the integrated virtual database DTD and sources' DTDs through assigning index numbers and specifying associated function names so that the DDXMI based on the mappings is automatically generated. Quilt is selected as the XML query language which processes user queries according to the DDXMI. It is assumed that the application users know what they want from the different sources, that is, they have their own integrated database schema in their mind, and know the semantics of the involved XML databases. A small-size global DTD and a mid-size global DTB are generated to verify the rluery generation and retrieval results with 3 XML document databases, that is, Master/ph.D thesis, research reports, and journal databases. The system has been developed with JavaCC and Java Servelet.

• Journal of the Korean Society for Library and Information Science
• /
• 제36권3호
• /
• pp.155-179
• /
• 2002

The purpose of this study is to extract metadata based on Dublin Core from national construction information DBs, to design XML schema from the extracted metadata and to apply the previous works to integrated information retrieval system. To extract metadata, co-work was performed with librarians in the field of construction information, and. as a result, twelve metadata elements from Dublin Core and one administrative metadata could be extracted. Based on the investigation and analysis of those thirteen metadata elements, XML schema design process was described in detail. finally, the service environments of integrated information retrieval system to which XML schema was applied was introduced. Further study was also provided.