• Journal of the Korea Safety Management & Science
• /
• v.12 no.1
• /
• pp.127-136
• /
• 2010

In this paper, the author proposed following two methods to improve the accuracy of the recommender system. First, in order to classify the users more accurately, the author used a EMC(Expanded Moving Center) heuristic algorithm which improved clustering accuracy. Second, the author proposed the Neighborhood-oriented preference prediction method that improved the conventional preference prediction methods, so the accuracy of the recommender system is improved. The test result of the recommender system which adapted the above two methods suggested in this paper was improved the accuracy than the conventional recommendation methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.423-428
• /
• 2017

These days, various and tons of education information are rapidly increasing and spreading due to Internet and smart devices usage. Recently, as e-Learning usage increasing, many instructors and students (learners) need to set a goal to maximize learners' result of education and education system efficiency based on big data analytics via online recorded education historical data. In this paper, the author applied Word2Vec algorithm (neural network algorithm) to find similarity among education words and classification by clustering algorithm in order to objectively recognize and analyze online recorded education historical data. When the author applied the Word2Vec algorithm to education words, related-meaning words can be found, classified and get a similar vector values via learning repetition. In addition, through experimental results, the author proved the part of speech (noun, verb, adjective and adverb) have same shortest distance from the centroid by using clustering algorithm.

• Journal of Korean Library and Information Science Society
• /
• v.41 no.1
• /
• pp.149-165
• /
• 2010

In this research, we analyze about the general service provided by Society of Korean journal articles of science and technology. Personalized retrieval services which are suitable to the articles service were developed based on this. That is, there are personalized retrieval system based on user's keyword, authors navigation system, automatic topic recommendation system based on author's keyword, and similar user automatic recommendation system. In this research, personalized service methods being suitable to the articles service of Society tries to be considered through the user survey.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.263-270
• /
• 2002

Most conventional systems of fire fighting control in a ship have been based on rule-based system in which expert knowledges are expressed with production rules. Renewing and adding of rules is needed continuously for the improvement of the system capability in an already build-up system and such adding and renewing procedures could hinder users from fluent utilization of a system. The author proposes an advanced fire fighting control intelligent system (A-FFIS) using rule-based and carte-based reasoning by clustering to implement conventional hybrid system (H-FFIS). Compared with H-FFIS, new approach with A-FFIS shows that the system proposed here improves fire detection rate and reduces fire detection time.

• The Journal of Information Systems
• /
• v.30 no.1
• /
• pp.21-44
• /
• 2021

Purpose The opportunities and approaches to big data have grown in various ways in the digital era. Business analytics is nowadays an inevitable strategy for organizations to earn a competitive advantage in order to survive in the challenged environments. The purpose of this study is to analyze the intellectual structure of business analytics literature to have a better insight for the organizations to the field. Design/methodology/approach This research analyzed with the data extracted from the database Web of Science. Total of 427 documents and 23,760 references are inserted into the analysis program CiteSpace. Author co-citation analysis is used to analyze the intellectual structure of the business analytics. We performed clustering analysis, burst detection and timeline analysis with the data. Findings We identified seven sub- areas of business analytics field. The top four sub-areas are "Big Data Analytics Infrastructure", "Performance Management System", "Interactive Exploration", and "Supply Chain Management". We also identified the top 5 references with the strongest citation bursts including Trkman et al.(2010) and Davenport(2006). Through timeline analysis we interpret the clusters that are expected to be the trend subjects in the future. Lastly, limitation and further research suggestion are discussed as concluding remarks.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.1
• /
• pp.141-146
• /
• 2018

The authors' author keywords are the most important elements that characterize the contents of the paper, By analyzing this in real time and providing it to users, It is possible to grasp research trends. Unstructured data of a journal created in a paper is constructed as a database, make use of this to make index data structure that can search in real time. In the index data structure, a thesis containing a specific keyword is searched, By extracting and clustering the author keywords, By presenting to the user a word cloud that can be displayed by size according to the weight, designed a method to visualize research trends. We also present the results of the research trend analysis of the keywords "virus" and "iris recognition" in the implemented system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.711-713
• /
• 2013

Various human resource information of the world can be found according to spread of social network such as facebook and twitter. There are an amounts of researcher information on the science and technology area but it is difficult to find a suitable researcher for research or business such as research partner, because researcher information is not systematically arranged. To solver this problem, we are constructing authority data system for science and technology based on authority information of overseas academic papers. In this paper, in order to construct the authority data, we extracts author identification elements from millions of overseas academic papers, which are published from 1994 to 2012. There are more than 50 author identification elements such as author name, affiliation, paper title, publisher, year, keywords, co-author, co-author's affiliation in Korean, English, Chinese, and Japanese. We construct the element database by extracting and storing an author identification information based on the elements from overseas academic papers. Future works includes that the authority database for overseas academic papers is constructed by storing an academic activities of researchers after author clustering with these extracted elements. The authority data is used to improve the researcher information utilization and activate community to find a suitable research partner or a business examiner.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.127-140
• /
• 2022

With the recent development of the ICT (information and communication technology), the revolution of the industry has moved on from the third industry to the fourth. There is no doubt that the companies would not survive in the future without adopting these technologies. The purpose of this research is to analyze the intellectual structure of the internet of things(IoT) literature for the Industry 4.0 to suggest a better insight for the field. The data for this research is extracted from the Web of Science database. Total of 1,631 documents and 72,754 references are used for the research with the analysis program CiteSpace. Author co-citation analysis is used to analyze the intellectual structure and performed clustering, timeline and burst detection analysis. We identified 12 sub-areas of IoT for the Industry 4.0 which are 'Supply Chain', 'Digital Twin', 'Smart Manufacturing System' and etc. Through the timeline analysis we can find out which clusters will increase or decrease its reputation. As concluding remarks, limitations and further research suggestions are discussed.

• Korean Journal of Computational Design and Engineering
• /
• v.1 no.1
• /
• pp.56-64
• /
• 1996

A quadrilateral-triangular mixed grid method for the solution of incompressible viscous flow is presented. The solution domain near the body surface is meshed using elliptic grid geneator to acculately simulate the viscous flow. On the other hand, we used unstructured triangular grid system generated by advancing front technique of a simple automatic grid generation algorithm in the rest of the computational domain. The present method thus is capable of not only handling complex geometries but providing accurate solutions near body surface. The numerical technique adopted here is PISO type finite element method which was developed by the present author. Investigations have been made of two-dimensional unsteady flow of Re=550 past a circular cylinder. In the case of use of the unstructured grid only, there exists a considerable amount of difference with the existing results in drag coefficient and vorticity at the cylinder surface; this may be because of the lack of the grid clustering to the surface that is a inevitable requirement to resolve the viscous flow. However, numerical results on the mixed grid show good agreements with the earlier computations and experimental data.

• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.174-185
• /
• 2020

Leukemia induced death has been listed in the top ten most dangerous mortality basis for human being. Some of the reason is due to slow decision-making process which caused suitable medical treatment cannot be applied on time. Therefore, good clinical decision support for acute leukemia type classification has become a necessity. In this paper, the author proposed a novel approach to perform acute leukemia type classification using sequential neural network classifier. Our experimental result only cover the first classification process which shows an excellent performance in differentiating normal and abnormal cells. Further development is needed to prove the effectiveness of second neural network classifier.