• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.87-92
• /
• 2024

In this paper, a RAG system was implemented using an existing Large Language Model (LLM) and Langchain library to develop a dental consultation chatbot. For this purpose, we collected contents from the webpage bulletin boards of domestic dental university hospitals and constructed consultation data with the advice and supervision of dental specialists. In order to divide the input consultation data into appropriate sizes, the chunk size and the size of the overlapping text in each chunk were set to 1001 and 100, respectively. As a result of the simulation, the Retrieval Augmented LLM searched for and output the consultation content that was most similar to the user input. It was confirmed that the accessibility of dental consultation and the accuracy of consultation content could be improved through the built chatbot.

• Journal of Korean Medicine Rehabilitation
• /
• v.34 no.1
• /
• pp.49-64
• /
• 2024

Objectives By bibliographically analyzing acupuncture treatment studies for temporomandibular disorders over the past 20 years, we found an overview of global trends and a new perspective on future research directions. Methods We searched on the Web of Science webpage through the formula (TS=[temporomandibular] OR TS=[craniomandibular] OR TS=[jaw]) AND (TS=[^*acupuncture] OR TS=[dry needl^*] OR TS=[warm needl^*] OR TS=[thread embed^*]) AND (PY=[2003-2022]). And it was analyzed by year, research field, academic journal, country, research institute, author, and keyword. Results 194 papers were searched, and 92 papers were finally selected. The number of papers published over the past 20 years has been on the rise. Research has been the most active in the field of Dentistry Oral Surgery Medicine. Brazil published the most papers. And by institution, Universidade de Sao Paulo published the most papers. Among the authors, Fernández-de-las-Peñas has published the most papers. In the analysis by keyword, the top five keywords were temporomandibular joint disorder, acupuncture, myofascial pain, pain and management. Conclusions This study will provide useful guidelines for setting the direction of research by referring to the research status and keyword analysis when conducting research on the acupuncture on temporomandibular disorder in the future.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.937-944
• /
• 2006

Although people's anxiety about the environmental problem has been getting higher, they are not provided good quality of knowledge about the environment. Based on this situation, Ecoblog can be a new type of online community to educate the public in ecological knowledge. Especially, Ecoblog can be utilized as a method of "preventive education", and it will contribute to reduce great amounts of environmental budget to restore contaminated environment to previous condition. Ecoblog also utilizes the concept of blog which user can create and append their site with chosen themes. A weblog or a blog is a non-commercial webpage regularly updated through the use of a blogging software which allows the user to "publish" kinds of amalgamations of text and graphics to the page as posts. The technology offered in Ecoblog is utilizing the concept of 4D place and game metaphor in order to provide users the sense of participation, interaction and immersion among them and the growing community. Thus, it requires applying the CAAD technology by implementing semantically well-defined building data model as a core database to create a 4D virtual community. This research focuses on defining a 4d spatial framework suitable for developing an online ecological community. Through our study, the state-of-the-art of online community has been studied at the first step. Second, the scenario of using EcoBlog described with content, visualization and navigation are defined based on the critical features derived at the first step. Finally, a 4d spatial framework composed of semantic building data model, content and rule database is constructed to propose factors that are necessary to establish an ecological virtual community. In conclusion, our framework could enhance the comprehension and interaction between users and virtual buildings in the ecological community by integrating the concept of game design, 4D CAD and semantic data model. Such framework can be applied to any online community for an educational purpose.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.6
• /
• pp.41-48
• /
• 2008

The realization of a monitoring system for senior citizens living alone through wireless sensor network. Due to the recent advances in medical science, people live longer than ever before which accelerates the number of senior citizens. The high rate of the old people in population causes some changes in the form of families, which results in the increasing number of old people living by themselves. This also causes a lot of social problems concerning aging population. For example, people found a dead body of 83-year-old, who had lived alone, after he passed away a month before. There is a national monitoring service for the old people of their daily lives, but the application of such system is very limited. Considering this, the current paper focuses on the realization of a monitoring system for senior citizens living alone through wireless sensor network. The system consists of ZigBee sensor network, which is based on standard IEEE 802.15.4. and the system uses Tmote Sky sensor mote made by Moteive, which is installed with TinyOS. The circumstances information data will be saved on DB and a household will be monitored through a Webpage or Mobile.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.10
• /
• pp.2292-2298
• /
• 2010

A mashup is a web page or application that uses and combines information, contents or Open APIs available on the web to create a new service. The mashup developed by the need not combination of simple information can contribute to new added-values with practicality and convenience. Thus, in this paper, we want to develop a RIA-based dynamic mashup service for the users considering weather forecast and marine information importantly. We design and implement the system that it can register a number of information about a domain dynamically through registration process based on the map and present a mark of domain location on the map and the information including internal environment, external environment and weather of related to the domain within a webpage. Implemented service need not require a tedious process visiting other web sites every time to confirm the relevant information because we can see simultaneously related information with a map within a page.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.386-390
• /
• 2007

In this paper we present an Ontology Instance Management Tool. OntoManager is a user-friendly interactive ontology Instance management tool with webpage annotation tool and an image annotation tool. It supports the user with the task of creating and maintaining ontology-based OWL-markup, creating of OWL-instances, attributes and relationships. It include an ontology browser for the exploration of the ontology and instances and a HTML browser that will display the annotated parts of the text. And OntoManager is an image annotation tool that allows users to markup regions of an image with respect to concepts in an ontology. It provides the functionality to import images, ontologies, instance bases, perform markup, and export the resulting annotations to disk or the Web.

• Journal of Forest and Environmental Science
• /
• v.23 no.1
• /
• pp.65-71
• /
• 2007

In early 2000's, about six Phytophthora species have been newly described leading mortality on coniferous and broad-leaved trees in forests. Also, some species of Phytophthora are responsible for ink disease in chestnut plantation near or within forests. Similar symptoms of ink disease were appeared in some areas of Kyungnam and Jeonnam providences in 2005, and the pathogen was isolated using Phytophthora- selective medium in 2006. Morphological and genetic analysis were performed to identify the isolate. Also, the pathogenicity was conducted to complete $K\ddot{o}ch^{\prime}s$ postulate and compare susceptibility among chestnut cultivars. The molecular analysis between P. katsurae and P. hevae were performed with the isolates obtained from different countries including Korea or the sequences downloaded from Phytophthora webpage. The result showed that the isolated pathogen from chestnut was P. katsurae. There is no report of P. katsurae in Korea until now. P. katsurae was re-isolated from inoculated chestnut cultivars. Also, there was a slight difference in susceptibility among chestnut cultivars. The rDNA sequence of our isolate showed 100% similarity with sequence of the isolate cultured from Japan and New Zealand.

• Journal of Digital Contents Society
• /
• v.16 no.2
• /
• pp.245-255
• /
• 2015

As people are highly interested in health, the number of people who participate in various sports programs is getting increased. But there is no web service which integrates all the information of the public sports facilities in Seoul and it's convenient to use the public sport facilities. So we propose an integrated information system whoever can find the public sports facilities in Seoul. The public APIs for the Seoul public sports facilities provided by Seoul city are used to integrate the information. Also, our web page provides various graphic function using pictures and videos of the facilities on the environment of HTML5. And it is the responsive webpage which can be provided on both desktop and mobile environment. By implementing the wizard page, the managers of the facilities who are not specialized can renew the information about their facilities easily. And for the easier searching, we provides three options of searching: local, subjects, themes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.895-901
• /
• 2004

This paper describes a two-phase intelligent method for filtering spam mail based on textual information and hyperlinks. Scince the body of spam mail has little text information, it provides insufficient hints to distinguish spam mails from legitimate mails. To resolve this problem, we follows hyperlinks contained in the email body, fetches contents of a remote webpage, and extracts hints (i.e., features) from original email body and fetched webpages. We divided hints into two kinds of information: definite information (sender`s information and definite spam keyword lists) and less definite textual information (words or phrases, and particular features of email). In filtering spam mails, definite information is used first, and then less definite textual information is applied. In our experiment, the method of fetching web pages achieved an improvement of F-measure by 9.4% over the method of using on original email header and body only.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.28 no.5
• /
• pp.701-712
• /
• 2004

This study is aimed at the application of the apparel size system to be applied for the Internet shopping mall in Korea. Especially this is focused on the presumption of the body measurement according to the age groups and the figure groups. In this regard, a sizing system is to be developed that could be used to approach consumers more easily and provide more fitness and accuracy in terms of size. The target study was on a group of women nineteen to forty-nine years of age. The 4th National Anthropometry Survey data were used in the examination. The results in the study are as follows ; (1) On the Internet apparel shopping malls in relation with this study, no matter what size in the ready-to-wear enterprises was selected by the consumers who once put their information in the member registration, the most appropriate sizes for them are automatically given and transferred to the order forms of chosen enterprises with aid of internal programs of the internet webpage. In addition, when consumers enter their body sizes in the units that are familiar to them, such as inches or centimeters, the units are automatically programed so that they can be converted for the sake of convenience. ; (2) To extract an estimation equation of body size through Multiple Regression Analysis, the circumferences of chest and hip could be presumed by stature, weight, and waist circumference of which most consumers were well aware. For more accurate regression equations, groupings were made in the three categories of age(19∼29/30∼39/40∼49) and in the three body types(Type N, A and H). Then, the regression equations were established for three sectors, $\circled1$ 'chest circumference not filled up', $\circled2$ 'hip circumference not filled up' and $\circled3$ 'neither filled up for chest nor for hip circumference'. The final results of regression were presented in