• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.109-131
• /
• 2014

As the demand of nuclear power plant equipment is continuously growing worldwide, the importance of handling nuclear strategic materials is also increasing. While the number of cases submitted for the exports of nuclear-power commodity and technology is dramatically increasing, preadjudication (or prescreening to be simple) of strategic materials has been done so far by experts of a long-time experience and extensive field knowledge. However, there is severe shortage of experts in this domain, not to mention that it takes a long time to develop an expert. Because human experts must manually evaluate all the documents submitted for export permission, the current practice of nuclear material export is neither time-efficient nor cost-effective. Toward alleviating the problem of relying on costly human experts only, our research proposes a new system designed to help field experts make their decisions more effectively and efficiently. The proposed system is built upon case-based reasoning, which in essence extracts key features from the existing cases, compares the features with the features of a new case, and derives a solution for the new case by referencing similar cases and their solutions. Our research proposes a framework of case-based reasoning system, designs a case-based reasoning system for the control of nuclear material exports, and evaluates the performance of alternative keyword extraction methods (full automatic, full manual, and semi-automatic). A keyword extraction method is an essential component of the case-based reasoning system as it is used to extract key features of the cases. The full automatic method was conducted using TF-IDF, which is a widely used de facto standard method for representative keyword extraction in text mining. TF (Term Frequency) is based on the frequency count of the term within a document, showing how important the term is within a document while IDF (Inverted Document Frequency) is based on the infrequency of the term within a document set, showing how uniquely the term represents the document. The results show that the semi-automatic approach, which is based on the collaboration of machine and human, is the most effective solution regardless of whether the human is a field expert or a student who majors in nuclear engineering. Moreover, we propose a new approach of computing nuclear document similarity along with a new framework of document analysis. The proposed algorithm of nuclear document similarity considers both document-to-document similarity (${\alpha}$) and document-to-nuclear system similarity (${\beta}$), in order to derive the final score (${\gamma}$) for the decision of whether the presented case is of strategic material or not. The final score (${\gamma}$) represents a document similarity between the past cases and the new case. The score is induced by not only exploiting conventional TF-IDF, but utilizing a nuclear system similarity score, which takes the context of nuclear system domain into account. Finally, the system retrieves top-3 documents stored in the case base that are considered as the most similar cases with regard to the new case, and provides them with the degree of credibility. With this final score and the credibility score, it becomes easier for a user to see which documents in the case base are more worthy of looking up so that the user can make a proper decision with relatively lower cost. The evaluation of the system has been conducted by developing a prototype and testing with field data. The system workflows and outcomes have been verified by the field experts. This research is expected to contribute the growth of knowledge service industry by proposing a new system that can effectively reduce the burden of relying on costly human experts for the export control of nuclear materials and that can be considered as a meaningful example of knowledge service application.

• Journal of the Korean Society of Food Culture
• /
• v.27 no.2
• /
• pp.128-141
• /
• 2012

This study focused on the historic documents known as $deungnok$, records created during preparations for royal events in the $Joseon$ Dynasty, rather than the often cited $uigwe$, the documents describing the Royal Protocol of the $Joseon$ Dynasty. As a reference to the food served at royal banquets, the $deungnok$ can enhance our understanding of royal banquet foods. Seven specimens of $deungnok$ describing royal banquet foods are currently in existence, created during preparations for royal events by the agencies in charge of food, the $Saongwon$ and $Jeonseonsa$. Owing to the nature of their authorship, the details recorded in these $deungnok$ hold great value as important resources for the study of royal banquet cuisine. $Naeoejinyeon$-$deungnok$, which documented an $oejinyeon$ banquet held at the $Junghwajeon$ Pavilion in November 1902, was somewhat disorganized and fragmented. $Jinyeonuigwe$ was more inclusive and well-summarized, since the former were progress reports to the King during banquet preparations that listed various items separately, such as dishes for each table setting and the kinds of flower pieces, and thus did not present a complete picture of all the details as a whole. The latter, on the other hand, were final reports created upon completion of a banquet, and contained more comprehensive records not only of the $chanpum$ (the menu of dishes served), but also the sorts of tableware and tables, floral arrangements, location, scale, and installation date of the $sukseolso$ (temporary royal kitchens for banquets). They also offer a more effective summary by simplifying details duplicated in identical table settings. Nevertheless, the $Naeoejinyeon$-$deungnok$ recorded some facts that cannot be gleaned from the $Jinyeonuigwe$, including the height of some dishes presented in piled stacks, as well as the specific names of dishes and their ingredients. The comparative study of the historic records in the $deungnok$ and $uigwe$ will be helpful in identifying and understanding the specific foods served at royal banquets. The $oejinyeon$-$seolchando$ diagrams in $Naeoejinyeon$-$deungnok$ depict the table settings for the King and the Crown Prince. The two diagrams contain large rectangles divided into three sections. In each section are similar-sized circles in which the names of dishes and the titles for table settings are recorded. From these records we can see that the arrangements of the table settings for the King and the Crown Prince are similar. The relationships and protocols shown in the arrangement of dishes and table settings for the King and the Crown Prince at royal banquets in the $Seolchando$ appear to be consistent. By comparing the two references, $deungnok$ and $uigwe$, which recorded the dishes served at royal banquets, the author was able to determine the height of some foods served in stacked arrangements, the names of $chanpum$, the ingredients used, and the configuration of the $chanpum$. The comparative review of these two written records, $deungnok$ and $uigwe$, will be helpful for a proper understanding of the actual food served at royal banquets.

• The KIPS Transactions:PartB
• /
• v.14B no.7
• /
• pp.513-522
• /
• 2007

Clustering is to divide given data and automatically find out the hidden meanings in the data. It analyzes data, which are difficult for people to check in detail, and then, makes several clusters consisting of data with similar characteristics. On-Line Document Clustering System, which makes a group of similar documents by use of results of the search engine, is aimed to increase the convenience of information retrieval area. Document clustering is automatically done without human interference, and the number of clusters, which affect the result of clustering, should be decided automatically too. Also, the one of the characteristics of an on-line system is guarantying fast response time. This paper proposed a method of determining the number of clusters automatically by geometrical information. The proposed method composed of two stages. In the first stage, centers of clusters are projected on the low-dimensional plane, and in the second stage, clusters are combined by use of distance of centers of clusters in the low-dimensional plane. As a result of experimenting this method with real data, it was found that clustering performance became better and the response time is suitable to on-line circumstance.

• Journal of Environmental Impact Assessment
• /
• v.28 no.3
• /
• pp.312-331
• /
• 2019

An offshore waste disposal facility refers to a landfill site for final landfilling of stabilized inorganic solid waste such as land and marine waste incineration materials, and the aim of such a facility is to solve the problem of insufficient waste disposal space on land and create and develop environmentally friendly marine spaces. The purpose of this study is to prepare guidelines for the construction of offshore waste disposal facilities, which reflect the need and importance of paying sufficient heed to environmental considerations from the initial stage of the project, in order to investigate, predict, and assess how such guidelines will affect the marine environment in relation to the construction of offshore waste disposal facilities, with the goal of minimizing the impact on and damage to the environment. For the purpose of this research, guidelines focusing on the construction of offshore waste disposal facilities were derived through an analysis of domestic cases and similar foreign cases and an assessment of their level of compliance with existing EIA guidelines through the operation of a discussion forum. In order to review the EIA report on similar cases in Korea, 17 EIA documents (2005~2016) for dredged soil dumping areas and ash ponds of thermal power plants were analyzed to investigate the status of marine organisms, marine physics, marine water quality, and marine sediment and to understand what types of problems can occur and what improvement measures can be taken. The purpose of these guidelines were to minimize damage to the marine environment by promoting EIA protocols in accordance with scientific and systematic procedures, to reduce the consultation period related to projects, to resolve social conflicts, and to reduce economic costs.

• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.131-146
• /
• 2011

It is becoming more essential than ever for office professionals to become competent in information collection/gathering and problem solving in today's global business society. In particular, office professionals do not only assist simple chores but are also forced to make decisions as quickly and efficiently as possible in problematic situations that can end in either profit or loss to their company. Since office professionals rely heavily on their tacit knowledge to solve problems that arise in everyday business situations, it is truly helpful and efficient to refer to similar business cases from the past and share or reuse such previous business knowledge for better performance results. Case-based reasoning(CBR) is a problem-solving method which utilizes previous similar cases to solve problems. Through CBR, the closest case to the current business situation can be searched and retrieved from the case or knowledge base and can be referred to for a new solution. This reduces the time and resources needed and increase success probability. The main purpose of this study is to design a system called COKRS(Case-based reasoning Office Knowledge Recommender System) and develop a prototype for it. COKRS manages cases and their meta data, accepts key words from the user and searches the casebase for the most similar past case to the input keyword, and communicates with users to collect information about the quality of the case provided and continuously apply the information to update values on the similarity table. Core concepts like system architecture, definition of a case, meta database, similarity table have been introduced, and also an algorithm to retrieve all similar cases from past work history has also been proposed. In this research, a case is best defined as a work experience in office administration. However, defining a case in office administration was not an easy task in reality. We surveyed 10 office professionals in order to get an idea of how to define a case in office administration and found out that in most cases any type of office work is to be recorded digitally and/or non-digitally. Therefore, we have defined a record or document case as for COKRS. Similarity table was composed of items of the result of job analysis for office professionals conducted in a previous research. Values between items of the similarity table were initially set to those from researchers' experiences and literature review. The results of this study could also be utilized in other areas of business for knowledge sharing wherever it is necessary and beneficial to share and learn from past experiences. We expect this research to be a reference for researchers and developers who are in this area or interested in office knowledge recommendation system based on CBR. Focus group interview(FGI) was conducted with ten administrative assistants carefully selected from various areas of business. They were given a chance to try out COKRS in an actual work setting and make some suggestions for future improvement. FGI has identified the user-interface for saving and searching cases for keywords as the most positive aspect of COKRS, and has identified the most urgently needed improvement as transforming tacit knowledge and knowhow into recorded documents more efficiently. Also, the focus group has mentioned that it is essential to secure enough support, encouragement, and reward from the company and promote positive attitude and atmosphere for knowledge sharing for everybody's benefit in the company.

• Korean Security Journal
• /
• no.50
• /
• pp.175-206
• /
• 2017

The current study described the history of Islamic extremism and the recent expansion of international Islamic extremism in Indonesia. For doing so, both content analysis of the existing written documents and qualitative interviews were conducted. For the content analysis, media reports and research articles were collected and utilized. For qualitative interviews, Indonesian students and workers in Korea, Korean spouses married to Indonesian, and Korean missionaries in Indonesia were contacted and interviewed. Qualitative interview was conducted between 30 minutes and 2 hours. On the spot, interviews were recorded and later transcribed into written documents. Due to the difficulty of identification of population and the uneasiness of accessability to th study subjects, convenient sampling and snowball sampling were used. According to the results, Islamic extremism in Indonesia had a deep historical root and generally shared similar historical experience with other muslim countries such as Afghanistan, Pakistan, Egypt, and Saudi Arabia where Islamic extremism was deeply rooted in. That is, Islamic extremism began as a reaction to the western imperialism, after independence, Islamic extremism elements were marginalized in the process of construction of the modern nation-state, and Islamic extremist movement was radicalized and became violent during the Soviet-Afghan War. In addition, after 9.11, Islamic extremism in Indonesia was connected to international Islamic extremism network and integrated into such global movement. Such a historical development of Indonesian Islamic extremism was quite organized and robust. Meanwhile, the eastward infiltration and expansion of international Islamic extremism such as IS and Al Qaeda was observed in Indonesia. Particularly, such a worrisome expansion was more clearly visible in the marginalized and underdeveloped countrysides in Indonesia. Such expansion in Indonesia could negatively affect on the security of South Korea. Geographically, Indonesia is proximate to South Korea. This geographical proximity could be a direct security threat to the Korean society, as if Islamic extremism in North Africa and Middle East becomes a direct security threat to Europe. Considering the presence of a large size of Indonesian immigrant workers and communities in South Korea, such a concern is very realistic. The arrest of an Indonesian Islamic extremism supporter in November, 2016, could be a harbinger of the coming trend of Islamic extremism expansion inside South Korea. The Indonesian Islamic community in South Korea could be a passage of Indonesian Islamic extremism into the South Korean society. In this context, it is timely and necessary to pay an attention to the recent trend of Islamic extremism expansion in Indonesia.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.131-150
• /
• 2015

Omission of noun phrases for obligatory cases is a common phenomenon in sentences of Korean and Japanese, which is not observed in English. When an argument of a predicate can be filled with a noun phrase co-referential with the title, the argument is more easily omitted in Encyclopedia texts. The omitted noun phrase is called a zero anaphor or zero pronoun. Encyclopedias like Wikipedia are major source for information extraction by intelligent application systems such as information retrieval and question answering systems. However, omission of noun phrases makes the quality of information extraction poor. This paper deals with the problem of developing a system that can restore omitted noun phrases in encyclopedia documents. The problem that our system deals with is almost similar to zero anaphora resolution which is one of the important problems in natural language processing. A noun phrase existing in the text that can be used for restoration is called an antecedent. An antecedent must be co-referential with the zero anaphor. While the candidates for the antecedent are only noun phrases in the same text in case of zero anaphora resolution, the title is also a candidate in our problem. In our system, the first stage is in charge of detecting the zero anaphor. In the second stage, antecedent search is carried out by considering the candidates. If antecedent search fails, an attempt made, in the third stage, to use the title as the antecedent. The main characteristic of our system is to make use of a structural SVM for finding the antecedent. The noun phrases in the text that appear before the position of zero anaphor comprise the search space. The main technique used in the methods proposed in previous research works is to perform binary classification for all the noun phrases in the search space. The noun phrase classified to be an antecedent with highest confidence is selected as the antecedent. However, we propose in this paper that antecedent search is viewed as the problem of assigning the antecedent indicator labels to a sequence of noun phrases. In other words, sequence labeling is employed in antecedent search in the text. We are the first to suggest this idea. To perform sequence labeling, we suggest to use a structural SVM which receives a sequence of noun phrases as input and returns the sequence of labels as output. An output label takes one of two values: one indicating that the corresponding noun phrase is the antecedent and the other indicating that it is not. The structural SVM we used is based on the modified Pegasos algorithm which exploits a subgradient descent methodology used for optimization problems. To train and test our system we selected a set of Wikipedia texts and constructed the annotated corpus in which gold-standard answers are provided such as zero anaphors and their possible antecedents. Training examples are prepared using the annotated corpus and used to train the SVMs and test the system. For zero anaphor detection, sentences are parsed by a syntactic analyzer and subject or object cases omitted are identified. Thus performance of our system is dependent on that of the syntactic analyzer, which is a limitation of our system. When an antecedent is not found in the text, our system tries to use the title to restore the zero anaphor. This is based on binary classification using the regular SVM. The experiment showed that our system's performance is F1 = 68.58%. This means that state-of-the-art system can be developed with our technique. It is expected that future work that enables the system to utilize semantic information can lead to a significant performance improvement.

• The Korean Journal of Archival Studies
• /
• no.11
• /
• pp.181-214
• /
• 2005

Metropolitan rapid transit system plays an essential role in the public transportation system of any large city, and its managing agency is usually charged with the responsibility of storing and managing the design drawings of the system. The drawings are important and historically valuable documents that must be kept permanently because they contain comprehensive data that is used to manage and maintain the system. However, no study has been performed in Korea on how well agencies are preserving and managing these records. Seoul Metropolitan Rapid Transit Corporation(SMRT) is the managing agency established by the city of Seoul to operate subway lines 5, 6, 7, and 8 more efficiently to serve its citizens. By the Act on Records Management in Public Institutions(ARMPI), SMRT should establish a records center to manage its records. Furthermore, all drawings produced by SMRT and other third party entities should be in compliance with the Act. However, SMRT, as a form of local public corporation, can establish a records center by its own way. Accordingly, the National Archives & Records Service(NARS) has very little control over SMRT. Therefore, the purpose of this study is to research and analyze the present state of storage and management of the drawings of metropolitan rapid transit in SMRT and is to find a desirable method of preservation and management for drawings of metropolitan rapid transit. In the process of the study, it was found that a records center is being considered to manage only general official documents and not to manage the drawings as required by ARMPI. SMRT does not have a records center, and the environment of management on the drawings is very poor. Although there is a plan to develop a new management system for the drawings, it will be non-compliant of ARMPI. What's happening at SMRT does not reflect the state of all other cities' metropolitan rapid transit records management systems, but the state of creation of records center of local public corporation is the almost same state as SMRT. There should be continuous education and many studies conducted in order to manage the drawings of metropolitan rapid transit efficiently by records management system. This study proposes a records center based on both professional records centers and union records centers. Although metropolitan rapid transit is constructed and managed by each local public corporation, the overall characteristics and processes of metropolitan rapid transit projects are similar in nature. In consideration of huge quantity, complexity and specialty of drawings produced and used during construction and operation of metropolitan rapid transit, and overlap of each local public corporation's effort and cost of the storage and management of the drawings, they need to be managed in a professional and united way. As an example of professional records center, there is the National Personnel Records Center(NPRC) in St. Louis, Missouri. NPRC is one of the National Archives and Records Administration's largest operations and a central repository of personnel-related records on former and present federal employees and the military. It provides extensive information to government agencies, military veterans, former federal employees, family members, as well as researchers and historians. As an example of union records center, there is the Chinese Union Dangansil. It was established by several institutions and organizations, so united management of records can be performed and human efforts and facilities can be saved. We should establish a professional and united records center which manages drawings of metropolitan rapid transit and provides service to researchers and the public as well as members of the related institutions. This study can be an impetus to improve interest on management of not only drawings of metropolitan rapid transit but also drawings of various public facilities.

• The Korean Journal of Archival Studies
• /
• no.3
• /
• pp.91-113
• /
• 2001

History always be re-interpreted as the time flows. 'The Sillok', Which was registered in Memory of World of UNESCO in 1997, is comprehensive documents of the Chosun Dynasty, which had been compiled after kings' death, The Sillok encompasses 473 years of the reign in their 848 volumes(1,893 chapters). It was a history itself and has been main source in studying Korean history. Due to the rise of studies on the Sillok, time has come to explore the nature of the Sillok and to criticize the text, which would be called 'The Sillok-Study'. In this context, this paper examined three concepts that categorize the nature of the Sillok as historical materials ;Is it book or record?; The Sillok in register system in pre-modern society; And the Sillok as the National Archives. Korean historians, including myself, haven't yet examined the question whether the Sillok is the Book or Record in terms of archival science. At first, I regarded it as history book, and with this presupposition, wrote several papers on the characteristics of the Sillok. However, I recognized that the Sillok are close to record rather that history book as I examined the definition of glossary of librarian study, OED (Oxford English Dictionary) and Encyclopedia of Britannica, etc. Definitely, the Sillok was neither compiled and published to be read and sold publicly, nor meant to the works of literature or scholarship. one may say that the court-historians wrote comments on the facts and therefore it was just scholarly work. However, because the court-historians produced their comments on their own businesses, the outcome of 'their scholarly works' were also records conceptually, as were daily court-journalists in Rome. Its publication also had a absolutely different meaning from that of modern society. It was a method to preserve the important national records and distributed each edition of them to plural repositories for its safety and security. How can we explain its book-like shape and the procedure of compilation after a kings' death. The answer is as follows ; In pre-modern society, it was a common record-keeping system in the world to register records materials in order to arrange the materials of different sizes and to store them conveniently. And the lack of scientific preservation or conservation skill also encouraged them to register original records. Actually, the court-historians who participated in the compiling process called themselves "registering officers". On the other hand, similar to social hierarchy, there was a hierarchical system of records, and the Sillok was placed at the top of this hierarchy. In conclusion, the Sillok was a kind of registered records in the middle ages and the supreme records in the records-world. In addition to this we can also conceptualize the Sillok as archives. Through the compiling process, the most important and valuable records were selected to be the parts of Sillok. This process corresponds to the modem records appraisal. In the next step, it was preserved in the Four Archives(史庫) which located at remote site as archives and only accessible by the descendents in the future, who might be the people of the next dynasty. And nobody could access or read the documents at that time except the authorized court-historians who were archivists of the Chosun Dynasty. From this perspective, I conclude that Sillok was the supreme confidential archives in the register system. I work for the Government Archives as a historian and archivist. Whenever I entered the exhibition hall of the Government Archives and Records Service(GARS) and saw the replica of the Archives of Taebeak Mountain built during Chosun period, I always asked to myself a question whether the Sillok can be a symbol of the archival tradition of Korea and the GARS. Now, I can say, 'Yes!' definitely.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.127-146
• /
• 2022

Recently, as word embedding has shown excellent performance in various tasks of deep learning-based natural language processing, researches on the advancement and application of word, sentence, and document embedding are being actively conducted. Among them, cross-language transfer, which enables semantic exchange between different languages, is growing simultaneously with the development of embedding models. Academia's interests in vector alignment are growing with the expectation that it can be applied to various embedding-based analysis. In particular, vector alignment is expected to be applied to mapping between specialized domains and generalized domains. In other words, it is expected that it will be possible to map the vocabulary of specialized fields such as R&D, medicine, and law into the space of the pre-trained language model learned with huge volume of general-purpose documents, or provide a clue for mapping vocabulary between mutually different specialized fields. However, since linear-based vector alignment which has been mainly studied in academia basically assumes statistical linearity, it tends to simplify the vector space. This essentially assumes that different types of vector spaces are geometrically similar, which yields a limitation that it causes inevitable distortion in the alignment process. To overcome this limitation, we propose a deep learning-based vector alignment methodology that effectively learns the nonlinearity of data. The proposed methodology consists of sequential learning of a skip-connected autoencoder and a regression model to align the specialized word embedding expressed in each space to the general embedding space. Finally, through the inference of the two trained models, the specialized vocabulary can be aligned in the general space. To verify the performance of the proposed methodology, an experiment was performed on a total of 77,578 documents in the field of 'health care' among national R&D tasks performed from 2011 to 2020. As a result, it was confirmed that the proposed methodology showed superior performance in terms of cosine similarity compared to the existing linear vector alignment.