• Journal of Korean Society of Archives and Records Management
• /
• v.9 no.1
• /
• pp.151-173
• /
• 2009

The classification in the Records and Archives Sciences focuses on the contextual information in producing and utilizing records rather than their contents. This study aimed at designing an automatic records classification system to enable an automatic classification focusing on the aggregation of the context of records rather than the contents of individual record in the classification scheme, structured on the basis of business activities analyses for records reflecting the business activities. The automatic records classification system was designed to have mutual supplements by constructing the classification scheme and thesaurus together as the classification reference, as well as the aggregation of records that have been already classified. Additionally included are plans to apply the classified contextual information of records to the classification reference on the real-time base right after the category assignment of records to be classified. Although there are limitations as the designed system depends on the quality of the contextual information, it is considered that the system could lead to ensure that the contextual information of records should be more substantial.

• Journal of the Korean Society for information Management
• /
• v.40 no.3
• /
• pp.99-118
• /
• 2023

The objective of this study is to identify performance factors in the automatic classification of records by utilizing metadata that contains the contextual information of records. For this study, we collected 97,064 records of original textual information from Korean central administrative agencies in 2022. Various classification algorithms, data selection methods, and feature extraction techniques are applied and compared with the intent to discern the optimal performance-inducing technique. The study results demonstrated that among classification algorithms, Random Forest displayed higher performance, and among feature extraction techniques, the TF method proved to be the most effective. The minimum data quantity of unit tasks had a minimal influence on performance, and the addition of features positively affected performance, while their removal had a discernible negative impact.

• Journal of the Korean Society for information Management
• /
• v.34 no.4
• /
• pp.321-344
• /
• 2017

Research on automatic classification of records and documents has been conducted for a long time. Recently, artificial intelligence technology has been developed to combine machine learning and deep learning. In this study, we first looked at the process of automatic classification of documents and learning method of artificial intelligence. We also discussed the necessity of applying artificial intelligence technology to records management using various cases of machine learning, especially supervised methods. And we conducted a test to automatically classify the public records of the Seoul metropolitan government into BRM using ETRI's Exobrain, based on supervised machine learning method. Through this, we have drawn up issues to be considered in each step in records management agencies to automatically classify the records into various classification schemes.

• Industrial Engineering and Management Systems
• /
• v.4 no.1
• /
• pp.102-108
• /
• 2005

This paper studies medical data classification methods, comparing decision tree and system reconstruction analysis as applied to heart disease medical data mining. The data we study is collected from patients with coronary heart disease. It has 1,723 records of 71 attributes each. We use the system-reconstruction method to weight it. We use decision tree algorithms, such as induction of decision trees (ID3), classification and regression tree (C4.5), classification and regression tree (CART), Chi-square automatic interaction detector (CHAID), and exhausted CHAID. We use the results to compare the correction rate, leaf number, and tree depth of different decision-tree algorithms. According to the experiments, we know that weighted data can improve the correction rate of coronary heart disease data but has little effect on the tree depth and leaf number.

• Journal of Korean Society of Archives and Records Management
• /
• v.22 no.1
• /
• pp.43-59
• /
• 2022

Electronic public records are classified simultaneously as production, a preservation period is granted, and after a certain period, they are transferred to an archive and preserved. This study intends to find a way to improve the efficiency in classifying transferred records and maintain consistent standards. To this end, the current record classification work process carried out by the National Archives of Korea was analyzed, and problems were identified. As a way to minimize the manual work of record classification by converging the required improvement, the process of identifying outlier candidates based on a list consisting of classified information of the transferred records was proposed and systemized. Furthermore, the proposed outlier discrimination process was applied to the actual records transferred to the National Archives of Korea. The results were standardized and constructed as a training data format that can be used for machine learning in the future.

• The Korean Journal of Archival Studies
• /
• no.59
• /
• pp.159-206
• /
• 2019

This study aims to analyze the details of the executive order of the president of the United States, which have been developed in the country's administrative system to institutionalize the guarantee of the people's right to know the classified records, as well as to protecting national secrets. This study also aims to present any implications for the development of the classified record management system of Korea. To this end, the previously issued EO concerning the classified records management were reviewed in terms of its classification, safeguard, and declassification. The analysis results showed that the EO by the president established and prescribed the special access program for national secrets, the system to exempt and suspend the automatic declassification, and the sanctions for protecting national secrets. The EO also established and prescribed the appointment system for the person with the authority to classify record, automatic declassification program, and Mandatory declassification review system, as well as the procedures for historical researcher and certain former government personal to access the classified records with the purpose of guaranteeing people's right to know. As a result, this study identified implications for the development of Korea's classified record management system, as follows : First, it is necessary to restructure the current classified record management system, by changing the operations that is dependent on the director of the National Intelligence Service to the one that is dependent on the President. Second, it is necessary to legislate a separate special law for the classified record management system. Third, a standing supervisory body should be established for the integrated management and for the consistent and routine supervision of the classified record management. Fourth, it is necessary to establish procedures to further review the classification of classified record to correct the defects of the current classification system, which has been abused and mismanaged by the national agencies and organizations that produce classified record.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.2
• /
• pp.435-452
• /
• 2023

This study experimented with automatic classification of subject headings using BERT-based transfer learning model, and analyzed its performance. This study analyzed the classification performance according to the main class of KDC classification and the category type of subject headings. Six datasets were constructed from Korean national bibliographies based on the frequency of the assignments of subject headings, and titles were used as classification features. As a result, classification performance showed values of 0.6059 and 0.5626 on the micro F1 and macro F1 score, respectively, in the dataset (1,539,076 records) containing 3,506 subject headings. In addition, classification performance by the main class of KDC classification showed good performance in the class General works, Natural science, Technology and Language, and low performance in Religion and Arts. As for the performance by the category type of the subject headings, the categories of plant, legal name and product name showed high performance, whereas national treasure/treasure category showed low performance. In a large dataset, the ratio of subject headings that cannot be assigned increases, resulting in a decrease in final performance, and improvement is needed to increase classification performance for low-frequency subject headings.

• The Korean Journal of Archival Studies
• /
• no.5
• /
• pp.3-37
• /
• 2002

Today the market of EDMS is esteemed more than 100 billions won. It signifies a comming of age of electronic records. The traditional archival theories which are based on the paper records are confronted with a new challenge. In some leading countries of archival studies reorientation of archives management has been tried by a number of distinguished specialists such as Bearman and Hedstrom since 10 years. As a consequence new paradigm of archival theories has been developed. Also in Korea this new paradigm has been introduced by some expert such as Lee, Sang-Min, Sul, Moon-won, Lee, Seung-Eok. However their arguments are too general to offer a concrete clue for new paradigm. Faced by new age of electronic records, it's important to start a discussion for the reasonable methods of electronic records management at once. The most drastically changed part of record management by the electronic technique is the life-cycle of records. The commonly practiced three-stage life-cycle is to be reduced to the two-stage life-cycle, and the concept of the spatial movement of records is to be changed. It can be also pointed that the public emerges as user from the early creating stage of records beyond time and space. Thus is can be said that the method of the management features dynamic and cohesive. The method of appraisal must be also changed and reproduced, so that it can reflect the various levels considering dynamics of the electronic records. Supposedly it will be a core factor that causes the change of methodology in records management with the change of life-cycle theory. It must be noted that various subjects would be involved in the work of classification and description over time and space and that feedback between them is of important. Description also tends to be made at the crating stage of records and structured dynamically. It results from the change of life-cycle and the introduction of the concept of continuum. Such trend allows us to start discussions on the assumption that description of both creator and archival professionals act together an important role. Of course, it is linked with the methodology in which most descriptions are made automatically at the early drafting stage of the structure. The meat date is formed on the assumption that there should be feedback between areas of automatic description, description of creators and archival professionals. The most important thing in description is to develop a suitable way how it is structured. An alternative must be offered for managing data set. As iweb that is being operated by Myongji university shows, records created in daily business are managed not as electronic records but as date base. This is because they exist outside the repository in the EDMS system. Since data set often has various sources, an alternative for classification needs to be developed. It is now likely that database is filed according to the created year to be transferred automatically to the repository. Over a long-term the total management of database, electronic records and electronic information will be a topic. A right direction of new paradigm will be found for both iweb and E-government, when practice and studies of theories are combined and interacted.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3384-3398
• /
• 2020

In recent years, as the environment has become an important issue in dealing with food, energy, and urban development, diverse environment-related applications such as environmental monitoring and ecosystem management have emerged. In such applications, automatic classification of animals using video or sound is very useful in terms of cost and convenience. So far, many works have been done for animal sounds classification using artificial intelligence techniques such as a convolutional neural network. However, most of them have dealt only with the sound of a specific class of animals such as bird sounds or insect sounds. Due to this, they are not suitable for classifying various types of animal sounds. In this paper, we propose a sound classification scheme based on a multi-feature network for classifying sounds of multiple species of animals. To do that, we first collected multiple animal sound datasets and grouped them into classes. Then, we extracted their audio features by generating mixed records and used those features for training. To evaluate the effectiveness of our scheme, we constructed an animal sound classification model and performed various experiments. We report some of the results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.4
• /
• pp.594-601
• /
• 2006

Coding of occupational and industrial codes is a major operation in census survey of Korean statistics bureau. The coding process has been done manually. Such manual work is very labor and cost intensive and it usually causes inconsistent results. This paper proposes an automatic coding system based on example-based learning. The system converts natural language input into corresponding numeric codes using code generation system trained by example-based teaming after applying manually built rules. As experimental results performed with training data consisted of 400,000 records and 260 manual rules, the proposed system showed about 76.69% and 99.68% accuracy for occupational code classification and industrial code classification, respectively.