• Journal of Information Management
• /
• v.24 no.4
• /
• pp.43-57
• /
• 1993

This paper discusses the basic concept of artificial intelligence(AI) and expert system and a particular technique(fuzzy logic) applied to expert systems. It examines expert system as search intermediaries during the past few years, particularly in terms of the following functions: 1) handling certain classes of questions on a particular database, 2) assisting in decision making for selecting databases or search terms, and 3) offering advice while keeping the end-user in the control of the searching process. The limitations and difficulties involved in developing such expert systems are also presented.

• Journal of the Korean Society for information Management
• /
• v.24 no.2
• /
• pp.89-104
• /
• 2007

This research attempts to give a personalized recommendation framework in large-sized music contents environment. Despite of existing studios and commercial contents for recommendation systems, large online shopping malls are still looking for a recommendation system that can serve personalized recommendation and handle large data in real-time. This research utilizes data mining technologies and new pattern matching algorithm. A clustering technique is used to get dynamic user segmentations using user preference to contents categories. Then a sequential pattern mining technique is used to extract contents access patterns in the user segmentations. And the recommendation is given by our recommendation algorithm using user contents preference history and contents access patterns of the segment. In the framework, preprocessing and data transformation and transition are implemented on DBMS. The proposed system is implemented to show that the framework is feasible. In the experiment using real-world large data, personalized recommendation is given in almost real-time and shows acceptable correctness.

• Journal of the Korean Society for information Management
• /
• v.30 no.1
• /
• pp.111-129
• /
• 2013

This study analyzed the process of multimedia services and indexed the core quality characteristics through the tools employed in 'Define' and 'Measure' steps of the 6 Sigma DMAIC methodology. To achieve the goal, as a case study of 'S' University Central Library, first, brainstorming technique was used to tap the librarians, second, interview with the half-time student workers, third, user's opinion on homepage was analyzed and lastly, the interview with the users. This study also drew some potential causal factors which would likely to affect the multimedia service using Process Map and C&E Diagram. Those factors were prioritized using X-Y matrix and Pareto Chart. This study revealed 14 factors affecting multimedia services: 'presence/absence of the persons who are in charge of selection', 'cycle of selection materials', 'presence/absence of seperated multimedia room', 'materials arrangement method', 'notification of popular materials', 'notification of documents arrivals', 'methods of noticing new arrivals', 'methods of ordering materials', 'cycle of checking order status', 'types of persons requesting materials', 'methods of requesting materials', 'checking of the status of the returned materials', 'methods of noticing materials in housed', and 'methods of ways to return overdue materials'.

• KEPCO Journal on Electric Power and Energy
• /
• v.6 no.4
• /
• pp.413-418
• /
• 2020

It is necessary to manage the prediction accuracy of the machine learning model to prevent the decrease in the performance of the grid network condition prediction model due to overfitting of the initial training data and to continuously utilize the prediction model in the field by maintaining the prediction accuracy. In this paper, we propose an automation technique for maintaining the performance of the model, which increases the accuracy and reliability of the prediction model by considering the characteristics of the power grid state data that constantly changes due to various factors, and enables quality maintenance at a level applicable to the field. The proposed technique modeled a series of tasks for maintaining the performance of the power grid condition prediction model through the application of the workflow management technology in the form of a workflow, and then automated it to make the work more efficient. In addition, the reliability of the performance result is secured by evaluating the performance of the prediction model taking into account both the degree of change in the statistical characteristics of the data and the level of generalization of the prediction, which has not been attempted in the existing technology. Through this, the accuracy of the prediction model is maintained at a certain level, and further new development of predictive models with excellent performance is possible. As a result, the proposed technique not only solves the problem of performance degradation of the predictive model, but also improves the field utilization of the condition prediction model in a complex power grid system.

• Journal of Information Management
• /
• v.21 no.2
• /
• pp.9-23
• /
• 1990

CD-ROM technique, not more than 10 years after development, goes through rapid growth, has been taken advantage of several practical application parts. Needless to say about bibliographic data, numeric value, the phonetics, an image and a picture data that are recorded as abstract or full text, and offered and applied to industry, information service including library, it can be used for library staffs, information retrieval. Escape from the need of one disc drive and one computer to access one disc, now we organize an ideal system that can be retrieved several CD-ROM used only one drive, several users can access several information, so networking is possible through LAN. In this article, we studied the function and type, characteristics, system, structure, data block, production procedure, standardization of CD-ROM LAN.

• Journal of the Korean Society for information Management
• /
• v.31 no.1
• /
• pp.99-118
• /
• 2014

This paper carried out co-word analysis of noun and noun phrase using text-mining technique in order to grasp the research trends on domestic and international information science articles. It was conducted based on collected titles and articles of the papers published in the Journal of the Korean Society for Information Management (KOSIM) and Journal of American Society for Information Science and Technology (JASIST) from 1990 to 2013. By dividing whole period into five publication window, this paper was organized into the following processes: 1) analysis of high frequency co-word pair to examine the overall trends of both information science articles 2) analysis of each word appearing with high frequency keyword to grasp the detailed subject 3) focused network analysis of trend after 2010 when distinctively new keyword appeared. The result of the analysis shows that KOSIM has considerable portion of studies conducted regarding topics such as library, information service, information user and information organization. Whereas, JASIST has focused on studies regarding information retrieval, information user, web information, and bibliometrics.

• Journal of Information Management
• /
• v.39 no.4
• /
• pp.47-66
• /
• 2008

This study introduced the machine learning algorithms to overcome the many different limitations involved with manual classification and to provide the users with faster and more accurate classification service. The experiments objects of the study were consisted of 100 literature titles for each of the eight subject categories in MeSH. The algorithms used to the experiments included Neural network, C5.0, CHAID and KNN. As results, the combination of the neural network and C5.0 technique recorded classification accuracy of 83.75%, which was 2.5% and 3.75% higher than that of the neural network alone and C5.0 alone, respectively. The number represented the highest accuracy rates among the four classification experiments. Thus the use of the neural network and C5.0 technique together will result in higher accuracy rates than the techniques individually.

• Journal of Industrial Convergence
• /
• v.21 no.12
• /
• pp.55-62
• /
• 2023

Recent ransomware attacks employ various techniques and pathways, posing significant challenges in early detection and defense. Consequently, the scale of damage is continually growing. This paper introduces a machine learning-based approach for effective ransomware detection by focusing on file encryption and encryption patterns, which are pivotal functionalities utilized by ransomware. Ransomware is identified by analyzing password behavior and encryption patterns, making it possible to detect specific ransomware variants and new types of ransomware, thereby mitigating ransomware attacks effectively. The proposed machine learning-based encryption behavior detection technique extracts encryption and encryption pattern characteristics and trains them using a machine learning classifier. The final outcome is an ensemble of results from two classifiers. The classifier plays a key role in determining the presence or absence of ransomware, leading to enhanced accuracy. The proposed technique is implemented using the numpy, pandas, and Python's Scikit-Learn library. Evaluation indicators reveal an average accuracy of 94%, precision of 95%, recall rate of 93%, and an F1 score of 95%. These performance results validate the feasibility of ransomware detection through encryption behavior analysis, and further research is encouraged to enhance the technique for proactive ransomware detection.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.2 no.1
• /
• pp.178-210
• /
• 1974

It needs to put into practice the systems analysis in the analysis of some operations and status of library for the purpose of systematizing the work of reforming in the new easier form to process, to storage, to retrieve and to make use of the increasing informations and data of library. In this study, some of systems which are generally using in every library was caught in the case study of K university library. Having analyzed them with the two methods of the flowcharting and mathematical analysis, we found the obstructive factors in operation. As the result of this research, it was gained the new system as the alternative one. A. Alternative System B. Advantages of alternative systems 1. In the reference room When it converts the present system into the new system, it can profit 6.771 won/user (13.815won-7.044won=6.771 won). Therefore, a half the average required cost of the present system can be saved. If this saving would be alloted for the cost 33,000won required to make the cataloging cards, it would be taken for 94 days (33,000 won ${\div}$ 6,771 won/user=4,874users. 4,874users ${\div}$ 52users/day=94days) to get it. The saving cost/year by the new system will be 95,417 won, and in the first year the initial cost (33,000won) reduces the saving cost to 62,417won. 2. In the periodical room The average required time for using the materials of the present system is 17 minutes/user and the average required cost/user is 23.775won, while the average required time of the new system is 4 minutes and the average required cost/user is 5.33won. Therefore, the new system has profit 4 times of the present system. Accordingly, it occurs when the dispersed periodical materials get together. 3. In the classification and cataloging When one processes - the oriental books - by the Linear Programming Technique, the maximum of the process can be increased from 11.6 volumes per librarian of the present system to 12 volumes per librarian of the new system increased 0.4 volume in a day, and cataloging by the manual printer can be shorten from 3 minutes per card of the present system to 1.5 minutes per card of the new system. Consequently, we can complete the other operations (books equipment, updating of cataloging cards, etc.) with 141 minutes which are saved in the course of the afore-mentioned works. 4. In the status of collections The average growth rate of 4 years from 1968 to 1971 is 9.825 %, and that of the purchased materials is 6.2% similar to the advanced nations, but it has the different position from 215,000 volumes by the Standard Degree for Establishment of College and University, and the difference between the total collections 151,671 volumes and Dunns' growth model ($N_t=N_oe^{-at}$) claimed by Leimkuhler 155,297 volumes in 1971 is 3,626 volumes, and for the purpose of compensation the difference, we found the fact that it needs to have the increased budget of 24~30% per year, Thus, if the budget of 24~30 % per year. Thus, if the budget would be increased per year as the rate of the afore-mentioned figure, it would be reached at the Standard Degree for Establishment of College and University in 1975, and thereafter, it can be decreased to the lebel which is able to maintain the growth rate of 5~6% per year.

• Journal of the Korean Society for information Management
• /
• v.23 no.1 s.59
• /
• pp.221-241
• /
• 2006

This research suggested a new patent index based on patent citation technique using cited information, For this purpose, comparison research on library and patent information related citation database providing citation index was done. The information quality and meaning on the impact factor of JCR and the technology factor of CHI were reinterpreted. The former emphasizes the quality of continuous publication using relative citation frequency. The latter only emphasizes the information itself because it assesses the quality of patent characteristics. To overcome these difficulties, the latter re-authorized a relative quality to the organization possessing the patent using technology impact factor. Three new patent index were proposed on the basis of cited information to complement this. However, the comparative object was limited to American patent information that presented cited information of patent applied cases, and the comparison and research of domestic patent information could not be done.