• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.2C
• /
• pp.208-218
• /
• 2006

In this paper, we introduce the creation methods of attack detection model using data mining technologies that can classify the latest attack types, and can detect the modification of existing attacks as well as the novel attacks. Also, we evaluate comparatively these attack detection models in the view of detection accuracy and detection time. As the important factors for creating detection models, there are data, attribute, and detection algorithm. Thus, we used NetFlow data gathered at the real network, and KDD Cup 1999 data for the experiment in large quantities. And for attribute selection, we used a heuristic method and a theoretical method using decision tree algorithm. We evaluate comparatively detection models using a single supervised/unsupervised data mining approach and a combined supervised data mining approach. As a result, although a combined supervised data mining approach required more modeling time, it had better detection rate. All models using data mining techniques could detect the attacks within 1 second, thus these approaches could prove the real-time detection. Also, our experimental results for anomaly detection showed that our approaches provided the detection possibility for novel attack, and especially SOM model provided the additional information about existing attack that is similar to novel attack.

• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.4
• /
• pp.315-334
• /
• 2013

This study performs opinion mining of newspaper articles, based on topics extracted by topic modeling. We analyze the attitudes of the news media towards a major issue of 'presidential election', assuming that newspaper partisanship is a kind of opinion. We first extract topics from a large collection of newspaper texts, and examine how the topics are distributed over the entire dataset. The structure and content of each topic are then investigated by means of network analysis. Finally we track down the chronological distribution of the topics in each of the newspapers through time serial analysis. The result reveals that both the liberal newspapers and the conservative newspapers exhibit their own tendency to report in line with their adopted ideology. This confirms that we can count on opinion mining technique based on topics in order to analyze opinion in a reliable fashion.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.2
• /
• pp.373-384
• /
• 2014

Data mining is to clarify pattern or correlation of mass data of complicated structure and to predict the diverse outcomes. This technique is used in the fields of finance, telecommunication, circulation, medicine and so on. In this paper, we selected risk factors of respiratory diseases in the field of medicine. The data we used was divided into respiratory diseases group and health group from the Gyeongsangbuk-do database of Community Health Survey conducted in 2012. In order to select major risk factors, we applied data mining techniques such as neural network, logistic regression, Bayesian network, C5.0 and CART. We divided total data into training and testing data, and applied model which was designed by training data to testing data. By the comparison of prediction accuracy, CART was identified as best model. Depression, smoking and stress were proved as the major risk factors of respiratory disease.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.643-648
• /
• 2003

In order to provide efficient retrieving results for user query on the web environment, the various searching algorithms have developed and considered user's preference and convenience. However, the searching algorithms are developed on the horizontal and non hierarchical web environment in general and could not apply to the complex hierarchical and functional web environments such like the enterprise network. In this paper, we purpose the multi-agent based web mining system which can provide the efficient mining results to the user on the special web environment. For doing this, we suggest the network model with the hierarchical web environment and model the multi agent based web mining system which has four corporation agents and fourteen process modules. Then, we explain the detailed functions of each agent considered the hierarchical environment according to the module. Especially, we purpose the new merging agent and improved ranking algorithm by using the graph theory.

• Journal of Digital Convergence
• /
• v.18 no.8
• /
• pp.37-48
• /
• 2020

This study aimed at understanding trends of living lab studies and deriving implications for directions of the studies by utilizing text mining. The study included network analysis and topic modelling based on keywords and abstracts from total 166 thesis published between 2011 and November 2019. Centrality analysis showed that living lab studies had been conducted focusing on keywords like innovation, society, technology, development, user and so on. From the topic modelling, 5 topics such as "regional innovation and user support", "social policy program of government", "smart city platform building", "technology innovation model of company" and "participation in system transformation" were extracted. Since the foundation of KNoLL in 2017, the diversification of living lab study subjects has been made. Quantitative analysis using text mining provides useful results for development of living lab studies.

• Journal of Korean Society for Quality Management
• /
• v.47 no.1
• /
• pp.97-108
• /
• 2019

Purpose: The purpose of this study is to propose a new Risk Priority Number(RPN) evaluation method which analyzes value of product functions by mining customer opinions in Social Network Service(SNS). Methods: A traditional RPN is measured by three evaluation standards (Severity, Occurrence, Detection) which are analyzed by manufacturing engineers and researchers. On the other hand, these standards are analyzed by customers' viewpoints through SNS opinion mining in this research. In order to extract customer feedbacks from textual data sets, the methodology in this paper implies natural language processing, hereby collecting product related data sets and analyzing the opinions automatically. An emotional polarity of an opinion indicates severity, while the number of negative opinion shows occurrence, and the entire number of customer opinion refers to detection. Results: The results of this study are as follows; As a result of the CRPN evaluation, it is confirmed that the features evaluated as risky are highly likely to be improved in the next series. Therefore, CRPN is an effective risk assessment model that reflects customer feedback. Conclusion: Reflecting customer feedback is a useful tool for risk assessment of the product as well as for developing new products and improving existing products.

• Journal of Intelligence and Information Systems
• /
• v.11 no.2
• /
• pp.17-29
• /
• 2005

The purpose of the study was to explore the potential of the Social Network Analysis as an analytical tool for scientific investigation of learner-learner, or learner-tutor interaction within a Computer Supported Corporative Learning (CSCL) environment. Theoretical and methodological implication of the Social Network Analysis had been discussed. Following theoretical analysis, an exploratory empirical study was conducted to test statistical correlation between traditional performance measures such as achievement and team contribution index, and the centrality measure, one of the many quantitative measures the Social Network Analysis provides. Results indicate the centrality measure was correlated with the higher order teaming performance and the peer-evaluated contribution indices. An interpretation of the results and their implication to instructional design theory and practices were provided along with some suggestions for future research.

• Geophysics and Geophysical Exploration
• /
• v.5 no.4
• /
• pp.272-279
• /
• 2002

During field survey of ground penetrating radar or borehole radar, we often encounter some problems which could be solved easily by modifying structure of the system such as antenna length, shape or array. In addition, it is necessary that the user could easily modify configuration of the radar system na test various array of antennas in order to verify and confirm numerical modeling results concerning radar antennas. We have developed network-analyzer-based, stepped-frequency georadar system. This system had been comprised with coaxial cable to confirm possibility of the system, then we have upgraded the system to use optical cable that is composed of optical/electric transducers, electric/optical transducers, amp, pre-amp and antennas. The software for the aquisition of data has been developed to control the system automatically using PC with GPIB communication and to display the obtained data graphically. We have tested the system in field survey na the results have been compared with those of RAMAC/GPR system.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.4
• /
• pp.549-566
• /
• 2022

Recently, artificial intelligence (AI) technology has progressed rapidly, and industries using this technology are significantly increasing. Further, analysis research using text mining, which is an application of artificial intelligence, is being actively developed in the field of social science research. About 125 laws, including joint laws, have been enacted under the Ministry of Oceans and Fisheries in various sectors including marine environment, fisheries, ships, fishing villages, ports, etc. Research on the laws under the Ministry of Oceans and Fisheries has been progressively conducted, and is steadily increasing quantitatively. In this study, the domestic research trends were analyzed through text mining, targeting the research papers related to laws of the Ministry of Oceans and Fisheries. As part of this research method, first, topic modeling which is a type of text mining was performed to identify potential topics. Second, co-occurrence network analysis was performed, focusing on the keywords in the research papers dealing with specific laws to derive the key themes covered. Finally, author network analysis was performed to explore social networks among authors. The results showed that key topics have been changed by period, and subjects were explored by targeting Ship Safety Law, Marine Environment Management Law, Fisheries Law, etc. Furthermore, in this study, core researchers were selected based on author network analysis, and the tendency for joint research performed by authors was identified. Through this study, changes in the topics for research related to the laws of the Ministry of Oceans and Fisheries were identified up to date, and it is expected that future research topics will be further diversified, and there will be growth of quantitative and qualitative research in the field of oceans and fisheries.

• The Korean Journal of Applied Statistics
• /
• v.29 no.7
• /
• pp.1257-1270
• /
• 2016

This study deals with the prediction of the total number of movie audiences as a measure for the box office. Prediction is performed by classification techniques of data mining such as decision tree, multilayer perceptron(MLP) neural network model, multinomial logit model, and support vector machine over time such as before movie release, release day, after release one week, and after release two weeks. Predictors used are: online word-of-mouth(OWOM) variables such as the portal movie rating, the number of the portal movie rater, and blog; in addition, other variables include showing the inherent properties of the film (such as nationality, grade, release month, release season, directors, actors, distributors, the number of audiences, and screens). When using 10-fold cross validation technique, the accuracy of the neural network model showed more than 90 % higher predictability before movie release. In addition, it can be seen that the accuracy of the prediction increases by adding estimates of the final OWOM variables as predictors.