• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.1
• /
• pp.459-466
• /
• 2011

In this paper, we proposed a data mining framework for the management of alerts in order to improve the performance of the intrusion detection systems. The proposed alert data mining framework performs alert correlation analysis by using mining tasks such as axis-based association rule, axis-based frequent episodes and order-based clustering. It also provides the capability of classify false alarms in order to reduce false alarms. We also analyzed the characteristics of the proposed system through the implementation and evaluation of the proposed system. The proposed alert data mining framework performs not only the alert correlation analysis but also the false alarm classification. The alert data mining framework can find out the unknown patterns of the alerts. It also can be applied to predict attacks in progress and to understand logical steps and strategies behind series of attacks using sequences of clusters and to classify false alerts from intrusion detection system. The final rules that were generated by alert data mining framework can be used to the real time response of the intrusion detection system.

• The KIPS Transactions:PartB
• /
• v.15B no.4
• /
• pp.347-354
• /
• 2008

In this paper, we propose a method for personalizing and intelligence of speech Web. The proposed system records information that was demanded in the past as a transaction, explores association rules from those transactions, and discovers itemsets from frequent requests. This method is to recommend relevant information, based on frequent itemsets, to users who have similar inclinations to previous users. As a result of experimenting and implementation of proposed system for verification, we confirmed that the proposed system can recommend previously frequently requested information as relevant information.

• Proceedings of the Korean Society of Marine Engineers Conference
• /
• 2002.05a
• /
• pp.225-231
• /
• 2002

A specialized web search engine is an internet tool for detecting information in finite cyber world. It helps to retrieve necessary information in internet sites quickly In this paper, we design and implement a prototype search engine using method of mining for the association rule discovery. It consists of a search engine part and a search robot part. The search engine uses keyword method and is considered as various user oriented interface. The search robot fetches information related to ship parts n world wide web. The experiments show that our search engine(AISE) is superior to other search engines in collecting necessary informations.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.266-272
• /
• 2002

Recently various of information suppliers provide information via WWW so the necessary of search engine grows larger. However the efficiency of most search engines is low comparatively because of using simple pattern match technique between user's query and web document. And a manifest contents of query for special expert field so much worse A specialized search engine returns the specialized information depend on each user's search goal. It is trend to develop specialized search engines in many countries. For example, in America, there are a site that searches only the recently updated headline news and the federal law and the government and and so on. However, most such engines don't satisfy the user's needs. This paper proposes the specialized search engine for ocean information that uses user's query related with ocean and search engine uses the association rules in web data mining. So specialized search engine for ocean provides more information related to ocean because of raising recall about user's query

• Journal of Internet Computing and Services
• /
• v.7 no.3
• /
• pp.169-178
• /
• 2006

In this paper, we define the large word sets which are noble variations the large item sets in mining association rules, and improve the accuracy for NaiveBayes based on the defined large word sets. In order to use them, a document is divided into the several paragraphs, and then each paragraph can be transformed as the transaction by extracting words in it. The proposed method was implemented by using Al:Categorizer framework and its accuracies were measured by the experiments for reuter-21578 data set. The results of the experiments show that the proposed method improves the accuracy of the conventional NaiveBayes.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.275-278
• /
• 2008

Recently, there are many research of datamining. On the transaction dataset, association rules is made by finding of interesting patterns. A part of mining, sub-structure mining is increased in interest of and applied to many high technology. But graph mining has more computing time then itemset mining. Therefore, that need efficient way for avoid duplication. GASTON is best algorithm of duplication free. This paper analyze GASTON and expect the future work.

• The Journal of the Korea Contents Association
• /
• v.12 no.4
• /
• pp.76-85
• /
• 2012

Through opinion mining, we can analyze the degree of positive or negative sentiments that customers feel about important entities or attributes in online customer reviews. But, the limit of the opinion mining techniques is to provide only simple functions in analyzing the reviews. In this paper, we proposed novel techniques that can analyze the online customer reviews multi-dimensionally. The novel technique is to modify the existing OLAP techniques so that they can be applied to text data. The novel technique, that is, multi-dimensional analytic model consists of noun, adjective and document axes which are converted into four relational tables in relational database. The multi-dimensional analysis model would be new framework which can converge the existing opinion mining, information summarization and clustering algorithms. In this paper, we implemented the multi-dimensional analysis model and algorithms. we recognized that the system would enable us to analyze the online customer reviews more complexly.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.9
• /
• pp.2354-2360
• /
• 2009

Healthcare is a field where ubiquitous computing is most widely used. We propose a mining-based healthcare multi-agent system for ubiquitous computing environments. This proposed scheme select diagnosis patterns using mining in the real-time biosignal data obtained from a patient's body. In addition, we classify them into normal, emergency and be ready for an emergency. This proposed scheme can deal with the enormous quantity of real-time sensing data and performs analysis and comparison between the data of patient's history and the real-time sensory data. We separate Association rule exploration into two data groups: one is the existing enormous quantity of medical history data. The other group is real-time sensory data which is collected from sensors measuring body temperature, blood pressure, pulse. Proposed system has advantage that can handle urgent situation in the far away area from hospital through PDA and mobile device. In addition, by monitoring condition of patient in a real time base, it shortens time and expense and supports medical service efficiently.

• Journal of Intelligence and Information Systems
• /
• v.13 no.2
• /
• pp.69-80
• /
• 2007

The preferences of customers change over time. However, existing collaborative filtering (CF) systems are static, since they only incorporate information regarding whether a customer buys a product during a certain period and do not make use of the purchase sequences of customers. Therefore, the quality of the recommendations of the typical CF could be improved through the use of information on such sequences. In this study, we propose a new methodology for enhancing the quality of CF recommendation that uses customer purchase sequences. The proposed methodology is applied to a large department store in Korea and compared to existing CF techniques. Various experiments using real-world data demonstrate that the proposed methodology provides higher quality recommendations than do typical CF techniques with better performance.

• Journal of Korea Spatial Information System Society
• /
• v.11 no.2
• /
• pp.119-132
• /
• 2009

Owing to the GIS technology, a vast volume of spatial data has been accumulated, thereby incurring the necessity of spatial data mining techniques. In this paper, we propose a new spatial data mining system named SD-Miner. SD-Miner consists of three parts: a graphical user interface for inputs and outputs, a data mining module that processes spatial mining functionalities, a data storage model that stores and manages spatial as well as non-spatial data by using a DBMS. In particular, the data mining module provides major data mining functionalities such as spatial clustering, spatial classification, spatial characterization, and spatio-temporal association rule mining. SD-Miner has own characteristics: (1) It supports users to perform non-spatial data mining functionalities as well as spatial data mining functionalities intuitively and effectively; (2) It provides users with spatial data mining functions as a form of libraries, thereby making applications conveniently use those functions. (3) It inputs parameters for mining as a form of database tables to increase flexibility. In order to verify the practicality of our SD-Miner developed, we present meaningful results obtained by performing spatial data mining with real-world spatial data.