• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.10
• /
• pp.59-68
• /
• 1998

The goal of data mining is to develop the automatic and intelligent tools and technologies that can find useful knowledge from databases. To meet this goal, we propose an efficient data mining algorithm based on the fuzzy decision tree. The proposed method combines comprehensibility of decision tree such as ID3 and C4.5 and representation power of fuzzy set theory. So, it can generate simple and comprehensive rules describing data. The proposed algorithm consists of two stages: the first stage generates the fuzzy membership functions using histogram analysis, and the second stage constructs a fuzzy decision tree using the fuzzy membership functions. From the testing of the proposed algorithm on the IRIS data and the Wisconsin Breast Cancer data, we found that the proposed method can generate a set of fuzzy rules from data efficiently.

• Proceedings of the Korea Database Society Conference
• /
• 1999.06a
• /
• pp.281-287
• /
• 1999

Decision class analysis (DCA) is viewed as a classification problem where a set of input data (situation-specific knowledge) and output data (a topological leveled influence diagram (ID)) is given. Situation-specific knowledge is usually given from a decision maker (DM) with the help of domain expert(s). But it is not easy for the DM to know the situation-specific knowledge of decision problem exactly. This paper presents a methodology fur sensitivity analysis of DCA under incomplete information. The purpose of sensitivity analysis in DCA is to identify the effects of incomplete situation-specific frames whose uncertainty affects the importance of each variable in the resulting model. For such a purpose, our suggested methodology consists of two procedures: generative procedure and adaptive procedure. An interactive procedure is also suggested based the sensitivity analysis to build a well-formed ID. These procedures are formally explained and illustrated with a raw material purchasing problem.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.281-287
• /
• 1999

Decision class analysis (DCA) is viewed as a classification problem where a set of input data (situation-specific knowledge) and output data(a topological leveled influence diagram (ID)) is given. Situation-specific knowledge is usually given from a decision maker (DM) with the help of domain expert(s). But it is not easy for the DM to know the situation-specific knowledge of decision problem exactly. This paper presents a methodology for sensitivity analysis of DCA under incomplete information. The purpose of sensitivity analysis in DCA is to identify the effects of incomplete situation-specific frames whose uncertainty affects the importance of each variable in the resulting model. For such a purpose, our suggested methodology consists of two procedures: generative procedure and adaptive procedure. An interactive procedure is also suggested based the sensitivity analysis to build a well-formed ID. These procedures are formally explained and illustrated with a raw material purchasing problem.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.1
• /
• pp.34-41
• /
• 1998

In this paper, I designed a P1394 serial bus chip as new bus interface architecture which can transmit the multimedia data at the rate of 400 Mbps and guarantee necessary bandwidth. because multimedia data become meaningless data after appropriate time, it is necessary to transfer multimedia data in real time, P1394 serial bus chip designed in this paper support isochronous transfer mode to solve this problem. Also, designed P1394 serial bus chip can transfer high quality video data or high quality audio data because it support the speed of 400 Mbps. While user must set device ID manually in previous interface such as SCSI, device ID is automatically determined if user connect each node with designed P1394 serial bus cable and power on. To design this chip, I verified the behavioral of the entrire system and synthesized layout. Also, I did layout the analog blocks and blocks which must be optimized in full custom.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.593-598
• /
• 2003

Machine learning organizes knowledge for efficient and accurate reuse. This paper is concerned with methods of concept learning from examples, which glean knowledge from a training set of preclassified ‘objects’. Ideally, training facilitates classification of novel, previously unseen objects. However, every learning system relies on processing and representation assumptions that may be detrimental under certain circumstances. We explore the biases of a well-known learning system, ID3, review improvements, and introduce some improvements of our own, each designed to yield accurate and pedagogically sound classification.

• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.435-441
• /
• 2013

This paper review about kerberos security authentication scheme and policy for big data service. It analyzed problem for security technology based on Hadoop framework in big data service environment. Also when it consider applying problem of kerberos security authentication system, it analyzed deployment policy in center of main contents, which is occurred in commercial business. About the related applied Kerberos policy in US, it is researched about application such as cross platform interoperability support, automated Kerberos set up, integration issue, OPT authentication, SSO, ID, and so on.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.785-796
• /
• 2019

Due to the view point, illumination, personal gait and other background situation, person re-identification across cameras has been a challenging task in video surveillance area. In order to address the problem, a novel method called Joint Bayesian across different cameras for person re-identification (JBR) is proposed. Motivated by the superior measurement ability of Joint Bayesian, a set of Joint Bayesian matrices is obtained by learning with different camera pairs. With the global Joint Bayesian matrix, the proposed method combines the characteristics of multi-camera shooting and person re-identification. Then this method can improve the calculation precision of the similarity between two individuals by learning the transition between two cameras. For investigating the proposed method, it is implemented on two compare large-scale re-ID datasets, the Market-1501 and DukeMTMC-reID. The RANK-1 accuracy significantly increases about 3% and 4%, and the maximum a posterior (MAP) improves about 1% and 4%, respectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.103-109
• /
• 2005

Research about P2P system have recently a lot of attention in connection of form that pass early Centralized P2P and is Decentralized P2P. Specially, Structured P2P System of DHT base have a attention to scalability and systematic search and high search efficiency by routing. But, Structured P2P System of DHT base have problem, file can be located only their unique File IDs that although user may wish to search for files using a set descriptive keyword or do not have the exact File ID of the files. This paper propose extended-CAN mechanism that creates File ID of Contents base and use KID and CKD for commonness keyword processing to support keyword search in P2P System of DHT base.

• Journal of KIISE:Databases
• /
• v.32 no.2
• /
• pp.177-192
• /
• 2005

In this paper, we introduce a structural redundancy method. It reduces the query processing cost incurred when reconfiguring an XML document from divided XML data in shredding XML documents into relations. The fundamental idea is that query performance can be enhanced by analyzing query patterns and replicating data essential for the query performance. For the practical and effective structural redundancy, we analyzed three types of ID, VALUE, and SUBTREE replication. In addition, if given XML data and queries are very large and complex, it can be very difficult to search optimal redundancy set. Therefore, a heuristic search method is introduced in this paper. Finally, XML query processing cost arising by employing the structural redundancy, and the efficiency of proposed search method arc analyzed experimentally It is manifest that XML read query is performed more quick]y but XML update query is performed more slowly due to the additional update consistency cost for replicas. However, experimental results showed that in-place ID replication is useful even in having excessive update cost. It was also observed that multiple-place SUBTREE replication can enhance read query performance remarkably if only update cost is not excessive.

• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.12
• /
• pp.511-516
• /
• 2013

The cases of identification forgery and counterfeiting are increasing under the current identification system, which was established based on social conditions and administrative environments over 20 years ago. This leads to an increase of various criminal acts including illegal loan using fake ID and a number of damages caused out of good intentions that result in interference with the operations of public organizations. In addition, according to the advancement of information society, privacy protection has emerged as an important issue. However, ID card exposes individuals' personal information, such as names, resident registration numbers, photos, addresses and fingerprints, and thus the incidents associated with illegal use of personal information are increasing continuously. Accordingly, this study aimed at examining the issues of ID card forgery/counterfeiting and privacy protection and at proposing a next-generation identification system to supplement such weaknesses. The top priority has been set as prevention of forgery/counterfeiting and privacy protection in order to ensure the most important function of national identification system, which is user identification.