• Journal of Internet Computing and Services
• /
• v.5 no.5
• /
• pp.93-103
• /
• 2004

The main function of the intrusion Detection System (IDS) usee to be more or less passive detection of the intrusion evidences, but recently it is developed with more diverse types and methodologies. Especially, it is required that the IDS should process large system audit data fast enough. Therefore the data mining or neural net algorithm is being focused on, since they could satisfy those situations. In this study, we first surveyed and analyzed the several recent intrusion trends and types. And then we designed and implemented an IDS using back-propagation algorithm of the neural net, which could provide more effective solution. The distinctive feature of our study could be stated as follows. First, we designed the system that allows both the Anomaly dection and the Misuse detection. Second, we carried out the intrusion analysis experiment by using the reliable KDD Cup ‘99 data, which would provide us similar results compared to the real data. Finally, we designed the system based on the object-oriented concept, which could adapt to the other algorithms easily.

• Journal of Broadcast Engineering
• /
• v.13 no.3
• /
• pp.319-327
• /
• 2008

The purpose of study is to investigate the customer oriented transaction environment for the customers' convenience, the plan of public policy in regard to the customer oriented T-Commerce, and the consumption pattern of customers' commercial transaction, necessary for the marketing strategy by analyzing the demand for the T-Commerce with the purchase intention and maximum willingness to pay according to the demographic factors, the pattern of commercial transaction, and the technology innovation types. The results showed that there were statistically significant relations between consumer's willingness price to pay for the T-commerce and the consumer's technology adoption types, monthly internet shopping amounts, and weekly TV-home shopping hours. The simulations on a basis of multiple regression analysis for the T-commerce were illustrated by those factors.

• Journal of Internet Computing and Services
• /
• v.10 no.5
• /
• pp.95-105
• /
• 2009

There are various studies to provide useful information for users on huge data of web-sites. Web usage mining among them is a method to extract meaningful patterns based on web users' log data. Most of existing patterns of web usage mining, however, had not considered users' diverse inclination but created general models. Web users' keywords can have various meaning upon their tendency and background knowledge. This study is for generating Multi Concept Keyword Model (MCK-Model) by analyzing web usage information on users' keywords of interest. MCK-Model can supply web page network for various inclination based on users' keywords of interest. Also, MCK-Model can be used to recommend the most proper web pages and it has been confirmed that the suggested method is useful enough.

• Journal of the Korea Society for Simulation
• /
• v.20 no.3
• /
• pp.111-117
• /
• 2011

This paper suggests the passenger model considered evacuation behavioral characteristics on the passenger ship fire using a rules-based agent technique. The existing evacuation simulation system was modeled only passenger speed. The speed-based model considered passenger's physical characteristics, so it couldn't consider evacuation behavioral characteristics. For solving this problem, we modeled the passenger model using a rule-based agent applied evacuation behavioral characteristics. The rule-based agent consists of knowledge base and inference engine. In knowledge base, we represented evacuation behavioral characteristics, and chose the examples of the evacuation behavioral characteristics to show various patterns of behavior. And we simulated in the IMO MSC/Circ.1238 example 8 and we proved the simulation results could represent variety patterns of human behavior.

• Journal of the Korean association of regional geographers
• /
• v.8 no.1
• /
• pp.98-109
• /
• 2002

The long term land-cover changes and the pattern of morphological changes in foredune ridges and unvegetated dunes were investigated for about 30 years through analysing aerial photographs in Shinduri coastal dunefield, Korea. As a result, forested dune area increased while unvegetated dune area decreased continuously since 1967. Foredune ridges retreated landward about 80m away from the former coast-line in the middle part while they advanced seaward after construction of dike in the northern part during last 3 decades. Unvegetated dunes in the middle part of the dunefield were eroded at seaward side and moved landward away. These facts mean not only coastal dune area has been affected by man-made effects such as afforestation and coastal developments but also shinduri coastal dune area has been stabilized by plants and has been negative sediment budget.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.3
• /
• pp.149-157
• /
• 2002

Todays, electronic commerce(EC) results to the revolution and new paradigm of business, more and more Web-based EC applications have emerged. But, it's web systems should be satisfied by customers and it should be successful to buying some goods in virtual stores with easy to use. The usability and acceptance of the EC web system is one of the key factors in the successful construction of EC system. In this paper, we considered the characteristics of information search and decision making process in the design of EC web system to be used easily and to be more acceptable to customers. On the basis of these characteristics, we could classified with the activities of the process of buying in the domestic web systems. And, the log files of experimental tasks were analyzed by the statistical method of data mining. As the these results, the important factors of the process of buying could be summarized, 5 user groups could be seen in EC customers, and the usage patterns of these groups were described. These results could be very useful to design user-oriented EC web system.

• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.2
• /
• pp.35-40
• /
• 2019

Traditional Malware Detection is susceptible for detecting malware which is modified by polymorphism or obfuscation technology. By learning patterns that are embedded in malware code, machine learning algorithms can detect similar behaviors and replace the current detection methods. Data must collected continuously in order to learn malicious code patterns that change over time. However, the process of storing and processing a large amount of malware files is accompanied by high space and time complexity. In this paper, an HDFS-based distributed processing system is designed to reduce space complexity and accelerate feature extraction time. Using a distributed processing system, we extract two API features based on filtering basis, 2-gram feature and APICFG feature and the generalization performance of ensemble learning models is compared. In experiments, the time complexity of the feature extraction was improved about 3.75 times faster than the processing time of a single computer, and the space complexity was about 5 times more efficient. The 2-gram feature was the best when comparing the classification performance by feature, but the learning time was long due to high dimensionality.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.2
• /
• pp.135-140
• /
• 2012

The mirror neuron system in the cerebrum, which are handled by visual information-based imitative learning. When we observe the observer's range of mirror neuron system, we can assume intention of performance through progress of neural activation as specific range, in include of partially hidden range. It is goal of our paper that imitative learning is applied to 3D vision-based intelligent system. We have experiment as stereo camera-based restoration about acquired 3D image our previous research Using Optical flow, unscented Kalman filter. At this point, 3D input image is sequential continuous image as including of partially hidden range. We used Hidden Markov Model to perform the intention recognition about performance as result of restoration-based hidden range. The dynamic inference function about sequential input data have compatible properties such as hand gesture recognition include of hidden range. In this paper, for proposed intention recognition, we already had a simulation about object outline and feature extraction in the previous research, we generated temporal continuous feature vector about feature extraction and when we apply to Hidden Markov Model, make a result of simulation about hand gesture classification according to intention pattern. We got the result of hand gesture classification as value of posterior probability, and proved the accuracy outstandingness through the result.

• Korean Journal of Heritage: History & Science
• /
• v.50 no.4
• /
• pp.64-81
• /
• 2017

Among the royal ceremonies of the Joseon Dynasty era, the articles used in the Jinjak ceremony are symbolic icons of their value during the era. It is very important to identify the purpose of the articles whose usage is ambiguous, by referring to various historical records. Moreover, it should be possible to classify the characteristics and the special context of the article during this process. To accomplish this purpose, I examined the articles related to and used in the processes of Jinjak ceremonies of Outer Jinchan of Myeongjeongjeon and Inner Jinchan of Jagyeongjeon, which are part of the Gichuk Jinchan Ceremony performed in February of the 29th year of King Sunjo. Especially, the definition of Jinjak will not just be limited to the action of offering liquor, but will include the whole series of procedures in offering the liquor. This is because the specific action of offering the liquor expresses cultural concepts and values that have meaning within the historical situation and context in the specific action of offering the liquor. There are three characteristics of the articles related to the Jinjak process of Outer Jinchan and Inner Jinchan of Gichuk Jinchan Ceremony. First, the articles of Jinjak are ranked strictly exactly according to the social status rankings. Second, the Jinjak articles are arranged for their symbolic meanings rather than their purpose. Third, the articles of Jinjak are symbolic icons expressing the values inherent in the process of offering liquor. Recently, there are events reviving the royal court banquet and the increase of interest in the royal culture. It such a situation, the systematic examination of articles of royal court banquets will be a process needed to restore the royal ceremony correctly in the future, and will be the foundation for studying the royal culture of the Joseon dynasty era.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.300-309
• /
• 2020

This study identified the types and dimensions of faculty-student interaction (FSI). A narrative methodology was applied within the qualitative research paradigm. Data was collected using individual in-depth interviews involving 10 students who had experiences of faculty-student interaction more than 6 times over the prior 6 semesters. Data was analyzed according to actors' perspectives, the motivation of actions, and actions toward goal achievement. Three major types of faculty-student interactions emerged from our analysis. First, the initiative interaction type reflects active characteristics of the narrator within FSI and is goal achievement-oriented. Second, the stereotyped interaction was characterized as a unified reaction to the FSI and not significantly related to self-development. Lastly, the reciprocal interaction reflected characteristics of narrators who had potential and flexibility for self-development in the circumstances involving support from professors. The results of this study indicate that faculty-student interaction does not represent the best way to support students for their successful school lives. Faculty needs professionality and sensitivity for student teaching, and students must exhibit curiosity and activeness in developing their knowledge. Positive outcomes from the FSI will be expected in supportive school environments.