• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.6
• /
• pp.539-544
• /
• 2013

In this paper, we was designed three-dimensional face recognition algorithm using polynomial based RBFNNs and proposed method to calculate the recognition performance. In case of two-dimensional face recognition, the recognition performance is reduced by the external environment like facial pose and lighting. In order to compensate for these shortcomings, we perform face recognition by obtaining three-dimensional images. obtain face image using three-dimension scanner before the face recognition and obtain the front facial form using pose-compensation. And the depth value of the face is extracting using Point Signature method. The extracted data as high-dimensional data may cause problems in accompany the training and recognition. so use dimension reduction data using PCA algorithm. accompany parameter optimization using optimization algorithm for effective training. Each recognition performance confirm using PSO, DE, GA algorithm.

• Journal of Internet Computing and Services
• /
• v.12 no.5
• /
• pp.29-37
• /
• 2011

Recently, many user-participating web services have been used widely as the evolution of internet web technology has rapidly been developed. Users share various content and opinion on line using a site like ‘Social bookmarking.’ Users can share others’ bookmarking history and create tags while bookmarking web sites; we call it collaborative tagging. In this paper, we studied empirical analysis for widely used social bookmarking and collaborative tagging which the result shows minority of users is actively using the bookmarking and a few sites and tags are used by majority of the users. 24% users tagged 80%, 75% sites and 81% tags were tagged below than 3 times. Types of bookmarking activities were found different by users and early appointed tags get more frequency by majority. We also identified relative proportions of tags on certain sites are becoming convergence gradually. We expect the result of this paper will give opportunities to help further developing social bookmarking system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.2
• /
• pp.135-143
• /
• 2020

Natural drought is a three-dimensional phenomenon that simultaneously evolves in time and space. To evaluate the link between meteorological and hydrological droughts, we defined a drought event from a three-dimensional perspective and analyzed the propagation characteristics in time and spaces. Overall results indicated that 77 % of the total cases of spatio-temporal droughts was propagated based on the single category relationship between meteorological and hydrological drought events, while 23 % was affected by multiple meteorological drought events to the occurrence of hydrological drougts. Especially, it turned out that the hydrological drought was caused by the spatio-temporal effects of the propagation of four meteorological drought events generated due to long-term lack of precipitation in 1994-1995. In addition, the meteorological drought caused by the lack of precipitation in the summer of 2001 lasted for several months, and was propagated to the hydrological drought in April 2002.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.1
• /
• pp.193-204
• /
• 2017

The security of Internet systems critically depends on the capability to keep anti-virus (AV) software up-to-date and maintain high detection accuracy against new malware. However, malware variants evolve so quickly they cannot be detected by conventional signature-based detection. In this paper, we proposed a malware classification method based on sequence patterns generated from the network flow of malware samples. We evaluated our method with 766 malware samples and obtained a classification accuracy of approximately 40.4%. In this study, malicious codes were classified only by network behavior of malicious codes, excluding codes and other characteristics. Therefore, this study is expected to be further developed in the future. Also, we can predict the attack groups and additional attacks can be prevented.

• Journal of Intelligence and Information Systems
• /
• v.12 no.2
• /
• pp.145-165
• /
• 2006

Information filtering systems, which are designed fur users' needs, do not satisfy user's diverse requests as their filtering accuracy is unstable sometimes. This study suggests an information filtering system based on cognitive brain mapping by simulating the processes of information in human brain. Compared to traditional filtering systems, which use specific words or pattern in their filtering systems, the method suggested in this article uses both key words and relationships among these words. The significance of this study is on simulating information storing processes in human brain by mapping both key words and their relationships among them together. To combine these two methods, this study finds balances in representing two methods by searching optimal weights of each of them.

• Journal of Digital Convergence
• /
• v.17 no.12
• /
• pp.445-450
• /
• 2019

lock in effect This study aims to examine the viewing pattern of travel vlog on video-sharing platform YouTube. Preliminary survey was conducted with in-depth interviews on the usability and sensibility aspects of creating pleasurable interfaces model. As a result, first, viewers obtains general information on travel using travel vlog. Second, there were difficulties from the informational quantity. Third, the contents marketing using travel vlog could have limitation when it comes to the consistency of product's exposure which common mass media advertisement format have. Improvements driven from this study may provide insight in contents marketing strategy to travel-related companies and provide practical help to creators in contents production.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.75-81
• /
• 2004

Signature based intrusion detection system (IDS), having stored rules for detecting intrusions at the library, judges whether new inputs are intrusion or not by matching them with the new inputs. However their policy has two restrictions generally. First, when they couldn`t make rules against new intrusions, false negative (FN) errors may are taken place. Second, when they made a lot of rules for maintaining diversification, the amount of resources grows larger proportional to their amount. In this paper, we propose the learning algorithm which can evolve the competent of anomaly detectors having the ability to detect anomalous attacks by genetic algorithm. The anomaly detectors are the population be composed of by following the negative selection procedure of the biological immune system. To show the effectiveness of proposed system, we apply the learning algorithm to the artificial network environment, which is a computer security system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.301-308
• /
• 2017

With the popularization of smart phones and the development of the Internet, many people use smart phones to conduct identity verification procedures. smart phones are easier and faster to authenticate than personal desktop computers. However, as Internet hacking technology and malicious code distribution technology rapidly evolve and attack types become more diverse, authentication methods suitable for mobile environment are required. As authentication methods, there are methods such as possessive-based authentication, knowledge-based authentication, biometric-based authentication, pattern-based authentication, and multi-element authentication. In this paper, we propose a user authentication mechanism that uses collected information as authentication factor using smart phone. Using the proposed authentication mechanism, it is possible to use the smart phone information and environment information of the user as a hidden authentication factor, so that the authentication process can be performed without being exposed to others. We implemented the user authentication system using the proposed authentication mechanism and evaluated the effectiveness based on applicability, convenience, and security.

• The Journal of the Petrological Society of Korea
• /
• v.28 no.2
• /
• pp.71-83
• /
• 2019

The volcanic rocks in Saryangdo area are composed of Witseom Andesite, Punghwari Tuff, Araetseom Andesite, Obido Formation, Namsan Rhyolite and Saryangdo Tuff in ascending order. The volcanic rocks has a range of andesite-rhyodacite-rhyolite, which indicates calc-alkaline series and volcanic arc of orogenic belt. In Harker diagrams for trace element and REE pattern, these are also distinguished into so three groups(Witseom Andesite, Araetseom Andesite and Saryangdo Tuff) that each unit is interpreted to have originated in different magma chamber. The Saryangdo Tuff exhibits systematically(chemical zonations that gradually change) from lower dacite to upper rhyolite in section. The systematic sequence of compositional variations suggests that the tuffs were formed by successive eruptions of upper to lower part of a zoned magma chamber in which relatively dacitic magma is surrounded around rhyolitic magma of the central part. The zoned magma chamber was formed from marginal accretion and crystal settling that resulted form magmatic differentiations by fractional crystallization.