• Journal of the Korea Society of Computer and Information
• /
• v.17 no.4
• /
• pp.11-18
• /
• 2012

Deep packet inspection which perform pattern matching to search for malicious patterns in the packet is most computationally intensive task. Hardware-based pattern matching is required for real-time packet inspection in high-speed network. In this paper, we have designed and implemented network intrusion detection hardware as a Microblaze-based SoC using Virtex-6 FPGA, which capture the network input packet, perform hardware-based pattern matching for patterns in the Snort rule, and provide the matching result to the software. We verify the operation of the implemented system using traffic generator and real network traffic. The implemented hardware can be used in network intrusion detection system operated in wire-speed.

• Journal of Digital Convergence
• /
• v.14 no.11
• /
• pp.267-273
• /
• 2016

Creation and Sharing of information which is structured data as well as various unstructured data. makes progress actively through the spread of mobile. Recently, Big Data extracts the semantic information from SNS and data mining is one of the big data technique. Especially, the general emotion analysis that expresses the collective intelligence of the masses is utilized using large and a variety of materials. In this paper, we propose the emotion prediction system architecture which extracts the significant keywords from social network paragraphs using n-gram and Korean morphological analyzer, and predicts the emotion using SVM and these extracted emotion features. The proposed system showed 82.25% more improved recall rate in average than previous systems and it will help extract the semantic keyword using morphological analysis.

• Journal of Digital Contents Society
• /
• v.8 no.1
• /
• pp.93-106
• /
• 2007

Web Applications are rapidly increasing and the structure becomes very complicated. However, when users explore such complex Web applications, they cannot often grasp the current location and get the information that they want. Therefore, a novel approach to model the navigation of Web application contents is required. In this study, a framework has been presented for modeling adaptive context-based contents navigation of Web applications. The framework performs activities including navigation analysis, navigation design, and navigation realization. first, in navigation analysis domain is analyzed by using use case, focusing on navigation. Next, in navigation design three models have been produced: a navigation information model, a profile, and a navigation interface model. Finally, in navigation realization a Webpage navigation model and a component navigation model have been produced. In this work, several formal definitions and rules for checking validity of navigation model have also been provided.

• Journal of KIISE
• /
• v.43 no.9
• /
• pp.1008-1014
• /
• 2016

Data such as Twitter, Facebook, and customer reviews belong to the informal document group, whereas, newspapers that have grammar correction step belong to the formal document group. Finding consistent rules or patterns in informal documents is difficult, as compared to formal documents. Hence, there is a need for additional approaches to improve informal document analysis. In this study, we classified Twitter data, a representative informal document, into ten categories. To improve performance, we revised and expanded features based on LDA(Latent Dirichlet allocation) word distribution. Using LDA top-ranked words, the other words were separated or bundled, and the feature set was thus expanded repeatedly. Finally, we conducted document classification with the expanded features. Experimental results indicated that the proposed method improved the micro-averaged F1-score of 7.11%p, as compared to the results before the feature expansion step.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.351-360
• /
• 2006

Proposed security system attacks it, and detect it, and a filter generation, a business to be prompt of interception filtering dates at attack information public information. inner IPS to attack detour setting and a traffic band security, different connection security system, and be attack packet interceptions and service and port interception setting. Exchange new security rule and packet filtering for switch type implementation through dynamic reset memory by real time, and deal with a packet. The attack detection about DDoS, SQL Stammer, Bug bear, Opeserv worm etc. of the 2.5 Gbs which was an attack of a hacker consisted in network performance experiment by real time. Packet by attacks of a hacker was cut off, and ensured the normal inside and external network resources besides the packets which were normal by the results of active renewal.

• Journal of KIISE:Software and Applications
• /
• v.33 no.8
• /
• pp.692-702
• /
• 2006

In this study, a weighted fuzzy min-max (WFMM) neural network model for pattern classification is proposed. The model has a modified structure of FMM neural network in which the weight concept is added to represent the frequency factor of feature values in a learning data set. First we present in this paper a new activation function of the network which is defined as a hyperbox membership function. Then we introduce a new learning algorithm for the model that consists of three kinds of processes: hyperbox creation/expansion, hyperbox overlap test, and hyperbox contraction. A weight adaptation rule considering the frequency factors is defined for the learning process. Finally we describe a feature analysis technique using the proposed model. Four kinds of relevance factors among feature values, feature types, hyperboxes and patterns classes are proposed to analyze relative importance of each feature in a given problem. Two types of practical applications, Fisher's Iris data and Cleveland medical data, have been used for the experiments. Through the experimental results, the effectiveness of the proposed method is discussed.

• Convergence Security Journal
• /
• v.15 no.7
• /
• pp.75-84
• /
• 2015

In an "NTFS Index Record Data Hiding" method messages are hidden by using file names. Windows NTFS file naming convention has some forbidden ASCII characters for a file name. When inputting Hangul with the Roman alphabet, if the forbidden characters for the file name and binary data are used, the codes are convert to a designated unicode point to avoid a file creation error due to unsuitable characters. In this paper, the problem of a file creation error due to non-admittable characters for the file name is fixed, which is used in the index record data hiding method. Using Hangul with Roman alphabet the characters cause a file creation error are converted to an arbitrary unicode point except Hangul and Roman alphabet area. When it comes to binary data, all 256 codes are converted to designated unicode area except an extended unicode(surrogate pairs) and ASCII code area. The results of the two cases, i.e. the Hangul with Roman alphabet case and the binary case, show the applicability of the proposed method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.563-566
• /
• 2017

In order to prevent livestock diseases and produce the high quality livestock products in the livestock industry, it is necessary to manage the conditions of the livestock farms in the optimal condition. Therefore, these days the research on livestock growth models that analyze the factors of the air environment, the breeding environment, and the numerical rules of livestock in vivo is being carried out to improve and manage the environment in which livestock are kept. However, conventional models of growth are not sufficient to support the decision-making to control complex environment in pen by analyzing and interpreting air environment and breeding environment in a complex way. In this paper, we propose a method to control the complex environment in pen by using artificial neural network model based on biological information, air environment, breeding environment and production information.

• Korean Journal of Crystallography
• /
• v.8 no.2
• /
• pp.75-80
• /
• 1997

A perovskite relaxor ferroelectrics PMN is used as an important material to investigate the diffusive phase transition phenomena. In this study PMN single crystals were grown and the microstructure were observed. For the growth of PMN single crystals, the spontaneous nucleation technique and the TSSG technique were used. 2-5mm single crystals were grown from PbO self flux and it was observed that only PMN crystals were grown when excess MgO was added over 100% as flux. Single crystals with well developed (001) faces were obtained from PbO-B2O3 flux. single crystals larger than 1 cm were grown from PbO-B2O3 flux by TXXG technique. For higher quality crystals, optimization of the variables such as the rotation speed of seed crystal, the orientation of seed crystal, and cooling rate is needed. With grown crystals, it was confirmed by TEM diffraction pattern of thin plate crystal that the 1:1 ordering of Mg2+ and Nb5+ with small volume exists.

• Journal of Digital Contents Society
• /
• v.2 no.1
• /
• pp.73-79
• /
• 2001

Most of the existing algorithms try to disseminate the multimedia contents of internet service provider(ISP), without taking into account the needs and characteristics of specific websites including e-learning systems with web-based .educational contents. Sometimes the client must select the best one among the replicated repositories. However, this is a less reliable approach because clients' selections are made without prior information on server load capacity. In this paper we propose an agent system inspired by the need of improving QoS of delivering web-based educational multimedia contents without incurring long access delays. This agent system consists of three components, Analyzer, Knowledge Base, and Automaton embedded the capacity algorithm. It analyzes and investigates traffic information collected from individual replicated server by learners' requests, and selects a server which is available and is expected to provide the fastest latency time and the lowest loaded capacity, and achieves high performance by dynamic replicating web resources among multiple repositories.