• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.595-602
• /
• 2009

Fuzzy rules, which represent the behavior of their system, are sensitive to fuzzy clustering techniques. If the classification abilities of such clustering techniques are improved, their systems can work for the purpose more accurately because the capabilities of the fuzzy rules and parameters are enhanced by the clustering techniques. Thus, this paper proposes a new hierarchically structured clustering algorithm that can enhance the classification abilities. The proposed clustering technique consists of two clusters based on correlationship and statistical characteristics between data, which can perform classification more accurately. In addition, this paper uses difference data sets to reflect the patterns and regularities of the original data clearly, and constructs multiple fuzzy systems to consider various characteristics of the differences suitably. To verify effectiveness of the proposed techniques, this paper applies the constructed fuzzy systems to the field of time series prediction, and performs prediction for nonlinear time series examples.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.27 no.1
• /
• pp.50-58
• /
• 2017

For nonlinear control system design, there are many studies based on TSK fuzzy model. However, TSK fuzzy modelling needs nonlinear dynamic equations of the object system or a data set fully distributed in input-output space. This paper proposes an modelling technique using only step input response data. The technique uses also the genetic algorithm. The object systems in this paper are nonlinear to control input variable or output variable. In the case of nonlinear to control input, response data obtained with several step input values are used. In the case of nonlinear to output, step input response data and zero input response data are used. This paper also presents a fuzzy controller design technique from TSK fuzzy model. The effectiveness of the proposed techniques is verified with numerical examples.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.4
• /
• pp.611-619
• /
• 2008

2.5D Mapping system that embody in this paper can make new design by doing draping to live various texture and model picture image of fashion clothes by pattern, and can confirm clothes work to simulation without producing direction sample or product directly. Also, the system can support function that can forecast fabric design and state of end article exactly, and the system can bring competitive power elevation of fashion industry and cost-cutting effect by doing draping using database of fabric and model picture image. 2.5D Mapping system composed and embodied by mesh warp algorithm module, light and shade extraction and application module, mapping path extraction module, mesh creation and transformation module, and 2.5D mapping module for more natural draping. Future work plans to study 3D fashion design system that graft together 3D clothes technology and 3D human body embodiment technology to do based on embodiment technology of 2.5D mapping system and overcomes expression limit of 2.5D mapping technology.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.647-650
• /
• 2009

In recent years, an understanding and concern about the Photo Realistic CG increased while the CG industry grew. The overall understanding of a system, an output and algorithm, and etc. are needed in order to implement the Photo Realistic CG. Moreover, for the realistic output on CG, the texture task that it is logical the various environment condition according to the physical environment and time, and etc.s has to show. For carrying out the Photo Realistic CG texture task, the extensity of a texture, the physical properties, a material, and an environment, the various access and the logical analysis are needed. Analyzed data reaches the direct affect to the final product for expressing. The realistic ancient history site, and the cultural inheritance and industrial product will be implemented with the ground of the research of the upper part in the imaginary realistic world.

• Journal of the Korea Society for Simulation
• /
• v.26 no.3
• /
• pp.105-113
• /
• 2017

This study considers an optimal investment planning for improving survivability from an air threat in the layered air defense system. To establish an optimization model, we first represent the layered air defense system as a network model, and then, present two optimization models minimizing the failure probability of counteracting an air threat subject to budget limitation, in which one deals with whether to invest and the other enables continuous investment on the subset of nodes. Nonlinear objective functions are linearized using log function, and we suggest dynamic programming algorithm and linear programing for solving the proposed models. After designing a layered air defense system based on a virtual scenario, we solve the two optimization problems and analyze the corresponding optimal solutions. This provides necessity and an approach for an effective investment planning of the layered air defense system.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.3
• /
• pp.23-29
• /
• 2002

The design of data processing of GIS requires efficient method with analysis procedure. This system is easy to be used and managed for presenting route according to conditions as a graphic user interface environmental window system by applying three tiers based object-oriented method. The tier of data is in charge of a class for the exchange, extraction and conservation of data between GeoMedia and application tiers. A route selection algorithm was applied to application tiers, considering all conditions which are necessary for the route selection between a beginning point and an end point, and it was added by module such as data handing, road condition, buffering, clothoid and AHP to select the alternative route followed by new condition. The user tier can express the data acquired by an application tier. Thus three tiers based architecture was presented by implementing design of GIB data processing for its efficiency.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.193-201
• /
• 2006

This paper presents a method that allows for detection of all rapid and gradual scene changes. The method features a combination of the current color histogram and the local $X^{2}-test$. For the purpose of this paper, the $X^{2}-test$ scheme outperforming existing histogram-based algorithms was transformed, and a local $X^{2}-test$ in which weights were applied in accordance with the degree of brightness was used to increase detection efficiency in the segmentation of color values. This Method allows for analysis and segmentation of complex time-varying images in the most general and standardized manner possible Experiments were performed to compare the proposed local $X^{2}-test$ method with the current $X^{2}-test$ method.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.1-6
• /
• 2019

The proposed model is developed to minimize the loss of information in incomplete data including missing data. The first step is to transform the learning data to compensate for the loss information using the data extension technique. In this conversion process, the attribute values of the data are filled with binary or probability values in one-hot encoding. Next, this conversion data is input to the deep learning model, where the number of entries is not constant depending on the cardinality of each attribute. Then, the entry values of each attribute are assigned to the respective input nodes, and learning proceeds. This is different from existing learning models, and has an unusual structure in which arbitrary attribute values are distributedly input to multiple nodes in the input layer. In order to evaluate the learning performance of the proposed model, various experiments are performed on the missing data and it shows that it is superior in terms of performance. The proposed model will be useful as an algorithm to minimize the loss in the ubiquitous environment.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.6
• /
• pp.1415-1425
• /
• 2018

MMORPG genre is based on the belief that all users in virtual world are equal. All users are able to obtain the corresponding wealth or status as they strive under the same resource, time. However, game bot is the main factor for harming this fair competition, causing benign gamers to feel a relative deprivation and deviate from the game. Game bots mainly form GFG(Gold Farming Group), which collects the goods in the game indiscriminately and adversely affects the economic system of the game. A general game bot detection algorithm is useful for detecting each bot, but it only covers few portions of GFG, not the whole, so it needs a wider range of detecting method. In this paper, we propose a method of detecting GFG based on items used in MMORPG genre. Several items that are mainly traded in the game were selected and the flows of those items were represented by a network. We Identified the characteristics of exchanging items of GFG bots and can identify the GFG's item trade network with real datasets from one of the popular online games.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.3
• /
• pp.531-539
• /
• 2019

This paper proposes the training features for malware family analysis and analyzes the multi-classification performance of ensemble models. We construct training data by extracting API and DLL information from malware executables and use Random Forest and XGBoost algorithms which are based on decision tree. API, API-DLL, and DLL-CM features for malware detection and family classification are proposed by analyzing frequently used API and DLL information from malware and converting high-dimensional features to low-dimensional features. The proposed feature selection method provides the advantages of data dimension reduction and fast learning. In performance comparison, the malware detection rate is 93.0% for Random Forest, the accuracy of malware family dataset is 92.0% for XGBoost, and the false positive rate of malware family dataset including benign is about 3.5% for Random Forest and XGBoost.