• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.187-197
• /
• 2020

Recently, various methods of text embedding using deep learning algorithms have been proposed. Especially, the way of using pre-trained language model which uses tremendous amount of text data in training is mainly applied for embedding new text data. However, traditional pre-trained language model has some limitations that it is hard to understand unique context of new text data when the text has too many tokens. In this paper, we propose self-supervised learning-based fine tuning method for pre-trained language model to infer vectors of long-text. Also, we applied our method to news articles and classified them into categories and compared classification accuracy with traditional models. As a result, it was confirmed that the vector generated by the proposed model more accurately expresses the inherent characteristics of the document than the vectors generated by the traditional models.

• Journal of Korea Multimedia Society
• /
• v.3 no.3
• /
• pp.290-297
• /
• 2000

For verifying consistency and completeness of some UML diagrams as a representative of the graphic notations for object-oriented designs, we first give an analysis of some UML diagrams and apply simple ER model to the UML diagrams. Next, we formally define this graphical representation as a set of sets and a set of functions. According to the semantics of these functions, we derive a set of rules to assure the consistency and completeness of this graphical representation. These rules will be included with a CASE tool, which possesses both the diagramming facility and the consistency and completeness checking capability.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.863-875
• /
• 2017

The traditional text similarity measurement methods based on word frequency vector ignore the semantic relationships between words, which has become the obstacle to text similarity calculation, together with the high-dimensionality and sparsity of document vector. To address the problems, the improved singular value decomposition is used to reduce dimensionality and remove noises of the text representation model. The optimal number of singular values is analyzed and the semantic relevance between words can be calculated in constructed semantic space. An inverted index construction algorithm and the similarity definitions between vectors are proposed to calculate the similarity between two documents on the semantic level. The experimental results on benchmark corpus demonstrate that the proposed method promotes the evaluation metrics of F-measure.

• The Journal of the Korea Contents Association
• /
• v.15 no.5
• /
• pp.132-141
• /
• 2015

Smart television(TV) is replacing the traditional television model and the importance of user experience(UX) is rising. User experience evaluates the emotion state of users such as immersion, pleasure, and interest. User experience together with usability is a principle to be considered as for designing a smart television. It contributes to improve user satisfaction and lead to the long-term purchase. User experience is more difficult to measure than usability, because UX evaluation requires to biological and psychological techniques. However, the disadvantages of these physiological and psychological techniques require high experimental costs and the restriction of experimental environment. The objective of this paper is first to review conventional methods regarding UX evaluation and suggests a new method for measuring the UX of smart TV which detects keywords related emotional representation. The text is acquired from purchase postscripts of smart TV in the Internet shopping malls. This method costs less than the questionnaire survey to detect emotion.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.15 no.2
• /
• pp.85-95
• /
• 1990

Structured modeling provides a formal mathematical framework, language, and computer-based environment for conceiving, representing, and manipulating a wide variety of model. It provides a natural framework for integrated modeling owing to its explicit representation power for computational dependencies among submodles. Nevertheless, it doesn't seem to offer a systematic way of composing a structured model from submodels. In order to develop a systematic way, this paper discusses three key issues : (1) Genus structure for model composition, (2) Storage of structured models, and (3) Integration of structured models. To formalize and visualize the approach, a programming module is developed to implemented the step-by-step integration.

• Journal of the military operations research society of Korea
• /
• v.27 no.2
• /
• pp.134-148
• /
• 2001

In this paper, air-defense simulation model, called "DADSim", will be introduced. DADSim(Distributed Air Defense Simulation Model) was developed by Modeling&Simulation Lab of K.N.D.U.(Korea National Defence Univ) Weapon Systems Department. This model is an analysis-purpose model in the engagement-level. DADSim can simulate not only the global air-defense or Korean Peninsula but also the local air-defense or a battle field. DADSim uses the DTED(digital terrain elevation data) LeveII it for the representation of peninsula terrain characteristics. The weapon systems cooperated in the model are low/medium-range missile systems such as HAWK, NIKE, SAM. DADSim was designed in the way of object-oriented development method, implemented by C++ language. The simulation view is an event-sequenced object-orientation. For the convenience of input, output analysis, GUI(Graphic User Interface) of menu, window, dialog box, etc. are provided to the user, For the execution of DADSim, Silicon Graphic IRIX 6.3 or high version is required. DADSim can be used for the effectiveness analysis of­defence systems. Some illustrative examples will be shown in this paper.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1990.04a
• /
• pp.49-60
• /
• 1990

Structured modeling provides a formal mathematical framework, language, and computer-based environment for conceiving, representing, and manipulating a wide variety of models. It provides a natural framework for integrated modeling owing to its explicit representation power for computational dependencies among submodels. Nevertheless, it doesn't seem to offer a systematic way of composing a structured model from submodels. In order to develop a systematic way, this paper discusses three key issues; (1) Genus structure of validated submodel, (2) Storing method of genus structure, and (3) Integration of genus structures to generate a new genus structure. To visualize the approach, a programming module is developed to implement the step-by-step integration.

• The KIPS Transactions:PartD
• /
• v.8D no.6
• /
• pp.843-852
• /
• 2001

Statistics concerning software errors indicate that more errors are introduced in analysis and design phase than implementation phase. Therefore, it is needed to check whether the design modeling is appropriate for own function and structure. This paper discussed the effective test method for the object-oriented design model, i.e., UML. A new method was proposed for generating test data. This method consists of category partition theory by the representation each element in UML model with OCL (Object Constraint Language). Test data generated in this way can be used for testing the source code functionality as well as for checking the design model.

• International Journal of Computer Science & Network Security
• /
• v.21 no.1
• /
• pp.84-96
• /
• 2021

Certainly, the success of the Unified Modeling Language (UML) as the de facto standard for modeling software systems does not imply closing the door on scientific exploration or experimentation with modeling in the field. Continuing studies in this area can produce theoretical results that strengthen UML as the leading modeling language. Recently, a new modeling technique has been proposed called thinging machine (TM) modeling. This paper utilizes TM to further understand UML, with two objectives: (a) Fine issues in UML are studied, including theoretical notions such as events, objects, actions, activities, etc. Specifically, TM can be used to solve problems related to internal cross-diagram integration. (b) TM applies a different method of conceptualization, including building a model on one-category ontology in contrast to the object-oriented paradigm. The long-term objective of this study is to explore the possibility of TM complementing certain aspects in the UML methodology to develop and design software systems. Accordingly, we alternate between UML and TM modeling. A sample UML model is redesigned in TM, and then UML diagrams are extracted from TM. The results clarify many notions in both models. Particularly, the TM behavioral specification seems to be applicable in UML.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.3216-3230
• /
• 2015

A hot-issued research topic in the workflow intelligence arena is the emerging topic of "workflow-supported organizational social networks." These specialized social networks have been proposed to primarily represent the process-driven work-sharing and work-collaborating relationships among the workflow-performers fulfilling a series of workflow-related operations in a workflow-supported organization. We can discover those organizational social networks, and visualize its analysis results as organizational knowledge. In this paper, we are particularly interested in how to visualize the degrees of closeness centralities among workflow-performers by proposing a graphical representation schema based on the Graph Markup Language, which is named to ccWSSN-GraphML. Additionally, we expatiate on the functional expansion of the closeness centralization formulas so as for the visualization framework to handle a group of workflow procedures (or a workflow package) with organizational workflow-performers.