• The Transactions of the Korea Information Processing Society
• /
• v.7 no.1
• /
• pp.29-40
• /
• 2000

With increasing amounts of information on the web and needs to access accurately them, it is very important to standardize metadata and to store and manage system. The RDF(Rdsource Description Framework) is a framework for representing exchanging, and reusing metadata. And, it can be processing uniformly the standardized metadata, because it uses XML(eXtensible Markup Language) syntax. The RDF schema provides a basic type system for use RDF models. In this paper, we propose rules and an algorithm to convert the RDF schema into an UML(Unified Modeling Language) class diagram and formal models to represent an object-oriented schema for the RDF schema. The proposed rules and algorithm are useful for natural mapping and the object modeling of RDF schema can be easily converted into the object-oriented schema, and the formal models supports an efficient environment for retrieving and processing object-oriented documents.

• Journal of Korea Game Society
• /
• v.19 no.5
• /
• pp.103-114
• /
• 2019

We have been studying a deep-learning program that can communicate with other users in online communities since 2017. But there were problems with processing a Korean data set because of Korean characteristics. Also, low usage of GPUs of RNN models was a problem too. In this study, as Natural Language Processing models are improved, we aim to make better results using these improved models. To archive this, we use a Transformer model which includes Self-Attention mechanism. Also we use MeCab, korean morphological analyzer, to address a problem with processing korean words.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.127-136
• /
• 2021

In the systems and software modeling field, a conceptual model involves modeling with concepts to support development and design. An example of a conceptual model is a description developed using the Unified Modeling Language (UML). UML uses a model multiplicity formulation approach, wherein a number of models are used to represent alternative views. By contrast, a model singularity approach uses only a single integrated model. Each of these styles of modeling has its strengths and weaknesses. This paper introduces a partial solution to the issue of multiplicity vs. singularity in modeling by adopting UML use cases and class models into the conceptual thinging machine (TM) model. To apply use cases, we adopt the observation that a use-case diagram is a description that shows the internal structure of the part of the system represented by the use case in addition to being useful to people outside of the system. Additionally, the UML class diagram is recast in TM representation. Accordingly, we develop a TMUML model that embraces the TM specification of the UML class diagram and the internal structure extracted from the UML use case. TMUML modeling introduces some of the advantages that have made UML a popular modeling language to TM modeling. At the same time, this approach supplies UML with partial model singularity. The paper details experimentation with TMUML using examples from the literature. Our results indicate that mixing UML with other models could be a viable approach.

• International conference on construction engineering and project management
• /
• 2007.03a
• /
• pp.337-345
• /
• 2007

Nowadays, it is convenient to use 3D modeling tools for general planning before construction. Normally, a 3D model is built with 3D CAD such as 3D Studio Max, Maya, etc. or simply with AutoCAD. All these software packages are effective in building 3D models but difficult to use, because many provided functions and tools require prior knowledge to build both 2D and 3D designs. Moreover, the traditional method of building 3D models is most time-consuming as experienced operators and manual input are required. Therefore, how to minimize the building time of 3D models and provide easy-to-use functions for users who are not familiar with 3D modeling becomes important. In this paper, the VisualLISP programming language is used to create a convenient tool for efficient generation of 3D components for the AutoCAD environment. This tool will be demonstrated with the generation of a 3D sluice, an artificial passage for water fitted with a valve or gate to stop or regulate water flow. With the tool, users only need to enter the parameters of a sluice in the edit box and the 3D model will be automatically generated in a few seconds. By changing parameters in the edit box and pressing the "OK" button, a new 3D sluice model will be generated in a short while.

• Korean Institute of Interior Design Journal
• /
• v.14 no.5 s.52
• /
• pp.254-261
• /
• 2005

This paper presents an attempt to develop a visual programming language-based 3D virtual reality authoring tool intended to compose virtual interior space. The rapid development of digital technology and the wide spread of the Intenet have expanded the different uses of virtual reality in a number of applications ranging from interior design to building maintenance. In particular, the construction of cyber spaces based on existing interior spaces is becoming increasingly important. Current research, however, remains at the level of converting 3D models into virtual reality models, despite practitioners' needs for structural space models. Moreover, commercial tools to build virtual reality space have the disadvantage of targeting people who have professional knowledge of computer programs and computer graphics. Accordingly, the 3D virtual reality authoring tool developed in this research - called the VESL system - enables virtual and structural space to be easily composed using intuitive and interactive visual interfaces, which are based on visual programming techniques. The VESL system also provides an XML based semantic description of interior space, to be used to describe interior space information. We anticipate that the virtual reality spaces composed by this system will be of considerable use in the fields of architecture and interior design. Further research issues identified at the end of the research include developing a converter/filter for transforming Internet virtual reality standard language, or VRML, and evaluating the application of the system for practical use.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.6
• /
• pp.62-70
• /
• 2000

In usual language models(LMs), the probability has been estimated by selecting highly frequent words from a large text side database. However, in case of adopting LMs in a specific task, it is unnecessary to using the general method; constructing it from a large size tent, considering the various kinds of cost. In this paper, we propose a construction method of LMs using a small size text database in order to be used in specific tasks. The proposed method is efficient in increasing the low frequent words by applying same sentences iteratively, for it will robust the occurrence probability of words as well. We carried out continuous speech recognition(CSR) experiments on 200 sentences uttered by 3 speakers using LMs by iterative teaming(IL) in a air flight reservation task. The results indicated that the performance of CSR, using an IL applied LMs, shows an 20.4% increased recognition accuracy compared to those without it. This system, using the IL method, also shows an average of 13.4% higher recognition accuracy than the previous one, which uses context-free grammar(CFG), implying the effectiveness of it.

• Journal of IKEEE
• /
• v.11 no.2
• /
• pp.89-94
• /
• 2007

This paper is a study on continuous speech recognition in the Korean language using HMM-based models with continuous density functions. Here, we propose the most efficient method of continuous speech recognition for the Korean language under the condition of a continuous HMM model with 2 to 44 density functions. Two voice models were used CI-Model that uses 36 uni-phones and CD-Model that uses 3,000 tri-phones. Language model was based on N-gram. Using these models, 500 sentences and 6,486 words under speaker-independent condition were processed. In the case of the CI-Model, the maximum word recognition rate was 94.4% and sentence recognition rate was 64.6%. For the CD-Model, word recognition rate was 98.2% and sentence recognition rate was 73.6%. The recognition rate of CD-Model we obtained was stable.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.24-29
• /
• 2022

Semantic role labeling task used in various natural language processing fields, such as information extraction and question answering systems, is the task of identifying the arugments for a given sentence and predicate. Predicate used as semantic role labeling input are extracted using lexical analysis results such as POS-tagging, but the problem is that predicate can't extract all linguistic patterns because predicate in korean language has various patterns, depending on the meaning of sentence. In this paper, we propose a korean predicate recognition method using neural network model with pre-trained embedding models and lexical features. The experiments compare the performance on the hyper parameters of models and with or without the use of embedding models and lexical features. As a result, we confirm that the performance of the proposed neural network model was 92.63%.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.133-140
• /
• 2022

We investigate the performance of deep learning-based Korean language models on a task of predicting the score range of Korean essays written by foreign students. We construct a data set containing a total of 304 essays, which include essays discussing the criteria for choosing a job ('job'), conditions of a happy life ('happ'), relationship between money and happiness ('econ'), and definition of success ('succ'). These essays were labeled according to four letter grades (A, B, C, and D), and a total of eleven essay score range prediction experiments were conducted (i.e., five for predicting the score range of 'job' essays, five for predicting the score range of 'happiness' essays, and one for predicting the score range of mixed topic essays). Three deep learning-based Korean language models, KoBERT, KcBERT, and KR-BERT, were fine-tuned using various training data. Moreover, two traditional probabilistic machine learning classifiers, naive Bayes and logistic regression, were also evaluated. Experiment results show that deep learning-based Korean language models performed better than the two traditional classifiers, with KR-BERT performing the best with 55.83% overall average prediction accuracy. A close second was KcBERT (55.77%) followed by KoBERT (54.91%). The performances of naive Bayes and logistic regression classifiers were 52.52% and 50.28% respectively. Due to the scarcity of training data and the imbalance in class distribution, the overall prediction performance was not high for all classifiers. Moreover, the classifiers' vocabulary did not explicitly capture the error features that were helpful in correctly grading the Korean essay. By overcoming these two limitations, we expect the score range prediction performance to improve.

• Geomechanics and Engineering
• /
• v.37 no.4
• /
• pp.395-418
• /
• 2024

The epicentral region of earthquakes is typically where liquefaction-related damage takes place. To determine the maximum distance, such as maximum epicentral distance (R_e), maximum fault distance (R_f), or maximum hypocentral distance (R_h), at which an earthquake can inflict damage, given its magnitude, this study, using a recently updated global liquefaction database, multiple ML models are built to predict the limiting distances (R_e, R_f, or R_h) required for an earthquake of a given magnitude to cause damage. Four machine learning models LSTM (Long Short-Term Memory), BiLSTM (Bidirectional Long Short-Term Memory), CNN (Convolutional Neural Network), and XGB (Extreme Gradient Boosting) are developed using the Python programming language. All four proposed ML models performed better than empirical models for limiting distance assessment. Among these models, the XGB model outperformed all the models. In order to determine how well the suggested models can predict limiting distances, a number of statistical parameters have been studied. To compare the accuracy of the proposed models, rank analysis, error matrix, and Taylor diagram have been developed. The ML models proposed in this paper are more robust than other current models and may be used to assess the minimal energy of a liquefaction disaster caused by an earthquake or to estimate the maximum distance of a liquefied site provided an earthquake in rapid disaster mapping.