• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.4
• /
• pp.64-75
• /
• 2008

Since the current database systems for managing geotechnical investigation results were limited by being described boring test result in point feature, it has been trouble for using other GIS data. Although there are some studies for spatial characteristics of subsurface modeling, it is rather lack of being interoperable with GIS, considering geotechnical engineering facts. This is reason for difficulty of practical uses. In this study, we has developed subsurface spatial information model through extracting needed geotechnical engineering data from geotechnical information DB. The developed geotechnical information clustering program(GEOCL) has made a cluster of boring formation(and formation ratio), classification of layer, and strength characteristics of subsurface. The interpolation of boring data has been achieved through zonal kriging method in the consideration of spatial distribution of created cluster. Finally, we make a subsurface spatial information model to integrate with digital elevation model, and visualize 3-dimensional model by subsurface spatial information viewing program(SSIVIEW). We expect to strengthen application capacity of developed model in subsurface interpretation and foundation design of construction works.

• KIISE Transactions on Computing Practices
• /
• v.22 no.8
• /
• pp.387-392
• /
• 2016

Context-aware systems require sensor data collecting model and context representing model to provide user-demand services. Sensor data collecting model consists of sensor access information, sensor value, and definition of value types. Context representing model involves certain keywords to symbolize environmental information including the field from sensor data collecting model that is described in markup language such as XML. However, duplicated keywords could be assigned to different contextual information by service developers. As a result, the system may cause misunderstanding and misleading wrong situational information from unintended contextual information. In this paper, we propose a context classification model for collecting appropriate access information and defining the specification of context.

• Journal of the Korean Society for Library and Information Science
• /
• v.58 no.3
• /
• pp.65-89
• /
• 2024

This study developed a model to classify news articles into categories of topic, genre, and region using a Korean Pre-trained Language model. To achieve this, a new news article classification system was designed by referring to the classification systems of domestic media outlets. The topic and genre classification models were implemented as hierarchical classification models that link the main categories and subcategories, and their performance was compared with that of an integrated category model. The evaluation results showed that the hierarchical structure classification model had the advantage of providing more precise categorization in ambiguous or overlapping categories compared to the integrated category model. For regional classification of news articles, a model was built to classify into 18 categories, and for regional news articles, the regional characteristics were clearly reflected in the text, resulting in high performance. This study demonstrated the effectiveness of classifying news articles from multiple perspectives-topic, genre, and region-and emphasized the significance of suggesting the potential for a multi-dimensional news article classification service that meets user needs.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.237-246
• /
• 2019

In order to improve the accuracy of the rating prediction of the recommendation model, not only user-item rating data are used but also consider auxiliary information of item such as comments, tags, or descriptions. The traditional approaches use a word-level model of the bag-of-words for the auxiliary information. This model, however, cannot utilize the auxiliary information effectively, which leads to shallow understanding of auxiliary information. Convolution neural network (CNN) can capture and extract feature vector from auxiliary information effectively. Thus, this paper proposes character-level deep-Convolution Neural Network based matrix factorization (Char-DCNN-MF) that integrates deep CNN into matrix factorization for a novel recommendation model. Char-DCNN-MF can deeper understand auxiliary information and further enhance recommendation performance. Experiments are performed on three different real data sets, and the results show that Char-DCNN-MF performs significantly better than other comparative models.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1290-1295
• /
• 2017

Document classification, a task of classifying the category of each document based on text, is one of the fundamental areas for natural language processing. Document classification may be used in various fields such as topic classification and sentiment classification. Neural network models for document classification can be divided into two categories: word-level models and character-level models that treat words and characters as basic units respectively. In this study, we propose a neural network model that combines character-level and word-level models to improve performance of document classification. The proposed model extracts the feature vector of each word by combining information obtained from a word embedding matrix and information encoded by a character-level neural network. Based on feature vectors of words, the model classifies documents with a hierarchical structure wherein recurrent neural networks with attention mechanisms are used for both the word and the sentence levels. Experiments on real life datasets demonstrate effectiveness of our proposed model.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.473-482
• /
• 2021

Although several Hangul generation models using deep learning have been introduced, they require a lot of data, have a complex structure, requires considerable time and resources, and often fail in style conversion. This paper proposes a model CKFont using the components of the initial, middle, and final components of Hangul as a way to compensate for these problems. The CKFont model is an end-to-end Hangul generation model based on GAN, and it can generate all Hangul in various styles with 28 characters and components of first, middle, and final components of Hangul characters. By acquiring local style information from components, the information is more accurate than global information acquisition, and the result of style conversion improves as it can reduce information loss. This is a model that uses the minimum number of characters among known models, and it is an efficient model that reduces style conversion failures, has a concise structure, and saves time and resources. The concept using components can be used for various image transformations and compositing as well as transformations of other languages.

• Journal of the Korean Society for information Management
• /
• v.40 no.3
• /
• pp.77-98
• /
• 2023

Large Language Models (LLMs) are becoming the major trend in the natural language processing field. These models were built based on research data, but information such as types, limitations, and risks of using research data are unknown. This research would present how to analyze and evaluate the LLMs that were built with research data: LLaMA or LLaMA base models such as Alpaca of Stanford, Vicuna of the large model systems organization, and ChatGPT from OpenAI from the perspective of research data. This quality evaluation focuses on the validity, functionality, and reliability of Data Quality Management (DQM). Furthermore, we adopted the Holistic Evaluation of Language Models (HELM) to understand its evaluation criteria and then discussed its limitations. This study presents quality evaluation criteria for LLMs using research data and future development directions.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.81-92
• /
• 2023

A privacy model is a technique that quantitatively restricts the possibility and degree of privacy breaches through privacy attacks. Representative models include k-anonymity, l-diversity, t-closeness, and differential privacy. While many privacy models have been studied, research on selecting the most suitable model for a given dataset has been relatively limited. In this study, we develop a system for recommending the suitable privacy model to prevent privacy breaches. To achieve this, we analyze the data features that need to be considered when selecting a model, such as data type, distribution, frequency, and range. Based on privacy model background knowledge that includes information about the relationships between data features and models, we recommend the most appropriate model. Finally, we validate the feasibility and usefulness by implementing a recommendation prototype system.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04a
• /
• pp.49-51
• /
• 2001

다중스레드 모델은 데이터플로우 모델의 내부적인 병렬성, 비동기적 자료 가용성과 폰 노이만 모델의 실행 지역성을 결합하여 병렬처리 시스템의 성능을 향상시켰다. 이 모델은 프로그램의 실행을 위하여 컴파일러에 의해 생성된 스레드를 수행하며, 스레드의 생성 방법에 따라 자원 활용 빈도나 동기화 빈도와 같은 스레드의 질이 결정되는 특징이 있다. 하지만 다중스레드 모델은 실행 모델이 특정 플랫폼에 제한되는 단점을 가지고 있다. 이에 반해 자바는 플랫폼에 독립거인 특징을 가지고 있어 다중스레드 모델의 스레드 코드를 실행 단위인 자바 언어로 변환하여 다중스레드 모델의 특징을 여러 플랫폼에서 수정 없이 사용할 수 있게 된다. 자바는 분산된 환경에 적합한 언어이기 때문에 본 논문에서 제안한 번역기에 의해 다중스레드 모델의 스레드 코드를 자바 언어로 변환한 후 자바의 원격 매소드 호출을 이용하여 다중스레드 모델의 스레드 코드를 분산된 환경에서 처리하였다. 본 논문은 다중스레드 코드가 로컬 컴퓨터에서 여러 스레드를 생성하여 처리하던 것을 자바의 원격 메소드 호출을 이용하여 분산된 환경에서 실행 가능하도록 한다. 다중스레드 모델의 스레드 코드를 분산 환경에서 실행 가능한 자바 바이트 코드로 변환하는 번역기를 설계, 구현한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.319-321
• /
• 2005

항해는 웹 응용의 대표적인 행위 특성이다. 본 연구에서는 UML 2.0의 행위 다이어그램 메타 모델을 확장한 웹 응용 항해 모델을 제안한다. 본 항해 모델은 딜 판정 항해 모델과 데이터 전송 관점 항해 모델로 구성된다. 뷰 관점 항해 모델은 UML 상태 기계 다이어그램을 확장하여 사용자에게 표시되는 항해를 기술한다. 데이터 전송 관점 항해 모델은 데이터가 전송되는 항해를 나타내며 UML 시퀀스 다이어그램을 확장하여 표현한다. 두 항해 모델은 상호 보완적으로 작용하여 온전한 항해 문맥을 형성한다. 본 논문에서는 UML 2.0 메타 모델의 확장점과 항해 모델의 표기법을 제시하고, 사례 연구를 통하여 실제적인 항해 모델의 예를 보인다.