• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.376-380
• /
• 2007

The national R&D information of ministries which define shared information related to national R&D projects has been derived. Among them, 21 percent are code items which can provide important standards to classify information and put out S&T statistics. Therefore, it is necessary to standardize the code items that are differently defined and managed by each research management specialized organization. For this, the National Science & Technology Information System(NTIS) intends to provide a clear code standard for the national R&D information of ministries by defining the NTIS Standard Code. In this study, we also describe the classification service to manage the NTIS Standard Code, National Standard Science and Technology Classification Codes which have been used for national R&D projects's survey and analysis as a unified way.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.157-167
• /
• 2020

With the recent advancement of computer hardware and the contribution of open source libraries to facilitate access to artificial intelligence technology, the use of machine learning (ML) and deep learning (DL) technologies in various fields of exploration geophysics has increased. In addition, ML researchers have developed complex algorithms to improve the inference accuracy of various tasks such as image, video, voice, and natural language processing, and now they are expanding their interests into the field of automatic machine learning (AutoML). AutoML can be divided into three areas: feature engineering, architecture search, and hyperparameter search. Among them, this paper focuses on hyperparamter search with Bayesian optimization, and applies it to the problem of facies classification using seismic data and well logs. The effectiveness of the Bayesian optimization technique has been demonstrated using Vincent field data by comparing with the results of the random search technique.

• Journal of Engineering Education Research
• /
• v.13 no.4
• /
• pp.93-108
• /
• 2010

The goal of this study is an analysis on linkage system between in machinery sector. The development of skill framework and national technical qualification items. This paper researched skills and created the skill level through reviewing domestic & foreign documents, interview with experts and in-depth discussions with expert group focusing on terminologies commonly used in the industrial settings. As a result of skill classification, authors were able to classify skills into three categories in medium-scale classification and 11 categories in small-scale classification, and also into total 42 categories through the re-classification of the small-scale classification. The skill level in the area of machine were classified the skill level in the area of machine into 7 level by reflecting the level system of the korean qualification frameworks, qualification and education course, and skill level in the industrial setting. Based on the skill frameworks, we provided definition of skill and skill group, definition of each different skill, and performance standards by skill and level. also, This paper suggests improving measure of national technical qualification items through analysizing linkage situation between skill frameworks & qualification items.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.15 no.3
• /
• pp.91-101
• /
• 2005

Although the studies on the analysis and classification of source-level vulnerabilities in operating systems are not direct and positive solutions to the exploits with which the host systems are attacked, It is important in that those studies can give elementary technologies in the development of security mechanisms. But, whereas Linux systems are widely used in Internet and intra-net environments recently, the information on the basic and fundamental vulnerabilities inherent in Linux systems has not been studied enough. In this paper, we propose characteristic classification and correlational analyses on the source-level vulnerabilities in Linux kernel that are opened to the public and listed in the SecurityFocus site for 6 years from 1999 to 2004. This study may contribute to expect the types of attacks, analyze the characteristics of the attacks abusing vulnerabilities, and verify the modules of the kernel that have critical vulnerabilities.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.469-472
• /
• 2022

With the recent development of intelligent transportation systems, various technologies applying deep learning technology are being used. To crackdown on illegal vehicles and criminal vehicles driving on the road, a vehicle type classification system capable of accurately determining the type of vehicle is required. This study proposes a vehicle type classification system optimized for mobile traffic control systems using YOLO(You Only Look Once). The system uses a one-stage object detection algorithm YOLOv5 to detect vehicles into six classes: passenger cars, subcompact, compact, and midsize vans, full-size vans, trucks, motorcycles, special vehicles, and construction machinery. About 5,000 pieces of domestic vehicle image data built by the Korea Institute of Science and Technology for the development of artificial intelligence technology were used as learning data. It proposes a lane designation control system that applies a vehicle type classification algorithm capable of recognizing both front and side angles with one camera.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.639-644
• /
• 2024

Recent developments in the use of drones on battlefields, extending beyond reconnaissance to firepower support, have greatly increased the importance of technologies for early automatic drone identification. In this study, to identify an effective image classification model that can distinguish drones from other aerial targets of similar size and appearance, such as birds and balloons, we utilized a dataset of 3,600 images collected from the internet. We adopted a transfer learning approach that combines the feature extraction capabilities of three pre-trained convolutional neural network models (VGG16, ResNet50, InceptionV3) with an additional classifier. Specifically, we conducted a comparative analysis of the performance of these three pre-trained models to determine the most effective one. The results showed that the InceptionV3 model achieved the highest accuracy at 99.66%. This research represents a new endeavor in utilizing existing convolutional neural network models and transfer learning for drone identification, which is expected to make a significant contribution to the advancement of drone identification technologies.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.21 no.1
• /
• pp.43-57
• /
• 2010

The purposes of this study are to examine how food and culture and Korean foods are reflected in the classification systems and to propose improvements of DDC to classify various subjects related to the materials of food and culture. For the study, six classification systems - DDC(Dewey Decimal Classification), UDC(Universal Decimal Classification), LCC(Library of Congress Classification), KDC(Korean Decimal Classification), NDC (Nippon Decimal Classification), China Library Classification - were analyzed in aspects of eating and drinking customs, eating etiquette, nutrition and diet, food and drink, meal and table service, beverage technology, and food technology. As a result, there were few headings about Korean food in six classification systems and it was necessary for DDC to have new headings for classifying Korean and Asian traditional foods and table services. Due to the literary warrant in classification systems, it is required to publish and disseminate various Korean food recipes and publications to add new headings or notes in future classification systems.

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.133-145
• /
• 2004

Combining multiple classifiers to obtain improved performance over the individual classifier has been a widely used technique. The task of constructing a multiple classifier system(MCS) contains two different issues : how to generate a diverse set of base-level classifiers and how to combine their predictions. In this paper, we review the characteristics of the existing multiple classifier systems: bagging, boosting, and stacking. And then we propose new MCSs: stacked bagging, stacked boosting, bagged stacking, and boasted stacking. These MCSs are a sort of hybrid MCSs that combine advantageous characteristics of the existing ones. In order to evaluate the performance of the proposed schemes, we conducted experiments with nine different real-world datasets from UCI KDD archive. The result of experiments showed the superiority of our hybrid MCSs, especially bagged stacking and boosted stacking, over the existing ones.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2007.11a
• /
• pp.762-767
• /
• 2007

The activity conducted throughout the life cycle of any facility generate an enormous quantity of data that needs to be stored, retrieved, communicated, and used by all parties involved. Advanced in technology have increased the opportunities for gathering, providing access to exchanging, and archiving all of this information for future reference. Considering that classification system of construction material is reviewed international exchange of information by the ISO standard, it is consist of classification form of construction process. As a result, this study analyzed to OmniClass Table-22(Master Format-20(4) for the purpose of gaining a the international standard and electronic information, and compared to OmniClass Table-23 ${\cdot}$ 35 ${\cdot}$ 41(UniClass, EPIC) for the expansion and standardization. Furthermore, it is tried to integrate with UN/SPSC attribute code for the establishing of application and international exchange.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.20 no.3
• /
• pp.219-232
• /
• 2009

This paper is intended to comparatively analyzed the KDC/NDC/DDC classification system for the field of civil engineering, the research field classification system of National Research Foundation of Korea, and the science and technology research field classification system of Korea Science and Engineering Foundation. And based on the analysis, it tried to propose the ways of improving the KDC classification system for the civil engineering field. As a result of the analysis, this paper has found that the KDC 5th-edition for the civil engineering field needed some corrections. That is, the classification items that reflect the trend of academic development should be added, the classification terminology of the basic theories of civil engineering should be properly developed, segmented topics should be added, any errors in classification codes and Korean/English descriptions should be corrected, and the omission of the KDC relative index of classification items should be solved. This paper proposed the ways of improving those problems.