• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.29-30
• /
• 2024

본 논문은 Krafton의 PUBG: BATTLEGROUNDS 게임에서 플레이어 분류를 목표로 하며, 포즈 추정기술을 사용하여 일반 플레이어와 봇을 구분한다. 이는 게임에서 직접 수집한 비디오 데이터를 기반으로 하며, 다음과 같은 두 가지 접근 방식을 제안한다. 첫 번째 방법은 동작 시퀀스 분석을 통해, 사용자의 특정동작 패턴을 식별하고 로지스틱 회귀 모델을 활용해 사용자 유형을 분류한다. 두 번째 방법은 YOLO-pose 모델을 사용하여 비디오 데이터에서 키포인트를 추출하고, 이를 LSTM 모델에 적용하여 프레임별로 사용자의 유형을 분류한다. 이러한 이중 접근 방식은 게임의 공정성과 사용자 경험을 향상시키는 새로운 도구를 제공하며, 보다 안전한 게임 환경에 기여할 수 있다. 이 연구는 게임 산업뿐만 아니라 보안 및 모니터링 분야에서도 동작 분석에 대한 혁신적인 접근 방식으로 활용될 잠재력을 가지고 있다.

• The Science & Technology
• /
• v.11 no.12 s.115
• /
• pp.21-26
• /
• 1978

1. 과학기술과 산업발전 (1)국가자원으로서의 기술 (2)기술승수효과(technological multiplier effect) 2. 우리나라 산업구조 고도화의 기본방향 (1)가공단계별 분류에 의한 산업구조의 전망 (2)산업구조 고도화의 목표와 방향

• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.181-182
• /
• 2019

국가과학기술지식정보서비스(NTIS)는 국가R&D 과제정보를 중심으로 참여인력, 성과(물), 참여기관 등의 정보를 연계하여 제공하고 있다. 각 과제정보는 한글 및 영문 키워드와 과학기술표준분류를 포함하고 있어, 과제정보를 중심으로 한 국가R&D정보 검색 및 분류에 활용하기 적합하다. 이러한 국가R&D정보를 서비스함에 있어 단순 검색을 벗어나 다양한 형태로 가공된 정보를 제공하기 위해서는 국가R&D 정보에 적합한 과학기술용어사전 구축이 필수적이다. 본 논문에서는 국가R&D 과제 키워드를 활용해 국가R&D정보에 적합한 과학기술용어사전을 구축하는 방안을 제안하고자 한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2609-2618
• /
• 2011

Under the knowledge-based economy in 21C, the convergence and complexity in science and technology are being more active. Interoperability between heterogeneous domains is a very important point considered in the field of scholarly information service as well information standardization. Thus we suggest the systematic solution method to flexibly extend classification scheme in order for content management and service organizations. Especially, This paper shows that automatic method for interoperability between heterogeneous scholarly classification code structures will be effective in enhancing the information service system.

• Journal of the Korean Society for information Management
• /
• v.34 no.4
• /
• pp.321-344
• /
• 2017

Research on automatic classification of records and documents has been conducted for a long time. Recently, artificial intelligence technology has been developed to combine machine learning and deep learning. In this study, we first looked at the process of automatic classification of documents and learning method of artificial intelligence. We also discussed the necessity of applying artificial intelligence technology to records management using various cases of machine learning, especially supervised methods. And we conducted a test to automatically classify the public records of the Seoul metropolitan government into BRM using ETRI's Exobrain, based on supervised machine learning method. Through this, we have drawn up issues to be considered in each step in records management agencies to automatically classify the records into various classification schemes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.144-150
• /
• 2017

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.22 no.4
• /
• pp.231-250
• /
• 2011

The purposes of this study are to review characteristics and research areas of environmental studies; to compare and analyze environmental studies in research classifications and Korean societies from Korea Research Foundation(KRF) as well as decimal classification systems such as KDC, DDC, NDC and to suggest several modifications for environmental studies in KDC for the next edition. First of all, environmental philosophy, environmental sociology, environmental education, environmental toxicology, environmental architecture, and environmental geography are suggested to add to the main schedule in KDC and -0276 green technology(environmental technology) is suggested to add to Table 1. Standard subdivision. And new classification numbers for environmental law and environmental public administration are suggested in law and public administration.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.33 no.2
• /
• pp.73-79
• /
• 2020

Building Information Modeling (BIM) tools have not only increased the use of technology in the design process, but also increased the need for more information standard systems. The object classification system consists of 327 types of construction results obtained from 25 kinds of facilities, 174 types of parts, and 207 types of construction parts. In the previous study, the property classification system was developed into 4 major classifications, 13 middle classifications, 58 small classifications (category), and 333 attribution information of roads and rivers. It is extremely difficult to input the property information according to such extensive object classification. In addition, the development of external applications such as Revit plug-ins has created a need to automate specific and repetitive tasks. Therefore, following the BIM property classification system, an attribute input program was implemented for the system to enhance the productivity and convenience of the BIM users.

• Database Research
• /
• v.34 no.3
• /
• pp.3-13
• /
• 2018

Text classification is one of the text mining technologies that classifies a given textual document into its appropriate categories and is used in various fields such as spam email detection, news classification, question answering, emotional analysis, and chat bot. In general, the text classification system utilizes machine learning algorithms, and among a number of algorithms, naïve Bayes and support vector machine, which are suitable for text data, are known to have reasonable performance. Recently, with the development of deep learning technology, several researches on applying deep neural networks such as recurrent neural networks (RNN) and convolutional neural networks (CNN) have been introduced to improve the performance of text classification system. However, the current text classification techniques have not yet reached the perfect level of text classification. This paper focuses on the fact that the text data is expressed as a vector only with the word dimensions, which impairs the semantic information inherent in the text, and proposes a neural network architecture based upon the semantic tensor space model.

• Journal of Industrial Convergence
• /
• v.22 no.10
• /
• pp.11-19
• /
• 2024

This study aims to discuss the appropriateness of domestic industrial classification by analyzing whether companies are grouped into similar categories within the domestic industry classification system. The industry classification was limited to the manufacturing industry and the professional, scientific, and technical services industry, and a homogeneity test was conducted on companies belonging to these two industries. A homogeneity test was performed using companies' accounting information, selecting total accruals, the difference between sales and accounts receivable increments, and tangible assets, which are critical components of the accrual model, to represent the role of industry classification. The analysis results confirmed that the homogeneity of companies in the manufacturing industry is relatively higher than that of companies in the professional, scientific, and technical services industry. The findings of this study suggest that while the industry classification is a highly useful system that enhances the understanding of companies by enabling analysis at both the company level and the industry level to which the company belongs, it has limitations as it assumes the homogeneity of companies within an industry. Therefore, the impact of industry classification should be considered according to the research objectives.