Design and evaluation of artificial intelligence models for abnormal data detection and prediction

주해종,송호빈 아이씨티플랫폼학회 2023 JOURNAL OF PLATFORM TECHNOLOGY Vol.11 No.6

In today's system operation, it is difficult to detect failures and take immediate action in the case of a shortage of manpower compared to the number of equipment or failures in vulnerable time zones, which can lead to delays in failure recovery. In addition, various algorithms exist to detect abnormal symptom data, and it is important to select an appropriate algorithm for each problem. In this paper, an ensemble-based isolation forest model was used to efficiently detect multivariate point anomalies that deviated from the mean distribution in the data set generated to predict system failure and minimize service interruption. And since significant changes in memory space usage are observed together with changes in CPU usage, the problem is solved by using LSTM-Auto Encoder for a collective anomaly in which another feature exhibits an abnormal pattern according to a change in one by comparing two or more features. did In addition, evaluation indicators are set for the performance evaluation of the model presented in this study, and then AI model evaluation is performed.

A study on real-time internet comment system through sentiment analysis and deep learning application

주해종,송호빈 아이씨티플랫폼학회 2023 JOURNAL OF PLATFORM TECHNOLOGY Vol.11 No.2

This paper proposes a big data sentiment analysis method and deep learning implementation method to provide a webtoon comment analysis web page for convenient comment confirmation and feedback of webtoon writers for the development of the cartoon industry in the video animation field. In order to solve the difficulty of automatic analysis due to the nature of Internet comments and provide various sentiment analysis information, LSTM(Long Short-Term Memory) algorithm, ranking algorithm, and word2vec algorithm are applied in parallel, and actual popular works are used to verify the validity. If the analysis method of this paper is used, it is easy to expand to other domestic and overseas platforms, and it is expected that it can be used in various video animation content fields, not limited to the webtoon field

VOD 콘텐츠 시청형태 빅데이터 분석을 위한 지능 시스템 연구

주해종,조문택,문석환 한국차세대컴퓨팅학회 2018 한국차세대컴퓨팅학회 논문지 Vol.14 No.3

This study investigated the system for analyzing the type of viewing such as genre, time zone, and rating level based on the VOD contents using 1 month of VOD contents clicks of subscribers according to the cable broadcasting VOD viewing format. First, we developed a system to provide data processing method and visibility to classify VOD content viewing data viewed for one month for analysis system according to analysis type. Second, the analytical system is used to derive VOD viewing style analysis results by genre, time zone, and deliberation level. This was able to analyze the tendency of viewers' usage according to specific genre, viewing time, and deliberation level. As a result, it can be expected that the use of VOD service will be increased if a recommendation service is provided to subscribers through the development of a personalized recommendation system according to the viewing style of VOD contents in the future. 본 연구는 이블 방송 VOD 가입자의 1개월간 이용한 VOD 콘텐츠 클릭 수를 상으로 장르별, 시간별, 심의등 별 등 가입자의 시청형태를 분석하기 한 시스템을 연구하다. 첫째, 분석 시스템 개발을 해 1개월 간 시청한 VOD 콘텐츠를 데이터 유형에 맞춰 분석하기 해 데이터 처리방법 가시성을 제공하는 시스템을 구성하다. 둘 째, 이러한 분석 시스템을 통해 장르별, 시간별, 심의 등별로 VOD시청형태에 한 분석 결과를 도출하다. 이 를 통해 이블 방송 VOD 가입자의 특정 장르별, 시청 시간별, 심의 등별에 따른 이용형태와 경향을 분석할 수 있다. 이 연구결과를 통해 향후 VOD 콘텐츠 시청형태에 따라 개인화된 추천 시스템 개발과 맞춤 서비스를 가입자에게 제 공할 경우, 유료 방송 VOD이용이 더 증가할 것으로 측할 수 있다.

객체 중심 데이타베이스의 설계방법론 및 스키마생성 자동화 도구의 구현에 관한연구

주해종,박영배 명지대학교 공학기술연구소 1989 공학기술연구소 논문집 Vol.4 No.-

The Object-Oriented DB is highly popular on the several parts of applications for a good many advantages. One way, the business of DB design has increased owing to usage increasement of information system, so the needs of design methodology which is systematic and reasonable have appeared. In this paper, we propose the design methodology of Object-Oriented Database. Also, as the topic of this paper, we implement ASTO (Automatic Schema Generation Tool for OODB) using the proposed design methodology. The tool was implemented using C Language on IBM-PC/AT.

의견정보 검색엔진을 위한 웹 콘텐츠 마이닝 시스템

주해종,박영배,최혜길,Joo, Hae-Jong,Park, Young-Bae,Choi, Hae-Gil 한국정보기술전략혁신학회 2009 情報學硏究 Vol.12 No.3

This research is about the design of an opinion drawing and analysis system through statistical based Web Mining of web contents, where data of opinions are automatically drawn and analyzed concerning web documents that are scattered around in various web sites that exist within the internet. Furthermore, provides a search service that can easily classify positive/negative opinions and also provide searching and statistical information. Users, who want to search for opinions, can input a specific keyword to observe opinions of others easily. In addition, there is a merit in materializing the monitoring system.

모바일 데이터베이스 환경의 신뢰성 보장 질의처리 시스템 설계

주해종,박영배,Joo, Hae-Jong,Park, Young-Bae 한국정보처리학회 2005 정보처리학회논문지D Vol.12 No.4

무선 네트워크(Wireless Network)의 약한 연결성 및 접속단절, 모바일 클라이언트의 이동성, 모바일 클라이언트의 휴대성으로 인해 발생하는 모바일 데이터베이스 시스템(Mobile Database System) 관련 이슈들과 이 문제들을 해결하기 위한 연구들도 한창이다 이동 컴퓨팅은 언제 어디서나 원하는 모든 정보를 이용할 수 있는 사용자의 편의성이나 성능 면에서의 요구를 만족시키고 있지만, 데이터 관리 측면에서는 해결되어야만 하는 많은 문제점들을 안고 있다. 본 논문은 모바일 클라이언트-서버(Mobile Client-Server) 환경에서 모바일 데이터베이스 시스템 특성상 가질 수 있는 무선 네트워크의 약한 연결성 및 접속성 단절로 인한 데이터베이스 비축(Database Hoarding)과 관련된 문제, 공유 데이터(Shared Data)의 일관성(Consistency)유지 문제, 그리고 로그(Log) 최적화 문제를 해결하기 위한 모바일 질의 처리 시스템(MQPS : Mobile Query Processing System)을 설계하는데 목적이 있다. 또한, MQPS의 효율성 증명을 위해 C-I-S(Client-Intercept-Server) 모델과의 성능비교를 통해 제안한 시스템이 우수하다는 것을 입증하였다. Many researches are going on with regard to issues and problems related to mobile database systems, which are caused by the weak connectivity of wireless networks, the mobility and the Portability of mobile clients. Mobile computing satisfies user's demands for convenience and Performance to use information at any time and in any Place, but it has many Problems to be solved in the aspect of data management. The purpose of our study is to design Mobile Query Processing System(MQPS) to solve problems related to database hoarding, the maintenance of shared data consistency and the optimization of logging, which are caused by the weak connectivity and disconnection of wireless networks inherent in mobile database systems under mobile client-server environments. In addition, we proved the superiority of the proposed MQPS by comparing its performance to the C-I-S(Client-Intercept- Server) model.

인터넷을 이용한 현장 시뮬레이션 헬스시스템에 관한 연구

주해종,한기준,편동현,Joo, Hae-Jong,Han, Ki-Jun,Pyun, Dong-Hyun 한국정보기술전략혁신학회 2003 情報學硏究 Vol.6 No.1

This paper supplies data of bulky amount such as slant environment by place's video and sound and topography that want all the world through internet. Therefore, do by purpose that offer spot simulation health system that use net that do so that can offer environment similar to that is run the country that want, area that want that user wants without receiving limitation in area.

모바일 클라이언트의 데이터 무결성 보장을 위한 보안모듈에 관한 연구

주해종,홍봉화,Joo, Hae-Jong,Hong, Bong-Hwa 한국정보기술전략혁신학회 2007 情報學硏究 Vol.10 No.3

This study aims to suggest an implementation methodology of security module for data integrity of mobile internet terminal. This is based on the WTLS(Wileless Transport Layer Security) of WAP Protocol. This security module is expected to achieve central role in conversion of wireless internet environment and emphasis of encryption technology and safe and calculable wireless communication environment construction.

CASE를 이용한 데이터웨어하우스 구축 방법에 관한 연구

주해종,한기준 한국컴퓨터정보학회 1999 한국컴퓨터정보학회지 Vol.6 No.1

실시간 처리 기반의 모바일 클라이언트-서버 시스템 구현

주해종,홍봉화,Joo, Hae-Jong,Hong, Bong-Wha 한국정보기술전략혁신학회 2006 情報學硏究 Vol.9 No.4

Many researches are going on with regard to issues and problems related to mobile database systems, which are caused by the weak connectivity of wireless networks, the mobility and the portability of mobile clients. Mobile computing satisfies user's demands for convenience and performance to use information at any time and in any place, but it has many problems to be solved in the aspect of data management. The purpose of our study is to Implement Real-Time Mobile Query Processing System(MQPS) to solve problems related to database hoarding, the maintenance of shared dataconsistency and the optimization of logging, which are caused by the weak connectivity and disconnection of wireless networks inherent in mobile database systems under mobile client server environments. In addition, we proved the superiority of the proposed MQPS by comparing its performance to the C I S(Client-Intercept-Srever) model.