• 산업경영시스템학회지
• /
• 제46권4호
• /
• pp.173-180
• /
• 2023

Smart factory companies are installing various sensors in production facilities and collecting field data. However, there are relatively few companies that actively utilize collected data, academic research using field data is actively underway. This study seeks to develop a model that detects anomalies in the process by analyzing spindle power data from a company that processes shafts used in automobile throttle valves. Since the data collected during machining processing is time series data, the model was developed through unsupervised learning by applying the Holt Winters technique and various deep learning algorithms such as RNN, LSTM, GRU, BiRNN, BiLSTM, and BiGRU. To evaluate each model, the difference between predicted and actual values was compared using MSE and RMSE. The BiLSTM model showed the optimal results based on RMSE. In order to diagnose abnormalities in the developed model, the critical point was set using statistical techniques in consultation with experts in the field and verified. By collecting and preprocessing real-world data and developing a model, this study serves as a case study of utilizing time-series data in small and medium-sized enterprises.

• Journal of Ecology and Environment
• /
• 제48권3호
• /
• pp.207-213
• /
• 2024

Spiders play a vital role in agricultural ecosystems by capturing and preying on small insects, thereby controlling the pests around crops. However, without directly collecting the specimen, it is challenging to accurately determine the species of the spider that formed the web and its diet. Spiders dissolve their prey with digestive fluids while consuming; thus, leaving very little residue in their digestive system. This study aimed to identify the spider that formed the web and the prey caught in the web using environmental DNA (eDNA) present in the spider web. For this purpose, eDNA using the mitochondrial cytochrome C oxidase subunit I (COI) gene was extracted from five adjacent spider webs collected from residences near agricultural environments. Based on the genes extracted from spider webs, it was confirmed that the most commonly found gene in all five spider webs was COI of Parasteatoda tepidariorum, and no other spider genes were detected. Among the five spider webs, prey was found in only one web, and in that web, genes of arthropods other than spiders were detected. The genes of the prey found in the spider web were identified to be those of Orthocladius tamarutilus, Tanytarsus tamagotoi, and Yemma exilis. Thus, without directly collecting arthropod specimens from the spider web, it was possible to identify the spider and its prey. This provides crucial information that can help in clearly understanding the predatory activities of spiders in agricultural ecosystems in the future.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 1998년도 학술발표회 발표논문집
• /
• pp.198-203
• /
• 1998

This study, a sub-one of comprehensive research works titled under “Rural Resources Evaluation System”, tried to verify utility/applicability of the developed model system through the case study works on 3 sample villages, Backya, Uyan and Suyu, representing the lowland, upland and seashore villages respectively. From the various surveying and collecting works including the official/statistical data collection, map analysis, insitu investigation, field survey and written material review, the original data set were obtained and manipulated into final input data for resources grading. After then, by the automatized calculation procedure of “Rural Resources Evaluation System”, score results for resources evaluation were finally produced with the total maximum score being 1,000. Through comparing works among score results of 3 case villages and between score results and areal characteristics of each case village, the applicability of the system developed in this study was well confirmed.

• 산업공학
• /
• 제12권3호
• /
• pp.374-381
• /
• 1999

In this paper, we propose an architecture of the DNC system for Shop Floor Control/Point of Production(SFC/POP). The DNC system to be presented this paper retrieves line-up sheets which include the drawing information, making a index database for line-up sheets, NC programs and tool adjustment data. And it is interface with a raw material, jig and tool information. Also, the DNC system transmits operation information to real workers rapidly, and supports realtime monitoring by collecting the state information of machines directly. In the analysis and design phases, this paper models realtime events using the state transition diagrams. In the implementation phase, we use the ORACLE DBMS(Database Management System) as the DBMS and Developer 2000 and Microsoft Visual C++ 5.0 as the programming tools.

• 한국정보통신학회논문지
• /
• 제6권8호
• /
• pp.1346-1351
• /
• 2002

분산된 네트워크 환경에서 침입탐지시스템을 구축하는 일은 단일 환경에서보다 매우 복잡하다. 특히, 각기 다른 운영체제시스템에서 발생하는 로그데이터의 수집과 분석 등에서 많은 문제가 발생한다. 따라서 본 논문에서는 이러한 문제를 해결하고자 에이전트 학습 시스템을 적용한 침입탐지시스템 모델을 제시한다. 에이전트 학습을 위한 알고리즘으로는 데이터 마이닝 알고리즘을 적용한다.

• 융합보안논문지
• /
• 제6권3호
• /
• pp.87-95
• /
• 2006

침입은 컴퓨터 자원의 무결성, 기밀성, 유효성을 저해하고 컴퓨터 시스템의 보안정책을 파괴하는 일련의 행위의 집합이다. 이러한 침입을 탐지하는 침입탐지시스템은 데이터 수집, 데이터의 가공 및 축약, 침입 분석 및 탐지 그리고 보고 및 대응의 4 단계로 구성되어진다. 침입탐지시스템의 방대한 데이터가 수집된 후, 침입을 효율적으로 탐지하기 위해서는 특징 선택이 중요하다. 이 논문에서 유전자 알고리즘과 결정트리를 활용한 특징 선택 방법을 제안한다. 또한 KDD 데이터에서 실험을 통해 방법의 유효성을 검증한다.

• International Journal of Contents
• /
• 제7권3호
• /
• pp.48-59
• /
• 2011

The present thesis is on a construction of the system which supports exhibition evaluation of curators, which automatically collects, keeps, and totalizes objective data on visitor behavior in museums, and which comprehensively displays the results by tables and graphs. The system is composed by access points and mobile exhibition exposition devices in the museum operating together. Obtainable visitor information include a user number, an average staying period, contents use hour, and exhibition viewing frequency. Prototype experiment at museums shows that the system is effective in efficient data collection and exhibition evaluation and is expected to become an information collecting tool for visitor research and an exhibition evaluation tool for exhibition improvement.

• 한국컴퓨터정보학회논문지
• /
• 제9권4호
• /
• pp.179-184
• /
• 2004

검침원이 방문을 통하여 계량기 지침을 읽고, 핸디 터미널을 이용하여 지침값을 입력하는 검침업무 시스템은 사생활 침해, 미검침 처리 및 오검침, 과다한 검침 비용 등의 문제가 발생하고 있다. 이런 고객서비스질의 저하를 막기 위하여 계량기의 지침을 자동으로 인식하고, RF 모듈를 이용하여 무선으로 검침데이터를 전송할 수 있는 원격검침 시스템을 설계하였다. 검침 데이터의 원시 자료 수집부터 수용가의 사용량 정보에 대한 통계정보 관리에 이르기까지의 전체적인 시스템을 설계함으로써 고객에게 보다 정확하고 구체적인 사용 정보를 제공하여 서비스의 만족도와 신뢰도를 향상 시킬 수 있으리라 사료된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.457-460
• /
• 2002

This paper is study on internet based remote control and monitoring for the system to purify water. environment of the water quality grew worse. therefore we require the effective system to purify water now national internet based remote control and monitoring make a sensation and are a problem to be solved. This paper demonstrate internet based remote control and monitoring for the system to purify water. This system including on server and many client distributed in whole country. The server is collecting information from the client. this information is then written inside Database. The Database is dealing with Website and Server and Client.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2008년도 춘계학술대회 논문집
• /
• pp.789-795
• /
• 2008

In recent, the rolling stocks are gradually complicated in respect with design and production to improve the safety and reliability. Also, the reliability centered maintenance corresponding with system specification or technical requirements is needed to meet the higher quality in railway service. In present, each railway authorities are collecting the failure's data using information system, applying those for maintenance works. However, this system has not established with systematic and scientific approach. This paper represents the existing activities and plans for RCM management system for AREX's EMU.