• 한국컴퓨터정보학회논문지
• /
• 제24권5호
• /
• pp.49-58
• /
• 2019

In this paper, we propose an edge cloud platform architecture for implementing smart factory. The edge cloud platform is one of edge computing architecture which is mainly focusing on the efficient computing between IoT devices and central cloud. So far, edge computing has put emphasis on reducing latency, bandwidth and computing cost in areas like smart homes and self-driving cars. On the other hand, in this paper, we suggest not only common functional architecture of edge system but also light weight cloud based architecture to apply to the specialized requirements of smart factory. Cloud based edge architecture has many advantages in terms of scalability and reliability of resources and operation of various independent edge functions compare to typical edge system architecture. To make sure the availability of edge cloud platform in smart factory, we also analyze requirements of smart factory edge. We redefine requirements from a 4M1E(man, machine, material, method, element) perspective which are essentially needed to be digitalized and intelligent for physical operation of smart factory. Based on these requirements, we suggest layered(IoT Gateway, Edge Cloud, Central Cloud) application and data architecture. we also propose edge cloud platform architecture using lightweight container virtualization technology. Finally, we validate its implementation effects with case study. we apply proposed edge cloud architecture to the real manufacturing process and compare to existing equipment engineering system. As a result, we prove that the response performance of the proposed approach was improved by 84 to 92% better than existing method.

• 스마트미디어저널
• /
• 제12권5호
• /
• pp.65-72
• /
• 2023

스마트팜은 농업과 ICT의 융복합을 통해 농업의 생산뿐만 아니라 유통과 소비를 포함한 농업과 관련된 다양한 분야로 새로운 가치를 창출하는 것을 의미한다. 국내에서도 스마트 농업 확산을 위한 임대형 스마트팜을 조성하고, 스마트팜 빅데이터 플랫폼을 구축하여 데이터 수집·활용 촉진. 스마트 APC 확대, 온라인거래소 운영 및 도매시장 거래정보 디지털화 등 산지에서 소비지까지 농산물 유통 디지털 전환을 추진하고 있다. 이처럼 농업 데이터는 다양한 출처에서 특성에 따라 정보가 생성되고 있지만, 통계 및 정형화된 데이터를 이용한 서비스로만 활용되고 있다. 이는 농업에서 생산·유통·소비까지 분산된 데이터 수집으로 인해 한계가 있으며 다양한 출처로부터의 다양한 형태의 데이터를 수집·처리하기 어렵기 때문이다. 그러므로 본 논문에서는 디지털 농업을 위한 국내 농업 데이터 수집·공유 현황을 분석하고 인공지능 서비스를 위한 데이터 수집·연계 방법을 제안한다. 그리고 제안하는 데이터를 이용하여 딥러닝 기반의 환경 인자를 추천하는 방법을 제안한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권4호
• /
• pp.1869-1886
• /
• 2018

This paper proposes a MIDI- and audio-based music genre classification method for Korean traditional music. There are many traditional instruments in Korea, and most of the traditional songs played using the instruments have similar patterns and rhythms. Although music information processing such as music genre classification and audio melody extraction have been studied, most studies have focused on pop, jazz, rock, and other universal genres. There are few studies on Korean traditional music because of the lack of datasets. This paper analyzes raw audio and MIDI phrases in Korean traditional music, performed using Korean traditional musical instruments. The classified samples and MIDI, based on our classification system, will be used to construct a database or to implement our Kontakt-based instrument library. Thus, we can construct a management system for a Korean traditional music library using this classification system. Appropriate feature sets for raw audio and MIDI phrases are proposed and the classification results-based on machine learning algorithms such as support vector machine, multi-layer perception, decision tree, and random forest-are outlined in this paper.

• 스마트미디어저널
• /
• 제4권2호
• /
• pp.26-33
• /
• 2015

본 논문은 영상에서 효과적으로 보행자를 삭제하는 자동 삭제 시스템을 제안한다. 첫 번째로 Histogram of Oriented Gradient(HOG) / Linear-Support Vector Machine(L-SVM)분류기를 이용하여 보행자를 찾고, 참조영상으로부터 적절한 배경을 습득하여 삭제될 보행자를 대체한다. 배경은 참조영상 내에서 검색하며 변경된 feather blender 연산은 대체 영역의 경계를 자연스럽게 만든다. 기존에 존재하던 대부분의 시스템이 수동인 것에 반해 제안된 시스템은 자동으로 객체를 검출하고 자연스러운 배경을 생성한다. 실험결과 대체된 영역의 PSNR 평균은 19.246으로 측정되었다.

• Tribology and Lubricants
• /
• 제24권3호
• /
• pp.111-121
• /
• 2008

An integrated in-line oil monitoring detector assigned for continuous in situ monitoring multiple parameters of oil performance for predicting economically optimal oil change intervals and equipment condition control is presented in this study. The detector estimates oil deterioration based on the information about chemical degradation, total contamination, water content of oil and oil temperature. The oil oxidation is estimated by "chromatic ratio", total contamination is measured by the changes in optical intensity of oil in three optical wavebands ("Red", "Green" and "Blue") and water content is evaluated as Relative Saturation of oil by water. The detector is able to monitor oils with low light absorption (hydraulic, transformer, turbine, compressor and etc. oils) as well as oils with rather high light absorption in visible waveband (diesel and etc. oils). In a case study that the detector is applied to a diesel engine oil, it is found that the detector provides good results on oil chemical degradation as well as soot concentration.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2009년도 학술대회
• /
• pp.677-684
• /
• 2009

다양한 센서 네트워크와 유비쿼터스 기술이 제공되는 지능형 협업 환경은 사용자를 위해 확장된 인터랙션을 제공할 수 있다. 기존의 인터랙션이 사용자와 컴퓨터 머신과의 직접적인 인터랙션이 주를 이룬 반면 새로 확장된 인터랙션은 사용자와 공간과의 인터랙션을, 실질적으로 공간을 구성하는, 관리와 제어가 가능한 구성요소와의 인터랙션을 나타낸다. 본 논문은 이러한 공간 인터랙션을 효과적으로 제공할 수 있도록 하기 위해서 공간 오브젝트를 등록, 인식하고, 특히 사용자의 의도에 맞는 태스크를 지원하기 위해 과거의 인터랙션 정보를 이용한 템플릿 기반 맵핑 알고리즘을 설계한다. 제안된 알고리즘을 이용하는 경우, 공간 오브젝트가 증가함에 따라 템플릿을 검색하여 처리하는데 드는 시스템의 비용이 어느 정도 향상되는지 실험을 통해 분석하도록 하며, 진행되는 모든 공간 인터랙션을 시각적으로 보여주기 위한 그래픽 기반의 도시 방법을 소개하고 결론을 맺는다.

• 한국컴퓨터정보학회논문지
• /
• 제23권7호
• /
• pp.19-26
• /
• 2018

This paper presents a structuring process of unstructured social network service (SNS) messages on rail services. We crawl messages about rail services posted on SNS and extract keywords indicating date and time, rail operating company, station name, direction, and rail service types from each message. Among them, the rail service types are classified by machine learning according to predefined rail service types, and the rest are extracted by regular expressions. Words are converted into vector representations using Word2Vec and a conventional Convolutional Neural Network (CNN) is used for training and classification. For performance measurement, our experimental results show a comparison with a TF-IDF and Support Vector Machine (SVM) approach. This structured information in the database and can be easily used for services for railway users.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2015년도 제46회 하계학술대회
• /
• pp.47-48
• /
• 2015

As the power system develops rapidly into a smarter and more flexible state, so must the communication technologies that support it. Machine to machine (M2M) communication in Smart Grid environment has been discussed in European Telecommunications Standards Institute (ETSI). The power system is not easily replaceable, due to system replacement cost. The M2M gateway is required in other to improve interoperability in M2M environment. The Distributed Network Protocol 3.0 (DNP3.0) is the most important standard in the SCADA systems for the power. It has been used for device data collection/control in Substation Systems, Distribution Automation System. If the DNP3.0 data model is combined with a set of contemporary web protocols, it can result in a major shift. We selected Constrained Application Protocol (CoAP) based on RESTful as M2M protocol. It is a specialized web transfer protocol for use with constrained nodes and constrained networks. We have used the OPNET Modeler 17.1 in order to verity the SOAP versus CoAP. In this paper, we propose the CoAP-based M2M Gateway to Distribution Automation system using DNP3.0 in Smart Grid Environment.

• Smart Structures and Systems
• /
• 제6권3호
• /
• pp.335-347
• /
• 2010

Recent advances in hardware and instrumentation technology have allowed the possibility of deploying very large sensor arrays on structures. Exploiting the huge amount of data that can result in order to perform vibration-based structural health monitoring (SHM) is not a trivial task and requires research into a number of specific problems. In terms of pressing problems of interest, this paper discusses: the design and optimisation of appropriate sensor networks, efficient data reduction techniques, efficient and automated feature extraction methods, reliable methods to deal with environmental and operational variability, efficient training of machine learning techniques and multi-scale approaches for dealing with very local damage. The paper is a result of the ESF-S3T Eurocores project "Smart Sensing For Structural Health Monitoring" (S3HM) in which a consortium of academic partners from across Europe are attempting to address issues in the design of automated vibration-based SHM systems for structures.

• 융합보안논문지
• /
• 제14권1호
• /
• pp.77-83
• /
• 2014

과거 안전에 대한 인식은 물리적 측면에서만 통용되었지만, 정보통신 기술의 발전으로 정보보안, 관리보안 측면으로 확대되어 다차원적인 보안 요구를 맞추기 위한 노력이 이루어지고 있다. 이러한 현실은 수요자의 눈높이도 인력경비에서 기계경비로 바뀌고 있는 실정이다. 이러한 기계 경비로의 전환은 인력 경비 업체의 수익성 문제를 야기 시키고, 현장에서의 신속하고 정확한 대응이 인력 경비에 비해 떨어지는 역부작용을 낳게 됐다. 따라서 본 연구에서는 인력에 의한 보안업무를 담당하는 시설경비에서 인력에 대한 수요자의 불신을 해소하고, 보다 높은 서비스를 제공하기 위해 다양한 업무형태 및 위치 정보를 최소화 할 수 있는 근태관리 시스템을 제안한다.