• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.111-114
• /
• 2008

The existence of noise bands may deform the typical shape of the spectrum, making the accuracy of clustering degraded. This paper proposes a statistical approach to remove noise bands in hyperspectral data using the correlation coefficient of bands as an indicator. Considering each band as a random variable, two adjacent signal bands in hyperspectral data are highly correlative. On the contrary, existence of a noise band will produce a low correlation. For clustering, the unsupervised ${\kappa}$-nearest neighbor clustering method is implemented in accordance with three well-accepted spectral matching measures, namely ED, SAM and SID. Furthermore, this paper proposes a hierarchical scheme of combining those measures. Finally, a separability assessment based on the between-class and the within-class scatter matrices is followed to evaluate the applicability of the proposed noise band removal method. Also, the paper brings out a comparison for spectral matching measures.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 제39회 하계학술대회
• /
• pp.227-228
• /
• 2008

This paper presents monitoring system based on IEC61400-25 for 750kW-class DFIG wind power generation system. It is consists of wind turbine PLC, Local and Remote I/O Server, human machine interface, and Web-server. Proposed System has been demonstrated in Daegi-ri, Kangwon-do, which aims to test IEC61400-25 communication capability of monitoring system and evaluate the performance of 750kW-class WTS.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.405-409
• /
• 2007

Each class in remotely sensed imagery has different spectral and spatial characteristics. Natural features have relatively smaller spatial changes than spectral changes. Meanwhile, urban area in which buildings, roads, and cars are included is inclined to face more changes of spatial variation than spectral one. This study aims to propose the new urban complexity index (UCI) based on the 3D DWT computation of remotely sensed imageries considering these characteristics. And then we analyze relation between index and land cover map. The 3DWUCI values are related to class and the indices of urban area are greater than natural area. The proposed UCI could be used to express effectively the standard of urban complexity over a wide area.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 ICEIC The International Conference on Electronics Informations and Communications
• /
• pp.447-450
• /
• 2004

This paper proposes remotely sensed image classification method by fuzzy c-means clustering algorithm using average intra-cluster distance. The average intra-cluster distance acquires an average of the vector set belong to each cluster and proportionates to its size and density. We perform classification according to pixel's membership grade by cluster center of fuzzy c-means clustering using the mean-values of training data about each class. Fuzzy c-means algorithm considered membership degree for inter-cluster of each class. And then, we validate degree of overlap between clusters. A pixel which has a high degree of overlap applies to the maximum likelihood classification method. Finally, we decide category by comparing with fuzzy membership degree and likelihood rate. The proposed method is applied to IKONOS remote sensing satellite image for the verifying test.

• 공학교육연구
• /
• 제25권5호
• /
• pp.55-67
• /
• 2022

Distance learning has become an efficient tool and is being widely used at work and in school. This research presents the results of a project-oriented entrepreneurship course taught both in classroom and online for a period of 3 years before and after the pandemic caused by COVID-19. Despite the various challenges, the outcome demonstrated that the students were able to attain required knowledge and capabilities in the online learning environment. As such, this paper discusses effective ways to blend in distance learning components so that both instructors and students can benefit from Internet-based education technologies. In the future, both face-to-face and virtual project work and study are likely to get integrated into a 'hyflex' class, which is flexible, on-offline education.

• 대한임베디드공학회논문지
• /
• 제7권2호
• /
• pp.113-120
• /
• 2012

In this paper we describe the integrated development environment for embedded software education. Our environment uses a cheap and widely available portable game console, Nintendo DS-lite. We have integrated open source development tools, and have implemented download shell, remote debugger. The results are all open source, and were used for university class for real embedded software education.

• 대한원격탐사학회지
• /
• 제11권3호
• /
• pp.101-116
• /
• 1995

최근 안전성과 경제성을 고려한 교통자료획득 방법으로 인공위성 영상자료를 사용하는 기술이 논의되어졌다. 본 논문은 인공위성영상을 이용한 고속도로 교통량 측정 자동화에 관한 연 구로서, 현재 사용되고 있는 교통량 측정방법의 단점 및 문제점을 평가, 분석하였으며, 본 보고서 에서 제안된 인공위성영상을 이용한 방안의 적용 및 가능성을 연구, 분석 하였다. 기존 인공위성 영상자료의 해상도가 교통자료획득에 적합하지 않으므로, 사진영상에 제안된 방 안을 도입하여, 실효성에 바탕을 둔 적용 여부를 검증하였다. 차량종류 및 교통량 측정에 필요한 인공위성영상의 해상도를 구하기 위하여 세 단계 (1m, 2m, 3,)의 사진영상해상도가 검토되었으며, 본 연구에서 제안된 일련의 영상처리 결과를 분석하였다. 전색성(panchromatic) 영상에서 도로와 차량의 반사율이 유사함으로, 도로상에서 차량을 탐지하 기 위하여 차량의 반사율을 이용하지않고 차량그림자의 반사율을 이용하였으며, 두가지 처리방법 이 제시되었다. 또한 차량종류를 구분하기위하여 여러가지 형태계수를 개발, 적용하였으며, 처리 과정을 상세히 설명하였다.

• 디자인학연구
• /
• 제17권2호
• /
• pp.463-470
• /
• 2004

본 연구에서는 비교적 간단한 구현 기술과 저가의 플랫폼으로 가상현실 체험을 해볼 수 있는 콘텐츠를 개발하고자 효과적인 가상현실 경험의 구현 요소를 연구하였으며, 그 요소는 현실감과 몰입감, 환상감의 구현 및 Tangible interaction의 사용으로 요약되었다. 이러한 요소들을 적용하여 경험 디자인 컨셉을 도출하고 상대적 현실감이 높은 실사 비디오 영상의 대화면 프로젝션(projection)과 비전 트레킹(Vision Tracking) 기술을 활용한 플랫폼을 디자인하였으며, Tangible device의 자연스러운 인터렉션을 적용한 가상현실 콘텐츠를 디자인하였다. 디자인 결과물은 전시의 형태로 제시하여 일반 사용자들의 체험 기회를 넓히고자 하였으며, Class Xylophone 2003과 VR Class의 두 가지 사례 연구를 통하여 컨텐츠 및 인터렉션 컨셉의 타당성을 검증하였고 다양한 가상현실 콘텐츠와 그 상업적 활용 가능성을 보여줌으로서 가상현실 분야의 저변 확대에 기여하고자 하였다.

• 한국지능시스템학회논문지
• /
• 제11권7호
• /
• pp.675-679
• /
• 2001

In this paper, we present a new competitive learning algorithm called Dynamic Competitive Learning (DCL). DCL is a supervised learning method that dynamically generates output neurons and initializes automatically the weight vectors from training patterns. It introduces a new parameter called LOG (Limit of Grade) to decide whether an output neuron is created or not. If the class of at least one among the LOG number of nearest output neurons is the same as the class of the present training pattern, then DCL adjusts the weight vector associated with the output neuron to learn the pattern. If the classes of all the nearest output neurons are different from the class of the training pattern, a new output neuron is created and the given training pattern is used to initialize the weight vector of the created neuron. The proposed method is significantly different from the previous competitive learning algorithms in the point that the selected neuron for learning is not limited only to the winner and the output neurons are dynamically generated during the learning process. In addition, the proposed algorithm has a small number of parameters, which are easy to be determined and applied to real-world problems. Experimental results for pattern recognition of remote sensing data and handwritten numeral data indicate the superiority of DCL in comparison to the conventional competitive learning methods.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 E
• /
• pp.2149-2151
• /
• 1999

This paper describes the impulse response characteristics of the grounding systems in power utility system. Several regulations regarding to electric power equipments, services and managements require that the groundings of class 1 ($E_1$) and class 2 ($E_2$) must be connected at the common point in grounding systems. In addition, the grounding for arrester ($E_{LA}$), which belongs to the grounding of class 1, should be connected at the same point. However, there is no method and position of common-connection at anywhere. In this work, when the impulse current was injected through the grounding conductor for arrester, the investigations measuring and analyzing potential rises induced at the common connection point and other grounding conductors were conducted. The experiments were carried out in the conditions of the grounding conductor of 25m long and the near or remote common connection from ground electrode. The lightning impulse current was applied so as to simulate the on-set of arrester due to lightning and/or switching surges.