• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 C
• /
• pp.1123-1125
• /
• 1999

This paper proposes an optimization technique using Genetic Algorithm(GA) for service restoration in the distribution system. Restoration planning problem can be treated as a combinatorial optimization problem. So GA is appropriate to solve the service restoration problem in the distribution network. But searching capabilities of the GA can be enhanced by developing relevant repairing operation and modifying GA operations. In this paper, we aimed at finding appropriate open sectionalizing switch position for the restoration of distribution networks after disturbances using enhanced GA with repairing operation and modified mutation. Simulation results show that proposed method found the open sectionalizing switches with less out of service area and minimize transmission line losses and voltage drop.

• 한국환경복원기술학회지
• /
• 제4권3호
• /
• pp.75-83
• /
• 2001

This study selected Yangpyung as a target site because Yangpyung is a area of high value blessed with well preserved natural resources and beautiful natural scene and where thoughtless development and malformed use of land are in progress under the mask of hotel, accommodations and sales facility which fits the interests of land owner. As for the method used for this study, I inquired into domestic/international instances and the concept of existing environmental indicators and assessment of suitability with a view to establish assessment indicators and pose the concept through theoretical investigation of green-network and to establish green-network. 17 articles of environmental indicators such as aspect analysis, contour, greenbelt, DEM, NDVI, nature conservation area, reservoir and area for the promotion of agriculture were chosen as a actual analysing n data for setting up assessment indicators. From the result of analysis, as anticipated, green zone in Yongmusan areas within Youngmun and Seojong areas were the center of green-network in the wide area green-network in Yangpyung and the restricted area by basin system, road and legal regulation was selected as spot area and finally arable land and reservoir were selected as base which connects core with spot.

• 한국환경복원기술학회지
• /
• 제7권5호
• /
• pp.66-74
• /
• 2004

Since 1960s urban streams in Seoul have been dried and polluted because of urbanization. So, these devastated urban stream environment need to be restored for the better life of residents. Since 1995 stream restoration project which is called Natural-Style Stream Project have begun. However, some projects focused on the restoration of park-style open space rather than restoration of stream environment. As a result there are some stream landscapes to be improved. Therefore, this study aims to investigate the current status of urban stream landscape after Natural Style Stream Project and to propose the alternatives for the urban stream landscape improvement. The study site is Yangjae stream, Seoul.

• 한국환경복원기술학회지
• /
• 제5권1호
• /
• pp.51-58
• /
• 2002

Since planning of green-network is deeply being discussed, natural environmental disruption from an enlarged civilization is causing serious problems for urban communities. The purpose of this research is to support green-network infrastructure of Gangnam-gu, Seoul, considering ecological environmental planning for urban parks. The Methodologies for this study are landcover classification, NDVI and subjective analysis, and residents' survey. Findings of this research are as follows : 1) Based on the results, the area adjacent to Daemo mountain shows significant differences between 1985 and 1999. These results imply that the green space has been decreasing and deeply destroying. 2) Residents' survey shows that people want to live with wild animals and plants in the natural park. Future development planning of urban park should consider primary factors : ecosystem, increasing inhabitants' participation.

• KIEE International Transactions on Power Engineering
• /
• 제2A권3호
• /
• pp.102-108
• /
• 2002

Due to the many attractive aspects of DG in the future power distribution system, distribution automation will be a center hub of integration of the distribution system and resources to satisfy the various needs of customers in a competitive and deregulated environment. In this paper, operation strategies are presented which use network reconfiguration of the automated distribution systems with DG as a real-time operation tool for loss reduction and service restoration from the view of distribution operation. The algorithms and operation strategies of an automated distribution system with DG are introduced to achieve the positive effects of DG in distribution systems. A simple case study shows the effectiveness of the proposed operation strategies.

• Journal of Electrical Engineering and Technology
• /
• 제7권3호
• /
• pp.288-296
• /
• 2012

The method proposed by the author is intended for assistance in decision-making (concerning changes of connections) by operators of complex distribution systems during states of malfunction (particularly in the events of malfunctions, for which the consequences encompass extended parts of the network), through designation of connection action scenarios (creating substitute configurations). It is the use by the classifying system working with the co-evolution algorithm that enables the effective creation of substitute scenarios for the Medium Voltage electric power distribution network. The author also completed works concerning the possibility of using cooperation of the evolutionary algorithm and the co-evolutionary algorithm with local search algorithms. The method drawn up may be used in current systems managing the work of distribution networks to assist network operators in taking decisions concerning connection actions in supervised electric power systems.

• 한국멀티미디어학회논문지
• /
• 제25권5호
• /
• pp.676-684
• /
• 2022

As realistic media are widespread in various image processing areas, image or video compression is one of the key technologies to enable real-time applications with limited network bandwidth. Generally, image or video compression cause the unnecessary compression artifacts, such as blocking artifacts and ringing effects. In this study, we propose a Deep Residual Channel-attention Network, so called DRCAN, which consists of an input layer, a feature extractor and an output layer. Experimental results showed that the proposed DRCAN can reduced the total memory size and the inference time by as low as 47% and 59%, respectively. In addition, DRCAN can achieve a better peak signal-to-noise ratio and structural similarity index measure for compressed images compared to the previous methods.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.448-449
• /
• 2022

이미지 업스케일링 분야에서 보간법을 이용하는 것보다 딥러닝을 이용한 방법이 우수한 결과를 보이고 있다. 그리고 홀로그램 업스케일링도 일반적인 보간법보다 딥러닝을 사용하는 것이 더 좋은 결과를 보이고 있다. 본 논문에서는 이에 대한 네트워크 구조 및 학습 결과를 분석한다. 동일한 가중치에서 네트워크의 깊이와 채널 수를 조절하여 학습한 결과를 비교한다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.234-236
• /
• 2020

Content-adaptive training and transmission of the model parameters of neural networks can boost up the SR performance with higher restoration fidelity. In this case, efficient transmission of neural network parameters are essentially needed. Thus, we propose a novel method of compressing the network model parameters based on the training of network model parameters in the sense that the residues of filter parameters and content loss are jointly minimized. So, the residues of filter parameters are only transmitted to receiver sides for different temporal portions of video under consideration. This is advantage for image restoration applications with receivers (user terminals) of low complexity. In this case, the user terminals are assumed to have a limited computation and storage resource.

• 한국컴퓨터그래픽스학회논문지
• /
• 제25권3호
• /
• pp.1-9
• /
• 2019

자율 주행 자동차나 소방 로봇과 같은 시스템에서 영상을 얻을 때 다양한 요인들로 인해 잡음, 블러와 같은 열화가 발생한다. 이런 열화된 영상에 직접 영상 분류와 같은 기술을 적용하기 어려워 열화 제거가 불가피하나 이러한 시스템들은 영상의 열화를 인식할 수 없어서 열화된 영상을 복원하는데 어려움이 있다. 본 논문에서는 영상에 적용된 열화를 인지하지 못하는 상황에서 여러 방법들로 열화된 영상으로부터 자연스럽고 선명한 영상을 복원하는 방법을 제안한다. 우리가 제안한 방법은 딥러닝 모델에 채널 어텐션 모듈과 스킵 커넥션을 사용하여 영상에 적용된 열화에 따라 복원에 필요한 채널에 높은 가중치를 적용해 복합 열화 영상의 복원을 진행한다. 이 방법은 다른 복합 열화 복원 방법에 비해 학습이 간단하고 기존의 다른 방법들에 비해 높은 복합 열화 복원 성능을 낸다.