http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
스마트 빌딩 시스템을 위한 심층 강화학습 기반 양방향 전력거래 협상 기법
이동구,이지영,경찬욱,김진영,Lee, Donggu,Lee, Jiyoung,Kyeong, Chanuk,Kim, Jin-Young 한국인터넷방송통신학회 2021 한국인터넷방송통신학회 논문지 Vol.21 No.5
본 논문에서는 스마트 빌딩 시스템과 전력망이 각각의 전력거래 희망가격을 제안하고 조정하는 양방향 전력거래 협상 기법에 심층 강화학습 기법을 적용한 전력거래 기법을 제안한다. 심층 강화학습 기법 중 하나인 deep Q network 알고리즘을 적용하여 스마트 빌딩과 전력망의 거래 희망가격을 조정하도록 하였다. 제안하는 심층 강화학습 기반 양방향 전력거래 협상 알고리즘은 학습과정에서 평균 43.78회의 협상을 통해 가격 협의에 이르는 것을 실험을 통해 확인하였다. 또한, 본 연구에서 설정한 협상 시나리오에 따라 스마트 빌딩과 전력망이 거래 희망가격을 조정하는 과정을 실험을 통해 확인하였다. In this paper, we propose a deep reinforcement learning algorithm-based bi-directional electricity negotiation scheme that adjusts and propose the price they want to exchange for negotiation over smart building and utility grid. By employing a deep Q network algorithm, which is a kind of deep reinforcement learning algorithm, the proposed scheme adjusts the price proposal of smart building and utility grid. From the simulation results, it can be verified that consensus on electricity price negotiation requires average of 43.78 negotiation process. The negotiation process under simulation settings and scenario can also be confirmed through the simulation results.
YOLO 네트워크를 활용한 전이학습 기반 객체 탐지 알고리즘
이동구,선영규,김수현,심이삭,이계산,송명남,김진영,Lee, Donggu,Sun, Young-Ghyu,Kim, Soo-Hyun,Sim, Issac,Lee, Kye-San,Song, Myoung-Nam,Kim, Jin-Young 한국인터넷방송통신학회 2020 한국인터넷방송통신학회 논문지 Vol.20 No.1
딥 러닝 기반 객체 탐지 및 영상처리 분야에서 모델의 인식률과 정확도를 보장하기 위해 다량의 데이터 확보는 필수적이다. 본 논문에서는 학습데이터가 적은 경우에도 인공지능 모델의 높은 성능을 도출하기 위해 전이학습 기반 객체탐지 알고리즘을 제안한다. 본 논문에서는 객체탐지를 위해 사전 학습된 Resnet-50 네트워크와 YOLO(You Only Look Once) 네트워크를 결합한 전이학습 네트워크를 구성하였다. 구성된 전이학습 네트워크는 Leeds Sports Pose 데이터셋의 일부를 활용하여 이미지에서 가장 넓은 영역을 차지하고 있는 사람을 탐지하는 네트워크로 학습을 진행하였다. 실험결과는 탐지율 84%, 탐지 정확도 97%를 기록하였다. To guarantee AI model's prominent recognition rate and recognition precision, obtaining the large number of data is essential. In this paper, we propose transfer learning-based object detection algorithm for maintaining outstanding performance even when the volume of training data is small. Also, we proposed a tranfer learning network combining Resnet-50 and YOLO(You Only Look Once) network. The transfer learning network uses the Leeds Sports Pose dataset to train the network that detects the person who occupies the largest part of each images. Simulation results yield to detection rate as 84% and detection precision as 97%.
다양한 박막 형성법을 사용한 ZnO 전자 추출층이 역구조 고분자 태양전지에 미치는 영향 연구
이동구(Donggu Lee),노승욱(Seunguk Noh),성명모(Myungmo Sung),이창희(Changhee Lee) 한국태양광발전학회 2013 Current Photovoltaic Research Vol.1 No.1
We investigated the effects of ZnO thin film deposition methods on the performance of inverted polymer solar cells with a structure of ITO/ZnO/P3HT:PCBM/MoO3/Al. The ZnO thin films were deposited by various methods (spin coating of nanoparticles, sol-gel process, atomic layer deposition) and their morphology was analyzed by atomic force microscopy (AFM). The device with ZnO nanoparticle thin films showed the highest power conversion efficiency of 3 % with low series resistance and high shunt resistance. The superior performance of the device with the ZnO nanoparticle layer is attributed to better electron extraction capability.
유기발광소자에 적용 가능한 NiO<sub>x</sub> 기반의 정공주입층 연구
김준모 ( Junmo Kim ),김예진 ( Yejin Gim ),이원호 ( Wonho Lee ),이동구 ( Donggu Lee ) 한국센서학회 2021 센서학회지 Vol.30 No.5
Organic semiconductors have received tremendous attention for their research because of their tunable electrical and optical properties that can be achieved by changing their molecular structure. However, organic materials are inherently unstable in the presence of oxygen and moisture. Therefore, it is necessary to develop moisture and air stable semiconducting materials that can replace conventional organic semiconductors. In this study, we developed a NiO<sub>x</sub> thin film through a solution process. The electrical characteristics of the NiO<sub>x</sub> thin film, depending on the thermal annealing temperature and UV-ozone treatment, were determined by applying them to the hole injection layer of an organic light-emitting diode. A high annealing temperature of 500 ℃ and UV-ozone treatment enhanced the conductivity of the NiO<sub>x</sub> thin films. The optimized NiO<sub>x</sub> exhibited beneficial hole injection properties comparable those of 1,4,5,8,9,11-hexaazatriphenylene hexacarbonitrile (HAT-CN), a conventional organic hole injection layer. As a result, both devices exhibited similar power efficiencies and the comparable electroluminescent spectra. We believe that NiO<sub>x</sub> could be a potential solution which can provide robustness to conventional organic semiconductors.
유기 발광 소자 디스플레이를 위한 적외선 램프 소스를 활용한 열 전사 픽셀 패터닝
배형우 ( Hyeong Woo Bae ),장영찬 ( Youngchan Jang ),안명찬 ( Myungchan An ),박경태 ( Gyeongtae Park ),이동구 ( Donggu Lee ) 한국센서학회 2020 센서학회지 Vol.29 No.1
This study proposes a pixel-patterning method for organic light-emitting diodes (OLEDs) based on thermal transfer. An infrared lamp was introduced as a heat source, and glass type donor element, which absorbs infrared and generates heat and then transfers the organic layer to the substrate, was designed to selectively sublimate the organic material. A 200 nm-thick layer of molybdenum (Mo) was used as the lightto- heat conversion (LTHC) layer, and a 300 nm-thick layer of patterned silicon dioxide (SiO<sub>2</sub>), featuring a low heat-transfer coefficient, was formed on top of the LTHC layer to selectively block heat transfer. To prevent the thermal oxidation and diffusion of the LTHC material, a 100 nm-thick layer of silicon nitride (SiN<sub>x</sub>) was coated on the material. The fabricated donor glass exhibited appropriate temperature-increment property until 249 ℃, which is enough to evaporate the organic materials. The alpha-step thickness profiler and X-ray reflection (XRR) analysis revealed that the thickness of the transferred film decreased with increase in film density. In the patterning test, we achieved a 100 μm-long line and dot pattern with a high transfer accuracy and a mean deviation of ± 4.49 μm. By using the thermal-transfer process, we also fabricated a red phosphorescent device to confirm that the emissive layer was transferred well without the separation of the host and the dopant owing to a difference in their evaporation temperatures. Consequently, its efficiency suffered a minor decline owing to the oxidation of the material caused by the poor vacuum pressure of the process chamber; however, it exhibited an identical color property.