http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
압축된 영상 복원을 위한 양자화된 CNN 기반 초해상화 기법
김용우,이종환,Kim, Yongwoo,Lee, Jonghwan 한국반도체디스플레이기술학회 2020 반도체디스플레이기술학회지 Vol.19 No.4
In this paper, we propose a super-resolution method that reconstructs compressed low-resolution images into high-resolution images. We propose a CNN model with a small number of parameters, and even if quantization is applied to the proposed model, super-resolution can be implemented without deteriorating the image quality. To further improve the quality of the compressed low-resolution image, a new degradation model was proposed instead of the existing bicubic degradation model. The proposed degradation model is used only in the training process and can be applied by changing only the parameter values to the original CNN model. In the super-resolution image applying the proposed degradation model, visual artifacts caused by image compression were effectively removed. As a result, our proposed method generates higher PSNR values at compressed images and shows better visual quality, compared to conventional CNN-based SR methods.
김용우,이종환,Kim, Yongwoo,Lee, Jonghwan 한국반도체디스플레이기술학회 2020 반도체디스플레이기술학회지 Vol.19 No.4
Based on the capture-emission energy (CEE) maps of CMOS devices, a physics-informed machine learning model for the bias temperature instability (BTI)-induced threshold voltage shifts and low frequency noise is presented. In order to incorporate physics theories into the machine learning model, the integration of artificial neural network (IANN) is employed for the computation of the threshold voltage shifts and low frequency noise. The model combines the computational efficiency of IANN with the optimal estimation of Gaussian mixture model (GMM) with soft clustering. It enables full lifetime prediction of BTI under various stress and recovery conditions and provides accurate prediction of the dynamic behavior of the original measured data.
저결함 그래핀 양자점 구조를 갖는 RGO 나노 복합체 기반의 저항성 메모리 특성
김용우,황성원,Kim, Yongwoo,Hwang, Sung Won 한국반도체디스플레이기술학회 2021 반도체디스플레이기술학회지 Vol.20 No.1
The RGO with controllable oxygen functional groups is a novel material as the active layer of resistive switching memory through a reduction process. We designed a nanoscale conductive channel induced by local oxygen ion diffusion in an Au / RGO+GQD / Al resistive switching memory structure. A strong electric field was locally generated around the Al metal channel generated in BIL, and the local formation of a direct conductive low-dimensional channel in the complex RGO graphene quantum dot region was confirmed. The resistive memory design of the complex RGO graphene quantum dot structure can be applied as an effective structure for charge transport, and it has been shown that the resistive switching mechanism based on the movement of oxygen and metal ions is a fundamental alternative to understanding and application of next-generation intelligent semiconductor systems.
기존 3차원 인터랙션 동작인식 기술 현황 파악을 위한 메타분석
김용우(YongWoo Kim),황민철(Min Cheol Whang),김종화(Jong Hwa Kim),우진철(Jin Cheol Woo),김치중(ChiJung Kim),김지혜(Ji Hye Kim) 대한인간공학회 2010 大韓人間工學會誌 Vol.29 No.6
Most of the research on three-dimensional interaction field have showed different accuracy in terms of sensing, mode and method. Furthermore, implementation of interaction has been a lack of consistency in application field. Therefore, this study is to suggest research trends of three-dimensional interaction using meta-analysis. Searching relative keyword in database provided with 153 domestic papers and 188 international papers covering three-dimensional interaction. Analytical coding tables determined 18 domestic papers and 28 international papers for analysis. Frequency analysis was carried out on method of action, element, number, accuracy and then verified accuracy by effect size of the meta-analysis. As the results, the effect size of sensor-based was higher than vision-based, but the effect size was extracted to small as 0.02. The effect size of vision-based using hand motion was higher than sensor-based using band motion. Therefore, implementation of three-dimensional sensor-based interaction and vision-based using hand motions more efficient. This study was significant to comprehensive analysis of three-dimensional motion recognition for interaction and suggest to application directions of three-dimensional interaction.
기계학습을 활용한 게임승패 예측 및 변수중요도 산출을 통한 전략방향 도출
김용우(Kim, Yongwoo),김영민(Kim, Young-Min) 한국게임학회 2021 한국게임학회 논문지 Vol.21 No.4
본 연구에서는 게임 초반 10분의 데이터를 이용하여 리그오브레전드 게임의 최종승패를 랭크별로 예측하고, 구축된 승패예측 모형으로부터 변수중요도를 추출하여 승리를 위한 초반 게임운영의 방향성을 알아보았다. 그 결과 모든 랭크에서 70% 이상의 정확도로 승패를 예측할 수 있었다. 이는 경기 양상이 대부분 뒤집히지 않고 최종승패로 이어지는 것을 의미하며, 이러한 경향성은 상위랭크로 갈수록 더욱 강하게 나타났다. 랭크와 무관하게 킬(데스)가 초반 게임에서 최종승패에 가장 큰 영향을 미치는 요소로 나타났으나, 일부 변수는 랭크에 따라 중요도 순위가 변화하였고 이는 유저가 속한 랭크에 따라 승리에 효과적인 초반 전략방향에 차이가 있음을 시사한다. In this study, models for predicting the final result of League of Legends game were constructed for each rank using data from the first 10 minutes of the game. Variable importance was extracted from the prediction models to derive strategic direction in early phase of the game. As a result, it was possible to predict final results with over 70% accuracy in all ranks. It was found that early game advantage tends to lead to the final win and this tendency appeared stronger as it goes to challenger ranks. Kill(death) was found to be the most influential factor for win, however, there were also variables whose importance rank changed according to rank. This indicates there is a difference in the strategic direction in the early stage of the game depending on the rank.
제올라이트와 제강슬래그에 의한 중금속과 영양염류 복합오염물질의 제거 효과
김용우(Yongwoo Kim),오명학(Myounghak Oh),박준범(Junboum Park),권오순(Osoon Kwon) 한국지반환경공학회 2014 한국지반환경공학회논문집 Vol.15 No.11
투수성 반응벽체 공법은 지하수 오염을 정화하는 대표적인 방법 중의 하나이다. 영양염류와 중금속 등 여러 가지 오염물질이 동시에 존재하는 경우 두 가지 이상의 반응성 매질을 적용한 반응벽체공법으로 복합오염물질의 제거가 가능하다. 본 연구에서는 반응성 매질로 제올라이트와 제강슬래그를 함께 사용하는 경우 복합오염물질의 제거능을 평가하였다. 영양염류인 암모늄과 인산염, 중금속인 카드뮴이 혼합된 복합오염물질에 대하여 연속회분식실험을 통하여 제올라이트 및 제강슬래그와의 반응순서에 따른 오염물질 제거능을 분석하였다. 연속회분식실험 결과에 의하면 제올라이트-제강슬래그 순서로 반응하는 경우 영양염류와 중금속의 복합오염물질에 대한 제거능이 더 좋은 것으로 나타났다. Permeable reactive barrier has been recognized as the one of representative methods for remediation of contaminated groundwater. Reactive barrier system containing two and more reactive materials can remove multiple contaminants such as nutritive salts and heavy metals. In this study, removal efficiency of multiple contaminants was evaluated when both zeolite and basic oxygen furnace slag were used as reactive materials. Sequential batch test which consists of two materials was performed to evaluate removal efficiency comparing the reaction order of them against nutritive slats including ammonium and phosphate and heavy metal including cadmium. As a result, zeolite-basic oxygen furnace slag sequence batch test showed the best efficiency for removal of multiple contaminants including nutritive salts and heavy metal.