http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
최현의(Hyun-Eui Choi),김태규(Tae-Kue Kim),박승규(Seung-Kyu Park),윤태성(Tae-Sung Yoon) 대한전기학회 2009 대한전기학회 학술대회 논문집 Vol.2009 No.7
Wheeled mobile robot has different mobility and steerability which determined by type of wheel and it's arrangement. Generally wheeled mobile robot's dynamics are nonlinear and various control methods have studied to control the mobile robot efficiently. In this paper, a T-S fuzzy modeling of a 2-wheeled mobile robot is made and a stable LMI-based state feedback fuzzy controller is designed and applied to the position control of the mobile robot for the reference trajectory following. Also, the verification of the designed controller is done by computer simulation.
김응석,최현일,이동의,강동진,Kim,Eung-Seok,Choi,Hyun-Il,Lee,Dong-Eui,Kang,Dong-Jin 한국방재학회 2009 한국방재학회논문집 Vol.9 No.6
본 연구의 목적은 Bhaskar 등(2000)의 연구를 우리나라 유역에 적용하여, 홍수사상에 따른 유출수문곡선의 특성을 이용한 돌발홍수지수를 산정함으로써 돌발홍수의 심각성 정도를 정량화하고자 하였다. 또한, Bhaskar 등(2000)의 연구내용을 보다 확장하여 돌발홍수지수와 강우강도, 강우지속시간 및 총유출량과의 상관관계를 정량적으로 분석하였다. 본 연구에서는 미계측유역인 매곡천 유역의 과거 31개의 호우사상에 대한 돌발홍수의 상대심도를 파악하기 위해, 강우-유출모의를 통한 홍수수문곡선을 모의하고 이에 따른 돌발홍수지수를 산정하여 돌발홍수심도를 정량화하였다. The aim of this study is to quantify the severity of flash food for a study watershed in Korea by estimation of flash food index using flood runoff hydrograph following Bhaskar et. al (2000). As an extension of the previous research, we examine the relation between flash food index and rainfall intensity, rainfall duration, and total runoff, respectively. This study has estimated the flash food index through simulated flood hydrographs to investigate the relative severity of flash flood in an ungauged basin, Megok river basin for 31 flood events.
그룹 집중 기술로 개선된 Trans-Unet기반 단일 영상 연무제거 신경망
홍찬의(Chan Eui Hong),최현덕(Hyun Duck Choi) 대한전자공학회 2022 전자공학회논문지 Vol.59 No.6
최근 컴퓨터 비전 기술이 발달하면서, 자율주행 분야에서 인공지능 기반 object detection, image segmentation 등의 컴퓨터 비전기술들이 주목받고 있다. 그러나 이러한 기술들은 야간이나 폭우, 안개 등 기후 악조건 주행환경에서는 영상 손실문제로 인해 성능이 급격하게 저하되고, 이는 치명적인 인명피해를 야기시킬 수 있다. 본 논문에서는 이러한 영상 악조건 속에서도 강인한 컴퓨터 비전기술을 확보하기 위해 Group Attention Block (GAB)을 제안하고 이를 Unet 구조와 Vision Transformer에 적용한 새로운 영상 연무제거 모델을 제안한다. 기존의 CNN(Convolution Neural Network)기반 encoder, decoder와 skip connection이 적용된 Unet구조를 통해 영상의 공간적인 정보를 활용한 특징맵을 추출하고 GAB를 적용하여 특징맵을 강화하며, 여기에 Vision Transformer를 추가 적용함으로써 inductive bias를 줄여 글로벌한 정보에서도 영상의 손실이 없도록 개선하였다. 제안하는 신경망 구조는 이전에 연구된 image dehazing 모델에 비해 PSNR(Peak Signal-to-Noise Ratio)과 SSIM(Structural Similarity Index Measure)에서 개선된 결과를 나타냄을 보여준다. With the recent development of computer vision technology, computer vision technologies such as artificial intelligence-based object detection and image segmentation are attracting attention in the field of autonomous driving. However, these technologies degrade performance due to image loss in driving environments under adverse weather conditions such as nighttime, heavy rain, and fog, which can cause fatal human casualties. In this paper, we propose a novel Group Attention Block (GAB) and a haze removal model combined with the Unet and Vision Transformer in order to get robust computer vision technologies even in such adverse image conditions. This network can capture the image feature with spatial information by CNN layer as well as capture global relations without inductive bias through Vision Transformer. Finally, GAB enhances these functions and helps the decoder to restore the clean image. The simulation results show an improvement in dehazing by PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index Measure) score compared to the previous image dehazing models.
Cell 방식 포장공정에서의 Missing Item 검사 및 관리 시스템
김현우(Hyeon-Woo Kim),최현의(Hyun-Eui Choi),안호균(Ho-Gyun An),윤태성(Tae-Sung Yoon) 대한전기학회 2009 정보 및 제어 심포지엄 논문집 Vol.2009 No.5
Cell type packaging line is more suitable for the products with various models and small quantities like mobile phone or mp3 player than conveyor type packaging line. Cell type packaging line is applicable to package various product models, but it can cause wrong product compositions and missing of items. So, automatic missing item detection system is needed. We designed an missing item detection system with a bar code reader, infrared sensors, and a digital camera. and also developed the programs for sensor data acquisition, image data processing. Gill, and data management.
천효석(Hyo Seok Cheon),최현의(Hyun Eui Choi),윤태성(Tae Sung Yoon),박승규(Seung Kyu Park) 대한전기학회 2010 대한전기학회 학술대회 논문집 Vol.2010 No.7
In this paper, a trajectory tracking control system for mobile robot is proposed using LMI based fuzzy control method. For this, firstly, mobile robot is designed as a combined form of linear sub systems by using T-S fuzzy method. Secondly, the control gains of state feedback controller for each linear sub system which stabilize the overall trajectory tracking control system are obtained by applying Lyapunov stability condition and solving the resultant LMI's. Also, some computer simulations using Simulink and experimentations using P3DX mobile robot are executed for the verification of the performance of the proposed trajectory tracking control system. The results show that T-S fuzzy control method is an efficient means for controlling a nonlinear system and the proposed trajectory tracking control system can be used usefully for the autonomous navigation of wheeled mobile robot.