http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 고정범 (검색결과 55 건)
- 무료
- 기관 내 무료
- 유료
-
-
CNN을 이용한 실내가구 인테리어배치 AR알고리즘 모델링에 대한 연구
고정범,김준용 한국컴퓨터정보학회 2022 한국컴퓨터정보학회논문지 Vol.27 No.10
In this paper, a model that can increase the efficiency of work in arranging interior furniture by applying augmented reality technology was studied. In the existing system to which augmented reality is currently applied, there is a problem in that information is limitedly provided depending on the size and nature of the company's product when outputting the image of furniture. To solve this problem, this paper presents an AR labeling algorithm. The AR labeling algorithm extracts feature points from the captured images and builds a database including indoor location information. A method of detecting and learning the location data of furniture in an indoor space was adopted using the CNN technique. Through the learned result, it is confirmed that the error between the indoor location and the location shown by learning can be significantly reduced. In addition, a study was conducted to allow users to easily place desired furniture through augmented reality by receiving detailed information about furniture along with accurate image extraction of furniture. As a result of the study, the accuracy and loss rate of the model were found to be 99% and 0.026, indicating the significance of this study by securing reliability. The results of this study are expected to satisfy consumers' satisfaction and purchase desires by accurately arranging desired furniture indoors through the design and implementation of AR labels. 본 논문에서는 증강현실 기술을 적용하여 실내 가구 인테리어를 배치하는데 작업의 효율성을 높일수 있는 모델을 연구하였다. 현재 증강현실을 적용한 기존 시스템에서는 가구의 이미지를 출력할 때기업 제품의 규모와 성격 등에 따라 정보가 제한적으로 제공되는 문제가 있다. 이러한 문제점을 해결하기위해 본 논문에서는 AR 레이블링 알고리즘을 제시하였다. AR 레이블링 알고리즘은 촬영된 이미지에서특징점을 추출하고 실내 위치 정보를 포함한 데이터베이스를 구축하였다. CNN 기법을 활용하여 실내공간에서 가구의 위치 데이터를 검출해 학습시키는 방법을 채택하였다. 학습한 결과를 통해 실내 위치와학습시켜 나타낸 위치와의 오차를 현저히 낮출 수 있다는 것을 확인한다. 또한 가구의 정확한 이미지추출과 함께 가구에 대한 상세한 정보를 받아 사용자가 원하는 가구들을 증강현실을 통해 쉽게 배치할수 있도록 하는 연구를 진행하였다. 연구 결과 모델의 정확도와 손실률이 99%, 0.026으로 나타나 신뢰성을확보하여 본 연구가 유의미함을 알 수 있었다. 본 연구 결과는 AR 레이블의 설계, 구현을 통해 원하는가구들을 실내에 정확히 배치하여 소비자의 만족도와 구매 욕구를 충족시킬 수 있을 것으로 기대된다.
-
-
-
풍력제어기를 위한 Printed Electronics 기반의 유연기판 제조기술에 관한 연구
고정범 (J. B. Ko ),칼리드 라만 (K. Rahman ),살림 칸 (S. Khan ),도양회 (Y. H. Doh ),김동수 (D. S. Kimg ),최경현 (K. H. Choi ) 한국동력기계공학회 2009 한국동력기계공학회 학술대회 논문집 Vol.2009 No.6
In this paper, printed electronics setup and equipment is discussed with respect to wind turbine control system, the laboratory fabricated system consists of a high speed camera with a high precession stage, high voltage source and ink pump system. An embedded software using Labview is designed for the control of the all sub domains system to work as a unit electro-hydrodynamics system (EHD). The high voltage source can provide DC of max 10 Kv and 20 mA current, the high power source which can be connected to the function generator to obtain different types of wave forms. The ink pump can also provide slow flow rate (2ul/hr) depending upon the nozzle size and ink properties, the wind controlling turbine is also attached with the system for more flexible connections to the system which also miniaturize the system.
-
급/배수 펌프의 외부진동과 소음데이터 분석을 통한 오류 예측 연구
고정범(J. B. Ko),유현승(H. S. Yoo),이희환(H. H. Lee),오금윤(G. Y. Oh) 한국기계가공학회 2024 한국기계가공학회 춘추계학술대회 논문집 Vol.2024 No.11
본 논문은 급/배수 펌프에서 외부 진동, 소음을 분석하여 결함과 이상을 사전예방하기 위한 데이터 분석방법을 제안한다. 본 연구에서 전력 스펙트럼 밀도(Power Spectral Density, PSD)를 활용하여 데이터를 시간 영역에서 주파수 영역으로 변환하고, 이를 통해 불규칙한 주파수 성분을 식별한다. 특정 주파수 범위의 변화를 모니터링함으로써 잠재적인 결함을 조기에 감지하고 예지보전(Predictive Maintenance)을 가능하게 하는 것이 본 연구의 목표이다. 제안하는 방법론으로 장비의 작동 주기와 측정 시간을 동기화하고, 진동, 소음을 정기적으로 측정하여 데이터를 수집하고, 이후 실시간 데이터는 사전에 설정된 기준값과 비교하여 편차를 식별하게 된다. 제안된 알고리즘은 펌프장비에서 실시간 모니터링과 사전 유지보수(Preemptive Maintenance)의 가능성을 한다.
-
고정범(Jeong Beom Ko),김형찬(Hyung Chan Kim),양영진(Young Jin Yang),김현범(Hyun Bum Kim),양성욱(Seong Wook Yang),오승호(Seung Ho Oh),도양회(Yang Hoi Doh),최경현(Kyung Hyun Choi) 한국기계가공학회 2016 한국기계가공학회지 Vol.15 No.6
The Biosensor biosensor pattern was developed by via an EHD (electro-hydro-dynamics (EHD) patterning process that was performed under atmospheric pressure at room temperature in a single step. The drop diameter was smaller than nozzle diameter and applied high viscosity conductive ink was applied in the EHD patterning method to provide a clear advantage over the piezo and thermal inkjet printing techniques. The Biosensor’s biosensor’s micro electrode pattern was printed by via a continuous EHD patterning method using 3three- type types of control parameters parameter (input voltage, patterning speed, nozzle pressure). High viscosity (1000 cps) conductive ink with 75 wt% of silver nanoparticles was used for experimentation. The incremental result of impedance of biosensor impedance was measured between the antibody (10 ugμg/ml) to spore (0.1 ng/ml, 10 ng/ml, and 1 ugμg./ml) reaction at frequency 493 MHz frequency.
-
-
고점도 전도성 잉크 패터닝 기술을 이용한 고성능 미세전극 패턴 구현
고정범(Jeong Beom Ko),김형찬(Hyung Chan Kim),당현우(Hyun Woo Dang),양영진(Young Jin Yang),최경현(Kyung Hyun Choi),도양회(Yang Hoi Doh) Korean Society for Precision Engineering 2014 한국정밀공학회지 Vol.31 No.1
EHD (electro-hydro-dynamics) patterning was performed under atmospheric pressure at room temperature in a single step. The drop diameter smaller than nozzle diameter and applied high viscosity conductive ink in EHD patterning method provide a clear advantage over the piezo and thermal inkjet printing techniques. The micro electrode pattern was printed by continuous EHD patterning method using 3-type control parameters (input voltage, patterning speed, nozzle pressure). High viscosity (1000cps) conductive ink with 75wt% of silver nanoparticles was used. EHD cone type nozzle having an internal diameter of 50μm was used for experimentation. EHD jetting mode by input voltage and applied 1st order linear regression in stable jet mode was analyzed. The stable jet was achieved at the amplitude of 1.4~1.8 kV. 10μm micro electrode pattern was created at optimized parameters (input voltage 1.6kV, patterning speed 25mm/sec and nozzle pressure -2.3kPa).
-
임피던스 센서 제작을 위한 잉크젯 기반 IDE 패턴적층공정 최적화 연구
정현윤,고정범 한국기계가공학회 2022 한국기계가공학회지 Vol.21 No.4
At present, it is possible to manufacture electrodes down to several micrometers (~ μm) using inkjet printingtechnology owing to the development of precision ejection heads. Inkjet printing technology is also used in themanufacturing of bio-sensors, electronic sensors, and flexible displays. To reduce the difference between theelectrode design/simulation performance and actual printing pattern performance, it is necessary to analyze andoptimize the processable area of the ink material, which is a fluid. In this study, process optimization wasconducted to manufacture an IDE pattern and fabricate an impedance sensor. A total of 25 IDE patterns wereproduced, with five for each lamination process. Electrode line width and height changes were measured bystacking the designed IDE pattern with a nanoparticle-based conductive ink multilayer. Furthermore, the optimalprocess area for securing a performance close to the design result was analyzed through impedance andcapacitance. It was observed that the increase in the height of stack layer 4 was the lowest at 4.106%, and theincrease in capacitance was measured to be the highest at 44.08%. The proposed stacking process pattern, whichis optimized in terms of uniformity, reproducibility, and performance, can be efficiently applied tobio-applications such as biomaterial sensing with an impedance sensor.
ScienceON연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
