• 인터넷정보학회논문지
• /
• 제20권5호
• /
• pp.105-111
• /
• 2019

인공지능, 빅데이터, 자율주행 등 4차 산업혁명시대를 이끄는 핵심기술은 컴퓨팅 파워의 급속한 발전과 사물인터넷에 기반한 초연결 네트워크를 통해 구현되고 서비스된다. 본 논문에서는 자율주행을 위한 기본적인 기능으로 다양한 환경에서도 정확하게 주행가능한 영역을 인식하여 추출하는 인공지능 딥러닝 모델들을 구현하고, 그 결과를 비교, 분석한다. 주행가능한 영역을 추출하는 딥러닝 모델은 영상 분할 분야에서 성능이 우수하고 자율주행 연구에서 많이 사용하는 Deep Lab V3+와 Mask R-CNN을 활용하였다. 다양한 환경에서의 주행 정보를 위해 여러 가지 날씨 조건과 주 야간 환경에서의 주행 영상 및 이미지를 제공하는 BDD 데이터셋을 학습데이터로 사용하였다. 활용한 모델들의 실험 결과, DeepLab V3+는 48.97%의 IoU를 보였으며, Mask R-CNN은 68.33%의 IoU로 더 우수한 성능을 보였다. 또한, 구현한 모델로 추출된 주행가능 영역을 이미지에 표시하여 육안으로 검사한 결과, Mask R-CNN은 83%, Deep Lab V3+는 69% 정확도로 Mask R-CNN이 Deep Lab V3+ 보다 주행가능한 영역을 추출하는 분야에서는 더 성능이 높은 것으로 확인하였다.

• 한국재료학회:학술대회논문집
• /
• 한국재료학회 1997년도 한국재료학회 추계학술발표회
• /
• pp.102-102
• /
• 1997

• 한국정보통신학회논문지
• /
• 제25권8호
• /
• pp.1039-1045
• /
• 2021

4차 산업 혁명과 IoT 기술의 발전으로 카메라 센서와 영상에 기반한 자동화 시스템이 다양한 분야에서 사용되고 있으며, 영상 및 신호처리의 관심이 높아지고 있다. 본 논문은 임펄스 잡음에 훼손된 영상을 복원하기 위한 디지털 필터 알고리즘을 제안한다. 제안한 알고리즘은 영상에 설정된 로컬 마스크를 기준으로 수직, 수평, 대각선 방향으로 8개의 마스크로 분할하며, 각 분할 마스크의 표준편차를 비교하여 기준값을 구한다. 최종 출력은 공간적 거리에 따른 가중치와 기준값을 사용한 가중치를 로컬 마스크에 적용하여 계산한다. 제안한 알고리즘을 평가하기 위해 기존 알고리즘과 시뮬레이션하였으며, 확대영상과 PSNR 등을 이용하여 성능을 비교하였다.

• 한국공작기계학회논문집
• /
• 제13권1호
• /
• pp.55-62
• /
• 2004

This paper addresses the method for figuring out the hole diameter on the mask containing the information about machining depth. With this mask e micro machining is carried out with a simple 2D movement of the mask. Based on e suggested method excimer laser ablation processes are modeled and determination of the optimal laser ablation conditions such as hole diameter, step size, mask movement velocity, etc. is completed. The excimer laser ablation simulation for creating 3D micro lens is carried out by employing determined ablation conditions to prove verification of the method. The results from simulation illustrated the average error of 140nm and e relative error of 2％.

• Journal of Korean Vacuum Science & Technology
• /
• 제1권1호
• /
• pp.1-12
• /
• 1997

A new three-dimensional (3D) Monte Carlo ion implantation simulator, TRICSI, has been developed to investigate 3D mask effects in the typical mask structure for ion implantation into crystalline silicon. We present the mask corner and mask size effects of implanted boron range profiles, and also show the calculated damage distributions by applying the modified Kinchin-Pease equation in the single-crystal silicon target. The simulator calculates accurately and efficiently the implanted-boron range profiles under the relatively large implanted area, using a newly developed search algorithm for the collision partner in the single-crystal silicon. All of the typical implant parameters such as dose, tilt and rotation angles, in addition to energy can be used for the 3D simulation of ion implantation.

• 패션비즈니스
• /
• 제8권2호
• /
• pp.154-167
• /
• 2004

The purpose of this study was to develop fashion designs using masks on the basis of plasticity of masks. This study was conducted both theoretically and empirically. In a theoretical study, mask-related research and fashion-related literature were examined. In an empirical study, masks used in collections since the 1990's were analyzed through fashion magazines and fashion web sites. Based on such theoretical researches, masks used in modern fashion collections were divided into accessories and clothing to analyze and three fashion designs were developed on the basis of results described above. This study intended to express a romantic look with primitive mood that added formative elements of a mask to the design concept of "Romantic-Primitive". First, forms of masks were simplified and deconstructed and then some methods such as textile printing, leather handicraft, or applique were expressed.

• 한국정밀공학회지
• /
• 제23권8호
• /
• pp.39-46
• /
• 2006

Nano-scale fabrication of silicon substrate based on the use of atomic force microscopy (AFM) was demonstrated. A specially designed cantilever with diamond tip, allowing the formation of damaged layer on silicon substrate by a simple scratching process, has been applied instead of conventional silicon cantilever for scanning. A thin mask layer forms in the substrate at the diamond tip-sample junction along scanning path of the tip. The mask layer withstands against wet chemical etching in aqueous KOH solution. Diamond tip acts as a patterning tool like mask film for lithography process. Hence these sequential processes, called tribo-nanolithography, TNL, can fabricate 2D or 3D micro structures in nanometer range. This study demonstrates the novel fabrication processes of the micro cantilever and diamond tip as a tool for TNL using micro-patterning, wet chemical etching and CVD. The developed TNL tools show outstanding machinability against single crystal silicon wafer. Hence, they are expected to have a possibility for industrial applications as a micro-to-nano machining tool.

• 한국멀티미디어학회논문지
• /
• 제24권8호
• /
• pp.1149-1160
• /
• 2021

Lack of sleep time increases risks of fatigue, hypomnesis, decreased emotional stability, indigestion, and dementia. The risks can be reduced by providing eyelid-warming, inducing sleep and improving sleep quality. However, effective warming temperature to an person varies depending on physical condition and the individual. The various types of frequencies can be identified in brain wave from a person and amount of frequencies is also changed continuously before and after sleep. Therefore we can identify the user's sleep stage with brain wave, namely EEG. Effective sleep induction is possible if warming temperature to a person is controlled based on EEG. In this paper, we propose customized warming control techniques based on EEG for a efficient and effective sleep induction. As an experiment, sleep induction effects of standard sleep mask and customized temperature control techniques sleep mask are compared. EEG data and warming temperature were measured in 100 experiments. At customized warming control techniques, experiments showed that the ratio of alpha and theta waves increased by 3.21%p and the time to sleep decreased by 85 seconds. It will contribute to effective sleep induction and performance verification methods in customized sleep mask systems.

• 한국산업보건학회지
• /
• 제32권2호
• /
• pp.111-115
• /
• 2022

Objectives: The purpose of this study is to verify whether droplet-induced propagation, the main route of infectious diseases such as COVID-19, can occur in semiconductor FAB (Fabrication), based on research results on general droplet propagation. Methods: Through data surveys droplet propagation was modeled through simulation and experimental case analysis according to general (without mask) and mask-wearing conditions, and the risk of droplet propagation was inferred by reflecting semiconductor FAB operation conditions (air current, air conditioning system, humidity, filter conditions). Results: Based on the results investigated to predict the possibility of spreading infectious diseases in semiconductor FAB, the total amount of droplet propagation (concentration), propagation distance, and virus life in FAB were inferred by reflecting the management parameter of semiconductor FAB. Conclusions: The total amount(concentration) of droplet propagation in the semiconductor fab is most affected by the presence or absence of wearing a mask and the line air dilution rate has some influence. when worn it spreads within 0.35~1m, and since the humidity is constant the virus can survive in the air for up to 3 hours. as a result the semiconductor fab is judged to be and effective space to block virus propagation due to the special environmental condition of a clean room.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.