• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1166-1174
• /
• 2017

In general, the detection of the vehicle license plate is a previous step of license plate recognition and has been actively studied for several decades. In this paper, we propose an algorithm to detect a license plate area of a moving vehicle from a video captured by a fixed camera installed on the road using the Convolution Neural Network (CNN) technology. First, license plate images and non-license plate images are applied to a previously learned CNN model (AlexNet) to extract and classify features. Then, after detecting the moving vehicle in the video, CNN detects the license plate area by comparing the features of the license plate region with the features of the license plate area. Experimental result shows relatively good performance in various environments such as incomplete lighting, noise due to rain, and low resolution. In addition, to protect personal information this proposed system can also be used independently to detect the license plate area and hide that area to secure the public's personal information.

• 로봇학회논문지
• /
• 제15권4호
• /
• pp.404-412
• /
• 2020

Typically everyday human life tasks involve at least two people moving objects such as tables and beds, and the balancing of such object changes based on one person's action. However, many studies in previous work performed their tasks solely on robots without factoring human cooperation. Therefore, in this paper, we propose cooperative robot for table balancing using Q-learning that enables cooperative work between human and robot. The human's action is recognized in order to balance the table by the proposed robot whose camera takes the image of the table's state, and it performs the table-balancing action according to the recognized human action without high performance equipment. The classification of human action uses a deep learning technology, specifically AlexNet, and has an accuracy of 96.9% over 10-fold cross-validation. The experiment of Q-learning was carried out over 2,000 episodes with 200 trials. The overall results of the proposed Q-learning show that the Q function stably converged at this number of episodes. This stable convergence determined Q-learning policies for the robot actions. Video of the robotic cooperation with human over the table balancing task using the proposed Q-Learning can be found at http://ibot.knu.ac.kr/videocooperation.html.

• Bulletin of the Korean Chemical Society
• /
• 제35권3호
• /
• pp.783-792
• /
• 2014

The binding interaction between a hemolytic peptide ${\delta}$-lysin and a zwitterionic lipid bilayer POPC was investigated through a series of molecular dynamics (MD) simulations. ${\delta}$-Lysin is a 26-residue, amphipathic, ${\alpha}$-helical peptide toxin secreted by Staphylococcus aureus. Unlike typical antimicrobial peptides, ${\delta}$-lysin has no net charge and it is often found in aggregated forms in solution even at low concentration. Our study showed that only the monomer, not dimer, inserts into the bilayer interior. The monomer is preferentially attracted toward the membrane with its hydrophilic side facing the bilayer surface. However, peptide insertion requires the opposite orientation where the hydrophobic side of peptide points toward the membrane interior. Such orientation allows the charged residues, Lys and Asp, to have stable salt bridges with the lipid head-group while the hydrophobic residues are buried deeper in the hydrophobic lipid interior. Our simulations suggest that breaking these salt bridges is the key step for the monomer to be fully inserted into the center of lipid bilayer and, possibly, to translocate across the membrane.

• 전자통신동향분석
• /
• 제33권5호
• /
• pp.121-134
• /
• 2018

The Von Neumann based architecture of the modern computer has dominated the computing industry for the past 50 years, sparking the digital revolution and propelling us into today's information age. Recent research focus and market trends have shown significant effort toward the advancement and application of artificial intelligence technologies. Although artificial intelligence has been studied for decades since the Turing machine was first introduced, the field has recently emerged into the spotlight thanks to remarkable milestones such as AlexNet-CNN and Alpha-Go, whose neural-network based deep learning methods have achieved a ground-breaking performance superior to existing recognition, classification, and decision algorithms. Unprecedented results in a wide variety of applications (drones, autonomous driving, robots, stock markets, computer vision, voice, and so on) have signaled the beginning of a golden age for artificial intelligence after 40 years of relative dormancy. Algorithmic research continues to progress at a breath-taking pace as evidenced by the rate of new neural networks being announced. However, traditional Von Neumann based architectures have proven to be inadequate in terms of computation power, and inherently inefficient in their processing of vastly parallel computations, which is a characteristic of deep neural networks. Consequently, global conglomerates such as Intel, Huawei, and Google, as well as large domestic corporations and fabless companies are developing dedicated semiconductor chips customized for artificial intelligence computations. The AI Processor Research Laboratory at ETRI is focusing on the research and development of super low-power AI processor chips. In this article, we present the current trends in computation platform, parallel processing, AI processor, and super-threaded AI processor research being conducted at ETRI.

• Nuclear Engineering and Technology
• /
• 제54권3호
• /
• pp.877-887
• /
• 2022

A new reactor concept is described that directly couples a supercritical CO₂ (sCO₂) power cycle with a CO₂-cooled, heavy water moderated pressure tube core. This configuration attains the simplification and economic potential of past direct-cycle sCO₂ concepts, while also providing safety and power density benefits by using the moderator as a heat sink for decay heat removal. A 200 MWe design is described that heavily leverages existing commercial nuclear technologies, including reactor and moderator systems from Canadian CANDU reactors and fuels and materials from UK Advanced Gas-cooled Reactors (AGRs). Descriptions are provided of the power cycle, nuclear island systems, reactor core, and safety systems, and the results of safety analyses are shown illustrating the ability of the design to withstand large-break loss of coolant accidents. The resulting design attains high efficiency while employing considerably fewer systems than current light water reactors and advanced reactor technologies, illustrating its economic promise. Prospects for the design are discussed, including the ability to demonstrate its technologies in a small (~20 MWe) initial system, and avenues for further improvement of the design using advanced technologies.

• 한국기계가공학회지
• /
• 제21권6호
• /
• pp.8-14
• /
• 2022

In this study reports experiments were conducted to determine the quality of weld beads of different materials, Al and Cu. Among the lasers used to make battery cells for electric vehicles, non-destructive testing was performed using deep learning to determine the quality of beads welded with the ARM laser. Deep learning was performed using AlexNet algorithm with a convolutional neural network structure. The results of quality identification were divided into good and bad, and the result value was derived that all the results were in agreement with 94% or more. Overall, the best welding quality was obtained in the experiment for the fixed ring beam output/variable center beam output, in the case of the fixed beam (ring beam) 500W and variable beam (center beam) 1,050W; weld bead failure was seldom observed. The tensile force test to confirm the reliability of welding reported an average tensile force of 2.5kgf/mm or more in all sections.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권1호
• /
• pp.85-96
• /
• 2023

The number of traffic accidents caused by wet or icy road surface conditions is on the rise every year. Car crashes in such bad road conditions can increase fatalities and serious injuries. Historical data (from the year 2016 to the year 2020) on weather-related traffic accidents show that the fatality rates are fairly high in Korea. This requires accurate prediction and identification of hazardous road conditions. In this study, a forecasting model is developed to predict the chances of traffic accidents that can occur on roads affected by weather and road surface conditions. Multiple deep learning algorithms taking into account AlexNet and 2D-CNN are employed. Data on orthophoto images, automatic weather systems, automated synoptic observing systems, and road surfaces are used for training and testing purposes. The orthophotos images are pre-processed before using them as input data for the modeling process. The procedure involves image segmentation techniques as well as the Z-Curve index. Results indicate that there is an acceptable performance of prediction such as 65% for dry, 46% for moist, and 33% for wet road conditions. The overall accuracy of the model is 53%. The findings of the study may contribute to developing comprehensive measures for enhancing road safety.

• 인터넷정보학회논문지
• /
• 제21권4호
• /
• pp.17-23
• /
• 2020

인간의 특성과 관련된 측정 항목을 나타내는 생체정보는 도난이나 분실의 염려가 없으므로 높은 신뢰성을 가진 보안 기술로서 큰 주목을 받고 있다. 이러한 생체정보 중 지문은 본인 인증, 신원 파악 등의 분야에 주로 사용된다. 신원을 파악할 때 지문 이미지에 인증을 수행하기 어려운 상처, 주름, 습기 등의 문제가 있을 경우, 지문 전문가가 전처리단계를 통해 직접 지문에 어떠한 문제가 있는지 파악하고 문제에 맞는 영상처리 알고리즘을 적용해 문제를 해결한다. 이때 지문에 상처와 주름이 있는 지문 영상을 판별해주는 인공지능 소프트웨어를 구현하면 손쉽게 상처나 주름의 여부를 확인할 수 있고, 알맞은 알고리즘을 선정해 쉽게 지문 이미지를 개선할 수 있다. 본 연구에서는 이러한 인공지능 소프트웨어의 개발을 위해 캄보디아 왕립대학교의 학생 1,010명, Sokoto 오픈 데이터셋 600명, 국내 학생 98명의 모든 손가락 지문을 취득해 총 17,080개의 지문 데이터베이스를 구축했다. 구축한 데이터베이스에서 상처나 주름이 있는 경우를 판별하기 위해 기준을 확립하고 전문가의 검증을 거쳐 데이터 어노테이션을 진행했다. 트레이닝 데이터셋과 테스트 데이터셋은 캄보디아의 데이터, Sokoto 데이터로 구성하였으며 비율을 8:2로 설정했다. 그리고 국내 학생 98명의 데이터를 검증 데이터 셋으로 설정했다, 구성된 데이터셋을 사용해 Classic CNN, AlexNet, VGG-16, Resnet50, Yolo v3 등의 다섯 가지 CNN 기반 아키텍처를 구현해 학습을 진행했으며 지문의 상처와 주름 판독에서 가장 좋은 성능을 보이는 모델을 찾는 연구를 수행했다. 다섯가지 아키텍처 중 지문 영상에서 상처와 주름 여부를 가장 잘 판별할 수 있는 아키텍처는 ResNet50으로 검증 결과 81.51%로 가장 좋은 성능을 보였다.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.455-462
• /
• 2020

Noise which is unwanted sound is a serious pollutant that can affect human health, as well as the working and living environment if exposed to humans. However, current noise management on the construction project is generally conducted after the noise exceeds the regulation standard, which increases the conflicts with inhabitants near the construction site and threats to the safety and productivity of construction workers. To overcome the limitations of the current noise management methods, the activities of construction equipment which is the main source of construction noise need to be managed throughout the construction period in real-time. Therefore, this paper proposed a framework for automatically detecting noise sources in construction sites in real-time based on convolutional neural networks (CNNs) according to the following four steps: (i) Step 1: Definition of the noise sources; (ii) Step 2: Data preparation; (iii) Step 3: Noise source classification using the audio CNN; and (iv) Step 4: Noise source detection using the visual CNN. The short-time Fourier transform (STFT) and temporal image processing are used to contain temporal features of the audio and visual data. In addition, the AlexNet and You Only Look Once v3 (YOLOv3) algorithms have been adopted to classify and detect the noise sources in real-time. As a result, the proposed framework is expected to immediately find construction activities as current noise sources on the video of the construction site. The proposed framework could be helpful for environmental construction managers to efficiently identify and control the noise by automatically detecting the noise sources among many activities carried out by various types of construction equipment. Thereby, not only conflicts between inhabitants and construction companies caused by construction noise can be prevented, but also the noise-related health risks and productivity degradation for construction workers and inhabitants near the construction site can be minimized.

• 수면정신생리
• /
• 제4권2호
• /
• pp.164-171
• /
• 1997

Introduction : Periodic limb movement disorder (PLMD) is shown to common in patients with OSA and may become evident or worsened when treated with nasal continuous positive airway pressure (CPAP). Whether this is due to im proved sleep continuity. adverse nocturnal body positioning, uncovered by CPAP, or due to the CPAP stimulus is still debat-ed. We hypothesized that the increase in PLM activity following CPAP is associated with more supine-sleeping tendencies when being treated with CPAP. In the present work, we compared differences in the PLMD index (PLMI) and sleeping position of patients with sleep disordered breathing before and after CPAP treatment. Method : We studied 16 patients (mean age 46 yr, 9M, 7F) with OSA (11 patients) or UARS (5 patients) who either had PLMD on initial polysomnogram (baseline PSG) or on nasal CPAP trial (CPAP PSG). All periodic leg movements were scored on anterior tibialis EMG during sleep according to standard criteria (net duration; 0.5-5.0 seconds, intervals; 4-90 seconds. 4 consecutive movements). Paired t-tests compared PLMD index (PLMI), PLMD-related arousal index (PLMD-ArI), respiratory disturbance index (RDI), and supine sleeping position spent with baseline PSG and CPAP PSG. Results : Ten patients (63%) on baseline PSG and fifteen patients (94%) on CPAP PSG had documented PLMD ($PLMI{\ge}5$) respectively with significant increase on CPAP PSG(p<0.05). Ten patients showed the emergence (6/10 patients) or substantial worsening (4/10 patients) of PLMD during CPAP trial. Mean CPAP pressure was $7.6{\pm}1.8\;cmH_2O$. PLMI tended to increase from baseline PSG to CPAP PSG, and significantly increase when excluding 2 outlier (baseline PSG, $19.0{\pm}25.8/hr$ vs CPAP PSG, $29.9{\pm}12.5/hr$, p<0.1). PLMD-ArI showed no significant change, but a significant decrease was detected when excluding 2 outlier (p<0.1). There was no significant sleeping positional difference (supine vs non-supine) on baseline PSG, but significantly more supine position (supine vs non-supine, p<0.05) on CPAP PSG. There was no significant difference in PLMI during supine-sleeping and nonsupine-sleeping position on both of baseline PSG and CPAP PSG. There was also no significant difference in PLMI during supine-sleeping position between baseline PSG and CPAP PSG. With nasal CPAP, there was a highly significant reduction in the RDI (baseline PSG, $14.1{\pm}21.3/hr$ vs CPAP PSG, $2.7{\pm}3.9/hr$, p<0.05). Conclusion : This preliminary data confirms previous findings that CPAP is a very effective treatment for OSA, and that PLMD is developed or worsened with treatment by CPAP. This data also indicates that supine-sleeping position is more common when being treated with CPAP. However, there was no clear evidence that supine position is the causal factor of increased PLMD with CPAP. It is, however, suggested that the relative movement limitation induced by CPAP treatment could be a contributory factor of PLMD.