• 천문학회보
• /
• 제45권1호
• /
• pp.46.1-46.1
• /
• 2020

DEEP-South (DEep Ecliptic Patrol of the Southern Sky) team will start the 2nd phase of KMTNet observation in Oct 2020. The DEEP-South observation mainly consists of three survey modes: (1) Activity survey (AS) that aims at finding active phenomena of small Solar System bodies. (2) Light curve survey (LS) targets to discover and characterize light variations of asteroids. And (3) Deep drilling survey (DS) focuses on the objects beyond the orbit of Jupiter (Centaurus and trans-Neptunian objects) as well as near Earth asteroids. For asteroid family (AF) studies and target of opportunity (TO) observations for urgent photometric follow-up, targeted mode will also be used. DEEP-South team is awarded 7.0% of the telescope time at each site every year from Oct 2020 to Sep 2023 in the 2nd phase of KMTNet operation which corresponds to about 75 full nights a year for the network. In this presentation, we will introduce our survey strategy and observation plan.

• 센서학회지
• /
• 제30권5호
• /
• pp.290-294
• /
• 2021

Experts have designed popular and successful model architectures, which, however, were not the optimal option for different scenarios. Despite the remarkable performances achieved by deep neural networks, manually designed networks for classification tasks are the backbone of object detection. One major challenge is the ImageNet pre-training of the search space representation; moreover, the searched network incurs huge computational cost. Therefore, to overcome the obstacle of the pre-training process, we introduce a network adaptation technique using a pre-trained backbone model tested on ImageNet. The adaptation method can efficiently adapt the manually designed network on ImageNet to the new object-detection task. Neural architecture search (NAS) is adopted to adapt the architecture of the network. The adaptation is conducted on the MobileNetV2 network. The proposed NAS is tested using SSDLite detector. The results demonstrate increased performance compared to existing network architecture in terms of search cost, total number of adder arithmetics (Madds), and mean Average Precision(mAP). The total computational cost of the proposed NAS is much less than that of the State Of The Art (SOTA) NAS method.

• 천문학회보
• /
• 제41권1호
• /
• pp.54.2-54.2
• /
• 2016

Korea Microlensing Telescope Network (KMTNet) is the first optical survey system of its kind in a way that three KMTNet observatories are longitudinally well-separated, and thus have the benefit of 24-hour continuous monitoring of the southern sky. The wide-field and round-the-clock operation capabilities of this network facility are ideal for survey and the physical characterization of small Solar System bodies. We obtain their orbits, absolute magnitudes (H), three dimensional shape models, spin periods and spin states, activity levels based on the time-series broadband photometry. Their approximate surface mineralogy is also identified using colors and band slopes. The automated observation scheduler, the data pipeline, the dedicated computing facility, related research activity and the team members are collectively called 'DEEP-South' (DEep Ecliptic Patrol of Southern sky). DEEP-South observation is being made during the off-season for exoplanet search, yet part of the telescope time is shared in the period between when the Galactic bulge rises early in the morning and sets early in the evening. We present here the observation mode, strategy, software, test runs, early results, and the future plan of DEEP-South.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.5159-5178
• /
• 2018

Network Intrusion detection is a rapidly growing field of information security due to its importance for modern IT infrastructure. Many supervised and unsupervised learning techniques have been devised by researchers from discipline of machine learning and data mining to achieve reliable detection of anomalies. In this paper, a deep convolutional neural network (DCNN) based intrusion detection system (IDS) is proposed, implemented and analyzed. Deep CNN core of proposed IDS is fine-tuned using Randomized search over configuration space. Proposed system is trained and tested on NSLKDD training and testing datasets using GPU. Performance comparisons of proposed DCNN model are provided with other classifiers using well-known metrics including Receiver operating characteristics (RoC) curve, Area under RoC curve (AuC), accuracy, precision-recall curve and mean average precision (mAP). The experimental results of proposed DCNN based IDS shows promising results for real world application in anomaly detection systems.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.626-637
• /
• 2018

Human exchanges information not only through words, but also through body gesture or hand gesture. And they can be used to build effective interfaces in mobile, virtual reality, and augmented reality. The past 2D gesture recognition research had information loss caused by projecting 3D information in 2D. Since the recognition of the gesture in 3D is higher than 2D space in terms of recognition range, the complexity of gesture recognition increases. In this paper, we proposed a real-time gesture recognition deep learning model and application in 3D space using deep learning technique. First, in order to recognize the gesture in the 3D space, the data collection is performed using the unity game engine to construct and acquire data. Second, input vector normalization for learning 3D gesture recognition model is processed based on deep learning. Thirdly, the SELU(Scaled Exponential Linear Unit) function is applied to the neural network's active function for faster learning and better recognition performance. The proposed system is expected to be applicable to various fields such as rehabilitation cares, game applications, and virtual reality.

• 반도체디스플레이기술학회지
• /
• 제22권1호
• /
• pp.129-133
• /
• 2023

Image compression is a fundamental technique in the field of digital image processing, which will help to decrease the storage space and to transmit the files efficiently. Recently many deep learning techniques have been proposed to promise results on image compression field. Since many image compression techniques have artifact problems, this paper has compared two deep learning approaches to verify their performance experimentally to solve the problems. One of the approaches is a deep autoencoder technique, and another is a deep convolutional neural network (CNN). For those results in the performance of peak signal-to-noise and root mean square error, this paper shows that deep autoencoder method has more advantages than deep CNN approach.

• 한국항공우주학회지
• /
• 제45권9호
• /
• pp.746-756
• /
• 2017

본 연구에서는 한국형 달 탐사 시험용 궤도선을 위한 심우주 추적망 (Deep Space Network)의 관측값을 구현하는 알고리즘을 개발하였다. 이 알고리즘을 활용하여 탐사선의 신호 지연 효과를 관측 모델을 통해 보정해서 계산된 관측값을 생성할 수 있다. 계산된 관측값으로 거리, 도플러, 방위각, 고도각을 생성하였다. 기하학적 데이터 값을 General Mission Analysis Tool (GMAT)의 시나리오를 통해 구하였으며, 계산된 관측값을 구하기 위해서 시간 지연 효과, 대류층 지연 효과, 대류권 내 하전 입자에 의한 지연 효과, 대류권 밖 하전 입자에 의한 지연 효과, 대류층에 의한 굴절 효과, 안테나에 의한 지연 효과를 고려하였다. 관측 모델들을 통해 구한 계산된 관측값은 시험용 궤도선의 정밀 궤도 결정을 위해 사용된다. 본 논문에서 개발한 데이터 시뮬레이션 모듈은 미 항공우주국의 궤도 결정 툴 박스 (Orbit Determination ToolBoX, ODTBX)를 이용해 검증되었다.

• 데이타베이스연구회지:데이타베이스연구
• /
• 제34권3호
• /
• pp.3-13
• /
• 2018

자동문서분류(Text Classification)는 주어진 텍스트 문서를 이에 적합한 카테고리로 분류하는 텍스트 마이닝 기술 중의 하나로서 스팸메일 탐지, 뉴스분류, 자동응답, 감성분석, 쳇봇 등 다양한 분야에 활용되고 있다. 일반적으로 자동문서분류 시스템은 기계학습 알고리즘을 활용하며, 이 중에서 텍스트 데이터에 적합한 알고리즘인 나이브베이즈(Naive Bayes), 지지벡터머신(Support Vector Machine) 등이 합리적 수준의 성능을 보이는 것으로 알려져 있다. 최근 딥러닝 기술의 발전에 따라 자동문서분류 시스템의 성능을 개선하기 위해 순환신경망(Recurrent Neural Network)과 콘볼루션 신경망(Convolutional Neural Network)을 적용하는 연구가 소개되고 있다. 그러나 이러한 최신 기법들이 아직 완벽한 수준의 문서분류에는 미치지 못하고 있다. 본 논문은 그 이유가 텍스트 데이터가 단어 차원 중심의 벡터로 표현되어 텍스트에 내재한 의미 정보를 훼손하는데 주목하고, 선행 연구에서 그 효능이 검증된 시멘틱 텐서공간모델에 기반하여 심층 신경망 아키텍처를 제안하고 이를 활용한 문서분류기의 성능이 대폭 상승함을 보인다.

• 천문학회보
• /
• 제44권2호
• /
• pp.78.1-78.1
• /
• 2019

There are a huge number of faint objects that have not been observed due to the lack of large and deep surveys. In this study, we demonstrate that a deep learning approach can produce a better quality deep image from a single pass imaging so that could be an alternative of conventional image stacking technique or the expensive large and deep surveys. Using data from the Sloan Digital Sky Survey (SDSS) stripe 82 which provide repeatedly scanned imaging data, a training data set is constructed: g-, r-, and i-band images of single pass data as an input and r-band co-added image as a target. Out of 151 SDSS fields that have been repeatedly scanned 34 times, 120 fields were used for training and 31 fields for validation. The size of a frame selected for the training is 1k by 1k pixel scale. To avoid possible problems caused by the small number of training sets, frames are randomly selected within that field each iteration of training. Every 5000 iterations of training, the performance were evaluated with RMSE, peak signal-to-noise ratio which is given on logarithmic scale, structural symmetry index (SSIM) and difference in SSIM. We continued the training until a GAN model with the best performance is found. We apply the best GAN-model to NGC0941 located in SDSS stripe 82. By comparing the radial surface brightness and photometry error of images, we found the possibility that this technique could generate a deep image with statistics close to the stacked image from a single-pass image.

• 천문학회지
• /
• 제49권5호
• /
• pp.225-232
• /
• 2016

We present an optical imaging survey of AKARI Deep Field South (ADF-S) using the Korea Microlensing Telescope Network (KMTNet), to find optical counterparts of dusty star-forming galaxies. The ADF-S is a deep far-infrared imaging survey region with AKARI covering around 12 deg², where the deep optical imaging data are not yet available. By utilizing the wide-field capability of the KMTNet telescopes (~4 deg²), we obtain optical images in B, R and I bands for three regions. The target depth of images in B, R and I bands is ~24 mag (AB) at 5σ, which enables us to detect most dusty star-forming galaxies discovered by AKARI in the ADF-S. Those optical datasets will be helpful to constrain optical spectral energy distributions as well as to identify rare types of dusty star-forming galaxies such as dust-obscured galaxy, sub-millimeter galaxy at high redshift.