• 한국우주과학회:학술대회논문집(한국우주과학회보)
• /
• 한국우주과학회 2010년도 한국우주과학회보 제19권1호
• /
• pp.28.4-29
• /
• 2010

이 연구는 심우주 추적망(Deep Space Network) 측정 시스템의 구현을 위한 한국형 심우주 항법 예비 소프트웨어(Korean Deep Space Orbit Determination Program version 1; K-DSODP ver.1)의 개발을 목표로 한다. 연구의 주 내용은 심우주 항법을 위한 기초 기술 연구로 지구로부터 달까지 진행하는 탐사선의 궤적 추정에 대한 것이며, 연구의 시작에 앞서 사용될 관측 데이터를 얻기 위해 한국형 심우주 항법 관측데이터 생성 소프트웨어(Korean Deep Space Observation Data Generation Program version 1; K-DSODGP ver.1)를 개발하여 사용하였다. 임의의 잡음이 추가된 가상의 관측 데이터를 생성한 후, 이 관측 데이터를 실제 궤도로 상정하여 기하학적인 관측 모델을 수립하였고, 일정한 시간 간격동안 모은 임의의 관측 데이터를 가지고 궤도 결정을 수행하여 추정된 궤도를 전파하였다. 궤도 결정 알고리즘을 구성하기 위해 기본적인 좌표계, 탐사선에 미치는 지구의 중력에 대한 동역학 모델, 천체력과 탐사선의 동역학 모델로 구성된 관측 모델들을 유도하였으며, 탐사선의 위치와 속도를 추정하는 과정에서 가중치 최소 자승법을 적용하여 추정 궤도와 실제 궤도의 최소화를 유도하였다. 이러한 일련의 과정을 통해 요구한 시각의 탐사선의 위치와 속도를 결정하는 궤도결정 시스템을 구현하였고, 궤도 결정 시스템의 성능을 평가하기 위해 전파된 궤도와 실제 궤도의 차이를 분석하였다. 결과적으로 300초마다 관측데이터를 받을 경우, 2일 이상의 궤도결정 시간간격을 상정했을 때 평균 오차는 각각 약 0.26km RMS(range), 6.84km/s RMS(range-rate) 이내의 결과를 얻었고, 600초마다 관측데이터를 받을 경우, 평균 오차는 각각 약 0.30km RMS (range), 6.35km/s RMS(range-rate) 이내의 안정적인 결과를 얻었다. 이 연구의 결과를 통하여 추후 심화된 심우주 항법 소프트웨어 개발을 위한 기반이 마련될 것이다.

• 한국항공우주학회지
• /
• 제36권4호
• /
• pp.357-367
• /
• 2008

향후 우리나라의 달탐사 임무에 대비하여 순간 추력을 이용한 한국형 달탐사 예비 임무 설계 소프트웨어를 개발하였다. 달 탐사 임무 수행을 위한 지구 출발 단계, 달 천이 단계, 달 도착 및 임무 수행 궤도 단계를 포함한 임무 설계가 이루어 졌다. 이 소프트웨어를 이용하면 순간 추력을 사용한 최적의 달탐사 비행궤적을 설계할 수 있다. 이를 바탕으로 우리나라의 우주 발사체인 KSLV-II를 사용할 때의 발사 가능한 달 탐사선의 최대 질량을 산출하여 보았다. 아울러 심우주 추적망을 이용하여 탐사선의 추적 가능 여부에 대한 해석이 이루어 졌으며 탐사선과의 통신, 태양 전지판의 지향점 해석 그리고 식기간의 분석을 위한 지구-달-탐사선-태양 간의 기하학적 위치에 대한 해석도 함께 이루어졌다.

• Journal of Astronomy and Space Sciences
• /
• 제30권4호
• /
• pp.255-267
• /
• 2013

In this research, the ground contact opportunity for the fictitious low lunar orbiter is analyzed to prepare for a future Korean lunar orbiter mission. The ground contact opportunity is basically derived from geometrical relations between the typical ground stations at the Earth, the relative positions of the Earth and Moon, and finally, the lunar orbiter itself. Both the cut-off angle and the orbiter's Line of Sight (LOS) conditions (weather orbiter is located at near or far side of the Moon seen from the Earth) are considered to determine the ground contact opportunities. Four KOMPSAT Ground Stations (KGSs) are assumed to be Korea's future Near Earth Networks (NENs) to support lunar missions, and world-wide separated Deep Space Networks (DSNs) are also included during the contact availability analysis. As a result, it is concluded that about 138 times of contact will be made between the orbiter and the Daejeon station during 27.3 days of prediction time span. If these contact times are converted into contact duration, the duration is found to be about 8.55 days, about 31.31% of 27.3 days. It is discovered that selected four KGSs cannot provide continuous tracking of the lunar orbiter, meaning that international collaboration is necessary to track Korea's future lunar orbiter effectively. Possible combinations of world-wide separated DSNs are also suggested to compensate for the lack of contact availability with only four KGSs, as with primary and backup station concepts. The provided algorithm can be easily modified to support any type of orbit around the Moon, and therefore, the presented results could aid further progress in the design field of Korea's lunar orbiter missions.

• 천문학회보
• /
• 제44권1호
• /
• pp.52.2-52.2
• /
• 2019

Global map of solar surface magnetic field, such as the synoptic map or daily synchronic frame, does not tell us real-time information about the far side of the Sun. A deep-learning technique based on Conditional Generative Adversarial Network (cGAN) is used to generate farside magnetograms from EUVI $304{\AA}$ of STEREO spacecrafts by training SDO spacecraft's data pairs of HMI and AIA $304{\AA}$. Farside(or backside) data of daily synchronic frames are replaced by the Ai-generated magnetograms. The new type of data is used to calculate the Potential Field Source Surface (PFSS) model. We compare the results of the global field with observations as well as those of the conventional method. We will discuss advantage and disadvantage of the new method and future works.

• 한국태양에너지학회 논문집
• /
• 제28권6호
• /
• pp.58-63
• /
• 2008

It is essential to investigate the structure and the main characteristic of Home USN (Ubiquitous Sensor Network) technologies in built ubiquitous environment while designing bio-sensors. For this study, Thermistor elements and Thermopile black body have been selected to implement ubiquitous technologies for bio-sensors and wireless network such as WiBro has been used to transfer sensing data to the BSN (Bio-Sensor Network) gateway. It is certain that efficiency of ubiquitous space design is improved if main components of each specific sensor network are analyzed precisely in digital way and corresponding communication modules are prepared accordingly. Ubiquitous technology, in conclusion, has to be applied not only with systematical mechanism or electronic setting but in human-centered atmosphere as well, keeping with deep consideration for bio-housing service factors in eco-friendly surrounding.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.365-380
• /
• 2022

The target detection algorithm based on supervised learning is the current mainstream algorithm for target detection. A high-quality dataset is the prerequisite for the target detection algorithm to obtain good detection performance. The larger the number and quality of the dataset, the stronger the generalization ability of the model, that is, the dataset determines the upper limit of the model learning. The convolutional neural network optimizes the network parameters in a strong supervision method. The error is calculated by comparing the predicted frame with the manually labeled real frame, and then the error is passed into the network for continuous optimization. Strongly supervised learning mainly relies on a large number of images as models for continuous learning, so the number and quality of images directly affect the results of learning. This paper proposes a dataset STAR-24K (meaning a dataset for Space TArget Recognition with more than 24,000 images) for detecting common targets in space. Since there is currently no publicly available dataset for space target detection, we extracted some pictures from a series of channels such as pictures and videos released by the official websites of NASA (National Aeronautics and Space Administration) and ESA (The European Space Agency) and expanded them to 24,451 pictures. We evaluate popular object detection algorithms to build a benchmark. Our STAR-24K dataset is publicly available at https://github.com/Zzz-zcy/STAR-24K.

• 천문학회보
• /
• 제42권2호
• /
• pp.60.2-61
• /
• 2017

A Convolutional Neural Network(CNN) is one of the well-known deep-learning methods in image processing and computer vision area. In this study, we apply CNN to two kinds of flare forecasting models: flare classification and occurrence. For this, we consider several pre-trained models (e.g., AlexNet, GoogLeNet, and ResNet) and customize them by changing several options such as the number of layers, activation function, and optimizer. Our inputs are the same number of SOHO)/MDI images for each flare class (None, C, M and X) at 00:00 UT from Jan 1996 to Dec 2010 (total 1600 images). Outputs are the results of daily flare forecasting for flare class and occurrence. We build, train, and test the models on TensorFlow, which is well-known machine learning software library developed by Google. Our major results from this study are as follows. First, most of the models have accuracies more than 0.7. Second, ResNet developed by Microsoft has the best accuracies : 0.77 for flare classification and 0.83 for flare occurrence. Third, the accuracies of these models vary greatly with changing parameters. We discuss several possibilities to improve the models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1759-1772
• /
• 2023

Chinese named entity recognition (NER) is a challenging work that seeks to find, recognize and classify various types of information elements in unstructured text. Due to the Chinese text has no natural boundary like the spaces in the English text, Chinese named entity identification is much more difficult. At present, most deep learning based NER models are developed using a bidirectional long short-term memory network (BiLSTM), yet the performance still has some space to improve. To further improve their performance in Chinese NER tasks, we propose a new NER model, IDCNN-BiLSTM-Highway, which is a combination of the BiLSTM, the iterated dilated convolutional neural network (IDCNN) and the highway network. In our model, IDCNN is used to achieve multiscale context aggregation from a long sequence of words. Highway network is used to effectively connect different layers of networks, allowing information to pass through network layers smoothly without attenuation. Finally, the global optimum tag result is obtained by introducing conditional random field (CRF). The experimental results show that compared with other popular deep learning-based NER models, our model shows superior performance on two Chinese NER data sets: Resume and Yidu-S4k, The F1-scores are 94.98 and 77.59, respectively.

• Smart Structures and Systems
• /
• 제29권6호
• /
• pp.777-783
• /
• 2022

Even though several deep learning-based methods have been applied in the field of acoustic source localization, the previous works have only been conducted using the two-dimensional representation of the beamforming maps, particularly with the planar array system. While the acoustic sources are more required to be localized in a spherical microphone array system considering that we live and hear in the 3D world, the conventional 2D equirectangular map of the spherical beamforming map is highly vulnerable to the distortion that occurs when the 3D map is projected to the 2D space. In this study, a 3D deep learning approach is proposed to fulfill accurate source localization via distortion-free 3D representation. A target function is first proposed to obtain 3D source distribution maps that can represent multiple sources' positional and strength information. While the proposed target map expands the source localization task into a point-wise prediction task, a PointNet-based deep neural network is developed to precisely estimate the multiple sources' positions and strength information. While the proposed model's localization performance is evaluated, it is shown that the proposed method can achieve improved localization results from both quantitative and qualitative perspectives.

• 한국BIM학회 논문집
• /
• 제13권3호
• /
• pp.12-20
• /
• 2023

Deep learning-based anomaly detection technology is used in various fields such as computer vision, speech recognition, and natural language processing. In particular, this technology is applied in various fields such as monitoring manufacturing equipment abnormalities, detecting financial fraud, detecting network hacking, and detecting anomalies in medical images. However, in the field of construction and architecture, research on deep learning-based data anomaly detection technology is difficult due to the lack of digitization of domain knowledge due to late digital conversion, lack of learning data, and difficulties in collecting and processing field data in real time. This study acquires necessary data through IoT (Internet of Things) from the viewpoint of monitoring for environmental management of architectural spaces, converts them into a database, learns deep learning, and then supports anomaly patterns using AI (Artificial Infelligence) deep learning-based anomaly detection. We propose an implementation process. The results of this study suggest an effective environmental anomaly pattern detection solution architecture for environmental management of architectural spaces, proving its feasibility. The proposed method enables quick response through real-time data processing and analysis collected from IoT. In order to confirm the effectiveness of the proposed method, performance analysis is performed through prototype implementation to derive the results.