• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3984-4005
• /
• 2017

Image recognition has become an increasingly important topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The recognition systems rely on a key component, i.e. the low-level feature or the learned mid-level feature. The recognition performance can be potentially improved if the data distribution information is exploited using a more sophisticated way, which usually a function over hidden variable, model parameter and observed data. These methods are called generative score space. In this paper, we propose a discriminative extension for the existing generative score space methods, which exploits class label when deriving score functions for image recognition task. Specifically, we first extend the regular generative models to class conditional models over both observed variable and class label. Then, we derive the mid-level feature mapping from the extended models. At last, the derived feature mapping is embedded into a discriminative classifier for image recognition. The advantages of our proposed approach are two folds. First, the resulted methods take simple and intuitive forms which are weighted versions of existing methods, benefitting from the Bayesian inference of class label. Second, the probabilistic generative modeling allows us to exploit hidden information and is well adapt to data distribution. To validate the effectiveness of the proposed method, we cooperate our discriminative extension with three generative models for image recognition task. The experimental results validate the effectiveness of our proposed approach.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.6
• /
• pp.620-628
• /
• 2010

Small satellites can be used for various space research and scientific or educational purposes due to advantages in small size, low-cost, and rapid development. Small Satellites have many advantages of application to Responsive Space. Compared to traditional larger satellites, however, Small satellites have many constraints due to limitations in size. Therefore, it is difficult to expect high performance. To approach maximum capability with minimal size, weight, and cost, standard modular platform of Small satellites is necessary. Modularity supports plug-and-play architecture. The result is Small satellites that can be combined quickly and reliably using plug-and-play mechanisms. For communication between modules, standard bus interface is needed. Controller Area Network(CAN) protocol is considered optimum data bus for modular Small satellite. CAN can be applied to data communication with high reliability. Hence, design optimization and simplification can also be expected. For ease of assembly and integration, modular design can be considered. This paper proposes development method for standardized modular Small satellites, and describes design of data interface based on CAN and a method of testing for modularity.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.23-25
• /
• 2021

This paper describes an approach of composing music with multiple AI composers. This approach enriches more the creativity space of artificial intelligence music composition than using only one composer. This paper presents a simple example with 2 different deep learning composers working together for composing one music. For the experiment, the two composers adopt the same deep learning architecture of an LSTM model trained with different data. The output of a composer is a sequence of notes. Each composer alternatively appends its output to the resulting music which is input to both the composers. Experiments compare different music generated by the proposed multiple composer approach with the traditional one composer approach.

• Korean Institute of Interior Design Journal
• /
• v.15 no.4 s.57
• /
• pp.97-105
• /
• 2006

Richard Meier has earned his recognition by developing his unique design approach and keeping consistency in design concept in museum architecture over the years of his practice. The purpose of this study is finding common characteristics of the exhibition space spatial organization based on actual site visit analysis. This study will mainly focus on the museums Richard Meier designed between 1979, which is the year he started, until 1997 which is the year Getty Museum opened. For the purpose of this study, Museum of Applied Art, Frankfurt(1979-85), High Museum of Art, Atlanta(1980-83), Museum of Contemporary Art, Barcelona(1987-95), and The J.Paul Getty Museum(1984-1997) have been selected for analysis. This study will reveal fundamental characteristics of Richard Meier's architectural philosophy through his early residential projects and give background information of the 'white architecture' Close analysis will continue by reviewing four museums selected specifically for this study and focus more from the point of issues such as; 1)applying various axis in space programming, 2)symbolic significance of exhibition space, 3)hierarchy of each space, 4)design elements and characteristics of the exhibition space. Furthermore, quantitative research on exhibition space organization will be done by Space Syntax theory method. The result of the study will be a significant data in designing a modern museum.

• KIEAE Journal
• /
• v.12 no.5
• /
• pp.29-34
• /
• 2012

A rental housing has a key role to supply the living space to non-ownership. A public rental housing is particularly aimed at providing the living space for the low-income households with a low rent fee. Therefore, the local government would try to maintain the facilities of the rental housing and to get the decent living condition. For getting the required living condition, it should make a maintenance plan, which contains the repair time, repair scope and targeted component and finishings. This study is aimed at providing the optimal repair time in 12 components and components of the rental housing which is controlled by the local government. The optimal repair time has two steps to get the final result. First, it would draw the 1'st repair time with the probabilistic and empirical approach. Second, comparing the drawn data and the service life, the optima repair time would be provided with considering the components' attributes. Result are as follows : First, the optimal repair time would be considered with the component attributes. There are user's convenience, its safety and physical aspect. Second, the kitchen utensils, elevator and water tap has a optimal time of 16, 19, 17 years respectively which is considered with physical aspect. In addition, the optima repair time of the wiring appliance and lighting equipment are 12 years and 10 years respectively.

• ETRI Journal
• /
• v.33 no.5
• /
• pp.741-751
• /
• 2011

This paper focuses on online speaker tracking for telephone conversations and broadcast news. Since the online applicability imposes some limitations on the tracking strategy, such as data insufficiency, a reliable approach should be applied to compensate for this shortage. In this framework, a set of reference speaker models are used as side information to facilitate online tracking. To improve the indexing accuracy, adaptation approaches in eigenvoice decomposition space are proposed in this paper. We believe that the eigenvoice adaptation techniques would help to embed the speaker space in the models and hence enrich the generality of the selected speaker models. Also, an index structure of the reference models is proposed to speed up the search in the model space. The proposed framework is evaluated on 2002 Rich Transcription Broadcast News and Conversational Telephone Speech corpus as well as a synthetic dataset. The indexing errors of the proposed framework on telephone conversations, broadcast news, and synthetic dataset are 8.77%, 9.36%, and 12.4%, respectively. Using the index tree structure approach, the run time of the proposed framework is improved by 22%.

• The Bulletin of The Korean Astronomical Society
• /
• v.40 no.2
• /
• pp.57.1-57.1
• /
• 2015

VLBI에서 관측 대역폭이 n배 증가될 경우 관측감도는 sqrt(n)만큼 향상되고, 이는 관측 연구 측면에서 기존에는 불가능하던 천체에 대한 연구 수행이 가능함을 의미한다. 관측 대역폭의 확대는 관측 데이터의 용량 증가를 의미하며 여기서 해당 데이터의 처리를 위한 초고속 데이터 기록시스템은 핵심적 역할을 한다. 이에 따라 현재 KVN에서는 미국 MIT Haystack 천문대에서 개발된 초고속 기록시스템인 Mark5B/B+와 Mark6를 운용 중에 있다. 하지만 이들 시스템의 경우 사실상 VLBI연구를 위한 목표로 특수 개발되었기에 유지 및 운영 측면에서 여러 불편이 있고, 성능에 있어서도 단일 스트림 기준으로 8Gbps를 넘지 못하는 한계를 안고 있다. 본 발표에서는 기존 시스템을 대체할 수 있는 기술로서 PCI 익스프레스 기반의 데이터 처리를 소개하고자 한다. 나아가 실제 관측 데이터에 대한 입출력 및 기존 시스템과의 성능 비교를 통해 광대역 관측 연구에 최적화된 기록 시스템을 제안하고자 한다.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.29-31
• /
• 2007

In this paper we propose an directional analytic approach in image data space for X-ray image which is detected from the X-ray projection system. Such a radiographic nondestructive testing has long been used for steel-tube inspection and weld monitoring. The welded area and thickness of steel-tube are detected from gradient radiating mechanism based on the evaluation of biased X-ray source position. The welded area is an ellipse type on low contrast X-ray image including noise. Noise originates from most of elements of the system. such as shielding CCD camera, imaging screen, X-ray source, inspected object, electronic circuits and etc.. Projection incorrectness and noise influence on imaging quality is to be represented by vertical pixels' distribution. Space analysis due to vertical direction also shows the segmental possibility between regions by visual edge evaluation.

• Journal of Positioning, Navigation, and Timing
• /
• v.10 no.2
• /
• pp.83-89
• /
• 2021

The extended Kalman filter (EKF) is widely used for global navigation satellite system (GNSS) applications. It is difficult to obtain precise positions with an EKF one-way (forward or backward) filter. In this paper, we propose an EKF smoother to improve the positioning accuracy by integrating forward and backward filters. For the EKF smoother experiment, we performed PPP using GNSS data received at the DAEJ reference station for a month. The effectiveness of the proposed approach is validated with multi-GNSS kinematic PPP experiments. The EKF smoother showed 35%, 6%, and 22% improvement in east, north, and up directions, respectively. In addition, accurate tropospheric zenith total delay (ZTD) values were calculated by a smoother. Therefore, the results from EKF smoother demonstrate that better accuracy of position can be achieved.

• Journal of Aerospace System Engineering
• /
• v.16 no.4
• /
• pp.17-27
• /
• 2022

In this study, a deep learning-based network that can predict the aerodynamic characteristics of airfoils was designed, and the feasibility of the proposed network was confirmed by applying aerodynamic data generated by Xfoil. The prediction of aerodynamic characteristics according to the variation of airfoil thickness was performed. Considering the angle of attack, the coordinate data of an airfoil is converted into image data using signed distance function. Additionally, the distribution of the pressure coefficient on airfoil is expressed as reduced data via proper orthogonal decomposition, and it was used as the output of the proposed network. The test data were constructed to evaluate the interpolation and extrapolation performance of the proposed network. As a result, the coefficients of determination of the lift coefficient and moment coefficient were confirmed, and it was found that the proposed network shows benign performance for the interpolation test data, when compared to that of the extrapolation test data.