• Proceedings of the Optical Society of Korea Conference
• /
• 2007.02a
• /
• pp.277-278
• /
• 2007

Even though high NA, Hyper SIL system easily decline the optical performance even a little alignment error. Not only to overcome this instability but to maintain the high NA gain, we suggest a new system (Optimum SIL) which is a combination of each advantage of Hyper SIL and Hemi SIL. Simulation results shows that Optimum SIL system has much higher tolerance to various performance-lowering factors than Hyper SIL system even with a relatively small NA resignation.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.17-30
• /
• 1999

This paper proposes a new stereophonic acoustic echo canceller to prevent impairments on the voice quality and to remove acoustic echo effectively appearing in stereo environment at the instant of abrupt change of the transmission room environment in teleconferencing system. In stereophonic acoustic echo canceller, the major defective problems are the large computational complexity of estimating echo path systems due to the long impulse response of the true echo paths and the performance degradation of echo canceller due to large correlation between dual stereo signals. Moreover, the change of the suboptimal solution for the echo canceller was considered as a critical deficient factor on to the performance of stereophonic echo canceller. To overcome these problems, this paper proposes pseudo stereophonic acoustic echo canceller using Hyper-plane projection algorithm, which shows the robustness to the environment change of the transmission room and the efficiency of computational complexity.

• ETRI Journal
• /
• v.42 no.5
• /
• pp.658-668
• /
• 2020

In edge computing, most procedures, including data collection, data processing, and service provision, are handled at edge nodes and not in the central cloud. This decreases the processing burden on the central cloud, enabling fast responses to end-device service requests in addition to reducing bandwidth consumption. However, edge nodes have restricted computing, storage, and energy resources to support computation-intensive tasks such as processing deep neural network (DNN) inference. In this study, we analyze the effect of models with single and multiple local exits on DNN inference in an edge-computing environment. Our test results show that a single-exit model performs better with respect to the number of local exited samples, inference accuracy, and inference latency than a multi-exit model at all exit points. These results signify that higher accuracy can be achieved with less computation when a single-exit model is adopted. In edge computing infrastructure, it is therefore more efficient to adopt a DNN model with only one or a few exit points to provide a fast and reliable inference service.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.137-143
• /
• 2019

As the performance of computers increases, the use of deep learning, which has faced technical limitations in the past, is becoming more diverse. In many fields, deep learning has contributed to the creation of added value and used on the bases of more data as the application become more divers. The process for obtaining a better performance model will require a longer time than before, and therefore it will be necessary to find an optimal model that shows the best performance more quickly. In the artificial neural network modeling a tuning process that changes various elements of the neural network model is used to improve the model performance. Except Gride Search and Manual Search, which are widely used as tuning methods, most methodologies have been developed focusing on heuristic algorithms. The heuristic algorithm can get the results in a short time, but the results are likely to be the local optimal solution. Obtaining a global optimal solution eliminates the possibility of a local optimal solution. Although the Brute Force Method is commonly used to find the global optimal solution, it is not applicable because of an infinite number of hyper parameter combinations. In this paper, we use a statistical technique to reduce the number of possible cases, so that we can find the global optimal solution.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1315-1321
• /
• 2005

Using hyper-elastic material has been increased gradually and its range was extended all over the industrial. In addition, the performance prediction of this material was required not only experimental methods like metal material but also numerical methods. In this study, we presented the process how to use numerical method for hyper-elastic material and then, it was applied for seat-ring of butterfly valve by using this process. The finite element analysis was executed to evaluate the mechanical characteristics of hyper-elastic material and search the optimum model considered conditions and features. According to that model the coefficient was obtained by using Contact analysis.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.5
• /
• pp.439-446
• /
• 2015

Recently, the importance of one-class classification problem is more increasing. However, most of existing algorithms have the limitation on providing the information that effects on the prediction of the target value. Motivated by this remark, in this paper, we suggest an efficient one-class classifier using hyper-rectangles (H-RTGLs) that can be produced from intervals including observations. Specifically, we generate intervals for each feature and integrate them. For generating intervals, we consider two approaches : (i) interval merging and (ii) clustering. We evaluate the performance of the suggested methods by computing classification accuracy using area under the roc curve and compare them with other one-class classification algorithms using four datasets from UCI repository. Since H-RTGLs constructed for a given data set enable classification factors to be visible, we can discern which features effect on the classification result and extract patterns that a data set originally has.

• Journal of the Korea Convergence Society
• /
• v.13 no.4
• /
• pp.17-24
• /
• 2022

Bitcoin is a peer-to-peer cryptocurrency designed for electronic transactions that do not depend on the government or financial institutions. Since Bitcoin was first issued, a huge blockchain financial market has been created, and as a result, research to predict Bitcoin price data using machine learning has been increasing. However, the inefficient Hyper-parameter optimization process of machine learning research is interrupting the progress of the research. In this paper, we analyzes and presents the direction of Hyper-parameter optimization through experiments that compose the entire combination of the Timesteps, the number of LSTM units, and the Dropout ratio among the most representative Hyper-parameter and measure the predictive performance for each combination based on Bitcoin price prediction model using LSTM layer.

• ETRI Journal
• /
• v.38 no.4
• /
• pp.735-745
• /
• 2016

The Paris agreement at the 21st Conference of the Parties (COP21) emphasizes the reduction of greenhouse gas emissions and increase in energy consumption in all areas. Thus, an important aspect is energy saving in buildings where the lighting is a major component of the electrical energy consumption. This paper proposes a building energy management system employing visible light communication (VLC) based on LED lighting. The proposed management system has key characteristics including personalization and localization by utilizing such VLC advantages as secure communication through light and location-information transmission. Considering the efficient implementation of an energy-consumption adjustment using LED luminaires, this paper adopts variable pulse position modulation (VPPM) as a VLC modulation scheme with simple controllability of the dimming level that is capable of providing a full dimming range. This paper analyzes the VPPM performances according to variable dimming for several schemes, and proposes a VPPM demodulation architecture based on dimming-factor acquisition, which can obtain an improved performance compared to a 2PPM-based scheme. In addition, the effect of a dimming-factor acquisition error is analyzed, and a frame format for minimizing this error effect is proposed.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.3
• /
• pp.83-90
• /
• 2020

Prototype selection offers the advantage of ensuring low learning time and storage space by selecting the minimum data representative of in-class partitions from the training data. This paper designs a new training data generation method using hyper-rectangles that can be applied to general classification algorithms. Hyper-rectangular regions do not contain different class data and divide the same class space. The median value of the data within a hyper-rectangle is selected as a prototype to form new training data, and the size of the hyper-rectangle is adjusted to reflect the data distribution in the class area. A set cover optimization algorithm is proposed to select the minimum prototype set that represents the whole training data. The proposed method reduces the time complexity that requires the polynomial time of the set cover optimization algorithm by using the greedy algorithm and the distance equation without multiplication. In experimented comparison with hyper-sphere prototype selections, the proposed method is superior in terms of prototype rate and generalization performance.

• Nuclear Engineering and Technology
• /
• v.34 no.1
• /
• pp.42-59
• /
• 2002

In order to transmute long-lived radioactive nuclides such as transuranics(TRU), Tc-99, and I- l29 in LWR spent fuel, a preliminary conceptual design study has been performed for the accelerator driven subcritical reactor system, called HYPER(Hybrid Power Extraction Reactor) The core has a hybrid neutron energy spectrum: fast and thermal neutrons for the transmutation of TRU and fission products, respectively. TRU is loaded into the HYPER core as a TRU-Zr metal form because a metal type fuel has very good compatibility with the pyre- chemical process which retains the self-protection of transuranics at all times. On the other hand, Tc-99 and I-129 are loaded as pure technetium metal and sodium iodide, respectively. Pb-Bi is chosen as a primary coolant because Pb-Bi can be a good spallation target and produce a very hard neutron energy spectrum. As a result, the HYPER system does not have any independent spallation target system. 9Cr-2WVTa is used as a window material because an advanced ferritic/martensitic steel is known to have a good performance under a highly corrosive and radiation environment. The support ratios of the HYPER system are about 4∼5 for TRU, Tc-99, and I-129. Therefore, a radiologically clean nuclear power, i.e. zero net production of TRU, Tc-99 and I-129 can be achieved by combining 4 ∼5 LWRs with one HYPER system. In addition, the HYPER system, having good proliferation resistance and high nuclear waste transmutation capability, is believed to provide a breakthrough to the spent fuel problems the nuclear industry is faced with.