• 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.

• Korean Journal of Cognitive Science
• /
• v.10 no.3
• /
• pp.1.2-1.2
• /
• 1999

시각적 선택에 대한 과거 정신물리학적, 신경 생리학적 연구결과를 토대로 Feature Gate 라는 신경 망 모형을 제안하였다. 이 모형에는 공간 배치도가 위계 적으로 구성되어 있으며, 정보의 흐름이 위계의 각 수준으로부터 그 다음 수준으로 넘어갈 때 주의 게이트에 의해 조절되도록 되어 있다. 주의 게이트들은 독특한 세부 특징을 가진 위치에 반응하는 상향식 시스템과 표적 세부 특징이 있는 위치에 반응하는 하향식 기제 모두에 의해 조절된다. 본 연구는 Feature Gate 모형의 하향식 기제에 초점을 맞추어 모형을 설명하고, 현재 다른 모형들이 설명하지 못하는 Moran & Desimone(1985)의 연구결과를 이 모형이 어떻게 설명하는지를 제시하고자 한다. Feature Gate 모형은 병렬 적인 세부특징 검색, 계열 적 접합표적 검색, 단서에 의한 주의의 점진적 감소 모형, 세부특징-주도적인 공간적 선택, 주의의 분할, 방해자극 위치의 억제, 주변 억제 등을 포함한 시각적 주의 연구의 여러 가지 많은 현상들을 설명하는데 하나의 일관적인 해석을 제공해 준다. 앞으로 이 모형을 더욱 확장, 발전 시켜 세부특징의 조합된 배열에 반응하는 상위 수준의 유닛을 사용한다면 시각적 선택과정이 포함된 형태 재인 모형으로 개발될 수 있다.

• The KIPS Transactions:PartB
• /
• v.11B no.5
• /
• pp.587-596
• /
• 2004

During recent years, a new framework, which aims to bring a unified and global approach in indexing, browsing and querying various digital multimedia data such as audio, video and image has been developed. This new system partitions each media stream into smaller units based on actual physical events. These physical events within oath media stream can then be effectively indexed for retrieval. In this paper, we present a new approach that exploits audio, image and video features to segment and analyze the audio-visual data. Integration of audio and visual analysis can overcome the weakness of previous approach that was based on the image or video analysis only. We Implement a web-based multi media data retrieval system called XCRAB and report on its experiment result.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.17 no.6
• /
• pp.75-82
• /
• 2018

This study suggests an optimal design process of an LMU, which is installed on the top side of offshore structures. The LMU is consist of EB(elastomeric bearing) and steel plate, and supports the vertical loads of offshore structures and assists its stable installation. The structural design requirement of the LMU is related to its stiffness. This study utilizes the finite element analysis to predict the stiffness. The stiffness of the EB depends on the size of the bearing. Thus, the design variables in this study are defined as the thickness, the width and the number of plates. Since the LMU has different loads for different locations, its stiffness should be designed differently. The multiobjective function is introduced to attain the target stiffness. In this process, the metamodel using the kriging interpolation method is adopted to replace the true stiffness.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.6
• /
• pp.13-20
• /
• 2017

High-rise building shapes are changing from orthogonal to irregular form and the current trend is to arrange members in geometric grid-patterns at the perimeter of buildings. This study proposes a simple model for the preliminary design of a hexagrid high-rise building. The size of the cross section is set to be different at each module and hexagrid unit, which is different from the previous studies in which all hexagrid members were the same. To examine the effect of hexagrid size on structural performance, 60-story hexagrid buildings with 1-, 2- and 4-story high modules are designed and analyzed. Maximum lateral displacement, steel tonnage, load carrying percentage of perimeter frame and combined strength ratio are compared for 15 buildings. As the lateral load carrying capacity of hexagrid structure was inferior to a diagrid structural system, proper lateral stiffness should be allocated to the core frame in a hexagrid structure. The best ratio of flexural to shear deformation was 4 and larger unit size was better in considering constructional cost and structural efficiency. As the maximum lateral displacements of the buildings were within 84%~108% of the limit, the proposed method seems to be applicable to preliminary design of hexagrid buildings.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.2
• /
• pp.324-334
• /
• 2017

The simulators for a plant unit master control (UMC) developed by domestic or overseas researchers have been developed for operator-training purposes. UMC simulators normally constructed at the end of the plant construction, despite the UMC logics, should be simulated to pre-check many signal interfaces within the power generation systems. Because of the differences in construction schedule, it is difficult for logic designers or commissioning engineers to simulate the UMC logic during the design or commissioning stage. In this background, this paper proposes a simulation method that can be used easily by plant logic designers or operators in the MATLAB Simulink programming environment. The core of the UMC is realized with a unique simulation algorithm based on mathematical analysis and functional blocks combination. In addition, an integer-based configuration was proposed to realize the plant target value control for the equipment in the logic. With these simulation methods, functions, e.g., load distribution, high-low limitations, frequency compensation, etc. were simulated. The results showed that the plant UMC logic can be simulated in Simulink without a plant simulator. The various functions proposed in this paper can provide useful information about Simulink-based simulation design for plant logic designers or commissioning engineers during the power plant construction period.

• Korean Journal of Cognitive Science
• /
• v.10 no.3
• /
• pp.1-15
• /
• 1999

Based on known physiological and psychophysical results, a neural network model for visual selection, called FeaureGate is proposed. The model consists of a hierarchy of spatial maps. and the flow of information from each level of the hierarchy to the next is controlled by attentional gates. The gates are jointly controlled by a bottom-up system favoring locations with unique features. and a top-down mechanism favoring locations with features designated as target features. The present study focuses on the top-down mechanism of the FeatureGate model that produces results similar to Moran and Desimone's (1985), which many current models have failed to explain, The FeatureGate model allows a consistent interpretation of many different experimental results in visual attention. including parallel feature searches and serial conjunction searches. attentional gradients triggered by cuing, feature-driven spatial selection, split a attention, inhibition of distractor locations, and flanking inhibition. This framework can be extended to produce a model of shape recognition using upper-level units that respond to configurations of features.

• Journal of Korea Water Resources Association
• /
• v.54 no.10
• /
• pp.795-805
• /
• 2021

In this study, after developing an LSTM-based deep learning model for estimating daily runoff in the Soyang River Dam basin, the accuracy of the model for various combinations of model structure and input data was investigated. A model was built based on the database consisting of average daily precipitation, average daily temperature, average daily wind speed (input up to here), and daily average flow rate (output) during the first 12 years (1997.1.1-2008.12.31). The Nash-Sutcliffe Model Efficiency Coefficient (NSE) and RMSE were examined for validation using the flow discharge data of the later 12 years (2009.1.1-2020.12.31). The combination that showed the highest accuracy was the case in which all possible input data (12 years of daily precipitation, weather temperature, wind speed) were used on the LSTM model structure with 64 hidden units. The NSE and RMSE of the verification period were 0.862 and 76.8 m³/s, respectively. When the number of hidden units of LSTM exceeds 500, the performance degradation of the model due to overfitting begins to appear, and when the number of hidden units exceeds 1000, the overfitting problem becomes prominent. A model with very high performance (NSE=0.8~0.84) could be obtained when only 12 years of daily precipitation was used for model training. A model with reasonably high performance (NSE=0.63-0.85) when only one year of input data was used for model training. In particular, an accurate model (NSE=0.85) could be obtained if the one year of training data contains a wide magnitude of flow events such as extreme flow and droughts as well as normal events. If the training data includes both the normal and extreme flow rates, input data that is longer than 5 years did not significantly improve the model performance.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.7
• /
• pp.91-98
• /
• 2010

Large corpus-based concatenating Text-to-Speech (TTS) systems can generate natural synthetic speech without additional signal processing. Because the improvements in the natualness, personality, speaking style, emotions of synthetic speech need the increase of the size of speech DB, it is necessary to prune the redundant speech segments in a large speech segment DB. In this paper, we propose a new method to construct a segmental speech DB for the Korean TTS system based on a clustering algorithm to downsize the segmental speech DB. For the performance test, the synthetic speech was generated using the Korean TTS system which consists of the language processing module, prosody processing module, segment selection module, speech concatenation module, and segmental speech DB. And MOS test was executed with the a set of synthetic speech generated with 4 different segmental speech DBs. We constructed 4 different segmental speech DB by combining CM1(or CM2) tree clustering method and full DB (or reduced DB). Experimental results show that the proposed method can reduce the size of speech DB by 23% and get high MOS in the perception test. Therefore the proposed method can be applied to make a small sized TTS.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.11
• /
• pp.41-47
• /
• 2016

High efficiency video coding (HEVC) employs a coding tree unit (CTU) to improve the coding efficiency. A CTU consists of coding units (CU), prediction units (PU), and transform units (TU). All possible block partitions should be performed on each depth level to obtain the best combination of CUs, PUs, and TUs. To reduce the complexity of block partitioning process, this paper proposes the PU mode skip algorithm with region of interest (RoI) selection using motion vector. In addition, this paper presents the CU depth level skip algorithm using the co-located block information in the previously encoded frames. First, the RoI selection algorithm distinguishes between dynamic CTUs and static CTUs and then, asymmetric motion partitioning (AMP) blocks are skipped in the static CTUs. Second, the depth level skip algorithm predicts the most probable target depth level from average depth in one CTU. The experimental results show that the proposed fast CU decision algorithm can reduce the total encoding time up to 44.8% compared to the HEVC test model (HM) 14.0 reference software encoder. Moreover, the proposed algorithm shows only 2.5% Bjontegaard delta bit rate (BDBR) loss.