• Journal of Digital Convergence
• /
• v.10 no.7
• /
• pp.167-172
• /
• 2012

In vocabulary recognition using HMM(Hidden Markov Model) by model for the observation of a discrete probability distribution indicates the advantages of low computational complexity, but relatively low recognition rate has the disadvantage that require sophisticated smoothing process. Gaussian mixtures in order to improve them with a continuous probability density CHMM (Continuous Hidden Markov Model) model is proposed for the optimization of the library system. In this paper is system configuration thread control in recognition Gaussian mixtures model provides a model to optimize of the CHMM vocabulary recognition. The result of applying the proposed system, the recognition rate of 98.1% in vocabulary recognition, respectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.105-110
• /
• 2015

This study proposes the more improved mathematical model than conventional that for the 3-DOF Helicopter System in Quanser Inc., and checks the validity about the proposed model by performance comparison between the controller based on the conventional model and that based on the proposed model. Research process is next : First, analyze the dynamics for the 3-DOF helicopter system and establish the linear mathematical model. Second, check the eliminated nonlinear-elements in linearization process for establishing the linear mathematical model. And establish the improved mathematical model including the parameters corresponding to the eliminated nonlinear-elements. At that time, it is used for modeling that Particle Swarm Optimization algorithm the meta-heuristic global optimization method. Finally, design the controller based on the proposed model, and verify the validity of the proposed model by comparison about the experimental results between the designed controller and the controller based on the conventional model.

• Aerospace Engineering and Technology
• /
• v.12 no.2
• /
• pp.24-29
• /
• 2013

A spacecraft radiator is a thermal control method to eject internally dissipated heat into the space generated from operation of unit boxes. The efficiency of thermal design may be improved by optimizing radiator design. In this paper, the optimization approach method of node-based radiator design was suggested which is to combine numerical thermal analysis with optimization algorithm. This method has meaning that it can be used practically to implement the spacecraft radiator design regardless of thermal analysis and optimization algorithm software and maintain the same basic concept of an ordinary radiator design approach based on node division of a thermal model. The overall analysis framework with thermal analysis and optimization algorithm would be presented.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.205-210
• /
• 2022

With the rapid development of the social economy and the continuous improvement of living standards, a favorable environment has been provided for the rapid development of the tourism industry. The highly developed Internet technology has provided people with more convenient online travel. With the rapid development of online tourism, tourism-related Internet businesses are also developing rapidly. This study first introduces the research background and significance of the study, and suggests the necessity of Ctrip's business model optimization study based on the development of social economy such as online tourism development hotspots and business model research issues. Ctrip explains the current status of research inside and outside the online travel industry and business model, in-depth introduction and analysis of related concepts and theories such as online travel and OTA business models, and expands them based on expert research. Several aspects such as insufficient Ctrip's existing business model, high current operating costs, major factors affecting suppliers, and slow development of new business were suggested, and alternatives were suggested to solve these problems. Ctrip maintained a sustainable competitive edge, including Ctrip's business model optimization strategy for value creation and innovation and Internet business model optimization strategy for customer value chains.

• Journal of the Korean association of regional geographers
• /
• v.16 no.6
• /
• pp.673-688
• /
• 2010

The purpose of this study is to develop an optimization model for reconstructing local administrative districts using spatial analysis and modeling. For this, literature related to reorganization of local administrative systems was critically reviewed and criteria for redistricting were extracted. An optimization model for reconstructing administrative districts was formulated based on these criteria. The model considered three criteria; homogeneity within a reconstructed district, equity among reconstructed districts, and spatial arrangement. Homogeneity for relieving spatial mismatch between administrative and living(economic) boundaries is measured by spatial interaction within a district. Equity among districts is evaluated using population, area, and financial independence. Finally, spatial arrangement is measured by compactness and contiguity. The developed optimization model was implemented using Automated Zoning Procedure(AZP) in GIS environment and applied to a problem aggregating Si-Gun administrative units into broader districts. Application results demonstrate that the model can provide optimal districts according to alternative objective functions.

• Composites Research
• /
• v.16 no.4
• /
• pp.36-43
• /
• 2003

In this research, the optimization of composite structures was performed using metamodels. The optimization of composite structures requires a lot of time when optimizing the result of the time-consuming analysis. Thus, metamodels are used to replace the time-consuming analysis with simple models. RSM, kriging and neural networks are widely used metamodels. RSM and kriging were used in this study. The ultimate failure load analysis of the composite structure was approximated by metamodels. The optimizations of the composite plate were performed to maximize ultimate failure load using genetic algorithm and metamodels.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.846-849
• /
• 2020

하이퍼파라미터(초매개변수) 최적화란 모델의 학습에 앞서 미리 설정해야 하는 값인 하이퍼파라미터의 최적값을 탐색하는 문제이다. 이때의 최적값은 학습을 끝낸 모델의 성능을 가능한 최대치로 높이게 하는 값이다. 한편, 최근 모바일 장치를 이용한 포지셔닝 데이터의 대량 수집이 가능해지면서 이를 활용하여 위치 기반 서비스(Location-Based Service)를 위한 데이터 분석 및 예측에 관한 연구가 활발히 이루어졌다. 그중 이동 경로를 이미지로 패턴화하여 국소 지역 내에서 다음 위치를 예측하는 CNN 모델에 대해서 하이퍼파라미터 튜닝을 진행하였다. 결과적으로 베이지안 최적화(Bayesian Optimization)를 통해 모델의 성능을 평균 3.7%, 최대 9.5%까지 개선할 수 있음을 확인하였다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.11
• /
• pp.989-996
• /
• 2016

This paper intends to develop the rotor track and balance (RTB) algorithm using the nonlinear RTB models and a real-coded hybrid genetic algorithm. The RTB response data computed using the trim solutions with variation of the adjustment parameters have been used to build nonlinear RTB models based on the quadratic interpolation functions. Nonlinear programming problems to minimize the track deviations and the airframe vibration responses have been formulated to find optimum settings of balance weights, trim-tab deflections, and pitch-link lengths of each blade. The results are efficiently resolved using the real-coded genetic algorithm hybridized with the particle swarm optimization techniques for convergence acceleration. The nonlinear RTB models and the optimized RTB parameters have been compared with those computed using the linear models to validate the proposed techniques. The results showed that the nonlinear models lead to more accurate models and reduced RTB responses than the linear counterpart.

• Geophysics and Geophysical Exploration
• /
• v.22 no.4
• /
• pp.202-209
• /
• 2019

In this study, an acoustic full-waveform inversion using Adam optimizer was proposed. The steepest descent method, which is commonly used for the optimization of seismic waveform inversion, is fast and easy to apply, but the inverse problem does not converge correctly. Various optimization methods suggested as alternative solutions require large calculation time though they were much more accurate than the steepest descent method. The Adam optimizer is widely used in deep learning for the optimization of learning model. It is considered as one of the most effective optimization method for diverse models. Thus, we proposed seismic full-waveform inversion algorithm using the Adam optimizer for fast and accurate convergence. To prove the performance of the suggested inversion algorithm, we compared the updated P-wave velocity model obtained using the Adam optimizer with the inversion results from the steepest descent method. As a result, we confirmed that the proposed algorithm can provide fast error convergence and precise inversion results.

• Journal of the KSME
• /
• v.35 no.8
• /
• pp.716-724
• /
• 1995

토폴로지 설계는 미리 형상이 결정되지 않은 새로운 개념의 제품을 설계하고자 할 때나 설계 경험이 풍부하지 못한 경우, 그 개념적 형상을 결정하는 데 매우 유용하다. 실제로 이러한 토폴 로지 설계의 결과를 최근 급속 시제품 제작기(rapid prototyping machine)와 함께 사용하게 되면 처음 개념설계에서 최초시제품의 형상을 예측하고 제작하는 데 많은 시간을 절약할 것으로 판 단된다. 그러나 토폴로지 최적화에 따른 구조물은 구조물의 한계 질량내에서 평균 강성이 가장 큰 구조물일 뿐, 국부적인 응력한계에 대한 최적화는 아니다. 따라서 최종적인 최적화 형상을 얻기 위해서는, 먼저 한계질량을 갖는 최적 토폴로지 구조물의 모델을 구하고, 이 모델에 대하여 설계변수에 따른 민감도 해석을 수행하여 최대응력의 한계값을 갖는 구조를 구하면 된다. 그림 10은 이러한 토폴로지 최적화와 민감도 해석을 통한 최적화를 수행하는 복합 최적설계 과정에 흐름도이다. 설계민감도 해석은 본 연구의 범위에 포함되지 않아서 여기서는 제외하였지만, 이에 관한 일반 상업화된 소프트웨어들이 많이 나와 있으므로 이를 참조하면 된다.