• Journal of the Korean Data and Information Science Society
• /
• 제10권2호
• /
• pp.465-472
• /
• 1999

We considered a bootstrap method for constructing confidenc intervals for a one parameter model using multinomial sampling. The convergence rates or the proposed bootstrap method are calculated for model-based maximum likelihood estimators(MLE) using multinomial sampling. Monte Carlo simulation was used to compare the performance of bootstrap methods with normal approximations in terms of the average coverage probability criterion.

• 한국정보통신학회논문지
• /
• 제26권5호
• /
• pp.662-667
• /
• 2022

의미역 결정 작업은 서술어와 문장 내 행위자, 피행위자, 장소, 시간 등 서술어와 관련 있는 논항들을 추출하는 작업이다. 기존 의미역 결정 방법은 문장의 언어학적 특징 추출을 위한 파이프라인을 구축하는데, 파이프라인 내 각 추출 작업들의 오류가 의미역 결정 작업의 성능에 영향을 미치기 때문에 현재는 End-to-End 방법의 신경망 모델을 이용한 방법들이 제안되고 있다. 본 논문에서는 의미역 결정 작업을 위해 Biaffine Average Attention 구조를 이용한 신경망 모델을 제안한다. 제안하는 모델은 기존 연구에서 제안된 특정 시점에 대한 레이블 예측을 위해 주변 시점 정보를 이용하는 LSTM 모델 대신 문장 내 서술어와 논항의 거리에 상관없이 문장 전체 정보에 집중할 수 있는 Biaffine Average Attention 구조로 이루어져 있다. 제안하는 모델의 성능 평가를 위해 F1 점수를 이용하여 기존 연구에서 제안한 BERT 기반의 모델들과 비교하였으며, 76.21%의 성능으로 비교 모델보다 높은 성능을 보였음을 확인하였다.

• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1548-1555
• /
• 2016

This paper presents an application of time series analysis in hourly wind speed simulation and forecast in Jeju Island, Korea. Autoregressive - moving average (ARMA) model, which is well in description of random data characteristics, is used to analyze historical wind speed data (from year of 2010 to 2012). The ARMA model requires stationary variables of data is satisfied by power law transformation and standardization. In this study, the autocorrelation analysis, Bayesian information criterion and general least squares algorithm is implemented to identify and estimate parameters of wind speed model. The ARMA (2,1) models, fitted to the wind speed data, simulate reference year and forecast hourly wind speed in Jeju Island.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권4호
• /
• pp.711-725
• /
• 2013

A heuristic with multi-byte suffix matching plays an important role in real pattern matching algorithms. By skipping many characters at a time in the process of comparing a given pattern with the text, the pattern matching algorithm based on a heuristic with multi-byte suffix matching shows a faster average search time than algorithms based on deterministic finite automata. Based on various experimental results and simulations, the previous works show that the pattern matching algorithms with multi-byte suffix matching performs well. However, there have been limited studies on the mathematical model for analyzing the performance in a standard manner. In this paper, we propose a new probabilistic model, which evaluates the performance of a heuristic with multi-byte suffix matching in an average-case search. When the theoretical analysis results and experimental results were compared, the proposed probabilistic model was found to be sufficient for evaluating the performance of a heuristic with suffix matching in the real pattern matching algorithms.

• 한국구조물진단유지관리공학회 논문집
• /
• 제6권2호
• /
• pp.157-165
• /
• 2002

Nonlinear analysis of the reinforced concrete beam subjected to torsion is presented. Seventeen equations involving seventeen variables are derived from the equilibrium equation, compatibility equation, and the material constitutive laws to solve the torsion problem. Newton method was used to solve the nonlinear simultaneous equations and efficient algorithms are proposed. Present model covers the behavior of reinforced concrete beam under pure torsion from service load range to ultimate stage. Tensile resistance of concrete after cracking is appropriately considered. The softened concrete truss model and the average stress-strain relations of concrete and steel are used. To verify the validity of present model, the nominal torsional moment strengths according to ACI-99 code and the ultimate torsional moment by present model are compared to experimental torsional strengths of 55 test specimens found in literature. The ultimate torsional moment strengths by the present model show good results.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회B
• /
• pp.2440-2443
• /
• 2008

This paper presents a three dimensional shape optimization procedure for a low-speed axial flow fan blade with a weighted average surrogate model. Reynolds-averaged Navier-Stokes equations with shear stress transport turbulence model are discretized by finite volume approximations. Six variables from airfoil profile and lean are selected as design variables. 3D RANS solver is used to evaluate the objective functions of total pressure efficiency. Surrogate approximation models for optimization have been employed to find the optimal design of fan blade. A search algorithm is used to find the optimal design in the design space from the constructed surrogate models for the objective function. The total pressure efficiency is increased by 0.31% with the weighted average surrogate model.

• International Journal of Automotive Technology
• /
• 제7권1호
• /
• pp.91-99
• /
• 2006

The diesel Auxiliary Power Unit (APU) for vehicle applications is a complex nonlinear system. For the purpose of this paper presents a dynamic average model of the whole system in an entirely physical way, which accounts for the non-ideal behavior of the diode rectifier, the nonlinear phenomena of generator-rectifier set in an elegant way, and also the dynamics of the dc load and diesel engine. Simulation results show the accuracy of the model. Based on the average model, a simple PI control scheme is proposed for the multivariable system, which includes the steps of model linearization, separate PI controller design with robust tuning rules, stability verification of the overall system by considering it as an uncertain one. Finally it is tested on a detailed switching model and good performances are shown for both set-point following and disturbance rejection.

• 전자공학회논문지
• /
• 제50권8호
• /
• pp.245-249
• /
• 2013

In this paper, we propose two rate control algorithms for multi-view extension of HEVC with two rate control algorithms adopted in HEVC and analyze the multi-view rate control performance. The proposed multi-view rate controls are designed on HEVC-based multi-view video coding (MV-HEVC) platform with consideration of high-level syntax, inter-view prediction, etc. not only for the base view but also for the extended views using the rate control algorithms based on URQ (Unified Rate-Quantization) and R-lambda model adopted in HEVC. The proposed multi-view rate controls also contain view-wise target bit allocation for providing the compatibility to the base view. By allocating the target bitrates for each view, the proposed multi-view rate control based on URQ model achieved about 1.83% of average bitrate accuracy and 1.73dB of average PSNR degradation. In addition, about 2.97% of average bitrate accuracy and 0.31dB of average PSNR degradation are achieved with the proposed multi-view rate control based on R-lambda model.

• 전력전자학회논문지
• /
• 제22권2호
• /
• pp.159-165
• /
• 2017

Small-signal modeling and controller design methodology are proposed to improve the dynamics and stability of a DC-DC dual active bridge (DAB) converter. The state-space average method has a limitation when applied to the DAB converter because its state variables are nonlinear and have zero average values in a switching period. Therefore, the small-signal model and the frequency response of the DAB converter are derived and analyzed using a generalized average method instead of conventional modeling methods. The design methodology of a lead-lag controller instead of the conventional proportional-integral controller is also proposed using the derived small-signal model. The accuracy and performance of the proposed small-signal model and controller are verified by simulation and experimental results with a 500 W prototype DAB converter.

• 디지털융복합연구
• /
• 제10권11호
• /
• pp.377-382
• /
• 2012

본 논문은 반향 제거 평균 예측 LMS 알고리즘을 이용하여 반향 잡음에 강인한 연속 음성 인식 모델인 CHMM 모델을 구성하는 방법을 제안하였다. 변화하는 반향 잡음에 적응하고 연속 음성 인식 성능 향상을 위한 반향 잡음 제거 평균 예측 LMS 알고리즘을 이용하여 CHMM 모델을 구성하였다. 제안한 알고리즘에 의해 구성된 CHMM 모델에 대하여 연속 인식 성능을 평가하였다. 실험 결과 변화하는 환경 잡음을 제거하여 얻은 음성의 SNR은 평균 1.93dB이 향상되었고 연속 음성의 인식률은 2.1% 향상되었다.