• 응용통계연구
• /
• 제35권4호
• /
• pp.485-499
• /
• 2022

표본오차와 비표본오차를 포함하는 총오차(total survey error)를 관리하는 것은 표본설계에서 매우 중요하다. 무응답으로 인해 발생한 비표본오차는 총오차에서 차지하는 비중이 매우 크며 이를 해결하는 방법인 무응답 대체에 관한 다수의 연구가 수행되었다. 최근 전통적 통계학 관련 기법에 추가하여 기계학습 관련 기법을 이용한 무응답 대체법이 다수 연구되고 실질적으로 사용되고 있다. 기존에 발표된 다수의 방법은 MCAR(missing completely at random) 또는 MAR(missing at random) 가정을 사용하고 있다. 그러나 관심변수에 영향을 받는 MNAR(missing not at random) 또는 무시할 수 없는 무응답(non-ignorable non-response; NN)은 편향을 발생시켜 대체 결과의 정확성을 크게 떨어뜨리지만 이에 관한 연구는 상대적으로 미미하다. 본 연구에서는 무시할 수 없는 무응답이 발생한 경우에 적용 가능한 무응답 대체법을 제안하였다. 특히 편향을 추정한 후 이를 제거하는 방법을 이용하여 무응답 대체 결과의 정확성을 향상하는 방법을 제안하였다. 또한, 모의실험을 이용하여 제안된 방법의 타당성을 확인하였다.

• 대기
• /
• 제29권5호
• /
• pp.551-566
• /
• 2019

Quantitative understanding of a random error that is associated with Lagrangian particle dispersion modeling is a prerequisite for backward-in-time mode simulations. This study aims to quantify the random error of the WRF-FLEXPART model and suggest an optimum number of the Lagrangian particles for backward-in-time simulations over the Seoul metropolitan area. A series of backward-in-time simulations of the WRF-FLEXPART model has conducted at two receptor points by changing the number of Lagrangian particles and the relative error, as a quantitative indicator of random error, is analyzed to determine the optimum number of the release particles. The results show that in the Seoul metropolitan area a 1-day Lagrangian transport contributes 80~90% in residence time and ~100% in atmospheric enhancement of carbon monoxide. The relative errors in both the residence time and the atmospheric concentration enhancement are larger when the particles release in the daytime than in the nighttime, and in the inland area than in the coastal area. The sensitivity simulations reveal that the relative errors decrease with increasing the number of Lagrangian particles. The use of small number of Lagrangian particles caused significant random errors, which is attributed to the random number sampling process. For the particle number of 6000, the relative error in the atmospheric concentration enhancement is estimated as -6% ± 10% with reduction of computational time to 21% ± 7% on average. This study emphasizes the importance of quantitative analyses of the random errors in interpreting backward-in-time simulations of the WRF-FLEXPART model and in determining the number of Lagrangian particles as well.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제14권4호
• /
• pp.365-375
• /
• 2014

This paper proposes an abnormal V-shaped-error-free non-blind deconvolution technique featuring an adaptively segmented forward-problem based iterative deconvolution (ASDCN) process. Unlike the algebraic based inverse operations, this eliminates any operations of differential and division by zero to successfully circumvent the issue on the abnormal V-shaped error. This effectiveness has been demonstrated for the first time with applying to a real analysis for the effects of the Random Telegraph Noise (RTN) and/or Random Dopant Fluctuation (RDF) on the overall SRAM margin variations. It has been shown that the proposed ASDCN technique can reduce its relative errors of RTN deconvolution by $10^{13}$ to $10^{15}$ fold, which are good enough for avoiding the abnormal ringing errors in the RTN deconvolution process. This enables to suppress the cdf error of the convolution of the RTN with the RDF (i.e., fail-bit-count error) to $1/10^{10}$ error for the conventional algorithm.

• International Journal of Advanced Culture Technology
• /
• 제11권3호
• /
• pp.310-314
• /
• 2023

The purpose of this study is to predict the remaining capacity of lithium-ion batteries and evaluate their performance using five artificial intelligence models, including linear regression analysis, decision tree, random forest, neural network, and ensemble model. We is in the study, measured Excel data from the CS2 lithium-ion battery was used, and the prediction accuracy of the model was measured using evaluation indicators such as mean square error, mean absolute error, coefficient of determination, and root mean square error. As a result of this study, the Root Mean Square Error(RMSE) of the linear regression model was 0.045, the decision tree model was 0.038, the random forest model was 0.034, the neural network model was 0.032, and the ensemble model was 0.030. The ensemble model had the best prediction performance, with the neural network model taking second place. The decision tree model and random forest model also performed quite well, and the linear regression model showed poor prediction performance compared to other models. Therefore, through this study, ensemble models and neural network models are most suitable for predicting the remaining capacity of lithium-ion batteries, and decision tree and random forest models also showed good performance. Linear regression models showed relatively poor predictive performance. Therefore, it was concluded that it is appropriate to prioritize ensemble models and neural network models in order to improve the efficiency of battery management and energy systems.

• 한국정보처리학회논문지
• /
• 제7권12호
• /
• pp.3944-3951
• /
• 2000

본 논문에서는 비화특성을 가진 새로운 FEC(Forward Error Correction) 부호기법으로 RCNC (Random Connection Node Convolutional) 부호화방식을 소개한다. 최근의 무선통신시스템은 다양한 멀티미디어 데이터 서비스를 하고 있다. 이러한 시스템은 전송 중 발생한 오류에 대한 정정 능력과 더불어 인증 사용자의 접근에 대한 비화 특성이 중요시된다. 이러한 문제를 해결하기 위한 방안으로 RCNC 부호화 방식은 전송 중 발생한 에러에 대한 오류 정정 기능을 가지면서, 전송데이터에 대한 비화성질을 부가하여 허용된 사용자 이외에는 접근이 불가능하도록 하는 암호화 특성을 가진다는 점이다. 본 논문에서는 RCNC 부호화 기법의 동작과 특성을 설명하고 있으며, 또한 컴퓨터 시뮬레이션을 이용하여 에러 정정 능력과 사용자 접근 허용정도를 검증하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.210-212
• /
• 1996

Random drift rate (i.e., random drift in angle rate) of a gyro represents the major error source of inertial navigation systems that are required to operate over long time intervals. It is uncorrectable and leads to an increase in the error with the passage of time. In this paper a technique is presented for analyzing random process from experimental data and the results are presented. The problem of estimating the a priori statistics of a random process is considered using time averages of experimental data. Time averages are calculated and used in the optimal data-processing techniques to determine the statistics of the random process. Therefore the contribution each component to the gyro drift process can be quantitatively measured by its statistics. The above techniques will be applied to actual gyro drift rate data with satisfactory results.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제17권1호
• /
• pp.147-155
• /
• 2017

A new endurance test-pattern generation on NAND-flash memory is proposed to improve test cost. We mainly focus on the correlation between the data-pattern and the device error-rate during endurance testing. The novelty is the development of testing method using quasi-random pattern based on device architectures in order to increase the test efficiency during time-consuming endurance testing. It has been proven by the experiments using the commercial 32 nm NAND flash-memory. Using the proposed method, the error-rate increases up to 18.6% compared to that of the conventional method which uses pseudo-random pattern. Endurance testing time using the proposed quasi-random pattern is faster than that of using the conventional pseudo-random pattern since it is possible to reach the target error rate quickly using the proposed one. Accordingly, the proposed method provides more low-cost testing solutions compared to the previous pseudo-random testing patterns.

• 산업기술연구
• /
• 제20권A호
• /
• pp.159-167
• /
• 2000

In the study rainfall frequency analysis attemped the many specific property data record duration it is differance from occur to error-term and probability ditribution of concern manifest. error-term analysis of method are fact sample data using method in other hand it is not appear to be fault that sample data of number to be small random variates. Therefore, day-rainfall data: to randomicity consider of this study sample data to the Monte Carlo method by randomize after data recode duration of form was choice method which compared an assumed maternal distribution from splitting frequency analysis consequence. In the conclusion, frequency analysis of chuncheon region rainfall appeared samll RMSE to the Gamma II distribution. In the rainfall frequency analysis estimate RMSE using random variates great transform, RMSE is appear that return period increasing little by little RMSE incresed and data number incresing to RMSE decreseing.

• Communications for Statistical Applications and Methods
• /
• 제25권3호
• /
• pp.275-282
• /
• 2018

This paper discusses the use of projections for the sums of squares in the analyses of variance for two-way nested design data. The model for this data is assumed to only have random effects. Two different sizes of experimental units are required for a given experimental situation, since nesting is assumed to occur both in the treatment structure and in the design structure. So, variance components are coming from the sources of random effects of treatment factors and error terms in different sizes of experimental units. The model for this type of experimental situation is a random effects model with more than one error terms and therefore estimation of variance components are concerned. A projection method is used for the calculation of sums of squares due to random components. Squared distances of projections instead of using the usual reductions in sums of squares that show how to use projections to estimate the variance components associated with the random components in the assumed model. Expectations of quadratic forms are obtained by the Hartley's synthesis as a means of calculation.

• 응용통계연구
• /
• 제34권5호
• /
• pp.697-710
• /
• 2021

상대오차를 이용한 예측법은 상대오차(혹은 퍼센트오차)가 중요시되는 분야, 특히 계량경제학이나 소프트웨어 엔지니어링, 또는 정부기관 공식통계 부분에서 기존 예측방법 외에 선호되는 예측방법이다. 그 동안 상대오차를 이용한 예측법은 선형 혹은 비선형 회귀분석 뿐 아니라, 커널회귀를 이용한 비모수 회귀모형, 그리고 정상시계열분석에 이르기까지 그 범위가 확장되어 왔다. 그러나, 지금까지의 분석은 고정효과(fixed effect)만을 고려한 것이어서 임의효과(random effect)에 관한 상대오차 예측법에 대한 확장이 필요하였다. 본 논문의 목적은 상대오차예측법을 일반화선형혼합모형(GLMM)에 속한 감마회귀(gamma regression), 로그정규회귀(lognormal regression), 그리고 역가우스회귀(inverse gaussian regression)의 패널자료(panel data)에 적용시키는데 있다. 이를 위해 실제 자동차 보험회사의 손해액 자료를 사용하였고, 최량예측량과 최량상대오차예측량을 각각 적용-비교해 보았다.