• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.125-126
• /
• 2014

센서 스트림 데이터는 센서 네트워크를 통해 수집되는 데이터로 실시간 처리를 요구하며, 연속적으로 끊임없이 발생하는 스트림 데이터이다. 이러한 스트림 데이터는 양이 방대하여 이를 저장하기가 매우 어려우며, 동시에 데이터를 검색하는 데에는 많은 시간이 소요된다. 본 논문에서는 센서 네트워크에서의 효율적인 스트림 데이터 처리 시스템을 제안한다. 이 시스템은 캐시테이블을 사용함으로써 데이터베이스에 최소화된 접근으로 데이터 스트림 관리 시스템의 성능을 개선하였다. 그리고 센서 네트워크에서 읽어 들여온 불완전 데이터를 효율적으로 정제하고 상위 단계로 전송한다.

• Survey Research
• /
• v.9 no.2
• /
• pp.1-27
• /
• 2008

Problems of incomplete data are pervasive in statistical analysis. In particular, incomplete data have been an important challenge in repeated measures studies. The objective of this study is to give a brief introduction to missing data mechanisms and conventional/recent missing data methods and to assess the performance of various missing data methods under ignorable and non-ignorable missingness mechanisms. Given the inadequate attention to longitudinal studies with missing data, this study applied recent advances in missing data methods to repeated measures models and investigated the performance of various missing data methods, such as FIML (Full Information Maximum Likelihood Estimation) and MICE(Multivariate Imputation by Chained Equations), under MCAR, MAR, and MNAR mechanisms. Overall, the results showed that listwise deletion and mean imputation performed poorly compared to other recommended missing data procedures. The better performance of EM, FIML, and MICE was more noticeable under MAR compared to MCAR. With the non-ignorable missing data, this study showed that missing data methods did not perform well. In particular, this problem was noticeable in slope-related estimates. Therefore, this study suggests that if missing data are suspected to be non-ignorable, developmental research may underestimate true rates of change over the life course. This study also suggests that bias from non-ignorable missing data can be substantially reduced by considering rich information from variables related to missingness.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.919-925
• /
• 2006

Maximum likelihood estimate(MLE) is obtained from the partial log-likelihood function for the cell probabilities of two way incomplete contingency tables proposed by Chen and Fienberg(1974). The partial log-likelihood function is modified by adding lagrangian multiplier that constraints can be incorporated with. Variances of MLE estimators of population proportions are derived from the matrix of second derivatives of the loglikelihood with respect to cell probabilities. Simulation results, when data are missing at random, reveal that Complete-case(CC) analysis produces biased estimates of joint probabilities under MAR and less efficient than either MLE or MI. MLE and MI provides consistent results under either the MAR situation. MLE provides more efficient estimates of population proportions than either multiple imputation(MI) based on data augmentation or complete case analysis. The standard errors of MLE from the proposed method using lagrangian multiplier are valid and have less variation than the standard errors from MI and CC.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.34 no.3
• /
• pp.3-10
• /
• 2018

It's not practical to collect all information at the entire degrees of freedom of finite element model. The incomplete measurements should be expanded for subsequent analysis and damage detection. This work presents the analytical methods to expand the incomplete static or dynamic response data. Using the expanded data, introducing the concept of residual force, and minimizing the performance index expressed as the stiffness matrix and its difference before and after damage, the variation in stiffness matrix is derived. Based on the difference in the stiffness matrix, the damage detection method of structures is also provided. The validity of the proposed methods is illustrated in a numerical application, the numerical results are analyzed for applications, and the applicability of both methods is investigated.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.2
• /
• pp.327-336
• /
• 2014

Recurrent event data occurs when a subject experiences same type of event repeatedly and is found in various areas such as the social sciences, Economics, medicine and public health. To analyze recurrent event data either a total time or a gap time is adopted according to research interest. In this paper, we analyze recurrent event data with incomplete observation gap using a gap time scale. That is, some subjects leave temporarily from a study and return after a while. But it is not available when the observation gaps terminate. We adopt an interval censoring mechanism for estimating the termination time. Furthermore, to model the association among gap times of a subject, a frailty effect is incorporated into a model. Programs included in Survival package of R program are implemented to estimate the covariate effect as well as the variance of frailty effect. YTOP (Young Traffic Offenders Program) data is analyzed with both proportional hazard model and a weibull regression model.

• The Journal of Information Technology and Database
• /
• v.3 no.2
• /
• pp.75-96
• /
• 1996

This study is intended to compare the effectiveness of the neural network inductive learning model with a vector space model in information retrieval. As a result, searches responding to incomplete queries in the neural network inductive learning model produced a higher precision and recall as compared with searches responding to complete queries in the vector space model. The results show that the hybrid methodology of integrating an inductive learning technique with the neural network model can help solve information retrieval problems that are the results of inconsistent indexing and incomplete queries--problems that have plagued information retrieval effectiveness.

• Communications for Statistical Applications and Methods
• /
• v.5 no.3
• /
• pp.695-706
• /
• 1998

In this paper we consider the setting where a group of n judges are to independently rank a series of κ objects, but the intended complete rankings are not realized and we are faced with analyzing randomly incomplete rank vectors. We discuss some tests based on Friedman statistics on the designs completed through rank imputation schemes suggested by Lordo and Wolfe (1994) and evaluate them on the basis of simulated power studies, constructing their appropriate null distributions.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.54 no.11
• /
• pp.498-502
• /
• 2005

The objectives of this paper are to provide information on the characteristics of the discharge signals in a low-voltage indoor outlet. Most of electrical fires are caused by short circuits, overheating of wires, deterioration and incomplete connection of wiring devices. The last two cases are predictable before the occurrence of fire because of its slow progress. We have simulated the discharge signals caused by the deterioration and incomplete connection of wiring devices using aged outlets. From the experimental data, we could characterize the frequency spectrums of the discharge signals depending on the cases. The higher frequency components of the signal are attenuated by the capacitance and inductance of power lines as the measuring point is getting away from the discharges. Main frequency components of the discharge signal are existent at 600kHz - 1.5MHz in incomplete connections and at 210H7z - 8MHz in deteriorations of the outlet.

• The Journal of Korean Physical Therapy
• /
• v.15 no.4
• /
• pp.384-397
• /
• 2003

The purpose of this study was to investigate the effect of Treadmill Training on WISCI level, walking velocity, walking endurance, motor score and gait cycle of spinal cord injury patient with incomplete. Four subjects with spinal cord injury participated in this study. They took walking excercise 5 times per week for 8 weeks. One time excercise spent 30minutes. The theraputic effect was evaluated by WISCI level, walk 10 meters test, walk for 12 minutes test, motor score and gait cycle. Four subjects were examined before, after 8 week, walking training. Collected data were statistically analyzed by SPSS PC for Wilcoxon signed rank test. The results of this study are as follows; 1) In WISCI level, walking velocity, walking endurance and motor score, post - treatment score were higher compared to pre-treatment score with statistical significance(p<0.05). 2) In Rt SLS, DLSII and Lt SLS, post-treatment percentage were higher compared to pre-treatment percentage with statistical significance(p<0.05). but DLSI were not statistical significance(p>0.05). The findings suggest that spinal cord injury patients with incomplete can improve their WISCI level, walking velocity, walking endurance, motor score and gait cycle through Treadmill gait training.

• Journal of the Korean Academy of Clinical Electrophysiology
• /
• v.2 no.1
• /
• pp.83-92
• /
• 2004

This study aims to the influenced factor analysis of spinal cord independence measure(SCIM), on walking velocity, walking endurance, time up & go(TUG), and subject characteristics. The subject of this study were 12 persons with incomplete spinal cord injury(ASIA C, D). All subject ambulatory with or without an assistive device. All participants were assessed on SCIM(score), walking velocity(m/s), walking endurance(m) and TUG(s). The data were analyzed using independent t-test and stepwise multiple regression. The results revealed that no statistical difference was noted in subject characteristics among SCIM, walking velocity, walking endurance, TUG(p>0.5). The independence score, breathing-sphincter control and ambulation were important factors in TUG(31.4%). The results suggest that SCIM may be an inappropriate assessment tool to predict gait ability of patient with incomplete spinal cord injury. Further study about gait speed, gait endurance and TUG by change of SCIM is needed using to patient of incomplete spinal cord injury.