• 한국환경과학회지
• /
• 제22권3호
• /
• pp.303-308
• /
• 2013

This paper proposed a new method for estimating missing values in time series rainfall data. The proposed method integrated the two most widely used estimation methods, general linear model(GLM) and ordinary kriging(OK), by taking a weighted average of covariance matrices derived from each of the two methods. The proposed method was cross-validated using daily rainfall data at thirteen rain gauges in the Hyeong-san River basin. The goodness-of-fit of the proposed method was higher than those of GLM and OK, which can be attributed to the weighting algorithm that was designed to minimize errors caused by violations of assumptions of the two existing methods. This result suggests that the proposed method is more accurate in missing values in time series rainfall data, especially in a region where the assumptions of existing methods are not met, i.e., rainfall varies by season and topography is heterogeneous.

• 응용통계연구
• /
• 제23권1호
• /
• pp.73-79
• /
• 2010

Missing values for unit root processes are imputed by the most recent observations. Treating the imputed observations as if they are complete ones, semiparametric unit root tests are extended to missing value situations. Also, an invariance principle for the partial sum process of the imputed observations is established under some mild conditions, which shows that the extended tests have the same limiting null distributions as those based on complete observations. The proposed tests are illustrated by analyzing an unequally spaced real data set.

• Journal of the Korean Statistical Society
• /
• 제13권1호
• /
• pp.57-68
• /
• 1984

A method of missing value estimation for a general design is descrived. In particular, the cases of missing value estimation for $2^k$ and $3^k$ design are explored and discussed. Some examples are illustrated to show the missing value estimation and the nonestimatimable cases.

• Communications for Statistical Applications and Methods
• /
• 제16권4호
• /
• pp.675-686
• /
• 2009

In this paper, it will be assumed that there are two distinct populations which are multivariate normal with equal covariance matrix. We also assume that the two populations are equally likely and the costs of misclassification are equal. The classification rule depends on the situation when the training samples include missing values or not. We consider the bootstrap confidence intervals for classification error rate when a block of observation is missing.

• Journal of the Korean Data and Information Science Society
• /
• 제18권3호
• /
• pp.585-598
• /
• 2007

It is so difficult to get complete data when we conduct a questionaire in actuality. And we get inefficient results if we analyze statistical tests with ignoring missing values. Therefore, we use imputation methods which evaluate quality of data. This study proposes a imputation method by decomposition and voting with ordinal data. First, data are sorted by each variable. After that, imputation methods are used by each decomposition level. And the last step is selection of values with voting. The proposed method is evaluated by accuracy and RMSE. In conclusion, missing values are related to each variable, median imputation method using decomposition and voting is powerful.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.95-99
• /
• 2023

Recently Machine Learning has been considered as one of the active research areas of Computer Science. The various Artificial Intelligence techniques are used to solve the classification problems of environmental sciences, biological sciences, and medical sciences etc. Due to the heterogynous and malfunctioning weather sensors a considerable amount of noisy data with missing is generated, which is alarming situation for weather prediction stockholders. Filling of these missing values with proper method is really one of the significant problems. The data must be cleaned before applying prediction model to collect more precise & accurate results. In order to solve all above stated problems, this research proposes a novel weather forecasting system which consists upon two steps. The first step will prepare data by reducing the noise; whereas a decision model is constructed at second step using regression algorithm. The Confusion Matrix will be used to evaluation the proposed classifier.

• 한국경제지리학회지
• /
• 제25권1호
• /
• pp.171-181
• /
• 2022

부동산 시장 분석에 있어 기본이 되는 정량적 데이터는 부동산 가격 지수이다. OECD와 같은 국제기구에서는 국가별 부동산 가격 지수를 공표하고, 한국부동산원에서는 광역시 단위와 시군구 단위의 지수를 산출한다. 그런데 공간단위를 시군구보다 정교한 동단위, 아파트 단지 단위로 설정하는 경우, 여러 문제점을 맞이하게 된다. 대표적인 문제는 결측치이다. 공간적 범위를 좁힐수록 단위 기간에 따라 거래가 적거나 아예 존재하지 않는 경우가 존재하기에 이 경우에는 지수의 산출이 불가능한 결측치가 발생할 수 있다. 본 연구에서는 지도학습 기반의 머신러닝 기법을 활용하여 특정 범위와 기간에 거래가 존재하지 않아 발생할 수 있는 결측치를 보완하는 기법을 제안한다. 본 모형을 통해 부동산 매매 지수의 실제값이 존재하는 것들의 예측을 통해 그 정확도를 검증하고 결측치가 발생한 것들의 예측도 해 볼 수 있었다.

• 한국측량학회지
• /
• 제37권5호
• /
• pp.293-302
• /
• 2019

In mountain accident events, it is important for the search team commander to determine the search area in order to secure the Golden Time. Within this period, assistance and treatment to the concerned individual will most likely prevent further injuries and harm. This paper proposes a method to determine the search priority area based on missing persons behavior and missing persons incidents statistics. GIS (Geographic Information System) and MCDM (Multi Criteria Decision Making) are integrated by applying WLC (Weighted Linear Combination) techniques. Missing persons were classified into five types, and their behavioral characteristics were analyzed to extract seven geographic analysis factors. Next, index values were set up for each missing person and element according to the behavioral characteristics, and the raster data generated by multiplying the weight of each element are superimposed to define models to select search priority areas, where each weight is calculated from the AHP (Analytical Hierarchy Process) through a pairwise comparison method obtained from search operation experts. Finally, the model generated in this study was applied to a missing person case through a virtual missing scenario, the priority area was selected, and the behavioral characteristics and topographical characteristics of the missing persons were compared with the selected area. The resulting analysis results were verified by mountain rescue experts as 'appropriate' in terms of the behavior analysis, analysis factor extraction, experimental process, and results for the missing persons.

• 응용통계연구
• /
• 제23권2호
• /
• pp.305-315
• /
• 2010

본 논문에서는 색조영상의 R-, G-, B-성분에서 랜덤결측된 화소값들의 대체를 위한 프리퀀티스틱(frequentictic) 기법을 제공한다. 이 기법은 관측영상을 가우시안 마코프 랜덤필드 상의 실현치로서 가정하고, 주어진 화소 내의 근방 화소들이 에지 강도에 따른 서로 다른 분산을 가지는 정규분포를 따른다고 설계함으로써 에지에서 결측화소 대체값이 이질적 색상에 영향 받지 않도록 한다. 이러한 모형하에서 우도가 최대화하도록 결측화소값들을 근사 EM 알고리즘에 기반 한 방법으로 모수들을 추정하고 결측화소를 대체한다. 제안된 방법의 결과들은 보간법에 기초한 대체법과 비교하여 그 유효성을 보인다.

• 한국IT서비스학회지
• /
• 제13권4호
• /
• pp.359-375
• /
• 2014

Researchers cannot avoid missing data in collecting data, because some respondents arbitrarily or non-arbitrarily do not answer questions in studies and experiments. Missing data not only increase and distort standard deviations, but also impair the convenience of estimating parameters and the reliability of research results. Despite widespread use of hot deck, researchers have not been interested in it, since it handles missing data in ambiguous ways. Hot deck can be complemented using K-nn, a method of machine learning, which can organize donor groups closest to properties of missing data. Interested in the role of k-nn, this study was conducted to impute missing data based on the hot deck method using k-nn. After setting up imputation of missing data based on hot deck using k-nn as a study objective, deletion of listwise, mean, mode, linear regression, and svm imputation were compared and verified regarding nominal and ratio data types and then, data closest to original values were obtained reasonably. Simulations using different neighboring numbers and the distance measuring method were carried out and better performance of k-nn was accomplished. In this study, imputation of hot deck was re-discovered which has failed to attract the attention of researchers. As a result, this study shall be able to help select non-parametric methods which are less likely to be affected by the structure of missing data and its causes.