• Geotechnical Engineering
• /
• v.9 no.3
• /
• pp.61-66
• /
• 1993

In this paper, the incorporation of qualitative(or soft) data, such as outputs of geophysical tests or construction experience which has so far been cumulated, was discussed for rock classsification. Geostatistics wart used for this research since the parameters for the design of tunnels are spatially correlated. In particular, indicator kriging technique, which is one of non -parametric approaches, was used. As a selection criteria for an optimal classification, the cost of errors was adopted and the binary classes were only considered for rock classification. In future, incorporating an appreciable amount of available qualitative data will be necessary in tunnelling projects in which quantitative data are scarce. In this respect, this research is of great significance.

• The Korean Journal of Applied Statistics
• /
• v.21 no.6
• /
• pp.969-980
• /
• 2008

This paper presents the comparison of four methods, linear, quadratic, canonical and non-parametric discriminant analyses to discriminate the consumers' taste grade with sensory variables, such as tenderness, juiciness, flavor, and overall acceptability based on Consumer Sensory Survey. The classification ability of each method is measured and compared by the resubstitution error rate.

• The Korean Journal of Applied Statistics
• /
• v.22 no.3
• /
• pp.479-488
• /
• 2009

The ${\kappa}$-Nearest Neighbors Classification(KNNC) is a popular non-parametric classification method which assigns a fixed number ${\kappa}$ of neighbors to every observation without consideration of the local feature of the each observation. In this paper, we propose an Adaptive Nearest Neighbors Classification(ANNC) as an alternative to KNNC. The proposed ANNC method adapts the number of neighbors according to the local feature of the observation such as density of data. To verify characteristics of ANNC, we compare the number of misclassified observation with KNNC by Monte Carlo study and confirm the potential performance of ANNC method.

• Journal of the Korean Statistical Society
• /
• v.4 no.1
• /
• pp.9-17
• /
• 1975

A, B 두 요인의 영향을 받고 있다고 생각되는 rc개 측정치가 있고 이것이 다음과 같이 $r\timesc$ 이차분류표로 정리되었다고 하자. 여기에서 $$y_{ij} = \mu + \alpha_i + \beta_j + \epsilon_{ij}$$ 와 같은 가법모형을 생각한다. 그리고 $\epsilon_{ij}$는 잔여항으로써 평균이 0, 분산이 $\sigma^2$인 정규분포를 한다고 가정하는 것이 보통이다. 또 이것은 모수모형인 경우 $E(y_{ij}) = \mu + \alpha_i + \beta_i, v(y_{ij}) = \sigma^2$임을 의미하는 것으로 생각된다. 그러나 자료에 따라서는 위에서와 같은 가법적 모형을 적용한다는 것이 적당하지 못한 경우가 있다.

• The Korean Journal of Applied Statistics
• /
• v.32 no.4
• /
• pp.593-605
• /
• 2019

Significant literature exists on the area under the ROC curve (AUC) and the volume under the ROC surface (VUS) which are statistical measures of the discriminant power of classification models. Whereas the partial AUC is restricted on the false positive rate, the two-way partial AUC is restricted on both the false positive rate and true positive rate, which could be more efficient and accurate than partial AUC. The two-way partial AUC was suggested as more efficient and accurate than the partial AUC. Partial VUS as well as the three-way partial VUS were also developed for the ROC surface. A proposed AUC is expressed in this paper with probability and integration using two truncated distribution functions restricted on both the false positive rate and true positive rate. It is also found that this AUC has a relation with the two-way partial AUC. The three-way partial VUS for the ROC surface is also related to the VUS using truncated distribution functions. These AUC and VUS are represented and estimated in terms of Mann-Whitney statistics. Their parametric and non-parametric estimation methods are explored based on normal distributions and random samples.

• The Korean Journal of Applied Statistics
• /
• v.23 no.6
• /
• pp.1093-1102
• /
• 2010

Even though the k-Nearest Neighbors Classification(KNNC) is one of the popular non-parametric classification methods, it does not consider the local features and class information for each observation. In order to overcome such limitations, several methods have been developed such as Adaptive Nearest Neighbors Classification(ANNC) and Modified k-Nearest Neighbors Classification(MKNNC). In this paper, we propose the Modified Adaptive Nearest Neighbors Classification(MANNC) that employs the advantages of both the ANNC and MKNNC. Through a real data analysis and a simulation study, we show that the proposed MANNC outperforms other methods in terms of classification accuracy.

• 한국노년학
• /
• v.37 no.3
• /
• pp.617-635
• /
• 2017

The aim of this study was to investigate both poverty and depression among older adults, focusing on the relationship of these two trajectories. For expanding the understanding about elderly poverty and depression, the study measured the longitudinal patterns of various transition in these two variables. The data for the study is 1st to 9th waves (2006-2014) of Korea Welfare Panel Study (KoWePS), and 4,431 older adults were used for the final analysis. For data analysis, Semi-parametric group-based modeling and Dual trajectory model were selected. The main results of this study were followings; First, The trajectory groups were identified: non-poverty, decrease poverty, increase poverty, remain high-poverty, chronic poverty groups and 4 trajectories of depression: stable, remain low-depression, risk of depression, chronic depression groups. Second, the study was tried to anticipate the longitudinal transition of poverty and depression status, and investigate the concurrent relationship in these two variables. It turned out that the stable poverty status led the stable depression, and vice versa. Based on these result, this study for elderly welfare were discussed to reduce risk for poverty and depression.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.319-319
• /
• 2018

최근 전 세계적으로 극한수문사상의 증가로 인한 피해의 규모와 빈도가 잦아지고 있다. 기후변화에 관한 정부 간 협의체(IPCC)5차 보고서에 따르면 우리나라는 모든 시나리오 하에서 평균 강수량이 증가하는 지역으로 분류되었다. 특히 강우와 태풍피해가 잦은 7월에서 9월의 강우량이 급격히 증가하는 것으로 나타나며 이는 현재보다 극한수문사상이 더욱 빈번하게 일어날 것이라 예상할 수 있다. 하지만 기존의 매개변수 추정방법은 이상치 산정기준을 넘어서는 극치를 제외하고 확률강우량을 산정하고 있는 실정이다. 따라서 본 연구에서는 이러한 기존의 매개변수 추정방법 보다 극한값에 강건한 MDPDE(minimum density power divergence estimator)를 이용한 매개변수 추정을 사용하여 우리나라 60개 강우관측소의 과거 강우관측자료에 대한 최적조율모수에 대한 빈도별 확률강우량을 추정하여 기존의 방법으로 산정한 확률강우량과 비교하였다. 이상치로 분류할 수 있는 극한수문사상이 발생한 우리나라 31개소에 대하여 MDPDE의 적용성을 검토한 결과 기존의 매개변수 추정방법에 비해 이상치를 포함한 100년 빈도 확률강우량이 약13.3% 감소하는 것으로 나타났다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.1
• /
• pp.21-31
• /
• 2002

This study applied each Neural Networks theory and Fuzzy Set theory to improve accuracy in remotely sensed images. Remotely sensed data have been used to map land cover. The accuracy is dependent on a range of factors related to the data set and methods used. Thus, the accuracy of maps derived from conventional supervised image classification techniques is a function of factors related to the training, allocation, and testing stages of the classification. Conventional image classification techniques assume that all the pixels within the image are pure. That is, that they represent an area of homogeneous cover of a single land-cover class. But, this assumption is often untenable with pixels of mixed land-cover composition abundant in an image. Mixed pixels are a major problem in land-cover mapping applications. For each pixel, the strengths of class membership derived in the classification may be related to its land-cover composition. Fuzzy classification techniques are the concept of a pixel having a degree of membership to all classes is fundamental to fuzzy-sets-based techniques. A major problem with the fuzzy-sets and probabilistic methods is that they are slow and computational demanding. For analyzing large data sets and rapid processing, alterative techniques are required. One particularly attractive approach is the use of artificial neural networks. These are non-parametric techniques which have been shown to generally be capable of classifying data as or more accurately than conventional classifiers. An artificial neural networks, once trained, may classify data extremely rapidly as the classification process may be reduced to the solution of a large number of extremely simple calculations which may be performed in parallel.

• Journal of the Korean Data and Information Science Society
• /
• v.12 no.2
• /
• pp.1-10
• /
• 2001

Neural networks we increasingly being seen as an addition to the statistics toolkit which should be considered alongside both classical and modern statistical methods. Neural networks are usually useful for classification and function estimation. In this paper we concentrate on function estimation using neural networks with weight decay factor The use of weight decay seems both to help the optimization process and to avoid overfitting. In this type of neural networks, the problem to decide the number of hidden nodes, weight decay parameter and iteration number of learning is very important. It is called the optimization of weight decay neural networks. In this paper we propose a automatic optimization based on genetic algorithms. Moreover, we compare the weight decay neural network automatically learned according to automatic optimization with ordinary neural network, projection pursuit regression and support vector machines.