• The Journal of Korean Association of Computer Education
• /
• v.17 no.6
• /
• pp.103-113
• /
• 2014

This study designed and implemented a query model for consecutive analyses of dynamic multivariate graph data. First, the query model consists of two procedures; setting the discriminant function, and determining an alteration method. Second, the query model was implemented as a query system that consists of a query panel, a graph visualization panel, and a property panel. A Node-Link Diagram and the Force-Directed Graph Drawing algorithm were used for the visualization of the graph. The results of the queries are visually presented through the graph visualization panel. Finally, this study used the data of worldwide import & export data of small arms to verify our model. The significance of this research is in the fact that, through the model which is able to conduct consecutive analyses on dynamic graph data, it helps overcome the limitations of previous models which can only perform discrete analysis on dynamic data. This research is expected to contribute to future studies such as online decision making and complex network analysis, that use dynamic graph models.

• The Korean Journal of Applied Statistics
• /
• v.8 no.1
• /
• pp.61-74
• /
• 1995

These days, many kinds of graphical methods have been developed, and it is possible to get information directly from data. Especially, R-code (Cook and Weisberg, 1994) make it possible to draw various kinds of two and three dimensional plots, and to rotate the axis of the plots. But the maximum dimensional of the plot is three, so we can not draw plot of one response variable with more than three explanatory variables. Li(1991, 1992) has developed a method to reduce the dimension of the explanatory variables, so it is possible to draw lower dimensional plots to get information of the full explanatory variables. One of the dimension reduction method developed by Li is pHd. In this paper, we have tried to apply the pHd method for the model with multivariate response.

• Communications for Statistical Applications and Methods
• /
• v.15 no.1
• /
• pp.65-76
• /
• 2008

Biplots are the multivariate analogue of scatter plots. They approximate the multivariate distribution of a sample in a few dimensions, typically two, and they superimpose on this display representations of the variables on which the samples are measured(Gower and Hand, 1996, Chapter 1). And the relationships between the observations and variables can be easily seen. Thus, biplots are useful for giving a graphical description of the data. However, this method does not give some concise interpretations between variables and observations when the number of observations are large. Therefore, in this study, we will suggest to interpret the biplot analysis by applying the K-means clustering analysis. It shows that the relationships between the clusters and variables can be easily interpreted. So, this method is more useful for giving a graphical description of the data than using raw data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.37-40
• /
• 2024

본 연구에서는 웨어러블 디바이스로부터 수집된 다변량 반려동물 행동 데이터를 처리하기 위해, GCN(Graph Convolutional Network)과 GRU(Gated Recurrent Unit)를 결합한 모델을 제안한다. 제안된 모델은 시계열 내부 구조를 활용하여 그래프 구조로 변환하고, DTW(Dynamic Time Warping) 유사도 분석을 통해 노드 간의 시간적 유사도를 기반으로 엣지를 생성한다. 실험결과로 DTW 기반 엣지 생성 방식이 유클리드 거리 및 선형 방식에 비해 더 높은 성능을 나타냈다. 본 연구는 반려동물의 행동을 정확히 분류하기 위한 효과적인 방법론을 제공한다.

• Resources Recycling
• /
• v.27 no.1
• /
• pp.84-91
• /
• 2018

In this study, a novel soft information based most probable classification scheme is proposed for sorting recyclable metal alloys with laser induced breakdown spectroscopy (LIBS). Regression analysis with LIBS captured spectrums for estimating concentrations of common elements can be efficient for classifying unknown arbitrary metal alloys, even when that particular alloy is not included for training. Therefore, partial least square regression (PLSR) is employed in the proposed scheme, where spectrums of the certified reference materials (CRMs) are used for training. With the PLSR model, the concentrations of the test spectrum are estimated independently and are compared to those of CRMs for finding out the most probable class. Then, joint soft information can be obtained by assuming multi-variate normal (MVN) distribution, which enables to account the probability measure or a prior information and improves classification performance. For evaluating the proposed schemes, MVN soft information is evaluated based on PLSR of LIBS captured spectrums of 9 metal CRMs, and tested for classifying unknown metal alloys. Furthermore, the likelihood is evaluated with the radar chart to effectively visualize and search the most probable class among the candidates. By the leave-one-out cross validation tests, the proposed scheme is not only showing improved classification accuracies but also helpful for adaptive post-processing to correct the mis-classifications.

• The Korean Journal of Applied Statistics
• /
• v.13 no.2
• /
• pp.297-306
• /
• 2000

Many users have made the most often use of the SAS system in statistical data analysis all over the world. But it is difficult to use the grand procedures and language of the SAS system. Therefore the side of program development has changed in the graphic-oriented and menu-centered way like SASj ASSIST, SASjINSICHT after a version 6.08 turned into the Window environment. A biplots is a multivariate data analysis technique that graphically describes both relationships among the multidimensional observations and relationships among the variables. But there were not the procedure and graphic interface for a biplots algorithm in the SAS system. In this paper, there are two objects. First, we supply users with the convenience of the environment of CLI, which is constructed with SASj AF and SCL, to solve the problem that we have programed a biplots algorithm with the SASjIML one by one. Second, we reflect the current of the Information Age which means the spread of various kinds of system construction to extract useful information from data with the help of the development of hardware and software.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.889-899
• /
• 2017

Independent component analysis is a multivariate approach to separate mixed signals into original signals. It is the most widely used method of blind source separation technique. ICA uses linear transformations such as principal component analysis and factor analysis, but differs in that ICA requires statistical independence and non-Gaussian assumptions of original signals. PCA have a natural ordering based on cumulative proportion of explained variance; howerver, ICA algorithms cannot identify the unique optimal ordering of the components. It is meaningful to set order because major components can be used for further analysis such as clustering and low-dimensional graphs. In this paper, we compare the performance of several criteria to determine the order of the components. Kurtosis, absolute value of kurtosis, negentropy, Kolmogorov-Smirnov statistic and sum of squared coefficients are considered. The criteria are evaluated by their ability to classify known groups. Two types of data are analyzed for illustration.

• Environmental and Resource Economics Review
• /
• v.20 no.3
• /
• pp.531-565
• /
• 2011

All previous studies analyzing multivariate time series data of EUA (European Union Allowance) price commonly used endogenous variables within the four variables and included the period from April to June of 2006 in the analysis, when the price distortion occurred. This study uses graph theory and structural vector error correction model (SVECM) to analyze the daily time series data of the EUA (European Union Allowance) price. As endogenous variables, five variables are considered for the analysis, including prices of crude oil, natural gas, electricity and coal in addition to carbon price. Data period is Phase 2 period (April 21, 2008 to March 31, 2010) to avoid the EUA price distortion of Phase 1 period (2005~2007). Further, the monthly data including the economic variables as endogenous variables are analyzed.

• The Korean Journal of Applied Statistics
• /
• v.28 no.6
• /
• pp.1171-1180
• /
• 2015

Multidimensional scaling (MDS) is a graphical technique of multivariate analysis to display dissimilarities among individuals into low-dimensional space. We often have two kinds of MDS which are metric MDS and non-metric MDS. Metric MDS can be applied to quantitative data; however, we need additional information about variables because it only shows relationships among individuals. Gower (1992) proposed a method that can represent variable information using trajectories of the pseudo-points for quantitative variables on the metric MDS space. We will call his method a 'replacement method'. However, the trajectory can not be represented even though metric MDS can be applied to binary data when we apply his method to binary data. Therefore, we propose a method to represent information of binary variables using pseudo-points called a 'partition method'. The proposed method partitions pseudo-points, accounting both the rate of zeroes and ones. Our metric MDS using the proposed partition method can show the relationship between individuals and variables for binary data.

• Korean Journal of Ichthyology
• /
• v.30 no.4
• /
• pp.224-231
• /
• 2018

Dietary niches can support the coexistence of sympatric species in marine ecosystems, which can lead to the presence of greater abundances of those species. Stomach contents of silver croaker (Pennahia argentata) and Japanese sillago (Sillago japonica) inhabiting the Nakdong River estuary, Korea were analyzed to determine diet compositions and the presence of any size-related and inter-specific feeding relationships. These species were bottom-feeding predators that consumed mainly benthic crustaceans and mollusks, but polychaetes were also important in the S. japonica diets. Non-metric multidimensional scaling (nMDS) ordination and multivariate analyses based on weight contributions of the different prey taxa to stomach contents revealed significant inter-specific dietary differences. Size-related change was also significant for P. argentata diets, but not for S. japonica. Canonical analysis of principal coordinate (CAP) ordination plot further demonstrated that differences in the type and range of prey ingested by the two species contributed such an inter-specific difference in the diet compositions. The results from this study provide clear evidence of niche segregation between co-occurring P. argentata and S. japonica in the Nakdong River estuary, which would reduce the likelihood of inter-specific competition for food resources.