• Journal of Korean Society of Transportation
• /
• v.36 no.2
• /
• pp.155-168
• /
• 2018

In this study, we studied the directional pattern of entering the intersection from the intersection upstream link prior to predicting short future (such as 5 or 10 minutes) intersection direction traffic volume on the interrupted flow, and examined the possibility of traffic volume prediction using traffic assignment model. The analysis method of this study is to investigate the similarity of patterns by performing cluster analysis with the ratio of traffic volume by intersection direction divided by 2 hours using taxi DTG (Digital Tachograph) data (1 week). Also, for linking with the result of the traffic assignment model, this study compares the impact area of 5 minutes or 10 minutes from the center of the intersection with the analysis result of taxi DTG data. To do this, we have developed an algorithm to set the impact area of intersection, using the taxi DTG data and traffic assignment model. As a result of the analysis, the intersection entry pattern of the taxi is grouped into 12, and the Cubic Clustering Criterion indicating the confidence level of clustering is 6.92. As a result of correlation analysis with the impact area of the traffic assignment model, the correlation coefficient for the impact area of 5 minutes was analyzed as 0.86, and significant results were obtained. However, it was analyzed that the correlation coefficient is slightly lowered to 0.69 in the impact area of 10 minutes from the center of the intersection, but this was due to insufficient accuracy of O/D (Origin/Destination) travel and network data. In future, if accuracy of traffic network and accuracy of O/D traffic by time are improved, it is expected that it will be able to utilize traffic volume data calculated from traffic assignment model when controlling traffic signals at intersections.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.18 no.6
• /
• pp.61-71
• /
• 2015

The objectives of this study are to construct an ecoregion map and to extract ecological factors from each ecoregion to adapt FLR (Forest Landscape Restoration) of North Korea. An ecological map was constructed by PCA(Principal Component Analysis) and MGC(Multivatiate Geographical Clustering). An ANOVA test verified the differences among ecoregions, and post-hoc pair wise comparisons were performed to determine similarities between them. Factor analysis was conducted to extract ecoregional characteristics. Ecoregions were distributed into clusters reflecting differences of south and north and of east and west of their ecological factors. About 12% of land area in North Korea shared similar ecological factors with South Korea, but the remaining 88% was found to be ecologically different. The ANOVA test showed a p-value of 0.000, indicating significant differences between the regions. Post-hoc pair wise comparisons indicated statistically significant similarities in annual mean temperature between ecoregion D and G, precipitation seasonality between ecoregion H and O, and precipitation of the warmest quarter between ecoregion K and O. Because ecoregion A and N showed same in their soil water contents, they were assumed that the dense of forest cover in the Southern ecoregion A is similar to that in the Northern ecoregion N of Korean peninsular. Based on the results of this study, it is necessary to accommodate quantitative and spatial based planning, when South Korea aids forest restoration projects in North Korea. In addition, it is recommended for both South and North Korea to share on Forest Landscape Restoration methodologies with each other.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.665-670
• /
• 2014

A SVM is a kind of binary classifier in order to find optimal hyperplane which separates training data into two groups. Due to its remarkable performance, the SVM is applied in various fields such as inductive inference, binary classification or making predictions. Also it is a representative black box model; there are plenty of actively discussed researches about analyzing trained SVM classifier. This paper conducts a study on a method that is automatically detecting the line-shaped echoes, sun strobe echo and radial interference echo, using the SVM algorithm because the line-shaped echoes appear relatively often and disturb weather forecasting process. Using a spatial clustering method and corrected reflectivity data in the weather radar, the training data is made up with mean reflectivity, size, appearance, centroid altitude and so forth. With actual occurrence cases of the line-shaped echoes, the trained SVM classifier is verified, and analyzed its characteristics using the decision tree method.

• Journal of the Economic Geographical Society of Korea
• /
• v.11 no.3
• /
• pp.492-507
• /
• 2008

Many classical network analysis methods approach networks in aspatial perspectives. Measuring network reliability and finding critical nodes in particular, the analyses consider only network connection topology ignoring spatial components in the network such as node attributes and edge distances. Using local network autocorrelation measure, this study handles the problem. By quantifying similarity or clustering of individual objects' attributes in space, local autocorrelation measures can indicate significance of individual nodes in a network. As an application, this study analyzed internet backbone networks in the United States using both classical disjoint product method and Getis-Ord local G statistics. In the process, two variables (population size and reliability) were applied as node attributes. The results showed that local network autocorrelation measures could provide local clusters of critical nodes enabling more empirical and realistic analysis particularly when research interests were local network ranges or impacts.

• Spatial Information Research
• /
• v.7 no.1
• /
• pp.1-12
• /
• 1999

The DTM(Digital Terrain Model) in GIS(Geographical Information System) shows the elevation from interpolation using data points surveyed. In panoramic flat landform, pixel size, resolution of source data may not be the problem in using DTM However, in mountainous landform like Korea, appropriate resolution accuracy of source data are important factors to represent the topography concerned. In this study, the difference in contour interval of source data, the resolution after interpolation, and different data structures were compared to figure out the accuracy of slope calculation using DTM from the topographic maps of Togyusan National Park Two types of GIS softwares, Idrisi(grid) ver. 2.0 using the altitude matrices and ArcView(TIN) ver. 3.0a using TIN were used for this purpose. After the analysis the conclusions are as follows: 1) The coarser resolution, the more smoothing effect inrepresenting the topography. 2) The coarser resolution the more difference between the grid-based Idrisi and the TIN-based ArcView. 3) Based on the comparison analysis of error for 30 points from clustering, there is not much difference among 10, 20, 30 m resolution in TIM-based Airview ranging from 4.9 to 6.2n However, the coarser resolution the more error for elevation and slope in the grid-based Idrisi. ranging from 6.3 to 10.9m. 4) Both Idrisi and ArcView could net consider breaklines of lanform like hilltops, valley bottoms.

• Korean Journal of Remote Sensing
• /
• v.31 no.2
• /
• pp.51-64
• /
• 2015

We improved the MODerate resolution Imaging Spectroradiometer (MODIS) land cover map over the Asia-Oceania region through the reclassification of the misclassified pixels. The misclassified pixels are defined where the number of land cover types are greater than 3 from the 12 years of MODIS land cover map. The ratio of misclassified pixels in this region amounts to 17.53%. The MODIS Normalized Difference Vegetation Index (NDVI) time series over the correctly classified pixels showed that continuous variation with time without noises. However, there are so many unreasonable fluctuations in the NDVI time series for the misclassified pixels. To improve the quality of input data for the reclassification, we corrected the MODIS NDVI using Correction based on Spatial and Temporal Continuity (CSaTC) developed by Cho and Suh (2013). Iterative Self-Organizing Data Analysis (ISODATA) was used for the clustering of NDVI data over the misclassified pixels and land cover types was determined based on the seasonal variation pattern of NDVI. The final land cover map was generated through the merging of correctly classified MODIS land cover map and reclassified land cover map. The validation results using the 138 ground truth data showed that the overall accuracy of classification is improved from 68% of original MODIS land cover map to 74% of reclassified land cover map.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.3
• /
• pp.89-101
• /
• 2015

Outbreaks of highly pathogenic avian influenza(HPAI) subtype H5N8 have occurred in Korea, January 2014 and it continued more than a year until 2015. And more than 5 million heads of poultry hads been damaged in 196 farms until May 2014. So, we studied the spatial, temporal and spatio-temporal patterns of the HPAI epidemics for understanding the propagation and diffusion characteristics of the 2014 HPAI. The results are expressed using GIS. Throughout the study period three epidemic waves occurred over the time. And outbreaks made three clusters in space. First spatial cluster is adjacent areas of province of Chungcheongbuk-do, Chungcheongnam-do and Gyeonggi -do. Second is Jeonlabuk-do Gomso Bay area. And the last is Naju and Yeongam in Jeollanam-do. Also, most of spatio-temporal clusters were formed in spatially high clustered areas. Especially, in Gomso Bay area space density and spatio-temporal density were concurrent. It means that the effective prevention activity for HPAI was carried out. But there are some exceptional areas such as Chungcheongbuk-do, Chungcheongnam-do, Gyeonggi-do adjacent area. In these areas the outbreak density was high in space but the spatio-temporal cluster was not formed. It means that the HPAI virus was continuing inflow over a long period.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.4
• /
• pp.175-181
• /
• 2014

Korean government proposed a new initiative 'government 3.0' with which the administration will open its dataset to the public before requests. City of Seoul is the front runner in disclosure of government data. If we know what kind of attributes are governing factors for any given segmentation, these outcomes can be applied to real world problems of marketing and business strategy, and administrative decision makings. However, with respect to city of Seoul, selection of optimal variables from the open dataset up to several thousands of attributes would require a humongous amount of computation time because it might require a combinatorial optimization while maximizing dissimilarity measures between clusters. In this study, we acquired 718 attribute dataset from Statistics Korea and conducted an analysis to select the most suitable variables, which differentiate Gangnam from other districts, using the Genetic algorithm and Dunn's index. Also, we utilized the Microsoft Azure cloud computing system to speed up the process time. As the result, the optimal 28 variables were finally selected, and the validation result showed that those 28 variables effectively group the Gangnam from other districts using the Ward's minimum variance and K-means algorithm.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.124-131
• /
• 2009

A reliable detection of regions in radiography is one of the most important task before the evaluation of defects on welded joints. The extracted features is to be classified into distinctive clusters for each segmented region. But conventional segmentation techniques give unsatisfactory results for this task due to the spatial superposition of intensity and low signal-to-ratio(SNR) in radiographic images. The usage of global or local processes not only provide the necessary noise resistance but also fail in classification of regions. In this paper, we presents an appropriate approach for segmentation of region-based indications in industrial Computed Radiography(CR) images. The geometric differences between welded and non-welded area which is generated on radiography as the representative regions(background, thickness, middle and welded region in steel tube image) have constructed the hierarchical structure. Although this structure is contaminated by noise, the scheme between regions can be selected by the help of local clustering based on distinctive geometric property of each region. Because of the geometric nature of the considered region and so that the region is selected layer by layer, and that the real class represents the boundary between regions, the vertical and horizontal clustering process in each layer must be judicious. In order to show the effectiveness of this approach, a comparative experiment of various segmentation method is performed on industrial steel tube CR images.

• Journal of the Korean association of regional geographers
• /
• v.7 no.3
• /
• pp.107-120
• /
• 2001

This study is concerned with providing a reliable procedure of calibrating a set of places specific distance parameters and with applying it to U.S. inter-State migration flows between 1985 and 1900. It attempts to conform to recent advances in quantitative geography that are characterized by an integration of ESDA(exploratory spatial data analysis) and local statistics. ESDA aims to detect the spatial clustering and heterogeneity by visualizing and exploring spatial patterns. A local statistic is defined as a statistically processed value given to each location as opposed to a global statistic that only captures an average trend across a whole study region. Whereas a global distance parameter estimates an averaged level of the friction of distance, place-specific distance parameters calibrate spatially varying effects of distance. It is presented that a poisson regression with an adequately specified design matrix yields a set of either origin-or destination-specific distance parameters. A case study demonstrates that the proposed model is a reliable device of measuring a spatial dimension of migration, and that place-specific distance parameters are spatially heterogeneous as well as spatially clustered.