• Journal of the Korean association of regional geographers
• /
• v.16 no.4
• /
• pp.428-439
• /
• 2010

Map of geographical names can give us information for understanding of region because geographical name reflects regional perception of human. This study aimed to make an web-based map by constructing database of geographical names. Main contents carried out research on methods for classification of geographical names, database construction, and mapping on the website. Geographical name classified into four categories of the physical geography, culture and historical geography, economic geography, and the other and also, 18 sub-categories by classification criteria. Geographical name designed to input by collecting geographical names from paper-based maps and vernacular place names only known to the local region. Fields of database consisted of address, coordinates, geographical name(hangeul, hanja), classification, explanation, photographs. Map of geographical names can be represented with regional geographical information. The result of research is expected to offer information for distribution of geographical names as well as regional interpretation.

• Journal of Korean Society for Geospatial Information Science
• /
• v.8 no.2 s.16
• /
• pp.23-33
• /
• 2000

On this study, Among the classification methods of land cover using satellite imagery, we compared the classification accuracy of Neural Network Classifier and that of Maximum Likelihood Classifier which has the characteristics of parametric and non-parametric classification method. In the assessment of classification accuracy, we analyzed the classification accuracy about testing area as well as training area that many analysts use generally when assess the classification accuracy. As a result, Neural Network Classifier is superior to Maximum Likelihood Classifier as much as 3% in the classification of training data. When ground reference data is used, we could get poor result from both of classification methods, but we could reach conclusion that the classification result of Neural Network Classifier is superior to the classification result of Maximum Likelihood Classifier as much as 10%.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.2001-2005
• /
• 2006

우리나라는 매년 집중호우로 인한 산사태로 인해 인적, 물질적 피해를 일으킨다. 반복적인 산사태의 피해를 방지 하기위해서는 산사태 예측 시스템이 필요하다. 본 연구에서는 안성시를 대상으로 GIS와 RS 자료를 활용하여 산사태 위험지를 분석하고자 Logistic 회귀분석 방법과 AHP 기법을 이용하였다. Logistic 회귀분석과 AHP 기법에는 6개의 인자(경사, 경사향, 고도, 토양배수, 토심, 토지이용)를 사용하여, 7등급으로 산사태 위험도를 분류하였다. Logistic 회귀분석 방법과 AHP 기법을 이용한 산사태 위험지도를 표본 자료와 비교하면 산사태가 발생한 표본에서 산사태 위험성이 높은(1-2등급)지역이 Logistic 회귀분석에서는 46.1% AHP 기법은 48.7%로 분류되어 AHP 기법이 분류도가 높다고 분석 되었다. 하지만 Logistic 회귀분석과 AHP 기법은 서로 분석 과정의 차이를 가지고 있기 때문에 Logistic 회귀분석과 AHP기법을 적용한 결과에 동일 가중치를 부여한 후 7개 등급으로 재분류(reclass)하여 산사태 위험지역을 추출 할 수 있는 방법론을 제시하였다. 그 결과 산사태가 발생한 표본에서 1-2등급지역이 58.9%로 분석되어 분류정확도를 높일 수 있었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.1
• /
• pp.81-86
• /
• 2012

In this paper, we proposed a new design methodology of a pattern classification rule based on the local linear discriminant analysis expanded from the generic linear discriminant analysis which is used in the local area divided from the whole input space. There are two ways such as k-Means clustering method and the differential evolutionary algorithm to partition the whole input space into the several local areas. K-Means clustering method is the one of the unsupervised clustering methods and the differential evolutionary algorithm is the one of the optimization algorithms. In addition, the experimental application covers a comparative analysis including several previously commonly encountered methods.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1D
• /
• pp.149-156
• /
• 2006

Existing method of landuse classification using aerial photographs or field survey requires relatively higher amount of time and cost due to necessary manual work. Especially in urban area where the pattern of landuse is densely aggregated, a landuse classification using satellite image is more complex. In this background, this study proposes a landuse classification method to utilize 1:1,000 digital topographic data and IKONOS satellite image. To prove the possibility of this method, the method was applied to Seoul metropolitan area. The results shows the total accuracy of approximately 95% and 14 landuse classes extracted. Based on the results from the pilot study, this method is applicable to landuse classification in urban area.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.2
• /
• pp.135-139
• /
• 2009

We present a new ensemble learning method that employs the set of region experts, each of which learns to handle a subset of the training data. We split the training data and generate experts for different regions in the feature space. When classifying a data, we apply a weighted voting among the experts that include the data in their region. We used ten datasets to compare the performance of our new ensemble method with that of single classifiers as well as other ensemble methods such as Bagging and Adaboost. We used SMO, Naive Bayes and C4.5 as base learning algorithms. As a result, we found that the performance of our method is comparable to that of Adaboost and Bagging when the base learner is C4.5. In the remaining cases, our method outperformed the benchmark methods.

• Journal of Korean Society for Geospatial Information Science
• /
• v.8 no.2 s.16
• /
• pp.47-60
• /
• 2000

On this study, Among the classification methods of land cover using satellite imagery, we compared the classification accuracy of Neural Network Classifier and that of Maximum Likelihood Classifier which has the characteristics of parametric and non-parametric classification method. In the assessment of classification accuracy, we analyzed the classification accuracy about testing area as well as training area that many analysts use generally when assess the classification accuracy. As a result, Neural Network Classifier is superior to Maximum Likelihood Classifier as much as 3% in the classification of training data. When ground reference data is used, we could get poor result from both of classification methods, but we could reach conclusion that the classification result of Neural Network Classifier is superior to the classification result of Maximum Likelihood Classifier as much as 10%.

• Journal of the Korean Geographical Society
• /
• v.50 no.5
• /
• pp.485-503
• /
• 2015

This study aims at evaluating geomorphological classification systems to predict the occurrence of landslides in mountainous region in Korea. Geomorphological classification systems used in this study are Catena, TPI, and Geomorphons. Study sites are Gapyeong-gun, Hoengseong-gun, Gimcheon-si, Yeoju-si/Yicheon-si in which landslide occurrence data were collected by local governments from 2001-2014. Catena method has objective classification standard to compare among regions objectively and understand the result intuitively. However, its procedure is complicated and hard to be automated for the general public to use it. Both TPI and Geomorphons have simple procedure and GIS-extension, therefore it has high accessibility. However, the results of both systems are highly dependent on the scale, and have low relevance to geomorphological formation process because focusing on shape of terrain. Three systems have low compatibility, therefore unified concept are required for broad use of landform classification. To assess the effectiveness of prediction on landslide by each geomorphological classification system, 50% of geomorphological classes with higher landslide occurrence are selected and the total landslide occurrence in selected classes are calculated and defined as 'predictive ability'. The ratio of terrain categorized by 'predictive ability' to whole region is defined as 'vulnerable area ratio'. An indicator to compare three systems which is predictive ability divided by vulnerable area ratio was developed to make a comprehensive judgment. As a result, Catena ranked the highest in suitability.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.5 no.1
• /
• pp.27-37
• /
• 2002

The classification accuracy of land cover has been considered as one of the major issues to estimate pollution loads generated from diffuse landuse patterns in a watershed. This research aimed to assess the effects of the acquisition methods and sampling size of training reference data on the classification accuracy of land cover using an imagery acquired by optical sensor(OPS) on JERS-1. Two kinds of data acquisition methods were considered to prepare training data. The first was to assign a certain land cover type to a specific pixel based on the researchers subjective discriminating capacity about current land use and the second was attributed to an aerial photograph incorporated with digital maps with GIS. Three different sizes of samples, 0.3%, 0.5%, and 1.0% of all pixels, were applied to examine the consistency of the classified land cover with the training data of corresponding pixels. Maximum likelihood scheme was applied to classify the land use patterns of JERS-1 imagery. Classification run applying an aerial photograph achieved 18 % higher consistency with the training data than the run applying the researchers subjective discriminating capacity. Regarding the sample size, it was proposed that the size of training area should be selected at least over 1% of all of the pixels in the study area in order to obtain the accuracy with 95% for JERS-1 satellite imagery on a typical small-to-medium-size urbanized area.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.11a
• /
• pp.69-70
• /
• 2014

연안지역에 대한 항공 하이퍼스펙트럴 영상으로부터 객체기반 분류방법을 이용하여 토지피복분류를 수행하고 기존에 주로 사용되어온 화소기반 분류기법에 의한 결과와 비교하였으며, 생성된 토지피복도로부터 해륙경계선인 수애선벡터를 용이하게 추출하는 방법을 제시하였다.