• 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%.

• 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.

• 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%.

• Korean Journal of Remote Sensing
• /
• v.29 no.1
• /
• pp.1-9
• /
• 2013

To classify the landfast ice in the north of the Greenland, observation data, multifrequency Synthetic Aperture Radar (SAR) images and texture images were used. The total four types of sea ice are first year ice, highly deformed ice, ridge and moderately deformed ice. The texture images that were processed by K-means algorithm showed higher accuracy than the ones that were processed by SAR images; however, overall accuracy of maximum likelihood algorithm using texture images did not show the highest accuracy all the time. It turned out that when using K-means algorithm, the accuracy of the multi SAR images were higher than the single SAR image. When using the maximum likelihood algorithm, the results of single and multi SAR images are differ from each other, therefore, maximum likelihood algorithm method should be used properly.

• Journal of the Korean Geographical Society
• /
• v.39 no.5 s.104
• /
• pp.786-803
• /
• 2004

These days, interests on land cover classification using not only multi-sensor data but also thematic GIS information, are increasing. Often, although we have useful GIS information for the classification, the traditional classification method like maximum likelihood estimation technique (MLE) does not allow us to use the information due to the fact that the MLE and the existing computer programs cannot handle GIS data properly. We proposed a new method for updating the image classification using multi-spectral and multi-temporal images. In this study, we have simultaneously extended the MLE to accommodate both multi-spectral images data and land cover data for land cover classification. In addition to the extended MLE method, we also have extended the empirical likelihood ratio estimation technique (LRE), which is one of non-parametric techniques, to handle simultaneously both multi-spectral images data and land cover data. The proposed procedures were evaluated using land cover map based on Landsat ETM+ images in the Anmyeon-do area in South Korea. As a result, the proposed methods showed considerable improvements in classification accuracy when compared with other single-spectral data. Improved classification images showed that the overall accuracy indicated an improvement in classification accuracy of $6.2\%$ when using MLE, and $9.2\%$ for the LRE, respectively. The case study also showed that the proposed methods enable the extraction of the area with land cover change. In conclusion, land cover classification produced through the combination of various GIS spatial data and multi-spectral images will be useful to involve complementary data to make more accurate decisions.

• Korean Journal of Remote Sensing
• /
• v.19 no.4
• /
• pp.329-339
• /
• 2003

In this study, an approach of image fusion in decision level has been proposed for unsupervised image classification using the images acquired from multiple sensors with different characteristics. The proposed method applies separately for each sensor the unsupervised image classification scheme based on spatial region growing segmentation, which makes use of hierarchical clustering, and computes iteratively the maximum likelihood estimates of fuzzy class vectors for the segmented regions by EM(expected maximization) algorithm. The fuzzy class vector is considered as an indicator vector whose elements represent the probabilities that the region belongs to the classes existed. Then, it combines the classification results of each sensor using the fuzzy class vectors. This approach does not require such a high precision in spatial coregistration between the images of different sensors as the image fusion scheme of pixel level does. In this study, the proposed method has been applied to multispectral SPOT and AIRSAR data observed over north-eastern area of Jeollabuk-do, and the experimental results show that it provides more correct information for the classification than the scheme using an augmented vector technique, which is the most conventional approach of image fusion in pixel level.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.2_2
• /
• pp.173-180
• /
• 2020

In Korea, due to the rapid increase in population due to industrialization, rivers were developed and managed with a focus on the completion and dimension of rivers. Due to the rapid increase in river use, there are so many river facilities indiscriminately that the administrative and management tasks are complicated and diversified in computerizing facilities and hydrologic data. Many methods have been proposed to solve this problem, but many problems exist. Among them, water has the same spectral characteristics, so it is difficult to subdivide into rivers, reservoirs, and dams. Therefore, this study subdivided the water system using supervised classification and GIS in order to efficiently manage the water resources by classifying the water system with the same spectral characteristics. In order to analyze the accuracy of the results, the accuracy of the objects classified using land cover map provided by environmental spatial information service was evaluated, and the result was an average of 91.75%, with 97.50% of rivers, 87.76% of reservoirs, and 90.00% of others.

• Korean Journal of Remote Sensing
• /
• v.13 no.1
• /
• pp.47-56
• /
• 1997

In this paper, remote sensing is used to estimate trophic state which is primary concern in a lake. In using remote sensing, this study estimated trophic state not with conventional method such as regression equations but with classification methods. As europhication is caused by the extraodinary proliferation of the algae, chlorophyll a and transparency are applied to remote sensing data.. Maximum Likelihood Classification and Minimum Distance Classification which are kinds of classification methods enabled trophic state to be confirmed in a lake. These are obtained as the result of applying remote sensing to classify trophic state in a lake. Firest, when we evaluate tropic state in a large area of water body, the application of remote sensing data can obtain more than 70% accuracies just in using basic classification methods. Second, in the aspect of classification, the accuracy of Minimum Distance Classification is usually better than that of Maximum Likelihood Classification. This result is caused that samples have normal distribution, but their numbers are a few to apply statistical method. Therefore, classification method is required such as artificial neural networks which are not influenced by statistical distribution. Third, this study enables the trophic state of water body to be analyzed and evaluated rapidly, periodically and visibly. Also, this study is good for forming proper countermeasure accompanying with trophic state progress extent in a lake and is useful for basic-data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.11 no.1
• /
• pp.55-60
• /
• 1993

Forest occupied a part of natural ecosystem carries out a role of purifying air, preserving water resource, prevention of the breeding and extermination, recreation areas and etc that preserve and for me one's living environment. In this study, the classification for management of this forest is performed with Landsat TM Image. The classes are decided needle-leaf trees, broad-leaf trees, farming land and grass land, and water. When the TM digital images are classified on computer, water is represented in 7∼13 D.N. of 4th band. But the others is appeared similar mostly specific values so that must be done image processing. When the images compounded 2ed band and 3ed band are processed with ratio of enhancement. Needle-leaf treas is represented in l18∼136 D.N. of 1st band, broad-leaf trees in 72∼91 D.N. of 3ed band, farm land and glass land in 96∼120 of 3ed band. Forest Information is classified with M.L.C, an image classification method. The errors of needle-leaf trees, broad-leaf trees, farm land and grass land, and water are appeared each －7.43, ＋1.89,＋7.58 and －2.04 as compared the digital image with investigation on the scene. Finally, these results are useful for classification of forest vegetation with Landsat TM Image.

• Clinical and Experimental Pediatrics
• /
• v.46 no.8
• /
• pp.758-762
• /
• 2003

Purpose : Our examination was designed to determine the diagnostic properties of the cutoff point for the prediction of bacteremia in febrile children less than 3 years of age. Cutoff point is the value that simultaneously maximizes both sensitivity and specificity. Methods : We conducted a retrospective study of febrile children, less than 3 years of age, who clinically have no identifiable source of fever. Peripheral blood leukocyte count(WBC), absolute neutrophil count(ANC), erythrocyte sedimentation rate(ESR) and C-reactive protein(CRP) were measured at the same time. All patients received blood culture, urine culture and/or CSF culture. Bacterial infection was defined as single pathogen isolated from the CSF or blood or a urinary tract infection (UTI). Patients were dichotomized into two groups : those with bacterial infection and no bacterial infection. We analyzed the characteristics of the children in the two groups. Results : Seventy-one patients(44 males; 27 females) were enrolled in the study. Twenty patients (28%) had a serious bacterial infection(twelve urinary tract infection, five bacteremia, three meningitis) and fifty-one(72%) had no serious bacterial infection. WBC, ESR and CRP were significantly different between the two groups(P<0.05). The cutoff point of WBC, ESR and CRP were $20,000/mm^3$, 30 mm/hr and 3.0 mg/dL, respectively. The sensitivity and specificity of each cutoff point were WBC(75%, 75%), ESR(79%, 68%) and CRP(83%, 77%), respectively. Conclusion : These data show the ability of predictors to identify febrile children less than 3 years of age with bacterial infection. Febrile children who reach the cutoff point must be treated intensively and those who do not reach the cutoff point can be carefully managed without administering antimicrobial agents.