• Korean Journal of Remote Sensing
• /
• v.37 no.4
• /
• pp.763-776
• /
• 2021

This paper introduces a method of selecting priority update areas for subdivided land cover maps by training orthoimages and serial cadastral maps in a deep learning model. For the experiment, orthoimages and serial cadastral maps were obtained from the National Spatial Data Infrastructure Portal. Based on the VGG-16 model, 51,470 images were trained on 33 subdivided classifications within the experimental area and an accuracy evaluation was conducted. The overall accuracy was 61.42%. In addition, using the differences in the classification prediction probability of the misclassified polygon and the cosine similarity that numerically expresses the similarity of the land category features with the original subdivided land cover class, the cases were classified and the areas in which the boundary setting was incorrect and in which the image itself was determined to have a problem were identified as the priority update polygons that should be checked by operators.

• International journal of advanced smart convergence
• /
• v.12 no.1
• /
• pp.92-100
• /
• 2023

Wireless communication technology is becoming increasingly prevalent in smart factories, but the rise in the number of wireless devices can lead to interference in the ISM band and obstacles like metal blocks within the factory can weaken communication signals, creating radio shadow areas that impede information exchange. Consequently, accurately determining the radio communication coverage range is crucial. To address this issue, a Radio Environment Map (REM) can be used to provide information about the radio environment in a specific area. In this paper, a technique for estimating an indoor REM usinga mobile robot and machine learning methods is introduced. The mobile robot first collects and processes data, including the Received Signal Strength Indicator (RSSI) and location estimation. This data is then used to implement the REM through machine learning regression algorithms such as Extra Tree Regressor, Random Forest Regressor, and Decision Tree Regressor. Furthermore, the numerical and visual performance of REM for each model can be assessed in terms of R2 and Root Mean Square Error (RMSE).

• Korean Journal of Environment and Ecology
• /
• v.32 no.6
• /
• pp.686-697
• /
• 2018

Due to the advance in remote sensing technology, it has become easier to more frequently obtain high resolution imagery to detect delicate changes in an extensive area, particularly including forest which is not readily sub-classified. Time-series analysis on high resolution images requires to collect extensive amount of ground truth data. In this study, the potential of land coverage mapas ground truth data was tested in classifying high-resolution imagery. The study site was Wonju-si at Gangwon-do, South Korea, having a mix of urban and natural areas. KOMPSAT-3A imagery taken on March 2015 and land coverage map published in 2017 were used as source data. Two pixel-based classification algorithms, Support Vector Machine (SVM) and Random Forest (RF), were selected for the analysis. Forest only classification was compared with that of the whole study area except wetland. Confusion matrixes from the classification presented that overall accuracies for both the targets were higher in RF algorithm than in SVM. While the overall accuracy in the forest only analysis by RF algorithm was higher by 18.3% than SVM, in the case of the whole region analysis, the difference was relatively smaller by 5.5%. For the SVM algorithm, adding the Majority analysis process indicated a marginal improvement of about 1% than the normal SVM analysis. It was found that the RF algorithm was more effective to identify the broad-leaved forest within the forest, but for the other classes the SVM algorithm was more effective. As the two pixel-based classification algorithms were tested here, it is expected that future classification will improve the overall accuracy and the reliability by introducing a time-series analysis and an object-based algorithm. It is considered that this approach will contribute to improving a large-scale land planning by providing an effective land classification method on higher spatial and temporal scales.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.18 no.6
• /
• pp.167-177
• /
• 2015

This study was conducted to establish an inventory and propose conservation strategies for 'village wetlands' in Asan city, Korea, using GIS. As results, the village wetlands are defined as such places as 'palustrine' wetland, village embankment, agricultural reservoir or small reservoirs located in or near the village and related to everyday life or farming. Firstly 807 provisional village wetlands(draft) were identified in Asan by using Arc-GIS 10.1, then 196 wetlands(final) were defined finally as village wetlands and listed the inventory of Asan Village Wetlands after being validated through office works and field survey. The office works analyzed minimum area(greater than $625m^2$), satellite images, the Korea Land Information System, land use map and land coverage map. To evaluate the function and conservation values, the 37 wetlands were selected for detailed surveying and function assessment based on the following criteria : 1) doubled code both wetland and reservoir at digital map, 2) located less than 100m from village and 3) ecologically connected to such ecological resources as seaside mudflats, mountains and green area and ecological passages for small size wildlifes. As the result of the wetland function assessments by the RAM method, 7 wetlands were found to have 'high' wetland function (conservation) 18 wetlands were 'medium' (enhancement) and 12 wetlands were 'low' (restoration or enhancement). Enhancing biodiversity and ecosystem services through ecological management of wetlands in Asan and connecting with the Ecological Natural Degree were proposed.

• Journal of Korean Society for Geospatial Information Science
• /
• v.9 no.1 s.17
• /
• pp.19-25
• /
• 2001

Satellite remote sensing, with its synoptic coverage, is used to evaluate the trophic state of large reservoir for agriculture in Kum River basin. The prediction model for chlorophyll-${\alpha}$ which was derived from Daecheong reservoir was applied to four LANDSAT TM imageries to generate a distribution map of trophic state. The chlorophyll-${\alpha}$ model was found to be reasonably reliable predictors for average trophic state value of reservoir. LANDSAT TM imagery data appears to have great utility in assessing trophic state of reservoir.

• Journal of Environmental Impact Assessment
• /
• v.17 no.4
• /
• pp.255-262
• /
• 2008

For the Han-river estuary and DMZ where white-naped crane (Grus vipio; endangered migratory bird) stopover or spend winter, the habitat composition and the habitat use pattern of white-naped crane were analyzed with the position data obtained by the satellite tracking method. By the use of geographic information system (GIS), the percent composition of seven habitat categories of white naped-crane data points (n=228) was analyzed. The chi-square test showed that the white-naped crane habitat use pattern was significantly different (p<0.05) from that of random points (n=228). It means that white-naped crane select and use particular habitat area in the Han-river estuary and DMZ.

• Economic and Environmental Geology
• /
• v.33 no.2
• /
• pp.129-138
• /
• 2000

The various types of geohazards like landslides resulted from civil construction (i.e. highway construction) must of analysed considering all the possible influential factor systematically. Thus, by using GIS, slope stability can be evaluated, and it can be used as a data for further detailed investigation. So the aim of this study is to present a data for decision making in selecting suitable point for remediation. For analysing slope instability, through appropriate definition and classification, landslide mechanism must be understood. In building GIS model, the selection of appropriate factors and their rating system should be made. For this, the characteristics and the mechanism of landslide have to be understood. And suitable coverage should be chosen for the model considering the slope conditions. In this study, field investigation in lst and 2nd Section, Chung-ang highway was carried out. From the field data, GIS model on slope instability was created. 5 coverages were used for it. From the result of this study, 12 unstable sections were found out and more detailed investigation is needed there.

• Plant Resources
• /
• v.5 no.1
• /
• pp.7-16
• /
• 2002

The purposes of this study were to clarify of floristic composition and the landscape structure on the habitats of each Ranunculus plant, which were distributed in Daejeon, Korea. Three taxa were distributed and investigated in this study. Floristic composition of habitats were organized by living in flatten open space needed a lot of sunlight and humidity species. Landscape ecological structure of habitats were defined by soils of coarse loamy and loamy skeletal, slope of under 15$^{\circ}$, under the (five percent of woody coverage at 100-300m above the sea levels. Distribution patterns of Ranunculus plants in Daejeon were presented on the 1km X 1km grid map.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.2
• /
• pp.170-179
• /
• 2007

This paper introduces the optimal disposition of direction finder using EM(Electro-magnetic) wave propagation analysis which is based on LR(Longley-Rice) propagation model and the characteristics of direction finder, emitter and terrain. Initial model is simulated and modified to minimize propagation error as a result of the field trials. Proposed analysis used line-of-sight analysis and mountain-top extraction algorithm to optimize the disposition in the assigned area and the result can be displayed in the 3D map in order of the percentage coverage for direction finding possibility area.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.2
• /
• pp.105-110
• /
• 2002

For the accuracy assessment of DTM obtained by Airborne Laser Mapping Systems (ALMS), we selected 500 m spaced test points and analyze the accuracy of the DTM by various methods including GPS survey. To estimate the height at the point in between the test points of the DTM we produced a TIN, and to analyze the accuracy we use a GPS coverage map overlaid with the TIN. Compared with the existing method, DTM by ALMS is shown to be relatively accurate, and therefore, ALMS is applicable to 1/5000 digital terrain mapping.