• Korean Journal of Remote Sensing
• /
• v.30 no.2
• /
• pp.207-218
• /
• 2014

The information on the land cover along stream corridor is important for stream restoration and maintenance activities. This study aims to review the different classification methods for mapping the status of stream corridors in Seom River using airborne RGB and CIR digital ortho imagery with a ground pixel resolution of 0.2m. The maximum likelihood classification, minimum distance classification, parallelepiped classification, mahalanobis distance classification algorithms were performed with regard to the improvement methods, the skewed data for training classifiers and filtering technique. From these results follows that, in aerial image classification, Maximum likelihood classification gave results the highest classification accuracy and the CIR image showed comparatively high precision.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.271-280
• /
• 1999

The topographical effect resulted from rugged terrains and inhomogeneous spectral characteristics due to the complexly mixed land cover condition of Korea substantially lower the remotely sensed land cover classification accuracy In this study, a topographic correction method using digital elevation model to alleviate the topographic effects. To deal with inhomogeneous spectral characteristic, a hybrid classifier with inclusion of prior probabilities was introduced. This investigation concluded that the topographical normalization and hybrid classification with prior probabilities are effective on rugged landscape. The overall and average classification accuracies were improved by 0.92％ and 1.016％ respectively. The most substantial and noticeable accuracy improvement was observed in forest areas.

• Communications for Statistical Applications and Methods
• /
• v.24 no.6
• /
• pp.543-559
• /
• 2017

Tree-based regression and classification ensembles form a standard part of the data-science toolkit. Many commonly used methods take an algorithmic view, proposing greedy methods for constructing decision trees; examples include the classification and regression trees algorithm, boosted decision trees, and random forests. Recent history has seen a surge of interest in Bayesian techniques for constructing decision tree ensembles, with these methods frequently outperforming their algorithmic counterparts. The goal of this article is to survey the landscape surrounding Bayesian decision tree methods, and to discuss recent modeling and computational developments. We provide connections between Bayesian tree-based methods and existing machine learning techniques, and outline several recent theoretical developments establishing frequentist consistency and rates of convergence for the posterior distribution. The methodology we present is applicable for a wide variety of statistical tasks including regression, classification, modeling of count data, and many others. We illustrate the methodology on both simulated and real datasets.

• International journal of advanced smart convergence
• /
• v.10 no.1
• /
• pp.216-224
• /
• 2021

Aim of this research was to classify forest types at Wando in Jeonnam Province and develop warm temperate forest management system with application of Remote Sensing and GIS. Another emphasis was given to the analysis of satellite images to compare forest type changes over 10 year periods from 2009 to 2019. We have accomplished this study by using ArcGIS Pro and ENVI. For this research, Landsat satellite images were obtained by means of terrestrial, airborne and satellite imagery. Based on the field survey data, all land uses and forest types were divided into 5 forest classes; Evergreen broad-leaved forest, Evergreen Coniferous forest, Deciduous broad-leaved forest, Mixed fores, and others. Supervised classification was carried out with a random forest classifier based on manually collected training polygons in ROI. Accuracy assessment of the different forest types and land-cover classifications was calculated based on the reference polygons. Comparison of forest changes over 10 year periods resulted in different vegetation biomass volumes, producing the loss of deciduous forests in 2019 probably due to the expansion of residential areas and rapid deforestation.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.20 no.6
• /
• pp.117-131
• /
• 2017

This study was conducted to draw vegetation landscape elements in the ancient literature, investigate plant community structure, understand vegetation structure, and suggest reasonal conservation management methods. As a result of analyzing ancient literature, geomorphological landscapes in Guryong valley were canyon landscape and valley surrounded in Mt. Chiak. Plant landscape factors were as followed. Rhododendron spp. spread around valley. Also, Pinus densiflora communities were distributed in Guryong valley around. Especially, the entrance zones of Guryong valley were described as covered with Pinus densiflora and Whangchangkumpyo(黃腸禁標). Therefore, it was estimated that entry of Guryong valley was covered with Pinus densiflora community landscape. As for current vegetation result, the main vegetation was divided into mixed deciduous broad-leaved trees community and Pinus densiflora community. As a result of analysis by TWINSPAN for community classification, five communities(Deciduous broadleaved trees, Pinus densiflora, Pinus densiflora-Abies holophylla, Abies holophylla, and Pinus koraiensis community) were classified. To maintain historic plant landscape and conserve crucial resources, Pinus densiflora community was classified as concentrated conservation management area($105,472m^2$). To maintain Pinus densiflora landscape which has high historical and cultural value of Guryong valley, it was considered that active density control of lower layer vegetation would be necessary. Accordingly, to conserve P. densiflora landscape, Whangchangkumpyo(?腸禁標), that area was separated into Pinus densiflora lower layer forest management area($84,029m^2$) and Pinus densiflora seedling conservation management area($21,443m^2$). In understory of Pinus densiflora lower layer flora, the target tree species for elimination and management were Quercus serrata and Quercus mongolica. They were $4{\sim}6trees/100m^2$ and their average diameter was 7.1cm. To preserve Pinus densiflora seedlings, areas with Sasa borealis, the ground vegetation of Pinus densiflora community, rate of 80% or more should be selected as priority management areas and concentrated elimination and management of Sasa borealis should be implemented. Likewise, traditional Pinus densiflora forest is a historically cultural heritage to preserve with sustainable interest and survey. Efficient management method through systematic monitoring system should be made.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.20 no.4
• /
• pp.77-87
• /
• 2017

In this study, we investigated the physical form of planting foundation of the parks and green spaces in the waterside of Korea and classified them into groups showing common features. It was clssified into 7 kinds of parks and green spaces of 27 waterside parks in Korea including landscape, ecology, art, shields, site boundaries, windbreaks, and soundproofing. As a result, the study was carried out on the detailed type and size estimation through the sampling survey of planting foundation of landscape and ecological type mounding which can be statistically analyzed. Landscape and ecological mounding have the characteristics of securing the ecological stability of the waterside planting areas and the diversity of planting landscape. It is possible to create a green landscape through various terrain changes such as enclosing, focusing, and panoramic view. The physical characteristics of ecological and landscape type mounding can be expressed as height, width, and length And physical data can appear in various forms and sizes depending on the purpose and function of the buffer effect of the land use in the waterside planting areas, the landscape creation, the ecological buffer. In this study, the range of the physical scale for landscape and ecological mounding of waterside parks and green spaces was calculated. The range of the mounding height was analyzed to be less than 1.25m and more than 1.25m and the average height was 0.74~1.08m and 1.75~2.75m respectively. In addition, the range of width of mounding was less than 6.13m, 6.13~17.5m, and more than 17.5m, and the average width of each was 3.45~4.95m, 7.05~10.85m and 31.54~51.54m respectively. The range for the length of mounding was less than 50m, 50~500m, and more than 500m. The mean length of each mounding was 34.0m, 116.3m and 955.8m. It is difficult to distinguish the difference between the waterside planting areas and the urban greenery in the purpose and function of landscape and ecological mounding. However, considering the average distance of 60m from the waterside and the average height of 1.26m, we can conclud that opened planting foundation is prefered to high mounding designs in waterside planting areas. It is expected that the results presented for the improvement of the logical and spatial value of the waterside parks and green areas planting foundation design can be served as the basic data helpful for practical application in landscape architecture planning and design.

• Korean Journal of Environment and Ecology
• /
• v.25 no.2
• /
• pp.175-188
• /
• 2011

The purpose of this study was to investigate the vegetation structure of Daphniphyllum macropodum community in the Geumseon Valley area of Naejangsan National Park. To do so, thirty-seven plots($100m^2$) were set up and surveyed. The surveyed plots were divided into four groups according to the analysis of classification by TWINSPAN; (I)Carpinus laxiflora community (II)Carpinus laxiflora community (III)Deciduous Broad-leaved community and (IV)Zelkova serrata community. The results of vegetation structure analysis were; Daphniphyllum macropodum did not appeared in the canopy later but in understory and shrub layer. Even though Daphniphyllum macropodum will not be dominant species in the canopy later, but it was expected that Daphniphyllum macropodum will be major species in understory and shrub layer. The expected age of forest of the Geumseon Valley where Carpinus laxiflora and Zelkova serrata were dominant trees in canopy layer, was about 50 years old while that of Daphniphyllum macropodum in understory layer was 20 years old.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.37 no.4
• /
• pp.12-21
• /
• 2009

The purpose of this study is to identify the characteristics of amenities available in Sunchang-gun, Jeonbuk province in Korea through ananalysis of survey data of rural amenity resources. This survey was performed over 4 years(from 2005 to 2008). The data were collected by field survey, interview, and Internet search. Descriptive statistics, regression and correlation analyses were performed to identify the characteristics of each Eup-Myun in Sunchang County. A regression analysis was also performed to compare provincial, national and other county data. Furthermore, a rank analysis was performed to classify the type of each region. Through this, the type of rural amenity resources was identified.

• Current Research on Agriculture and Life Sciences
• /
• v.27
• /
• pp.59-67
• /
• 2009

The purpose of this study is to propose the methodology for introducing green infrastructure that can improve the health of citizens by promoting walkability. The methodology is composed of the following three phases: classification of the types of green spaces, selection of core green spaces with two separate analyses, and introduction of the framework of green infrastructure to promote walkability. In the first phase, the classification of the types of green spaces was carried out in order to understand existing distribution pattern of green spaces in study site. In the second phase, walkable blocks were selected by such methods as walkability value. Through these two analyses, all the blocks were divided into three groups according to the ranking figured up the second analyses' results. The blocks in the first group, the group involved in the top 30% and having the greatest ranking, were defined as walkable blocks. In the last phase, a basic frame of the green infrastructure in study site was introduced by connecting the walkable blocks with using other blocks and the green spaces over 1ha. In case study, 28 important green spaces and 35 walkable blocks were selected through the two analysis process. Then, the basic framework of green infrastructure based on the selected 28 important green spaces and 35 walkable blocks was introduced. The methodology applied to this study can be used to get the best selections of the proper green infrastructure in accordance with the purpose of the ecological and recreational local development. In particular, this study will suggest a specific analysis model to use for the ecological and walkable urban planning with green spaces existing in the city.

• Korean Journal of Environment and Ecology
• /
• v.28 no.2
• /
• pp.197-204
• /
• 2014

The purpose of this study was to investigate the vegetation structure of Daphniphyllum macropodum community in the Yeong-sil and Seong-panack. To do so, 26plots ($(20m{\times}20m)$) were set up and surveyed. Plant communities were classified with 3 groups according to the analysis of classification by TWINSPAN and DCA Ordination; Pinus densiflora-Carpinus laxiflora (I), Carpinus laxiflora-Quercus serrata (II) and Carpinus tschonoskii (III). Daphniphyllum macropodum is appearing in understory and shrub layer of all groups. We found that Daphniphyllum macropodum will be dominated in understory and shrub layer. These results was judeged that these influence is depended on difference of altitude and accompanied species. Accompanied species were lived in similar growth environment to Daphniphyllum macropodum. That species were Styrax japonica, Quercus serrata of understory and Ilex crenata, Taxus cuspidata of shrub layer.