• Korean Journal of Environment and Ecology
• /
• v.28 no.4
• /
• pp.457-471
• /
• 2014

This study aims to present an evaluation scheme to improve the problems in tree shapes and tree growth which were identified through shape and growth assessments of landscape trees currently planted in Haedoji Park, Songdo, Incheon Metropolitan City after plant structure status and propriety review for funtion of space and concept of planting. Suitability the planting concept was evaluated according to function of space. The result indicated that the shade planting areas accounted for 29.5% of the the shade spaces area. 58.7%, respectively planting areas of visual landscape. And 11.8%, respectively planting areas of buffer. Because the planting areas was lacked according to the park established spatial configuration of central facilities and the result of plant young trees. Plant structure status required consideration with plant structure, density, size, growth status for improve planting function. The tree assessment was performed on a total of 28 species and 600 trees of which 22 species and 209 trees were planted in the buffer zone, 8 species and 71 trees in the shade zone, 16 species and 266 trees in the visual landscape zone, and 4 species and 54 trees in the ecological landscape zone. The trees were divided into grades based on their assessment score and were statistically grouped by the functional zone in where they are planted and by tree species to verify their significance. The tree shape assessment was an average of 56.6 points and the tree growth assessment was an average of 76.0 points. Using the results of the tree assessments, the tree standards for each functional space were identified and a concept of optimum planting and cultivating was applied. When applying the shape assessment results by zone to the concept of planting, since trees for buffering require high functionality they received E's, the lowest grade; as trees for ecological landscaping require diverseness and naturalness, they received D's; since trees for shading require utilization, they received C's as trees with branching at the main stems were considered; and since trees for visual landscaping required aesthetical value, they received A's and B's. When applying the growth assessment results by zone to the concept of planting, based on planting foundations of favorable and poor, for buffering, visual landscaping, and ecological landscaping, trees from grades A to E could be planted, and for shading, trees from grades A to C could be planted. For a cultivation plan that could improve the growth of the trees, we proposed that the topography of the land be selected considering the tree's characteristics and that a method of pot seeding be used. Also, to improve the shape of the trees, we proposed that poles be used to improve the growth of vertically-straight stems, an appropriate planting density be applied for reasonable branch growth, manage tree shape to maintain good crowning, and better manage fertilization to maintain a reasonable crown density.

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.1
• /
• pp.121-127
• /
• 2002

The volume of electronic commerce based on Internet and network traffic is increasing rapidly. The objective of this study is to examine the current status of the exponentially multiplying cyber-shopping mall phenomenon. To this end, data obtained from a single cyber-shopping mall exemplified customer purchasing behavior and provided decision tree and correspondence analysis derived customer segmentation and merchandise.

• Smart Media Journal
• /
• v.13 no.1
• /
• pp.24-35
• /
• 2024

The combination of Artificial Intelligence and the Internet of Things (AIoT) has gained significant popularity. Deep neural networks (DNNs) have demonstrated remarkable success in various applications. However, deploying complex AI models on embedded boards can pose challenges due to computational limitations and model complexity. This paper presents an AIoT-based system for smart parking lots using edge devices. Our approach involves developing a detection model and a decision tree for occupancy status classification. Specifically, we utilize YOLOv5 for car license plate (LP) detection by verifying the position of the license plate within the parking space.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.19 no.3
• /
• pp.93-102
• /
• 2016

An invasive disturbance species has caused harm to biodiversity and ecosystem. To address the issue, identifying the characteristics of a habitat for invasive disturbance species is considered for forest management. This study analyzed a status of plant species by field survey based on belt transect method in the capital areas and established a predictive model for invasive disturbance species by logistic regression. As results of the study, the number of herb, vine, and invasive disturbance species and a canopy cover of tree would decrease from the forest edge to core areas (p<0.001). The predictive model was derived with variables of altitude, Topographic Wetness Index, distance to forest edge, and canopy cover of tree. It can be useful in estimating the presence or absence of species and predicting its spatial distribution. Further studies are needed to identify the pathway of introduction, spread, and possibility of germination for understanding the status of invasive disturbance species in more depth.

• Journal of Forest and Environmental Science
• /
• v.31 no.3
• /
• pp.164-176
• /
• 2015

Cyathea gigantea is a tree fern distributed throughout humid tropical regions of northeast India and other parts of the country. However, wild populations of this species are largely affected by various natural and anthropogenic activities. Therefore, an attempt was made to study the population structure and regeneration status of C. gigantea in and around greater Itanagar area of Papum Pare district, Arunachal Pradesh. Altogether 45 patches, ranging from 19.63 to $260m^2$ of area, were randomly sampled to study population structure and regeneration status of the species. Population study showed highest number of youngs in the height class of 0.50-0.75 m while, immatures were recorded highest in the height class of 2.0 to 2.5 m. Majority of the matures belonged to 6-9 m height class while it was recorded maximum in the diameter class of 10-15 cm. Average density of C. gigantea was $0.07individuals\;ha^{-1}$ which varied greatly among different patches with a range of 2 to 14. Significant correlations were found between patch size and density of youngs, immatures, matures and total density. Maximum concentration of youngs was observed in patch size $60-140m^2$, while for immatures, it was highest in patch size $20-160m^2$. Similarly, highest concentration of matures was observed in patch size $20-80m^2$ and $80-180m^2$. Population structure of the total population exhibited inverted pyramid shaped distribution. Population structure consisting of youngs, immatures, matures showed that around 60% patches lack of regenerating individuals which depict very poor natural regeneration of the species. Effective conservation strategies are therefore to be formulated to save C. gigantea from the threat of extinction in near future.

• Survey Research
• /
• v.4 no.2
• /
• pp.1-21
• /
• 2003

We proposed imputation strategies for marital status in the Population and Housing Census 2000 in Korea to illustrate the effective missing value imputation methods for social survey. The marital status which have relatively high non-response rates in the Census are considered to develope the effective missing value imputation procedures. The Classification and Regression Tree(CART)is employed to construct the imputation cells for hot-deck imputation, as well as to predict the missing value by model-based approach. We compare to imputation methods which include the CART model-based imputation and the sequential hot-deck imputation based on CART. Also we check whether different modeling for each region provides the more improved results. The results suggest that the proposed hot-deck imputation based on CART is very efficient and strongly recommendable. And the results show that different modeling for each region is not necessary.

• Journal of Korean Biological Nursing Science
• /
• v.21 no.1
• /
• pp.85-97
• /
• 2019

Purpose: This study was performed to analyze the levels of blood pressure and to identify good or poor blood pressure control (BPC) groups among hypertension patients. The study was based on the Korea National Health and Nutrition Examination Survey (KNHANES VI and VII) conducted from 2013 to 2016. Methods: The sociodemographic and clinical data of 4,151 Korean hypertension patients aged 20-79 years and who were taking antihypertensive medications was extracted from the KNHANES VI and VII database. Descriptive statistics for complex samples and a decision-tree analysis were performed using the SPSS WIN 24.0 program. Results: The mean age was $62.46{\pm}0.21years$. The mean systolic blood pressure (SBP) was $128.07{\pm}0.28mmHg$, and the diastolic blood pressure (DBP) was $76.99{\pm}0.21mmHg$. 71.9% of participants showed normal blood pressure (SBP < 140mmHg and DBP < 90mmHg). From the decisiontrees analysis, the characteristics of participants related to good BPC group were presented with 9 different pathways same as those from the poor BPC group. Good or poor BPC groups were classified according to the patients' characteristics such as age, living status, occupation, education, hypertension diagnosis period, numbers of comorbidity, perceived health status, total cholesterol, high density lipoprotein-cholesterol, alcohol drinking per month, and depressive mood. Total cholesterol level (< 201mg/dL or ${\geq}201mg/dL$ cutoff point) was the most significant predictor of the participants' BPC group. Conclusion: This decision-tree model with the 18 different pathways can form a basis for the screening of hypertension patients with good or poor BPC in either clinical or community settings.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.22 no.2
• /
• pp.49-57
• /
• 2019

The street trees increase the liveability of cities by reducing stormwater runoff, improving air quality, storing carbon, providing shade, and ameliorating the urban heat-island effect. In this study, the health status of street trees in Suwon was evaluated, and the factors affecting the growth of the trees were also derived. In order to evaluate the growth and health of street trees, field survey was carried out on a total of 125 trees in 25 sections of the Deogyeong-daero where is through the city. During the field survey, the following items were examined: Street trees health status (i.e. species, height, DBH (diameter at breast height), planting types, vigor, etc.), soil factors (i.e. soil temperature, humidity, pH, hardness, etc.), and environmental factors (i.e. landuse, road width, etc.). As the results of field survey, the main species of the street trees was Zelkova serrata, which was healthy in most of the sections. The factors such as planting types, soil temperatures, tree root cover, road extension, distance from the road were derived to affect the growth and health of street trees, and the differences were significant. The results of this study were derived the following conclusions for vigorous street trees: First, it is important to install and maintain the protection facilities like tree root cover for the growth of trees. Second, it is necessary to discuss how to plant multiple trees in narrow spaces like a street green space. Third, it is important to provide appropriate soil conditions continuously for growth of threes. Finally, it should be utilized as a mitigation measure of urban heat island effects.

• Journal of Forest and Environmental Science
• /
• v.38 no.2
• /
• pp.90-101
• /
• 2022

The study aims to assess composition, diversity and population indices of natural regeneration of woody species in Jebel El Gerrie forest reserve, Blue Nile State, Sudan. We conducted field work between December 2018 and January 2019. We used random sampling to collect vegetation data in the forest where we made a total of 90 circular sample plots (radius 17.84 m) and distributed them proportionally to the area of each of the four density-based vegetation classes of the forest i.e. high density (C1), medium density (C2), low density (C3) and crop land (C4). In each sample plot we identified all regenerating tree species and counted their regeneration frequencies. We calculated ecological metrics of regeneration frequency, density, abundance, richness, evenness, diversity and importance value index (IVI) and drew abundance rank curve. Results revealed that out of fifteen mature tree species present, natural regeneration of 8 species, which belong to 6 families, was observed. The relatively most frequently naturally regenerating and abundant species were Anogeissus leiocarpa and Combretum hartmannianum. Richness, evenness and diversity of regenerating species were 1.33, 0.82 and 1.7, respectively. One-way ANOVA (α=0.05) of mean regeneration densities disclosed that there were significant differences (F_3,86=16.77, p=0.000) between C2 & C3 (p=0.000) and C2 & C4 (p=0.000). While regeneration of seven tree species were absent, two, two and four species were of good, poor and fair regeneration status, respectively. A comparison of mean density of natural regeneration with that of parent trees reflects a poor regeneration status of the forest. The study provides empirical results on the regeneration status of species and signifies the need for management interventions for species conservation and restoration, maintenance of biodiversity and sustainable production.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.29 no.1
• /
• pp.140-151
• /
• 2001

This study based on the theoretical understanding of multi-layer planting which have engineering, ecological and landscape benefits, was conducted to find out the status of multi-layer planting in the apartment and neighborhood park in Seoul. This study was also aimed to seek for the problematic matters, and suggest a solution on the current multi-layer planting. The results of this study were as follows; 1) Since landscape woody plants have been classified just as tree and shrub in Korea, the classification for the multi-layer planting has been unreasonable, and landscape woody plants might have been classified as tree, sub-tree and shrub, or upper, middle, and lower-layer, It could be defined that upper layer is over eight meters in full growth, middle over 3-8 meters and lower under 3 meters. 2) In apartments, the upper layer consisted of eighteen species, the middle and lower layer seven species each. In neighborhood parks, the upper layer consisted of fifteen species, and the middle and lower layer five species each. 3) In terms of planting year of the surveyed areas, there were no differences in the number of species when planting year of the apartment was divided into two groups, the first half(1900-1995) and the second(1996-2000). But, in terms of individual occupation, the percentage was decreased in upper layer, while there was increasing in middle and lower layer. 4) As the result of survey of multi-layered area, it appeared that apartment was shown 0.65 percent and neighborhood park 0.61 percent of the planted area, which was less than 1 percentage of landscape architecturally planted area. 5) In apartment, the number of individual in middle layers has been increased in the first half and the second, but with respect to the correlation with multi-layered area, the apartments had the "$\rho$=0.208", saying that increasing middle layer was scattered planting instead of multi-layered planting. 6) In planting at the apartments in Korea, the planting density was limited, because the layer division was restricted to only tree and shrub. On the contrary, it was divided into upper, middle and lower tree in Japan. Therefore, in Korea, it should be classified as the planting density by dividing into tree, sub-tree, and shrubs, or upper, middle and lower tree by the law. And, it should be considered that the multi-layered planting has a proper organic relation as well as the planting density.g density.