• Korean Journal of Environment and Ecology
• /
• v.34 no.1
• /
• pp.27-41
• /
• 2020

The purpose of this study was to survey vegetation characteristics of Jeopdo (island) for the construction of a database. We installed and analyzed 52 plots with 100㎡ quadrat to investigate the vegetation characteristics. The community classification based on TWINSPAN found seven categories of vegetation communities in the surveyed region: Pinus thunbergii-Pinus densiflora community, Pinus densiflora-Quercus serrata community, Carpinus turczaninowii-Quercus variabilis community, Carpinus turczaninowii-Quercus acutissima community, Quercus variabilis-Carpinus turczaninowii community, Castanopsis sieboldii community, and Actinodaphne lancifolia-Camellia japonica community. The vegetation in Jeopdo is largely composed of evergreen conifer trees community (communities I and II), Carpinus turczaninowii-deciduous broad-leaved trees such as Quercus spp. community (communities III, IV, and V), and evergreen broad-leaved trees community (communities VI and VII). The evergreen conifer tree (Quercus serrata) community is currently competing with Pinus densiflora and Pinus thunbergii. The current state is expected to continue due to the lack of forces, such as Castanopsis sieboldii and Actinodaphne lancifolia, in the succession middle stage and climax stage. The current state of Carpinus turczaninowii-deciduous broad-leaved trees such as Quercus spp. community is expected to last for a long time due to slow vegetation development because of soil conditions. The evergreen broad-leaved trees community is transforming from the initial stage of Pinus densiflora and Pinus thunbergii through the stage in Quercus serrata to Castanopsis sieboldii and Actinodaphne lancifolia. The overall ages of the specimens were similar, and the oldest tree was the 59-year old Castanopsis sieboldii. The correlation analysis of major species showed a high positive correlation between Pinus thunbergii and Eurya japonica, Pinus densiflora and Fraxinus sieboldiana, and Actinodaphne lancifolia and Camellia japonica and a high negative correlation between Pinus densiflora and Carpinus turczaninowii and Carpinus turczaninowii and Eurya japonica.

• Korean Journal of Environment and Ecology
• /
• v.33 no.5
• /
• pp.552-564
• /
• 2019

The purpose of this study was to investigate vegetation characteristics of evergreen broad-leaved forests in the area of Duryunsan Provincial Park, where the deciduous broad-leaved trees and evergreen broad-leaved trees are mixed and thus had a high botanical value. To investigate the vegetation characteristics, we installed 40 quadrats with an area of $100m^2$ each for survey and analysis. Haenam-gun, where the Duryunsan Provincial Park is located, is a warm-temperate forest region. The meteorological data for the past 40 years showed a coldness index of $-8^{\circ}C$, a monthly warmth index of $109.2^{\circ}C$, and annual mean precipitation of 1,310.5mm, indicating it is an ideal habitat for the distribution of evergreen broad-leaved forest. The results of community classification based on TWINSPAN showed three categories of vegetation communities in the surveyed region: Quercus acuta community-I, Q. acuta community-II, and Neolitsea sericea-Aphananthe aspera community. In the evergreen broad-leaved forest in the Duryunsan Provincial Park, Q. acuta dominant in the canopy were expanding their presence in the understory. In addition to the Q. acuta, N. sericea and Cinnamomum yabunikkei, which are evergreen broad-leaved trees of the canopy, were found in all layers. The deciduous broad-leaved trees such as Q. variabilis, Q. serrata, and Carpinus tschonoskii were culled, and the transition to Q. acuta evergreen broad-leaved trees was ongoing. N. sericea community appeared locally. The species diversity index of N. sericea-A. aspera community was lower at 1.0798 than that of Q. acuta Community-I at 1.3208 and Q. acuta Community-II at 1.4916.

• Journal of Korean Society of Forest Science
• /
• v.87 no.4
• /
• pp.631-641
• /
• 1998

The objectives of this study were 1) to classify the types of Quercus mongolica stands at Mt. Joongwang and compare their quality, and 2) to determine the proper future tree number of Q. mongolica per ha and the appropriate distance between the future trees. The results from this study were as follows : Q. mongolica stands at Mt. Joongwang was classified into four types, pure Q. mongolica stand as stand type I, Q. mongolica - hardwood stand as stand type II, Q. mongolica - Pines densiflora stand as stand type III, Hardwood - Q. mongolica stand as stand type IV, according to mixture rate in stand volume. Stand type IV showed the best quality stem of Q. mongolica among the stand types, and the stem quality of Q. mongolica in Q. mongolica stand mixed with hardwood as stand types II and IV was better than those in pure Q. mongolica stand as stand type I and in Q. mongolica - P. densiflora stand as stand type III. If the management goal for Q. mongolica stand is to produce its high quality-timber, it is desirable to sustain proper mixture rate of Q. mongolica with another hardwoods. The proper number of future trees in pure Q. mongolica stand as stand type I was 122trees/ha and reasonable distance between the future trees was 9.15m. The distance between future trees in other stand types was 7.2m to 9.3m for stand types II and IV, while 8.0m for stand type III. Thus, the classification of Q. mongolica stand type based on stand character and maturity, and proper stem number of future tree and optimum distance between future trees would be a useful forest tending work.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1407-1422
• /
• 2022

This study was conducted to classify tree species and assess the classification accuracy, using SE-Inception, a classification-based deep learning model. The input images of the dataset used Worldview-3 and GeoEye-1 images, and the size of the input images was divided into 10 × 10 m, 30 × 30 m, and 50 × 50 m to compare and evaluate the accuracy of classification of tree species. The label data was divided into five tree species (Pinus densiflora, Pinus koraiensis, Larix kaempferi, Abies holophylla Maxim. and Quercus) by visually interpreting the divided image, and then labeling was performed manually. The dataset constructed a total of 2,429 images, of which about 85% was used as learning data and about 15% as verification data. As a result of classification using the deep learning model, the overall accuracy of up to 78% was achieved when using the Worldview-3 image, the accuracy of up to 84% when using the GeoEye-1 image, and the classification accuracy was high performance. In particular, Quercus showed high accuracy of more than 85% in F₁ regardless of the input image size, but trees with similar spectral characteristics such as Pinus densiflora and Pinus koraiensis had many errors. Therefore, there may be limitations in extracting feature amount only with spectral information of satellite images, and classification accuracy may be improved by using images containing various pattern information such as vegetation index and Gray-Level Co-occurrence Matrix (GLCM).

• Journal of Acupuncture Research
• /
• v.28 no.3
• /
• pp.85-100
• /
• 2011

Objectives : The purpose of this thesis is to help the preparation of oriental medicine clinical guidelines for drawing up the standards of oriental medicine demonstration and diagnosis classification about the neck pain. Methods : Statistical analysis about Gyeonghangtong(頸項痛), Nakchim(落枕), Sagyeong(斜頸), Hanggang (項强) classified experts' opinions about neck pain patients by Delphi method is conducted by using oriental medicine diagnosis questionnaire. The result was classified by using linear discriminant analysis (LDA), diagonal linear discriminant analysis (DLDA), diagonal quadratic discriminant analysis (DQDA), K-nearest neighbor classification (KNN), classification and regression trees (CART), support vector machines (SVM). Results : The results are summarized as follows. 1. The result analyzed by using LDA has a hit rate of 84.47% in comparison with the original diagnosis. 2. High hit rate was shown when the test for three categories such as Gyeonghangtong and Hanggang category, Sagyeong caterogy and Nakchim caterogy was conducted. 3. The result analyzed by using DLDA has a hit rate of 58.25% in comparison with the original diagnosis. The result analyzed by using DQDA has a accuracy of 57.28% in comparison with the original diagnosis. 4. The result analyzed by using KNN has a hit rate of 69.90% in comparison with the original diagnosis. 5. The result analyzed by using CART has a hit rate of 69.60% in comparison with the original diagnosis. There was a hit rate of 70.87% When the test of selected 8 significant questions based on analysis of variance was performed. 6. The result analyzed by using SVM has a hit rate of 80.58% in comparison with the original diagnosis. Conclusions : Statistical analysis using oriental medicine diagnosis questionnaire on neck pain generally turned out to have a significant result.

• The Journal of Korean Medicine
• /
• v.32 no.1
• /
• pp.12-35
• /
• 2011

Objectives: The two criteria to clarify the toxicity of a herbal diet are well known. Although mechanical analysis of effective ingredients, a western approach, is widely used, the toxicity presence classification through the herbal analysis from a viewpoint of a theory of the herbal medicine properties has been disregarded. This study is for the safe use of a herbal diet through classification and study of toxicity presence in the herbal diet from the view of a theory of herbal medicine properties, one of the methods of Oriental Medicine. Methods: We classified and studied the toxicity presence in four kinds of herbal diets, waters and grains, animals groups, fruits and vegetables, and herbs and trees, excluding mineral natural drugs, of 1,400 kinds of medicines in 16 chapters of Tang-aec-pyeon, Dong-ui-bo-gam, for which the herbal analysis from a viewpoint of the theory of the herbal medicine properties has been used. The criteria of the toxicity presence in the herbal diet have been largely classified into the toxicant and the non-toxicant, and the toxicant is in turn classified into the insignificant, the medium and the significant. The category to clarify herbal diet has been limited to simultaneous utilization of food and natural drugs. The main text is Dong-ui-bo-gam, although diverse other references have also been used. Results: There are toxicant diets: a kind of tortoise meat of animals groups; five kinds of grains part in fruits and vegetables: aengdo, peach, oyat, small apple and gingko nut; and 12 kinds of vegetables part in fruits and vegetables: ginger, oriental cabbage, lettuce, chongbaek, onion, garlic, leek, fern, houttuynia cordata (myeol), pyeongji, geundae, and spinach, which should be prohibited from long-term use both as food and medicine. Conclusion: If herbal diet is used as health food supplements or food, the toxicity presence should be considered on the grounds of an Oriental Medicine theory of the herbal medicine properties.

• Korean Journal of Environment and Ecology
• /
• v.22 no.2
• /
• pp.173-183
• /
• 2008

This research was aimed at looking into the vegetation structure of Abies holophylla forest distributed between Iljumun of Woljeong Temple and Keumgang bridge in Odaesan National Park. It was found that existed a total of 977 tree of Abies holophylla which are more than 20cm in DBH within the target site, and in 2006 when the survey was made, the number of fallen trees and poor growth trees was about 96, accounting for 9.8% of all. The age of Abies holophylla ranged from 41 years to 135 years($11\sim82cm$ in DBH). The number of Abies holophylla over 100cm in DBH was 8 and the largest Abies holophylla was 175cm in DBH and 31m in height. Its density was 5.9 individuals per $400m^2$. As a result of the analysis of the plant community structure using the TWINSP AN classification, Abies holophylla was divided into four community types. Firstly, Pinus densiflora-Abies holophylla community was predicted to vary into Abies holophylla community. In case of other three other communities, Abies holophylla communities were predicted to compete with deciduous broadleaf trees, such as Tilia amurensis and Acer pictum subsp. mono. Abies holophylla forest adjacent to Woljeong Temple of Odaesan National Park has a high value as sustainable resources for culture, landscape and tourism. Thus, it is necessary to clarify the reason for the incidence of poor growth trees and fallen trees among all trees of Abies holophylla and take counter-measures against it for the preservation and management of Abies holophylla forest. In addition, a more aggressive managrment like getting rid of the deciduous broadleaf trees, such as Tilia amurensis and Acer pictum subsp. mono, which appear mostly on understory layer or shrub layer within Abies holophylla, and continuous management is also needed for the young trees of Abies holophylla which are feared to be pressurized outside from their neighboring trees because their initial growth after germination is very slow.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.223-232
• /
• 2023

A widely used method for monitoring land cover using high-resolution satellite images is to classify the images based on the colors of the objects of interest. In urban areas, not only major objects such as buildings and roads but also vegetation such as trees frequently appear in high-resolution satellite images. However, the colors of vegetation objects often resemble those of other objects such as buildings, roads, and shadows, making it difficult to accurately classify objects based solely on color information. In this study, we propose a method that can accurately classify not only objects with various colors such as buildings but also vegetation objects. The proposed method uses the normalized difference vegetation index (NDVI) image, which is useful for detecting vegetation objects, along with the RGB image and classifies objects into subclasses. The subclass classification results are fused, and the final classification result is generated by combining them with the image segmentation results. In experiments using Compact Advanced Satellite 500-1 imagery, the proposed method, which applies the NDVI and subclass classification together, showed an overall accuracy of 87.42%, while the overall accuracy of the subchannel classification technique without using the NDVI and the subclass classification technique alone were 73.18% and 81.79%, respectively.

• The Korean Journal of Ecology
• /
• v.17 no.3
• /
• pp.391-413
• /
• 1994

The northernmost type of the monogolian oak forests in the Russian Far East was studied in terma of syntaxonomy and synchorology. Hand-sorting method, computer program TWIN-SPAN, CANOCO and SYN-TAX III were engaged for the classification and data analysis. Correlation between plant communitie and environmental factors was analyzed by DCA (Detrended Correspondence Analysis) using NeCD (Net Contribution Degree) of species. Three plant communities were recognized: the Abieti holophyllae-Quercetum mongolicae, the Lespedezo-quercetum mongolicas and the Rosa ussuriensis-Quercus mongolica communit. They were included into the alliance Jeffersonio-Quercion monogolicae which is representative to the cool-Temperate forests mixed by conierous and broadleaved trees in southern Sikhote Alin. Human impact was signified as the most important factor to interpret the disjunction of plant communities of which DCA ordination yielded sharp contrasting objects (i.e. stands and species). In the amhi-Tonghae region, alaogous vegetation types such as the Jeffersonio-Quercion monogolicae of Russian Far East, the Quercion grosseserratae of Japanese Hokkaido and the Pino koraiensis-Quercion monogolicae of Koream peninusula were reviewed in terms of similarity of species composition and stratum structure. It is signified that the Jeffersonio-Quercion monogolicae was one of the continental types more similar to Korean alliance that to Japanese one.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.2
• /
• pp.13-21
• /
• 1996

The necessity and usefulness of higher-order neural networks have been well-known since early days of neurocomputing. However the explosive number of terms has hampered the design and training of such networks. In this paper we present an evolutionary learning method for efficiently constructing problem-specific higher-order neural models. The crux of the method is the neural tree representation employing both sigma and pi units, in combination with the use of an MDL-based fitness function for learning minimal models. We provide experimental results in classification and prediction problems which demonstrate the effectiveness of the method. I. Introduction topology employs one hidden layer with full connectivity between neighboring layers. This structure has One of the most popular neural network models been very successful for many applications. However, used for supervised learning applications has been the they have some weaknesses. For instance, the fully mutilayer feedforward network. A commonly adopted connected structure is not necessarily a good topology unless the task contains a good predictor for the full *d*dWs %BH%W* input space.