• Journal of Forest and Environmental Science
• /
• v.33 no.1
• /
• pp.66-73
• /
• 2017

This study was conducted to evaluate the ecological attributes of forest types which were classified by cluster analysis in the natural forest of Mt. Odae on the basis of the vegetation data (232 sampling points) from the point-quarter sampling methods. For the classified types, the species composition was expressed by importance value to describe the stand structure and the species diversity was quantified using the Shannon's diversity index. Recognized forest types were 1) Quercus mongolica-Pinus densiflora-Betula ermanii forest type, 2) Mixed mesophytic forest type, 3) Q. mongolica forest type, 4) B. ermanii forest type. Species diversity indices of total and overstory were highest in the Mixed mesophytic forest type (3.465 and 2.942), and lowest in the B. ermanii forest type (0.118 and 0.832). In addition to that, Q. mongolica-P. densiflora-B. ermanii forest type was calculated as 3.226 and 2.565, and Q. mongolica forest type was calculated as 2.776 and 1.218 in total and overstory, respectively. It was considered that after the P. densiflora and B. ermanii first invaded and site condition became good, Q. mongolica-P. densiflora-B. ermanii forest type was dominated by Q. mongolica. Mixed mesophytic forest type showed the most stable stand structure with various species distributed uniformly. Q. mongolica forest type would preserve the present stand status for a while, and the B. ermanii in B. ermanii forest type would be pressed by other species over time.

• Journal of Korean Society of Rural Planning
• /
• v.26 no.1
• /
• pp.101-112
• /
• 2020

Recently, public awareness regarding mountain villages' landscapes is increasing. Thus, this study aimed to provide standards for conservation, management and creation of mountain village landscape by characterizing and classifying those exist. 286 mountain villages' data were collected and 19 variables - extracted from GIS spatial information and statistic data of mountain villages, chosen as right sources according to former studies - were utilized to conduct factor and cluster analysis. As a result of the factor analysis, 7 characteristics of the mountain villages' landscapes were defined - 'Location', 'Cultivation', 'Ecology·Nature', 'Tourism', 'Residence', 'Recreation'. The K-means cluster analysis categorized the mountain villages' landscapes into four types - 'Residential', 'Touristic', 'General', 'Environmentally protected'. The classification was examined to be appropriate by field assessment, and basic guidelines of mountain village landscape management were set. The results of this study are expected to be utilized planning and implementing regarding mountain village landscape in the future.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1167-1175
• /
• 2018

Microarray data plays an essential role in diagnosing and detecting cancer. Microarray analysis allows the examination of levels of gene expression in specific cell samples, where thousands of genes can be analyzed simultaneously. However, microarray data have very little sample data and high data dimensionality. Therefore, to classify microarray data, a dimensional reduction process is required. Dimensional reduction can eliminate redundancy of data; thus, features used in classification are features that only have a high correlation with their class. There are two types of dimensional reduction, namely feature selection and feature extraction. In this paper, we used k-means algorithm as the clustering approach for feature selection. The proposed approach can be used to categorize features that have the same characteristics in one cluster, so that redundancy in microarray data is removed. The result of clustering is ranked using the Relief algorithm such that the best scoring element for each cluster is obtained. All best elements of each cluster are selected and used as features in the classification process. Next, the Random Forest algorithm is used. Based on the simulation, the accuracy of the proposed approach for each dataset, namely Colon, Lung Cancer, and Prostate Tumor, achieved 85.87%, 98.9%, and 89% accuracy, respectively. The accuracy of the proposed approach is therefore higher than the approach using Random Forest without clustering.

• Journal of Korean Society of Forest Science
• /
• v.100 no.3
• /
• pp.504-521
• /
• 2011

This study was carried out phytosociological forest community analysis, the sampled dada were collected and studied by 1,456 plots from 1993 to 2009 for 17 years in the 22 mountain area of South Korea. Four opposed species groups were classified and 10 vegetation units were divided as a result of forest vegetation classification. The 10 units were closely correlated with major environmental factors such as geological features, climatic conditions, topographical configurations, and etc. Therefore the forest vegetation of South Korea could be conclusively abstracted by 10 vegetation units and 7 eco-types.

• KIISE Transactions on Computing Practices
• /
• v.22 no.9
• /
• pp.455-460
• /
• 2016

Recently, with more severe types felonies such as robbery and sexual violence, the importance of crime prediction and prevention is emphasized. For accurate and prompt crime prediction and prevention, both a classification model of crime with high accuracy based on past criminal records and well-designed system interface are required. However previous studies on the analysis of crime factors have limitations in terms of accuracy due to the difficulty of data preprocessing. In addition, existing crime monitoring systems merely offer a vast amount of crime analysis results, thereby they fail to provide users with functions for more effective monitoring. In this paper, we propose a classification model for types of crime based on random-forest algorithms and system design factors for real-time crime prediction. From our experiments, we proved that our proposed classification model is superior to others that only use criminal records in terms of accuracy. Through the analysis of existing crime monitoring systems, we also designed and developed a system for real-time crime monitoring.

• Journal of Korean Society of Forest Science
• /
• v.104 no.1
• /
• pp.14-25
• /
• 2015

This study was carried out to classify forest communities and to aggregate forest cover types for the complex and diversified natural forest areas of Guryongsan, Sobaeksan, Baekhwasan, Sokrisan, and Baekhaksan in the middle part of Baekdudaegan. The vegetation data were collected by point-centered quarter sampling method. One thousand one hundred fourteen sample points were subjected to cluster analysis to classify 27 forest communities, which were aggregated into 7 representative forest cover types on the basis of community similarity from composition of canopy species. They were Quercus mongolica forest cover type, mixed mesophytic forest cover type, Q. variabilis forest cover type, Pinus densiflora forest cover type, the others deciduous forest cover type, Q. serrata forest cover type, and subalpine forest cover type. The Q. mongolica forest cover type was most widely distributed in the study areas. It was assumed that abundance of Q. mongolica might be negatively associated with species diversity. Mixed mesophytic forest cover type and the others deciduous forest cover type were commonly distributed in the areas of valley, on the other hand, Q. mongolica cover type and P. densiflora cover type tended to be distributed in the areas of ridge.

• Korean Journal of Environment and Ecology
• /
• v.29 no.2
• /
• pp.236-249
• /
• 2015

The master plan of forest land management proposes forest watershed management that considers regional characteristics in order to overcome the problem of uniform forest land management. In order to manage the forest watersheds in Gyeonggi-do, this study classified 1,823 forest watersheds in Gyeonggi-do and attempted to understand their characteristics. It conducted a factor analysis and cluster analysis from the perspective of conservation value and development pressure using forest land indicators. In terms of conservation value, three factors were drawn: the topography factor, vegetation factor and public service factor, while in terms of development pressure, three factors were drawn: the easiness of development factor, economic benefits factor and development activity factor. Using these factors, forest watersheds were divided into three clusters in terms of conservation value while they were divided into three clusters in terms of development pressure. Using the results of the cluster analysis from a conservation-development perspective, the forest watersheds were classified into nine different types, and the characteristics were identified by each type. It is judged that the factors and clusters drawn as a result of the research accurately reflect the present conditions of Gyeonggi-do, and the nine types of forest watersheds have clear characteristics according to each type, which are judged to be utilized in forest management in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.5132-5148
• /
• 2017

Cyber attacks are evolving commensurate with recent developments in information security technology. Intrusion detection systems collect various types of data from computers and networks to detect security threats and analyze the attack information. The large amount of data examined make the large number of computations and low detection rates problematic. Feature selection is expected to improve the classification performance and provide faster and more cost-effective results. Despite the various feature selection studies conducted for intrusion detection systems, it is difficult to automate feature selection because it is based on the knowledge of security experts. This paper proposes a feature selection technique to overcome the performance problems of intrusion detection systems. Focusing on feature selection, the first phase of the proposed system aims at constructing a feature subset using a sequential forward floating search (SFFS) to downsize the dimension of the variables. The second phase constructs a classification model with the selected feature subset using a random forest classifier (RFC) and evaluates the classification accuracy. Experiments were conducted with the NSL-KDD dataset using SFFS-RF, and the results indicated that feature selection techniques are a necessary preprocessing step to improve the overall system performance in systems that handle large datasets. They also verified that SFFS-RF could be used for data classification. In conclusion, SFFS-RF could be the key to improving the classification model performance in machine learning.

• Journal of Korean Society of Forest Science
• /
• v.34 no.1
• /
• pp.47-56
• /
• 1977

I have investigated and compared the morphology of vascular bundle shown in the section of culm wall of bamboo trees growing on Mt. Jiri which were classified by Grosser and Liese with their methods of morphological classification. The results obtained were as follows: 1. It was shown that there are no b.g.i. types of bamboo classified by Grosser and Liese among the bamboo trees on Mt. Jiri (Phyllostachys and Sasa). 2. As for the thickness of the culm wall in the culm, it was shown that the culm wall of the Phyllostachys becomes thinner in proportion to its nearness to the upper part of the tree, but no distinctive difference appeared in the Sasa. 3. The c, d, and e types of Sasa were the same as those of the Phyllostachys, but there was a vascular bundle type of the a' type, which was quite different from that of the Phyllostachys. 4. It was shown that the a', d, and e types of Sasa were distributed in a zone less than 500m above sea level, but no a' type was distributed in the high mountain area except for the c, d and e types which ranged from 600m to 1000m above sea level. Such facts mean that the vascular bundle sheath has changed in quantity because of the height of mountain. 5. In general, as compared with the Phyllostachys, the Sasa (types a, c, d and e which included a new type a) have fewer vascular bundles. 6. Considering the above results, it is thought that not by the current Sasa classification method based on observation of the the study of Sasa form the outside, but by a new method of classification based on the aspect of the physiological construction as seen from the inside wall is advanced. I believe this new method of classification to be a first step towards an epoch-making methodological advance and encourage the further study of it.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.17 no.1
• /
• pp.65-79
• /
• 2014

This study selected Nakdong River basin zone in Daegu as an example area to conduct landscapetope classification and aesthetic value assessment of landscape according to the classified landscapetope. The main result of this research can be summed up as following. First, the result of landscapetope type classification showed 28 types of landscapetope including complex residential area (AA), natural stream type with copious vegetation (BA), forest type centered on mixed forest of soft and hardwood (EB) along with 129 types of imputed specific landscapetope. The result of the total first assessment using B-VAT showed the first grade 10 types, II grade 4 types, III grade6 types, IV grade 3 types, 5 types for V grade with the lowest value. The second assessment conducted toward the landscapetope types with the grade higher than the average (including III grade) in the result of the first assessment showed that there are 66 spaces for the sites (1a, 1b) with special meaning for aesthetic landscape evaluation. And also, there were 69 spaces for those (2a, 2b, 2c) with meaning for aesthetic landscape evaluation. The design model of this research is largely divided into improvement goal and specific execution plan. First, the improvement goal is divided into 6 categories including conservation area, complementary area, and restoration area, and the specific execution plan is divided into 14 categories including special landscape management area, general landscape management area, conservation of hill areas with optically good condition. A comprehensive master plan was suggested by directly applying the set landscape planning model to the subject place of this research.