• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.21-28
• /
• 2022

All health problems that occur in the circulatory system are refer to cardiovascular illness, such as heart and vascular diseases. Deaths from cardiovascular disorders are recorded one third of in total deaths in 2019 worldwide, and the number of deaths continues to rise. Therefore, if it is possible to predict diseases that has high mortality rate with patient's data and AI system, they would enable them to be detected and be treated in advance. In this study, models are produced to predict heart disease, which is one of the cardiovascular diseases, and compare the performance of models with Accuracy, Precision, and Recall, with description of the way of improving the performance of the Decision Tree(Decision Tree, KNN (K-Nearest Neighbor), SVM (Support Vector Machine), and DNN (Deep Neural Network) are used in this study.). Experiments were conducted using scikit-learn, Keras, and TensorFlow libraries using Python as Jupyter Notebook in macOS Big Sur. As a result of comparing the performance of the models, the Decision Tree demonstrates the highest performance, thus, it is recommended to use the Decision Tree in this study.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.7
• /
• pp.89-95
• /
• 2009

This paper proposes a tag indexing scheme for RFID tag using spatial index. The tag being used for the inventory management and the tag's location is determined by the position of readers. Therefore, the reader recognizes the tag, which is attached products and thereby their positions can be traced down. In this paper, we propose hTag-tree( Hybrid Tag index) which manages RFID tag attached products. hTag-tree is a new index, which is based on tag's attributes with fast searching, and this tag index manages RFID tags using reader's location. This tag index accesses rapidly to tags for insertion, deletion and updating in dynamic environment. This can minimize the number of node accesses in tag searching comparing to previous techniques. Also, by the extension of MER in present tag index, it is helpful to stop the lowering of capacity which can be caused by parent node approach. The proposed index experiment deals with the comparison of tag index. Fixed Interval R-tree, and present spatial index, R-tree comparison. As a result, the amount of searching time is significantly shortened through hTag-tree node access in data search. This shows that the use of proposed index improves the capacity of effective management of a large amount of RFID tag.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.6 no.6
• /
• pp.86-95
• /
• 2003

The object of this paper is to correct check the tree situation and quantity around highway. Also, those data utilize in order to establish plan about how to the long and short term landscape construction and maintain program. The result of this study can be summarized as follows; 1. Tree decrease rates for 8 branch offices were Jongbu(5.62%), Gangwon(4.32%), Chungcheong (3.35%), Honam(5.62%), Gyeongbuk(3.06%), Gyeongnam(5.60%), Seorak training center(0.31%), Headquarter(1.54%). Also decrease causes were traffic accidents(1.8%), air po11ution(4.7%), humid damage(0.9%), insect and disease(1.2%), wind and rainfall(3.4%), dry damage(3.5%), cold damage (1.0%), fire(3.1%), damage of the man and anima1(4.1%), remove bad tree(13.1%), bad rooting(9.5%) and etc.(53.7%). 2. Improve methods of tree death problems were regulation management(ferti1ize, irrigation and pesticide work), improvement of draining system, Pull out the weeds, Plant native plants, utilize organic matter fertilize and plant environment trees.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.14 no.5
• /
• pp.103-112
• /
• 2011

Old big tree transcends the simple meaning of trees as they are the natural monuments that embody the people's history and culture of this land. The Cultural Heritage Administration of Korea(CHA) defines and protects old big tree based not only on the size of the tree but also on its definitive cultural and natural factors such as value, implications, and originality. This research aims to identify and analyze the growth conditions, soil conditions and location character of 20 old big tree in Gyeongsangnamdo korea. The research examined the soundness of the arboreal form, the degree of damage on the bark, as well as the quantity of leafs levels to evaluate the overall condition of growth and development. Also, 9 elements such as soil texture, nitrogen and organic matter content, soil pH, phosphoric acid and EC were further analyzed The research analyzed in correlation of Growth condition and soil. Tree health related positivity that total nitrogen and organic matter. The result which analyzes location character, With natural monument old big trees raising a hand the area where is contiguous appeared with the fact that the farming village style where the rice field and the arable land of field etc. This research aimed at generating some foundational reference data for the analysis of the habitation and management conditions of natural monument old big tree within the Gyeongsangnamdo korea.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.40 no.2
• /
• pp.19-29
• /
• 2015

The purpose of this study is to suggest the grid search method for selecting an optimal decision tree model. It chooses optimal values for the maximum depth of tree and the minimum number of observations that must exist in a node in order for a split to be attempted. Therefore, the grid search method guarantees building a decision tree model that shows more precise and stable classifying performance. Through empirical analysis using data of job satisfaction of workplace reserve force commanders, we show that the grid search method helps us generate an optimal decision tree model that gives us hints for the improvement direction of labor conditions of Korean workplace reserve force commanders.

• Industrial Engineering and Management Systems
• /
• v.10 no.4
• /
• pp.272-278
• /
• 2011

Decision tree as a classification tool is being used successfully in many areas such as medical diagnosis, customer churn prediction, signal detection and so on. The main advantage of decision tree classifiers is their capability to break down a complex structure into a collection of simpler structures, thus providing a solution that is easy to interpret. Since decision tree is a top-down algorithm using a divide and conquer induction process, there is a risk of reaching a local optimal solution. This paper proposes a procedure of optimally determining thresholds of the chosen variables for a decision tree using an adaptive particle swarm optimization (APSO). The proposed algorithm consists of two phases. First, we construct a decision tree and choose the relevant variables. Second, we find the optimum thresholds simultaneously using an APSO for those selected variables. To validate the proposed algorithm, several artificial and real datasets are used. We compare our results with the original CART results and show that the proposed algorithm is promising for improving prediction accuracy.

• Journal of Forest and Environmental Science
• /
• v.37 no.1
• /
• pp.14-24
• /
• 2021

A plant community is a group of populations that coexist in space and interact directly or indirectly with the environment. In this paper, we determined the pattern of tree species composition in response to soil variables in Khadimnagar National Park (KNP), which is one of the least studied tropical forests in Bangladesh. Soil and vegetation data were collected from 71 sample plots. Canonical Correspondence Analysis (CCA) with associated Monte Carlo permutation tests (499 permutations) was carried out to determine the most significant soil variable and to explore the relationship between tree species distribution and soil variables. Soil pH and clay content (pH with p<0.01 and Clay content with p<0.05) were the most significant variables that influence the overall tree species distribution in KNP. Soil pH is related to the distribution and abundance of Syzygium grande and Magnolia champaca, which were mostly found and dominant species in KNP. Some species were correlated with clay content such as Artocarpus chaplasha and Cassia siamea. These observations suggest that both the physico-chemical properties of soil play a major role in shaping the tree distribution in KNP. Hence, these soil properties should take into account for any tree conservation strategy in this forest.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.4
• /
• pp.29-37
• /
• 2010

The change detection of XML documents is a major research area. However, though XML becomes a file format for Hangul documents, research on change detection of Hangul documents based on the characteristics of Hangul documents is rather scarce. Since format data in Hangul documents are very large, which is different from ordinary XML documents, it is not proper to apply general XML change detection algorithms such as X-treeDiff+ to Hangul documents without any change. In this paper, we propose new contents-based matching algorithm and implement it in X-treeDiff+. The result of our testing shows better performance for most documents in editing process.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.9-15
• /
• 2024

Tree-based algorithms have been the dominant methods used build a prediction model for tabular data. This also includes personal credit data. However, they are limited to compatibility with categorical and numerical data only, and also do not capture information of the relationship between other features. In this work, we proposed an ensemble model using the Transformer architecture that includes text features and harness the self-attention mechanism to tackle the feature relationships limitation. We describe a text formatter module, that converts the original tabular data into sentence data that is fed into FinBERT along with other text features. Furthermore, we employed FT-Transformer that train with the original tabular data. We evaluate this multi-modal approach with two popular tree-based algorithms known as, Random Forest and Extreme Gradient Boosting, XGBoost and TabTransformer. Our proposed method shows superior Default Recall, F1 score and AUC results across two public data sets. Our results are significant for financial institutions to reduce the risk of financial loss regarding defaulters.

• Journal of Korean Society of Forest Science
• /
• v.90 no.4
• /
• pp.437-444
• /
• 2001

This paper discusses applications of neural network to forest stand field data processing and determining suitable tree species for site-specific stand characteristics. For site-specific species selection, considered were 5 major coniferous species : P. densiflora for. erecta, L. leptolepis, P. koraiensis, P. densiflora, P. thunbergii. Among 1,320 sample plot data sets, 200 data sets with the highest site index (40 data sets for each species) were chosen as the test sets for investigation. Each data set includes 13 factors describing the site characteristics of the corresponding sample plot. The results of this investigation indicate high performance of neural network in data processing procedures for extracting data sets or measurement parameters without any recognizable pattern. These data sets or measurement parameters are those which have rare effect on site-specific species suitability or disturb pattern classification procedures of neural network because of unrecognizable patterns involved. Also the results have shown high potential of neural network in determining the best-suitable tree species for site characteristics. The % accuracy of the neural network model in determining the best-suitable tree species for site characteristics ranges from 77.6% to 91.8% associated with the combination of Site factors.