• The KIPS Transactions:PartA
• /
• v.11A no.2
• /
• pp.159-164
• /
• 2004

In the previous researches, tree comparison methods are almost studied in comparing weighted or labeled tree(decorated tree). But in this paper, we propose a tree comparison and similarity evaluation algorithm can be applied to comparison of two normal trees. The algorithm converts two trees into node string using unparser, evaluates similarity and finally return similarity value from 0.0 to 1.0. In the experiment part of this paper, we visually presented matched nodes and unmatched nodes between two trees. By using this tree similarity algorithm, we can not only evaluate similarity between two specific programs or documents but also detect duplicated code.

• Journal of Forest and Environmental Science
• /
• v.39 no.4
• /
• pp.203-212
• /
• 2023

Directional felling is a felling method practised by the Forestry Department in Peninsular Malaysia as prescribed in Field Work Manual (1997) for Selective Management Systems (SMS) in forest harvesting. Determining the direction of tree felling in Peninsular Malaysia is conducted during the pre-felling inventory 1 to 2 years before the felling operation. This study aimed to predict and analyze the direction of tree felling using the vector-based path distance back link method in Geographic Information Systems (GIS) and compare it with the felling direction observed on the ground. The study area is at Balah Forest Reserve, Kelantan, Peninsular Malaysia. A Path Distance Back Link (spatial analyst) function in ArcGIS Pro 3.0 was used in predicting tree felling direction. Meanwhile, a binary classification was used to compare the felling direction estimated using GIS and the tree felling direction observed on the ground. Results revealed that 61.3% of 31 trees predicted using the vector-based projection method were similar to the felling direction observed on the ground. It is important to note that dynamic changes of natural constraints might occur in the middle of tree felling operation, such as weather problems, wind speed, and unpredicted tree falling direction.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.133-136
• /
• 2002

This paper presents a new method of Huffman decoding which gives a significant improvement of processing efficiency based on the reconstruction of an efficient one-dimensional array data structure incorporating the numeric interpretation of the accrued codewords in the binary tree. In the Proposed search method, the branching address is directly obtained by the arithematic operation with the incoming digit value eliminating the compare instruction needed in the binary tree search. The proposed search method gives 30% of improved Processing efficiency and the memory space of the reconstructed Huffman table is reduced to one third compared to the ordinary ‘compare and jump’ based binary tree. The experimental result with the six MPEG-2 AAC test files also shows about 198% of performance improvement compared to those of the widely used conventional sequential search method.

• Journal of the Korean Statistical Society
• /
• v.25 no.1
• /
• pp.1-24
• /
• 1996

In selecting a final tree, Breiman, Friedman, Olshen, and Stone(1984) compare the prediction risks of a pair of tree, where one contains the other, using the standard error of the prediction risk of the larger one. This paper proposes an approach to selection of a final tree by using the standard error of the difference of the prediction risks between a pair of trees rather than the standard error of the larger one. This approach is compared with CART's for simulated data from a simple regression model. Asymptotic results of the approaches are also derived and compared to each other. Both the asymptotic and the simulation results indicate that final trees by CART tend to be smaller than desired.

• Journal of Korean Institute of Industrial Engineers
• /
• v.37 no.3
• /
• pp.191-197
• /
• 2011

The group Steiner tree problem is a generalization of the Steiner tree problem that is defined as follows. Given a weighted graph with a family of subsets of nodes, called groups, the problem is to find a minimum weighted tree that contains at least one node in each group. We present some existing and some new formulations for the problem and compare the relaxations of such formulations.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.1
• /
• pp.9-15
• /
• 2010

As catenary supply electric power directly to the railway system, it is very important to prevent an accident of a catenary for appropriate train operation. This paper proposed the assessment the outage data for "British Catenary Safety Analysis Report" and Korean data to compare the reliability of the railway system. The analyzed data were applied to Event Tree and Fault Tree algorithm to calculate the reliability indices of railway system. Event tree is created and gate results of fault tree analysis are used as the source of event tree probabilities. Fault tree represents the interaction of failures and basic events within a system. Event Tree and Fault Tree analysis result is helpful to assess the reliability to interpreted. The reliability indices can be used to determine the equipment to be replaced for the entire system reliability improvement.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2008.10a
• /
• pp.430-434
• /
• 2008

The group Steiner tree problem is a generalization of the Steiner tree problem that is defined as follows. Given a weighted graph with a family of subsets of nodes, called groups, the problem is to find a minimum weighted tree that contains at least one node in each group. We present some existing and some new formulations for the problem and compare the relaxations of such formulations.

• Industrial Engineering and Management Systems
• /
• v.4 no.1
• /
• pp.102-108
• /
• 2005

This paper studies medical data classification methods, comparing decision tree and system reconstruction analysis as applied to heart disease medical data mining. The data we study is collected from patients with coronary heart disease. It has 1,723 records of 71 attributes each. We use the system-reconstruction method to weight it. We use decision tree algorithms, such as induction of decision trees (ID3), classification and regression tree (C4.5), classification and regression tree (CART), Chi-square automatic interaction detector (CHAID), and exhausted CHAID. We use the results to compare the correction rate, leaf number, and tree depth of different decision-tree algorithms. According to the experiments, we know that weighted data can improve the correction rate of coronary heart disease data but has little effect on the tree depth and leaf number.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.7
• /
• pp.1218-1224
• /
• 2016

This paper presents the results of a study on the effect of surface modified alumina nanocomposites on electrical tree growth in epoxy insulation. Treeing experiments were conducted at a fixde AC voltage (500kV/mm, 10kV/60Hz)on unfilled epoxy sample as well as epoxy nanocomposites of 4 types with different loading and surface modified GDE gram. Time for tree growth as well as tree propagation length were studied. The results show that there is a significant improvement tree propagation time compare unfilled epoxy to epoxy nano alumina composites. Different tree propagation shapes as well as slower tree growth with 4 types nano alumina composites were observed.

• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.2
• /
• pp.1-6
• /
• 2023

In this paper, we present a new method for classifying malicious URLs to reduce cases of learning difficulties due to unfamiliar and difficult terms related to information protection. This study plans to extract only visually distinguishable features within the URL structure and compare them through map learning algorithms, and to compare the contribution values of the best map learning algorithm methods to extract features that have the most impact on classifying malicious URLs. As research data, Kaggle used data that classified 7,046 malicious URLs and 7.046 normal URLs. As a result of the study, among the three supervised learning algorithms used (Decision Tree, Support Vector Machine, and Logistic Regression), the Decision Tree algorithm showed the best performance with 83% accuracy, 83.1% F1-score and 83.6% Recall values. It was confirmed that the contribution value of https is the highest among whether to use https, sub domain, and prefix and suffix, which can be visually distinguished through the feature contribution of Decision Tree. Although it has been difficult to learn unfamiliar and difficult terms so far, this study will be able to provide an intuitive judgment method without explanation of the terms and prove its usefulness in the field of malicious URL detection.