• The Transactions of the Korea Information Processing Society
• /
• v.6 no.12
• /
• pp.3469-3476
• /
• 1999

In spatial database based on spatial data structures, instead of one-dimensional indexing structure, new indexing structure which corresponds to multi-dimensional features of spatial objects is required. In order to meet those requirements, in this paper we proposed new indexing structure for efficient retrieval of spatial database by carrying through the feature analysis of conventional multi-dimensional indexing structures. To improve the sequential search method of supernodes in the conventional X-tree and to reduce the retrieval time in case of generating the huge supernode, we proposed a indexing structure integrating the kd-tree based on point index structure into the X-tree. We implemented the proposed indexing structure and analyzed its retrieval time according to the dimension and distribution of experimental data.

• Korean Journal of Ecology and Environment
• /
• v.49 no.3
• /
• pp.236-243
• /
• 2016

It was a case study to use as a basic data for efficient the preservation and management of subalpine coniferous forest in national parks. It is based on inhabitation condition of 210 individuals of Abies koreana Wilson that was found through local investigation in the sub-alpine zone of Jirisan National Park and Songnisan National Park. It analyzed the effect of the geographical location and topographical features, which are the basics of location environment, on the growth of A. koreana. The variables related to the growth of A. koreana are tree height and diameter at breast height. Topographical features include geographical longitude, altitude above sea level, slope of the mountains, aspect that describes the direction in which a slope faces and topographical wetness index. Topographical features were extracted through GIS spatial analysis. It used canonical correlation analysis to estimate whether the two variables groups have related to each other and how much they are related, if any, and estimated the effect of the geographical and topographical features on the growth structure of A. koreana using multiple regression analysis. The tree height and diameter at breast height that represent the growth structure of A. koreana show greater relation to geographical latitude distribution than topographical feature and the geographical and topographical factors show greater relation to diameter at breast height than tree height. The growth structure's variable and geographical and topographical variable of A. koreana have meaningful relation and the result shows that geographical and topographical variables explain 18.1% of the growth structure. The variables that affect the diameter at breast height of A. koreana are geographical latitude, topographical wetness index, aspect and altitude, which are put in order of statistical significance. The higher the latitude is, the smaller the diameter at breast height. Depending on the topographical feature, it becomes bigger. The variable that affects the tree height is topographical wetness index, which was the only meaningful variable. Overall, the tree height and diameter at breast height that are related to the growth structure of A. koreana are affected by geographical and topographical feature. It showed that the geographical feature affected it the most. Especially the effect of water among the topographical features is expected to be bigger than the other topographical factors. Based on the result, it is expected that geographical and topographical feature is an important factor for the growth structure of A. koreana. Even though it considered only the geographical and topographical features and used spatial analysis data produced by GIS, the research results will be useful for investigating and researching the growth environment of coniferous forest inhabiting in sub-alpine zone of national parks and are expected to be used as basic data for establishing measures to efficiently manage and preserve evergreen needleaf tree such as A. koreana.

• Journal of Korea Multimedia Society
• /
• v.23 no.9
• /
• pp.1155-1163
• /
• 2020

Deep learning approach is emerging as a new way to improve the accuracy of tree species identification using bark image. However, the approach has not been studied enough because it is confronted with the problem of acquiring a large volume of bark image dataset. This study solved this problem by utilizing a pretrained off-the-shelf DCNN model. It compares the discrimination power of bark features extracted by each DCNN model. Then it extracts the features by using a selected DCNN model and feeds them to a multi-layer perceptron (MLP). We found out that the ResNet50 model is effective in extracting bark features and the MLP could be trained well with the features reduced by the principal component analysis. The proposed approach gives accuracy of 99.1% and 98.4% for BarkTex and Trunk12 datasets respectively.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.5
• /
• pp.141-148
• /
• 1994

Both the neural network classifier utilizing multi-layer perceptron and the linear tree classifier composed of hierarchically structured linear discriminating functions can form arbitrarily complex decision boundaries in the feature space and have very similar decision making processes. In this paper, a new method for automatically choosing the number of neurons in the hidden layers and for initalzing the connection weights between the layres and its supporting theory are presented by mapping the sequential structure of the linear tree classifier to the parallel structure of the neural networks having one or two hidden layers. Experimental results on the real data obtained from the military ship images show that this method is effective, and that three exists no siginificant difference in the classification acuracy of both classifiers.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.415-421
• /
• 2007

This paper proposes a convolution tree kernel-based approach for relation extraction where the parse tree is expanded with entity features such as entity type, subtype, and mention level etc. Our study indicates that not only can our method effectively capture both syntactic structure and entity information of relation instances, but also can avoid the difficulty with tuning the parameters in composite kernels. We also demonstrate that predicate verb information can be used to further improve the performance, though its enhancement is limited. Evaluation on the ACE2004 benchmark corpus shows that our system slightly outperforms both the previous best-reported feature-based and kernel-based systems.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2002.04a
• /
• pp.274-283
• /
• 2002

This paper presents an efficient models for reinforeced concrete structures using CART-ANFIS(classification and regression tree-adaptive neuro fuzzy inference system). a fuzzy decision tree parttitions the input space of a data set into mutually exclusive regions, each of which is assigned a label, a value, or an action to characterize its data points. Fuzzy decision trees used for classification problems are often called fuzzy classification trees, and each terminal node contains a label that indicates the predicted class of a given feature vector. In the same vein, decision trees used for regression problems are often called fuzzy regression trees, and the terminal node labels may be constants or equations that specify the Predicted output value of a given input vector. Note that CART can select relevant inputs and do tree partitioning of the input space, while ANFIS refines the regression and makes it everywhere continuous and smooth. Thus it can be seen that CART and ANFIS are complementary and their combination constitutes a solid approach to fuzzy modeling.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.652-654
• /
• 2021

Attacks such as DDoS are detected by the intrusion detection system and can be prevented early. DDoS attack traffic was analyzed using the decision tree. Deterministic features with high importance were found, and the accuracy was verified by proceeding the decision tree for only those properties. And the contents of false positive and false negative traffic were analyzed. As a result, the accuracy of one attribute was 98% and the two attributes were 99.8%, respectively.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.6
• /
• pp.1058-1062
• /
• 2008

In clinical decision support system(CDSS), unlike rule-based expert method, appropriate data-driven machine learning method can easily provide the information of individual feature(clinical test) for disease classification. However, currently developed methods focus on the improvement of the classification accuracy for diagnosis. With the analysis of feature importance in classification, one may infer the novel clinical test sets which highly differentiate the specific diseases or disease states. In this background, we introduce a novel CDSS that integrate a classifier and feature selection module together. Random forest algorithm is applied for the classifier and the feature importance measure. The system selects the significant clinical tests discriminating the diseases by examining the classification error during backward elimination of the features. The superior performance of random forest algorithm in clinical classification was assessed against artificial neural network and decision tree algorithm by using breast cancer, diabetes and heart disease data in UCI Machine Learning Repository. The test with the same data sets shows that the proposed system can successfully select the significant clinical test set for each disease.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.187-194
• /
• 1996

In this paper, we propose regression neural networks based on regression trees. We map regression trees into three layered feedforward networks. We put multi feature split functions in the first layer so that the networks have a better chance to get optimal partitions of input space. We suggest two supervised learning algorithms for the network training and test both in single feature split and multifeature split functions. In experiments, the proposed regression neural networks is proved to have the better learning performance than those of the single feature split regression trees and the single feature split regression networks. Furthermore, we shows that the proposed learning schemes have an effect to prune an over-grown tree without degrading the learning performance.

• Journal of the Semiconductor & Display Technology
• /
• v.14 no.4
• /
• pp.56-60
• /
• 2015

Mobile devices like smartphones and tablets are becoming increasingly capable in terms of processing power. Although they are already used in computer vision, no comparable measurement experiments of the popular feature extraction algorithm have been made yet. That is, local feature descriptors are widely used in many computer vision applications, and recently various methods have been proposed. While there are many evaluations have focused on various aspects of local features, matching accuracy, however there are no comparisons considering on speed trade-offs of recent descriptors such as ORB, FAST and BRISK. In this paper, we try to provide a performance evaluation of feature descriptors, and compare their matching precision and speed in KD-Tree setup with efficient computation of Hamming distance. The experimental results show that the recently proposed real valued descriptors such as ORB and FAST outperform state-of-the-art descriptors such SIFT and SURF in both, speed-up efficiency and precision/recall.