• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.82-84
• /
• 2001

데이터 분류(classification)란 이미 분류된 객체집단군 즉, 학습 데이터에 대한 분석을 바탕으로 아직 분류되지 않는 개체의 소속 집단을 결정하는 작업이다. 현재까지 제안된 여러 가지 분류 모델 중 결정 트리(decision tree)는 인간이 이해하기 쉬운 형태를 갖고 있기 때문에 탐사적인 데이터 마이닝(exploatory)작업에 특히 유용하다. 본 논문에서는 결정 트리 분류에 다중 추상화 수준 문제(multiple abstraction level problem)를 소개하고 이러한 문제를 다루기 위한 실용적인 방법을 제안한다. 데이터의 다중 추상화 수준 문제를 해결하기 위해 추상화 수준을 강제로 같게 하는 것이 문제를 해결할 수 없다는 것을 보인 후, 데이터 값들 사이의 일반화, 세분화 관련성을 그대로 유지하면서 존재하는 유용화할 수 있는 방법을 제시한다.

• Communications for Statistical Applications and Methods
• /
• v.11 no.3
• /
• pp.539-551
• /
• 2004

Multiple responses are often observed in many application fields, such as customer's time-of-day pattern for using internet. Some decision trees for multiple responses have been constructed by many researchers. However, if the response is a high-dimensional vector that can be thought of as a discretized function, then fitting a multivariate decision tree may be unsuccessful. Yu and Lambert (1999) suggested spline tree and principal component tree to analyze high dimensional response vector by using dimension reduction techniques. In this paper, we shall propose factor tree which would be more interpretable and competitive. Furthermore, using Korean internet company data, we will analyze time-of-day patterns for internet user.

• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.2
• /
• pp.21-25
• /
• 2023

The purpose of this study was to compare the performance using multiple regression models to predict the energy consumption of steel industry. Specific independent variables were selected in consideration of correlation among various attributes such as CO2 concentration, NSM, Week Status, Day of week, and Load Type, and preprocessing was performed to solve the multicollinearity problem. In data preprocessing, we evaluated linear and nonlinear relationships between each attribute through correlation analysis. In particular, we decided to select variables with high correlation and include appropriate variables in the final model to prevent multicollinearity problems. Among the many regression models learned, Boosted Decision Tree Regression showed the best predictive performance. Ensemble learning in this model was able to effectively learn complex patterns while preventing overfitting by combining multiple decision trees. Consequently, these predictive models are expected to provide important information for improving energy efficiency and management decision-making at steel industry. In the future, we plan to improve the performance of the model by collecting more data and extending variables, and the application of the model considering interactions with external factors will also be considered.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.2
• /
• pp.53-58
• /
• 2013

A Fat-Tree topology has multiple paths between any pair of hosts. The delay for the multiple paths with an equal number of hops depends mainly on the queuing delay. However, most of the existing load-balancing schemes do not sufficiently exploit the characteristics of Fat-Tree. In most schemes load-balancing is performed at a flow level. Packet-level load-balancing schemes usually require the availability of special transport layer protocols to address packet reordering. In this paper, we propose a new packet-level load-balancing scheme which can enhance network utilization while minimizing packet reordering in Fat-Trees. Simulation results show that the proposed scheme provides as high TCP throughput as a randomized flow-level Valiant load balancing scheme for a best case.

• Research in Plant Disease
• /
• v.23 no.4
• /
• pp.355-362
• /
• 2017

The 4 viruses, the Apple chlorotic leaf spot virus (ACLSV), Apple stem pitting virus (ASPV), Apple stem grooving virus (ASGV), and Apple mosaic virus (ApMV) and 1 viroid, Apple scar skin viroid (ASSVd) are known major viral pathogens of apple trees in Korea. Infection degree of the 5 viral pathogens in the commercial nursery trees of major apple cultivars, 'Hongro', 'Fuji' and bud mutation of 'Fuji' was investigated. Infection ratio of the ACLSV, ASPV and ASGV for scion of an apple cultivar 'Hongro' were 100%, 81.3% and 100%, respectively. On the other hand, no infection for either ApMV and ASSVd detected. For the root stock of the cultivar, infection ratio of ACLSV, ASPV and ASGV showed 87.5%, 81.3% and 100% as well as ApMV and ASSVd were 12.5% and 6.3%, respectively. From the scion of apple cultivars 'Fuji' and bud mutation of 'Fuji', infection ratio of ACLSV, ASPV and ASGV showed 86.7%, 86.7% and 100%, respectively. Whereas, no infection for either ApMV or ASSVd detected. From the root stock of the cultivars, infection ratio of ACLSV, ASPV and ASGV showed 86.7%, 93.3% and 93.3% as well as ApMV and ASSVd were 12.5% and 6.3%, respectively. Result of our study indicates that most of commercial nursery apple trees were supplied with multiple infections by apple viruses causing potential losses for apple growers and, henceforth, agricultural policy for supply of the virus-free trees should be employed as soon as possible.

• Journal of the Korean Society of Safety
• /
• v.31 no.5
• /
• pp.187-194
• /
• 2016

A single fire event within a fire area can cause multiple initiating events considered in internal events probabilistic safety assessment (PSA). For an example, a fire event in turbine building fire area can cause a loss of the main feed-water and loss of off-site power initiating events. This fire initiating event could result in special plant responses beyond the scope of the internal events PSA model. One approach to address a fire initiating event is to develop a specific fire event tree. However, the development of a specific fire event tree is difficult since the number of fire event trees may be several hundreds or more. Thus, internal fire events PSA model has been generally constructed by modifications of the pre-developed internal events PSA model. New accident sequence logics not covered in the internal events PSA model are separately developed to incorporate them into the fire PSA model. Recently, many fire PSA models have fire induced initiating event fault trees not shown in an internal event PSA model. Up to now, there has been no analytical comparative study on the constructions of fire events PSA model using internal events PSA model with and without fault trees of initiating events. In this study, the changing process of internal events PSA model to fire events PSA model is analytically presented and discussed.

• The KIPS Transactions:PartA
• /
• v.9A no.3
• /
• pp.341-350
• /
• 2002

As network environments have been improved and the use of internet has been increased, mobile agent technologies are widely used in the fields of information retrieval, network management, electronic commerce, and parallel/distributed processing. Recently, a lot of researchers have studied the concepts of parallel/distributed processing based on mobile agents. SPMD is the parallel processing method which transmits a program to all the computers participated in parallel environment, and performs a work with different data. Therefore, to transmit fast a program to all the computers is one of important factors to reduce total execution time. In this paper, we consider the parallel environment consisting of mobile agents system, and propose a new method which transmits fast a mobile agent code to all the computers using binomial trees in order to efficiently perform the SPMD parallel processing. The proposed method is compared with another ones through experimental evaluation on the IBM's Aglets, and gets greatly better performance. Also this paper deals with fault tolerances which can be occurred in transmitting a mobile agent using binomial trees.

• Journal of Ecology and Environment
• /
• v.35 no.2
• /
• pp.91-98
• /
• 2012

This study was performed in order to suggest the possibility of tree species classification using high-resolution QuickBird-2 images spectral characteristics comparison(digital numbers [DNs]) of tree species, tree species classification, and accuracy verification. In October 2010, the tree species of three conifers and eight broad-leaved trees were examined in the areas studied. The spectral characteristics of each species were observed, and the study area was classified by image classification. The results were as follows: Panchromatic and multi-spectral band 4 was found to be useful for tree species classification. DNs values of conifers were lower than broad-leaved trees. Vegetation indices such as normalized difference vegetation index (NDVI), soil brightness index (SBI), green vegetation index (GVI) and Biband showed similar patterns to band 4 and panchromatic (PAN); Tukey's multiple comparison test was significant among tree species. However, tree species within the same genus, such as $Pinus$ $densiflora-P.$ $rigida$ and $Quercus$ $mongolica-Q.$ $serrata$, showed similar DNs patterns and, therefore, supervised classification results were difficult to distinguish within the same genus; Random selection of validation pixels showed an overall classification accuracy of 74.1% and Kappa coefficient was 70.6%. The classification accuracy of $Pterocarya$ $stenoptera$, 89.5%, was found to be the highest. The classification accuracy of broad-leaved trees was lower than expected, ranging from 47.9% to 88.9%. $P.$ $densiflora-P.$ $rigida$ and $Q.$ $mongolica-Q.$ $serrata$ were classified as the same species because they did not show significant differences in terms of spectral patterns.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2018.04a
• /
• pp.52-52
• /
• 2018

Apple (Malus domestica) is one of the most economically important fruits in Korea. But virus infection has decreased sustainable production of apple and caused the serious problems such as yield loss and poor fruit quality. Virus or viroid infection including Apple chlorotic leaf spot virus (ACLSV), Apple stem pitting virus (ASPV), Apple stem grooving virus (ASGV), Apple mosaic virus (ApMV) and Apple scar skin viroid (ASSVd) has been also reported in Korea, furthermore, its damages and economic losses have increased constantly. In our research, we tried to survey virus infection for commercial nursery trees of major apple cultivars, especially dwarfing rootstocks 'M.9' and 'M.26' as well as scions. Trees were collected from 11 locations which have produced a great amount of apple nursery stocks in Korea. Infection degree was investigated in apple cultivars, 'Hongro' and 'Fuji' using RT-PCR method. In the scion of cultivar 'Hongro', infection ratio of ACLSV, ASPV and ASGV were 100%, 81.8% and 100% respectively. In the rootstock of cultivar 'Hongro', infection ratio of ACLSV, ASPV, ASGV and ApMV were 90.9%, 81.8%, 100% and 9.1% respectively. In the scion of cultivar 'Fuji', infection ratio of ACLSV, ASPV and ASGV were 81.8%, 90.9% and 100% respectively. In the rootstock of cultivar 'Fuji', infection ratio of ACLSV, ASPV, ASGV and ApMV were 81.8%, 90.9%, 100% and 9.1% respectively. Infection of ASSVd was not detected in both cultivars. From our results, it was found that most of apple rootstocks and scions had multiple infections by apple viruses which have caused economic damage in fruit production.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.4B
• /
• pp.346-353
• /
• 2011

Routing schemes that service applications with various delay times, maintaining the long network life time are required in wireless sensor & actor networks. However, it is known that network lifetime and hop count of trees used in routing methods have the tradeoff between them. In this paper, we propose a Pareto Ant Colony Optimization algorithm to find the Pareto tree set such that it optimizes these both tradeoff objectives. As it enables applications which have different delay times to select appropriate routing trees, not only satisfies the requirements of various multiple applications but also guarantees long network lifetime. We show that the Pareto tree set found by proposed algorithm consists of trees that are closer to the Pareto optimal points in terms of hop count and network lifetime than minimum spanning tree which is a representative routing tree.