• Journal of Information Processing Systems
• /
• v.14 no.2
• /
• pp.418-434
• /
• 2018

With the increasing use of the Internet and electronic documents, automatic text categorization becomes imperative. Several machine learning algorithms have been proposed for text categorization. The k-nearest neighbor algorithm (kNN) is known to be one of the best state of the art classifiers when used for text categorization. However, kNN suffers from limitations such as high computation when classifying new instances. Instance selection techniques have emerged as highly competitive methods to improve kNN through data reduction. However previous works have evaluated those approaches only on structured datasets. In addition, their performance has not been examined over the text categorization domain where the dimensionality and size of the dataset is very high. Motivated by these observations, this paper investigates and analyzes the impact of instance selection on kNN-based text categorization in terms of various aspects such as classification accuracy, classification efficiency, and data reduction.

• Journal of information and communication convergence engineering
• /
• v.7 no.1
• /
• pp.35-40
• /
• 2009

Many researchers strive to research on ways on how to improve the performance of RFID system and many papers were written to solve one of the major drawbacks of potent technology related with data management. As RFID system captures billions of data, problems arising from dirty data and large volume of data causes uproar in the RFID community those researchers are finding ways on how to address this issue. Especially, effective data management is important to manage large volume of data. Data reduction techniques in attempts to address the issues on data are also presented in this paper. This paper introduces readers to a new data reduction algorithm that might be an alternative to reduce data in RFID Systems. A process on how to extract data from the reduced database is also presented. Performance study is conducted to analyze the new data reduction algorithm. Our performance analysis shows the utility and feasibility of our categorization reduction algorithms.

• Communications for Statistical Applications and Methods
• /
• v.23 no.3
• /
• pp.259-268
• /
• 2016

High-dimensional survival data with large numbers of predictors has become more common. The analysis of such data can be facilitated if the dimensions of predictors are adequately reduced. Recent studies show that a method called sliced inverse regression (SIR) is an effective dimension reduction tool in high-dimensional survival regression. However, it faces incapability in implementation due to a double categorization procedure. This problem can be overcome in the right-censoring type by transforming the observed survival time and censoring status into a single variable. This provides more flexibility in the categorization, so the applicability of SIR can be enhanced. Numerical studies show that the proposed transforming approach is equally good to (or even better) than the usual SIR application in both balanced and highly-unbalanced censoring status. The real data example also confirms its practical usefulness, so the proposed approach should be an effective and valuable addition to usual statistical practitioners.

• Ecology and Resilient Infrastructure
• /
• v.3 no.3
• /
• pp.207-211
• /
• 2016

This study focuses on the categorization of the phenomenon of vegetative recruitment on riparian channels, so called, the phenomenon from "white river" to "green river", and proposes for the corresponding research direction. According to the literature review and research outputs obtained from the authors' previous research performed in Korea within a limited scope, the necessary and sufficient conditions for the recruitment and retrogression of riparian vegetation may be the mechanical disturbance (riverbed tractive stress), soil moisture (groundwater level, topography, composition of riverbed material, precipitation etc.), period of submergence, extreme weather, and nutrient inflow. In this study, two categories, one for the reduction in spring flood due to the change in spring precipitation pattern in unregulated rivers and the other for the increase in nutrient inflow into streams, both of which were partially proved, have been added in the categorization of the vegetative recruitment and retrogression on the riparian channels. In order to scientifically investigate further the phenomenon of the riparian vegetative recruitment and retrogression and develop the working riparian vegetative models, it is necessary to conduct a systematic nationwide survey on the "white to green" rivers, establishment of the categorization of the vegetation recruitment and retrogression based on the proof of those hypotheses and detailed categorization, development of the working mathematical models for the dynamic riparian vegetative recruitment and retrogression, and adaptive management for the river changes.

• Journal of the Korean Society for Library and Information Science
• /
• v.43 no.1
• /
• pp.313-332
• /
• 2009

Cross-language text categorization(CLTC) can classify documents automatically using training set from other language. In this study, collections appropriated for CLTC were extracted from KTSET. Classification performance of various CLTC methods were compared by SVM classifier using machine translation. Results showed that the classification performance in the order of poly-lingual training method, training-set translation and test-set translation. However, training-set translation could be regarded as the most useful method among CLTC, because it was efficient for machine translation and easily adapted to general environment. On the other hand, low performance was shown to be due to the feature reduction or features with no subject characteristics, which occurred in the process of machine translation of CLTC.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.2
• /
• pp.195-202
• /
• 2001

In this paper, we show a study on how to model a phoneme of which acoustic feature is changed according to both left-hand and right-hand phonemes. For this purpose, we make a comparative study on two kinds of algorithms; a unit reduction algorithm and decision tree modeling. The unit reduction algorithm uses only statistical information while the decision tree modeling uses statistical information and Korean acoustical information simultaneously. Especially, we focus on how to model context-dependent phonemes based on decision tree modeling. Finally, we show the recognition rate when context-dependent phonemes are obtained by the decision tree modeling.

• Environmental and Resource Economics Review
• /
• v.25 no.4
• /
• pp.565-590
• /
• 2016

In accordance with the global efforts to reduce greenhouse gas emissions, Korean government submitted its INDC (Intended Nationally Determined Contribution) of 25.7% for domestic reduction and the total of 37% reduction by 2030 including the purchase of emission reduction permit from abroad. In this study, 25.7% reduction target is being evaluated to see its impact on domestic energy system using the integrated assessment model, GCAM (Global Change Assessment Model). Results show that electricity generation from fossil fuel technologies using coal and gas decrease by 28.0%, 13.5% while that of biomass, wind power, solar energy increase by 47.6%, 22.0% and 45.4%, respectively. It is worth noting that so called new technology such as USC (ultra supercritical power generation) does not contribute to achieving the emission reduction target and careful and quantitative analysis is required for such categorization in the future.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.358-360
• /
• 2006

LDA는 그룹간 간격을 최대화하고 그룹내 분산을 최소화하는 선형변환을 구함으로써 차원 감소된 공간에서 분별력(classification performance)을 높이는 선형 차원 감소 방법이다. 본 논문에서는 저샘플 문제(undersampled problem)에서 LDA를 적용할 수 있도록 QR-분해를 이용한 효율적인 차원 감소 방법을 제안한다. 특히 제안되는 방법은 문서 분류 문제에서처럼 한 문서가 몇 개의 카테고리에 중복적으로 속하는 경우 등 데이터의 독립성이 보장되지 않는 경우에도 효과적으로 적용될 수 있다는 장점이 있다.

• Journal of Korean Neurosurgical Society
• /
• v.39 no.6
• /
• pp.432-437
• /
• 2006

Objective : In order to establish the index of degeneration, the authors performed a histochemical study with Safranin-O staining and investigated the occurrence of apoptosis in the human intervertebral disc. Methods : Eighteen intervertebral disc specimens surgically extracted from the patients and two additional specimens from the autopsied cases were stained with Safranin-O for proteoglycan according to a standard protocol. Terminal deoxynucleotidyl transferase-mediated deoxyuridine triphosphate- biotin nick end labeling[TUNEL] was used to detect the fragmented DNA known to be associated with apoptotic cell death and classification scheme was formulated for categorization of the degree of Safranin-O staining [normal, moderate reduction, faint] by modification of Makin's histological-histochemical grading. The Kruskal-Wallis H test and Chi-square test were used for statistical analysis. Results : The statistical results showed a significant difference in the mean age between "normal" Safranin-O staining group and the others [19.3 versus 55, 43.4, p=0021]. However, there was no statistically significant correlation between Safranin-O staining and MR grading of disc degeneration. Only six of eighteen surgical specimens and none in autopsies showed positive apoptotic cells in TUNEL staining. Conclusion : The determination of the degree of degeneration in surgically obtained disc tissue per se by histochemical staining or by the degree of apoptosis that corresponds to its morphologic change was not feasible.

• Clinical and Experimental Pediatrics
• /
• v.64 no.5
• /
• pp.196-207
• /
• 2021

Over the last few decades, the rates of pediatric obesity have more than doubled regardless of sociodemographic categorization, and despite these rates plateauing in recent years there continues to be an increase in the severity of obesity in children and adolescents. This review will discuss the pediatric obesity mediated cardiovascular disease (CVD) risk factors such as attenuated levels of satiety and energy metabolism hormones, insulin resistance, vascular endothelial dysfunction, and arterial stiffness. Additionally, early intervention to combat pediatric obesity is critical as obesity has been suggested to track into adulthood, and these obese children and adolescents are at an increased risk of early mortality. Current suggested strategies to combat pediatric obesity are modifying diet, limiting sedentary behavior, and increasing physical activity. The effects of exercise intervention on metabolic hormones such as leptin and adiponectin, insulin sensitivity/resistance, and body fat in obese children and adolescents will be discussed along with the exercise modality, intensity, and duration. Specifically, this review will focus on the differential effects of aerobic exercise, resistance training, and combined exercise on the cardiovascular risks in pediatric obesity. This review outlines the evidence that exercise intervention is a beneficial therapeutic strategy to reduce the risk factors for CVD and the ideal exercise prescription to combat pediatric obesity should contain both muscle strengthening and aerobic components with an emphasis on fat mass reduction and long-term adherence.