• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• Journal of the Korean earth science society
• /
• v.32 no.6
• /
• pp.525-536
• /
• 2011

In any applications using various types of spatial data, it is very important to account for the scale differences among available data sets and to change the scale to the target one as well. In this paper, we propose to use a geostatistical downscaling approach based on vaiorgram deconvloution and block simulation to generate fine-scale categorical thematic maps from coarse-scale fraction data. First, an iterative variogram deconvolution method is applied to estimate a point-support variogram model from a block-support variogram model. Then, both a direct sequential simulation based on area-to-point kriging and the estimated point-support variogram are applied to produce alternative fine-scale fraction realizations. Finally, a maximum a posteriori decision rule is applied to generate the fine-scale categorical thematic maps. These analytical steps are illustrated through a case study of land-cover mapping only using the block fraction data of thematic classes without point data. Alternative fine-scale fraction maps by the downscaling method presented in this study reproduce the coarse-scale block fraction values. The final fine-scale land-cover realizations can reflect overall spatial patterns of the reference land-cover map, thus providing reasonable inputs for the impact assessment in change of support problems.

• Journal of Information Technology and Architecture
• /
• v.9 no.3
• /
• pp.233-241
• /
• 2012

Architecture framework (AF) is a guideline to define components needed to develop and operate enterprise architecture (EA), and to define relationships among the components. There are many architecture frameworks to operate EA of governments and businesses such as Zachman framework, DoDAF, TOGAF, FEAF, and TEAF. DoDAF is the most representative AF to support the development of the EA in the military domain. DoDAF is composed of eight viewpoints and 40 views that are affiliated with the viewpoints. To develop an AF for a specific goal, system architects decide a set of views. Furthermore, they determine data that are needed for a view modeling. However, views and data in DoDAF are structurally inter-related explicitly and/or implicitly. So, developing an AF for a specific goal is going to be a project to be carried out over a long haul. To reduce the burden of its development, in this paper, we develop ONT-SAF (Ontology for DoDAF) that can infer inter-relationships like referential and transitive relationships and the sequences among the views. Furthermore, to promote reusability and consistency of the views and the data within an AF, we adopt the view-data separation strategy. ONT-DAT contains classes like 'viewpoint', 'view', 'data', 'expression method', and 'reference model', and 11 properties including 'hasView.' To prove the effectiveness of ONT-SAF, we perform a case study.

• Journal of vocational education research
• /
• v.35 no.4
• /
• pp.109-129
• /
• 2016

Korea has recently invested much of its effort in fostering talents in scientific fields to establish a foundation for sustainable future growth. From this perspective, the ministry of education has come up with a special rule aimed at achieving the substantiality of engineering schools in universities. The ministry has been providing educational support by providing a tech-innovation center, industry-oriented education, and policies such as PRIME. Despite this support, most students in the natural science field end up being hired in fields not related to their majors. There has been a growing opinion regarding the need for career education for these students. In this research, based on a social cognitive career theory (SCCT) model that provides a comprehensive understanding of career development, this research would like to practically examine the relationship among college students' career preparation behaviors and influencing variables, such as grit, career decision-making self-efficacy, outcome expectation, and major interest. Data from 153 natural-science majors at A college in Korea were collected and analyzed using path analysis. The result was that the data strongly supported the model explaining the relationship between career preparation behaviors and influencing variables. Based on this result, we propose that career education that can promote grit, career decision-making self-efficacy, outcome expectation, and major interest is required to encourage students in the field of the natural sciences to pursue career preparation behaviors related to their majors.

• Proceedings of the Technology Innovation Conference
• /
• 1996.12a
• /
• pp.196-238
• /
• 1996

Because global innovation-based competition is increasing and the amount of R&D expenditures becomes severely large, it is more likely that mergers and collaborative ventures tend to affect adversely to R&D competition Against this trend, enforcing agency of advanced countries including U.S.A are reassessing certain aspects of competition policy toward mergers and acquisition to ensure that procompetitive, efficiency-enhancing transactions are permitted. The role of competition policy is developing and appropriating new technology and protects the risks involved in the licensing contract of technologies. The role of intellectual property rights is also contrived to promote technological innovation and to increase consumer welfare. That is to say, dynamic efficiency of intellectual property rights includes (l) increase in social welfare and (2) promotion of growth by improvement of quality through invention and commercialization of new product as well as enhanced productive efficiency thorough appropriating new process. Because intellectual property rights are licensed to make use of complementary inputs, the rule of reason approach seems proper when applying antitrust law. To analyze the "Antitrust Guidelines for the Licensing and Acquisition of Intellectual Property"by DOJ and FTC in U.S.A, the author surveyed pros and cons on innovation market approach. This approach will only be used in a narrow range of situations when the evidence is solid, concentration numbers are extremely high, and the agencies can predict with a high degree of certainty that the merger will likely lead either to a slowing in the pace of innovation or the loss of an alternative research track that is likely to lead to a product beneficial to consumers. The author introduces the studies on licensing contract of intellectual property rights and competition polices on behalf of potential inquirers. Also the author invites the interdisciplinary researchers to analyze further with a model on the aspects of the "Notice 1995-10 for Types and Criteria on Unfair Transaction Behavior in International Contracts" by Fair Trade Committee of Korea.

• Korean Journal of Biological Psychiatry
• /
• v.19 no.3
• /
• pp.140-145
• /
• 2012

Objectives : ST8SIA2 (ST8 alpha-N-acetyl-neuraminide alpha-2, 8-sialyltransferase 2 gene) is located at 15q26, a susceptibility locus for schizophrenia. Some previous research had indicated that single-nucleotide polymorphisms (SNPs) in the promoter region of ST8SIA2 were associated with schizophrenia in Japanese and Chinese populations. We investigated the association between SNPs in the promoter region of ST8SIA2 and schizophrenia in the Korean population. Methods : The study subjects were 190 Korean patients with schizophrenia and 190 healthy controls. We performed allelic, genotypic, and haplotypic association analyses for rs3759916, rs3759915 and rs3759914 of ST8SIA2. All genotypes were determined by direct sequencing. Results : In the genotype-based analysis, rs3759914 showed a nominally significant association with schizophrenia under recessive genotypic model (p = 0.047). However, this association did not remain statistically significant after correction for multiple testing. Both allelic and haplotype analyses did not show any significant association. Conclusions : These findings suggest that ST8SIA2 does not play a major role in the susceptibility to schizophrenia in the Korean population. Further studies with a larger number of subjects are required to definitively rule out minor effects of this gene on schizophrenia vulnerability.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.1
• /
• pp.116-126
• /
• 2006

The purpose of this study is to analyze the growing course of Busan, Gimhae and Jinhae and further find patterns of the urban growth. This study shows that patterns of the urban growth differ from city to city, being influenced by the city's characteristics. Acknowledging this fact would help the decision maker to determine the developing plan of the urban. The methodology for this study is as follows; Fuzzy set concept is applied to minimize the data loss. At the same time, the AHP is used to give a relative weight to each factor. In order to be able to manage the change based on the dynamic model and time, Cellular Automata is introduced to simulate the growth of urban. The results show that the pattern of Gimhae's and Jinhae's growth is the same, whereas that of Busan is different from them. That is to say, each city has regional characteristics. And the pattern of the urban growth is influenced by the regional conditions of the city.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.723-733
• /
• 2009

The crucial problems of K-means clustering are deciding the number of clusters and initial centroids of clusters. Hence, the steps of K-means clustering are generally consisted of two-stage clustering procedure. The first stage is to run hierarchical clusters to obtain the number of clusters and cluster centroids and second stage is to run nonhierarchical K-means clustering using the results of first stage. Here we provide automated K-means clustering procedure to be useful to obtain initial centroids of clusters which can also be useful for large data sets, and provide software program implemented using R.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.139-155
• /
• 2003

This paper presents the new methodology of analyzing and classifying patterns of customers in mobile telecommunication market to enhance the performance of predicting the credit information based on the decision tree and neural network. With the application of variance selection process from decision tree, the systemic process of defining input vector's value and the rule generation were developed. In point of customer management, this research analyzes current customers and produces the patterns of them so that the company can maintain good customer relationship and makes special management on the customer who has huh potential of getting out of contract in advance. The real implementation of proposed method shows that the predicted accuracy is higher than existing methods such as decision tree(CART, C4.5), regression, neural network and combined model(CART and NN).

• Journal of KIISE
• /
• v.41 no.11
• /
• pp.992-1005
• /
• 2014

Coreference resolution finds all expressions that refer to the same entity in a document. Coreference resolution is important for information extraction, document classification, document summary, and question answering system. In this paper, we adapt Stanford's Multi-pass sieve system, the one of the best model of rule based coreference resolution to Korean. In this paper, all noun phrases are considered to mentions. Also, unlike Stanford's Multi-pass sieve system, the dependency parse tree is used for mention extraction, a Korean acronym list is built 'dynamically'. In addition, we propose a method that calculates weights by applying transitive properties of centers of the centering theory when refer Korean pronoun. The experiments show that our system obtains MUC 59.0%, $B_3$ 59.5%, Ceafe 63.5%, and CoNLL(Mean) 60.7%.