• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.576-579
• /
• 2009

The amount of incoming e-mails is increasing rapidly due to the wide usage of Internet. Therefore, it is more required to classify incoming e-mails efficiently and accurately. Currently, the e-mail classification techniques are focused on two way classification to filter spam mails from normal ones based mainly on Bayesian and Rule. The clustering method has been used for the multi-way classification of e-mails. But it has a disadvantage of low accuracy of classification. In this paper, we propose a novel multi-way e-mail classification method that uses PCA for automatic category generation and dynamic category hierarchy for high accuracy of classification. It classifies a huge amount of incoming e-mails automatically, efficiently, and accurately.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.742-745
• /
• 2017

본 논문은 심장질환 도메인에 데이터 마이닝 기법을 적용한 연구로, 기존 환자의 정보에 대하여 K-최근접 이웃 알고리즘을 통해 결측 값을 대체하고, 대표적인 예측 분류기인 나이브 베이지안, 소포트 벡터 머신, 그리고 다층 퍼셉트론을 적용하여 각각 결과를 비교 및 분석한다. 본 연구의 실험은 K 최적화 과정을 포함하고 10-겹 교차 검증 방식으로 수행되었으며, 비교 및 분석은 정확도와 카파 통계치를 통해 판별한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.531-534
• /
• 2001

사이버 공간에서 활발히 이뤄지는고 있는 전자 상거래에 있어서 불특정 다수에게 고정된 광고를 뿌려주는 방식의 광고는 그 효과에 있어 제한이 있다. 본 논문에서는 베이지안 학습법에 기초한 회원 고객의 특성에 따른 분류화를 통한 고객에 따라 타겟광고가 가능한 기법에 대해 연구하고 이를 가능하게 하는 시스템을 제안한다.

• Journal of KIISE:Software and Applications
• /
• v.34 no.12
• /
• pp.1065-1074
• /
• 2007

Among various methods to compare reference signatures with an input signature, the segment-to-segment matching method has more advantages than global and point-to-point methods. However, the segment-to-segment matching method has the problem of having lower recognition rate according to the variation of partitioning points. To resolve this drawback, this paper proposes a signature verification method by considering linear discriminant analysis as well as segment-to-segment matching method. For the final decision step, we adopt statistical based Bayesian classifier technique to effectively combine two individual systems. Under the various experiments, the proposed method shows better performance than segment-to-segment based matching method.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.1
• /
• pp.77-87
• /
• 2009

Bayesian methods have been focused in recent years for solving small area estimation problems. In this paper, the hierarchical Bayes procedure is implemented via MCMC techniques and compared with the results of One-way, GLM-Normal, and GLM-Gamma cases by analyzing real data of insurance benefit for customer segmentations. After analyzing insurance benefit real data for customer segmentations, we can conclude that the insurance benefit estimator through the small area estimation is more efficient than the estimators by other methods. In addition, we found that the small area estimation gave accurate estimation result for the small number domains.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.449-450
• /
• 2009

사용자의 인터넷 소비성향을 파악하고 그에 적응적인 인프라 리소스를 제공하는 일은 네트워크 설계/관리자나 인터넷 서비스 공급자(ISP)들에게는 주요 관심사이다. 이러한 분석은 한정된 네트워크 자원을 보다 적절한 지점에 효율적인 방식으로 투자하도록 도와준다. 본 논문은 각종 인터넷 서비스를 활용하는 사용자들의 서비스(각종 인터넷 어플리케이션) 소비성향을 네트워크 트래픽 관찰만으로 파악할 수 있는 성향분류 척도를 제안한다. 아울러 베이지안 분류기를 사용하여 제안 척도를 활용한 사용자 성향 분류 방법을 함께 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.476-479
• /
• 2021

DBMS 파라미터 튜닝이란 데이터베이스에서 제공하는 다양한 파라미터의 값을 조율하여, 최적의 성능을 도출하는 과정이다. 데이터베이스 종류에 따라 파라미터 개수가 수십 개에서 수백 개로 다양하며, 각 기능이 모두 다르기 때문에 최적의 조합을 찾는 것은 쉽지 않다. 선행 연구에서는 BO 기법을 사용하여 적절한 파라미터 값을 추출했지만, 파라미터 개수에 비례하여 차원이 커지는 문제가 발생한다. 본 논문에서는 통계적으로 파라미터를 분류하여 탐색 공간을 줄인 다음 단계적으로 BO 를 수행하는 PBO 방식을 제안한다. 파라미터 값을 랜덤하게 할당하여 벤치마킹한 결과값을 군집화한 후, 각 군집별로 파라미터와의 연관성을 분석해 높은 상관관계를 가진 파라미터를 매칭시켜 분류한다. 제안하는 방법론을 검증하기 위하여 8 가지 회귀 모델과의 비교 실험을 통해 제안한 방법론의 우수성을 검증하였다.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.5
• /
• pp.605-610
• /
• 2002

In this paper, we propose a Internet filtering tool which allows parents to manage their children's Internet access, block access to Internet sites they deem inappropriate. The other filtering tools which like Cyber Patrol, NCA Patrol, Argus, Netfilter are oriented only URL filtering or keyword detection methods. Thease methods are used on limited fields application. But our approach is focus on image color space model. First we convert RGB color space to HLS(Hue Luminance Saturation). Next, this HLS histogram learned by our classification method tools which include cohesion factor, naive baysian, N-nearest neighbor. Then we use voting for result from various classification methods. Using 2,000 picture, we prove that 2-layer voting result have better accuracy than other methods.

• Journal of Navigation and Port Research
• /
• v.47 no.1
• /
• pp.1-9
• /
• 2023

Many studies have analyzed marine accidents, and since marine accident information is updated every year, it is necessary to periodically analyze and identify the causes. The purpose of this study was to prevent accidents by identifying and analyzing the causes of marine accidents using previous and new data. In marine accident data, 1,921 decisions by the Korea Maritime Safety Tribunal on marine accidents on fishing ships over 16 years were collected in consideration of the specificity of fishing ships, and 1,917 cases of accident notification text history by the Ministry of Maritime Affairs and Fisheries over 3 years were collected. The decision data and text data were classified according to variables and quantified. Prior probability was calculated using a Bayesian network using the quantified data, and fishing ship marine accidents were predicted using backward propagation. Among the two collected datasets, the decision data did not provide the types of fishing ships and fishing areas, and because not all fishing ship accidents were included in the decision data, the text data were selected. The probability of a fishing ship marine accident in which engine damage would occur in the West Sea was 0.0000031%, as calculated by backward propagation. The expected effect of this study is that it is possible to analyze marine accidents suitable for the characteristics of actual fishing ships using new accident notification text data to analyze fishing ship marine accidents. In the future, we plan to conduct research on the causal relationship between variables that affect fishing ship marine accidents.

• Journal of KIISE:Software and Applications
• /
• v.35 no.12
• /
• pp.774-779
• /
• 2008

In this work, we describe comments classification system using topic signature. Topic signature is widely used for selecting feature in document classification and summarization. Comments are short and have so many word spacing errors, special characters. We firstly convert comments into 7-gram. We consider the 7-gram as sentence. We convert the 7-gram into 3-gram. We consider the 3-gram as word. We select key feature using topic signature and classify new inputs by the Naive Bayesian method. From the result of experiments, we can see that the proposed method is outstanding over the previous methods.