• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2019년도 추계학술발표대회
• /
• pp.968-971
• /
• 2019

본 논문에서는 정상과 봇넷 트래픽을 분류하기 위해 트래픽 데이터에서 페이로드 패턴을 추한다. 추출된 가변 길이의 패턴으로 마코브 체인 분류 모델을 학습한다. 마코브 체인 모델은 상태 변이 확률을 계산하며, 봇넷 트래픽에서 나타나는 규칙적인 패턴을 학습하기 적합하다. 모델 성능 개선을 위해서 페이로드 패턴의 최소 길이와 마코브 체인 모델의 최적 상태 수 파라미터를 찾는다. 다중 분류 실험 결과로 약 0.95의 정확도와 0.02의 오탐률을 보였다.

• Journal of Information Management
• /
• 제20권1호
• /
• pp.66-85
• /
• 1989

The purpose of this study is to verify the following two hypotheses by using a test collection of 3.815 documents on the subject of chemistry. First hypothesis is that a Markov chain model can be used t9 describe and predict authors' movements among subareas of a discipline. Second hypothesis is that a transition matrix of the Markov chain can be applied to describ the intellectual structure of a discipline en the multidimensional space. The results of this study have shown that the Markov chain is a good model to be used to study the movement of korean chemists in 7 subtopics in chemistry and understand the intellectual structure of chemistry.

• The Korean Journal of Applied Statistics
• /
• 제13권2호
• /
• pp.505-514
• /
• 2000

A Markov Chain Monte Carlo method with data augmentation is developed to compute the features of the posterior distribution. For each observed failure epoch, we introduced mixture failure model of Rayleigh and Erlang(2) pattern. This data augmentation approach facilitates specification of the transitional measure in the Markov Chain. Gibbs steps are proposed to perform the Bayesian inference of such models. For model determination, we explored sum of relative error criterion that selects the best model. A numerical example with simulated data set is given.

• Journal of KIISE:Computing Practices and Letters
• /
• 제16권12호
• /
• pp.1264-1268
• /
• 2010

In this paper, we propose a behavior pattern analysis method for users tasking on hands-on security exercise missions. By analysing and evaluating the observed user behavior data, the proposed method discovers some significant patterns able to contribute mission successes or fails. A Markov chain modeling approach and algorithm is used to automate the whole analysis process. How to apply and understand our proposed method is briefly shown through a case study, "network service configurations for secure web service operation".

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제8권3호
• /
• pp.1-10
• /
• 2009

Bus delay time is occurred as the result of traffic condition and important factor to predict bus arrival time. In this paper, transition probability matrixes between bus stops are made by using Markov Chain and it is predicted bus delay time with them. As the results of study, it is confirmed a possibility of adapting the assumption which it has same bus transition probability between stops through paired-samples T-test and overcame the limitation of exiting studies in case there is no scheduled bus arrival time for each stops with using bus interval time. Therefore it will be possible to predict bus arrival time with Markov Chain.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 대한산업공학회/한국경영과학회 1996년도 춘계공동학술대회논문집; 공군사관학교, 청주; 26-27 Apr. 1996
• /
• pp.491-494
• /
• 1996

주문이 매 시점마다 있는 것이 아니라 간헐적인, 즉 어느 시점에는 주문이 있고(ON) 다른시점에는 주문이 없는(OFF) 패턴에서 미래의 주문량에 대한 예측을 고려한다. 다음 시점의 예측량은 우선 주문이 있을 것인가에 대한 판단과 주문이 있다면 어느정도가 예상되는가 하는 문제의 두 가지 측면을 모두 고려해야 한다. 기존의 예측모델은 주문량 자체에 대한 고려가 일반적이며 주문시기에 대한 고려는 전무한 상태이기 때문에 이와 같은 주문패턴을 반영시키는데는 어려움이 따른다고 볼 수 있다. 본 논문에서는 이러한 주문패턴을 마코브 체인으로 모델링하고, 이러한 형태의 상태전이확률(state transition probaility) 추정식이 각각 독립적인 오목함수 (concave function)로 구성되어 있음을 보인다. 또한 확률적으로 표현되는 미래의 주문상태들에 대한 패턴을 확정시키는 알고리듬과 주문량 추정에 있어서 과거의 주문패턴을 반영시키는 모델을 제시한다.

• Journal of Korean Institute of Industrial Engineers
• /
• 제38권4호
• /
• pp.249-253
• /
• 2012

This paper suggests a numerical method for valuation of American options under the Kou model (double exponential jump diffusion model). The method is based on approximation of underlying asset price using a finite-state, time-homogeneous Markov chain. We examine the effectiveness of the proposed method with simulation results, which are compared with those from the conventional numerical method, the finite difference method for PIDE (partial integro-differential equation).

• Proceedings of the Korean Information Science Society Conference
• /
• 한국정보과학회 2010년도 한국컴퓨터종합학술대회논문집 Vol.37 No.1(A)
• /
• pp.152-153
• /
• 2010

• Convergence Security Journal
• /
• 제8권4호
• /
• pp.173-181
• /
• 2008

Recently, Worm epidemic models have been developed in response to the cyber threats posed by worms in order to analyze their propagation and predict their spread. Some of the most important ones involve mathematical model techniques such as Epidemic(SI), KM (Kermack-MeKendrick), Two-Factor and AAWP(Analytical Active Worm Propagation). However, most models have several inherent limitations. For instance, they target worms that employ random scanning in the network such as CodeRed worm and it was able to be applied to the specified threats. Therefore, we propose the probabilistic of worm propagation based on the Markov Chain, which can be applied to cyber threats such as Mass SQL Injection worm. Using the proposed method in this paper, we can predict the occurrence probability and occurrence frequency for each threats in the entire system.

• Journal of the Korean Data and Information Science Society
• /
• 제10권1호
• /
• pp.119-133
• /
• 1999

A Markov Chain Monte Carlo method is developed to compute the software reliability model. We consider computation problem for determining of posterior distibution in Bayseian inference. Metropolis algorithms along with Gibbs sampling are proposed to preform the Bayesian inference of the Mixed model with record value statistics. For model determiniation, we explored the prequential conditional predictive ordinate criterion that selects the best model with the largest posterior likelihood among models using all possible subsets of the component intensity functions. To relax the monotonic intensity function assumptions. A numerical example with simulated data set is given.