• 한국정보보호학회:학술대회논문집
• /
• 한국정보보호학회 2002년도 종합학술발표회논문집
• /
• pp.53-56
• /
• 2002

This paper discusses the quorum based algorithm for group mutual exclusion defined by Yuh-Jzer Joung. Group mutual exclusion[4,5,6] is a generalization of mutual exclusion that allows a resource to be shared by processes of the same group, but requites processes of different groups to use the resource in a mutually exclusive style. Joung proposed a quorum system, which he referred to as the surficial quorum system for group mutual exclusion and two modifications of Maekawa's algorithm[6]. He mentioned that when a process may belong to more than one group, the process must identify one of the groups it belongs when it wishes to enter CS(Critical Section). However, his solution didn't provide mechanism of identifying a group which maximizes the possibility to enter CS. In this paper, we provide a mechanism for identifying that each process belongs to which group.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.420-423
• /
• 2001

In this paper, the Multi-FNNs(Fuzzy-Neural Networks) architecture is identified and optimized using HCM(Hard C-Means) clustering method and genetic algorithms. The proposed Multi-FNNs architecture uses simplified inference and linear inference as fuzzy inference method and error back propagation algorithm as learning rules. Here, HCM clustering method, which is carried out for the process data preprocessing of system modeling, is utilized to determine the structure of Multi-FNNs according to the divisions of input-output space using I/O process data. Also, the parameters of Multi-FNNs model such as apexes of membership function, learning rates and momentum coefficients are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is used to achieve a sound balance between approximation and generalization abilities of the model. To evaluate the performance of the proposed model we use the time series data for gas furnace and the NOx emission process data of gas turbine power plant.

• International Journal of Reliability and Applications
• /
• 제8권1호
• /
• pp.53-66
• /
• 2007

This paper proposes a new non-homogeneous Poisson process software reliability growth model based on the coverage information. The new model incorporates the coverage information in the fault detection process by assuming that only the faults in the covered constructs are detectable. Since the coverage growth behavior depends on the testing strategy, the fault detection process is first modeled for the general testing strategy and then realized for the uniform testing. Finally the model for the uniform testing is empirically evaluated by applying it to real data sets.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제40권2호
• /
• pp.253-263
• /
• 2001

Developing mathematical thinking skills is one of the most important goals of school mathematics. In particular, recent performance based on assessment has focused on the teaching and learning environment in school, emphasizing student's self construction of their learning and its process. Because of this reason, people related to mathematics education including math teachers are taught to recognize the fact that the degree of students'acquisition of mathematical thinking skills and strategies(for example, inductive and deductive thinking, critical thinking, creative thinking) should be estimated formally in math class. However, due to the lack of an evaluation tool for estimating the degree of their thinking skills, efforts at evaluating student's degree of mathematics thinking skills and strategy acquisition failed. Therefore, in this paper, mathematical thinking was studied, and using the results of study as the fundamental basis, mathematical thinking process model was developed according to three types of mathematical thinking - fundamental thinking skill, developing thinking skill, and advanced thinking strategies. Finally, based on the model, evaluation factors related to essential thinking skills such as analogy, deductive thinking, generalization, creative thinking requested in the situation of solving mathematical problems were developed.

• Communications for Statistical Applications and Methods
• /
• 제28권5호
• /
• pp.477-491
• /
• 2021

The Markov modulated Brownian motion is a substantial generalization of the classical Brownian Motion. On the other hand, the Markovian arrival process (MAP) is a point process whose family is dense for any stochastic point process and is used to approximate complex stochastic counting processes. In this paper, we consider a superposition of the Markov modulated Brownian motion (MMBM) and the Markovian arrival process of jumps which are distributed as the bilateral ph-type distribution, the class of which is also dense in the space of distribution functions defined on the whole real line. In the model, we assume that the inter-arrival times of the MAP depend on the underlying Markov process of the MMBM. One of the subjects of this paper is introducing how to obtain the first passage probabilities of the superposed process using a stochastic doubling algorithm designed for getting the minimal solution of a nonsymmetric algebraic Riccatti equation. The other is to provide eigenvalue and eigenvector results on the superposed process to make it possible to apply the GTH-like algorithm, which improves the accuracy of the doubling algorithm.

• 한국전자거래학회지
• /
• 제25권3호
• /
• pp.1-13
• /
• 2020

기계학습(machine learning)이란 주어진 데이터에 대한 일반화 과정으로부터 특정 문제를 해결할 수 있는 모델(model) 생성 기술을 의미한다. 우수한 성능의 모델을 생성하기 위해서는 양질의 학습데이터와 일반화 과정을 위한 학습 알고리즘이 준비되어야 한다. 성능 개선을 위한 한 가지 방법으로서 앙상블(Ensemble) 기법은 단일 모델(single model)을 생성하기보다 다중 모델을 생성하며, 이는 배깅(Bagging), 부스팅(Boosting), 스태킹(Stacking) 학습 기법을 포함한다. 본 논문은 기존 스태킹 기법을 개선한 다중 스태킹 앙상블(Multiple Stacking Ensemble) 학습 기법을 제안한다. 다중 스태킹 앙상블 기법의 학습 구조는 딥러닝 구조와 유사하고 각 레이어가 스태킹 모델의 조합으로 구성되며 계층의 수를 증가시켜 각 계층의 오분류율을 최소화하여 성능을 개선한다. 4가지 유형의 데이터셋을 이용한 실험을 통해 제안 기법이 기존 기법에 비해 분류 성능이 우수함을 보인다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권7호
• /
• pp.339-349
• /
• 2001

This paper suggests an optimal identification method for complex and nonlinear system modeling that is based on Fuzzy-Neural Networks(FNN). The proposed Hybrid Identification Algorithm is based on Yamakawa's FNN and uses the simplified inference as fuzzy inference method and Error Back Propagation Algorithm as learning rule. In this paper, the FNN modeling implements parameter identification using HCM algorithm and hybrid structure combined with two types of optimization theories for nonlinear systems. We use a HCM(Hard C-Means) clustering algorithm to find initial apexes of membership function. The parameters such as apexes of membership functions, learning rates, and momentum coefficients are adjusted using hybrid algorithm. The proposed hybrid identification algorithm is carried out using both a genetic algorithm and the improved complex method. Also, an aggregated objective function(performance index) with weighting factor is introduced to achieve a sound balance between approximation and generalization abilities of the model. According to the selection and adjustment of a weighting factor of an aggregate objective function which depends on the number of data and a certain degree of nonlinearity(distribution of I/O data), we show that it is available and effective to design an optimal FNN model structure with mutual balance and dependency between approximation and generalization abilities. To evaluate the performance of the proposed model, we use the time series data for gas furnace, the data of sewage treatment process and traffic route choice process.

• 한국경영과학회지
• /
• 제23권2호
• /
• pp.131-156
• /
• 1998

Cooperative query answering is a research effort to develop a fault-tolerant and intelligent database system using the semantic knowledge base constructed from the underlying database. Such knowledge base has two aspects of usage. One is supporting the cooperative query answering Process for providing both an exact answer and neighborhood information relevant to a query. The other is supporting ongoing maintenance of the knowledge base for accommodating the changes in the knowledge content and database usage purpose. Existing studies have mostly focused on the cooperative query answering process but paid little attention on the dynamic knowledge base maintenance. This paper proposes a multi-level knowledge representation framework called Knowledge Abstraction Hierarchy (KAH) that can not only support cooperative query answering but also permit dynamic knowledge maintenance. The KAH consists of two types of knowledge abstraction hierarchies. The value abstraction hierarchy is constructed by abstract values that are hierarchically derived from specific data values in the underlying database on the basis of generalization and specialization relationships. The domain abstraction hierarchy is built on the various domains of the data values and incorporates the classification relationship between super-domains and sub-domains. On the basis of the KAH, a knowledge abstraction database is constructed on the relational data model and accommodates diverse knowledge maintenance needs and flexibly facilitates cooperative query answering. In terms of the knowledge maintenance, database operations are discussed for the cases where either the internal contents for a given KAH change or the structures of the KAH itself change. In terms of cooperative query answering, database operations are discussed for both the generalization and specialization Processes, and the conceptual query handling. A prototype system has been implemented at KAIST that demonstrates the usefulness of KAH in ordinary database application systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.4008-4023
• /
• 2022

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.

• 한국정보처리학회논문지
• /
• 제1권2호
• /
• pp.225-236
• /
• 1994

지금껏 발표된 많은 연구 결과에 의하면 신경망 시스템의 일반화 정도(정확도) 는 통계적 모델과의 비교 평가에서 그 일반화 정도가 그들과 버금가거나 우수하다는 평가를 받고 있다. 그러나, 이러한 신경망 시스템의 우수한 예측 결과는 불량 데이타 (noisy data)가 거의 없는 건전한 데이타, 혹은 일정량의 불량 데이타를 제어할 수 있을 만큼 충분한 양의 데이타로 신경망을 학습시켰을 경우에만 얻을 수가 있었다. 실제 문제-특히, 경제, 경영상의 문제-를 풀기 위하여 모아진 실 데이타는 신경만 시 스템이 만족할 만한 예측 결과를 보일 수 있을 정도의 건전한 데이타가 못되는 것이 현실이다. 따라서, 본 연구에서는 일정량의 불량 데이타를 포함하고 있는 훈련 데이타 를 통해 신경만을 훈련시킬 경우 신경망 시스템의 일반화 정도를 높일 수 있는 방법 에 대하여 논하였다. 본 연구의 관찰된 실험 결과에 의하면 신경망 시스템의 일반화 정도를 높이기 위해 훈련 데이타에서 같은 입력값을 갖는데도 불구하고 서로 상반되 는 출력값을 갖는 불량 데이타들을 골라내어 신경망 시스템을 훈련시키는 방법을 제 안하였다. 아울러, 두개의 서로 상반된 결과값을 갖는 불량 데이타로 신경만을 훈련 시켰을 경우 두 결과값의 평균값에 의해 신경망의 가중치(weight)조정이 된다는 이전 의 연구결과［25］도 입증되었다. 또한, 본고에서는 현재 진행중에 있는 신경망을 이 용한 신용 평가 시스템 개발에 관한 중간 결과도 기술되어 있다.