• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.35.3-35
• /
• 2002

Reinforcement Learning (RL) is one of machine learning methods and an RL agent autonomously learns the action selection policy by interactions with its environment. At the beginning of RL research, it was limited to problems in environments assumed to be Markovian Decision Process (MDP). However in practical problems, the agent suffers from the incomplete perception, i.e., the agent observes the state of the environments, but these observations include incomplete information of the state. This problem is formally modeled by Partially Observable MDP (POMDP). One of the possible approaches to POMDPS is to use historical nformation to estimate states. The problem of these approaches is how t..

• Communications for Statistical Applications and Methods
• /
• v.9 no.1
• /
• pp.33-38
• /
• 2002

We prove that blocked complete dialler crosses using balance incomplete block design are A-, D-, E-optimal design. Also, we provide such blocked complete dialled crosses and their average efficiency with table.

• Communications for Statistical Applications and Methods
• /
• v.20 no.4
• /
• pp.283-290
• /
• 2013

Subjects can experience two types of recurrent events in a longitudinal study. In addition, there may exist intermittent dropouts that results in repeated observation gaps during which no recurrent events are observed. Therefore, theses periods are regarded as non-risk status. In this paper, we consider a special case where information on the observation gap is incomplete, that is, the termination time of observation gap is not available while the starting time is known. For a statistical inference, incomplete termination time is incorporated in terms of interval-censored data and estimated with two approaches. A shared frailty effect is also employed for the association between two recurrent events. An EM algorithm is applied to recover unknown termination times as well as frailty effect. We apply the suggested method to young drivers' convictions data with several suspensions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.397-402
• /
• 2007

In this paper, we present a method for clustering incomplete Microarray data using alternating optimization in which a prior imputation method is not required. To reduce the influence of imputation in preprocessing, we take an alternative optimization approach to find better estimates during iterative clustering process. This method improves the estimates of missing values by exploiting the cluster Information such as cluster centroids and all available non-missing values in each iteration. The clustering results of the proposed method are more significantly relevant to the biological gene annotations than those of other methods, indicating its effectiveness and potential for clustering incomplete gene expression data.

• Proceedings of the KAIS Fall Conference
• /
• 2003.11a
• /
• pp.105-110
• /
• 2003

Collaborative filtering is one of the methodologies that are most widely used for recommendation system. It is based on a data matrix of each customer's preferences of products. There could be a lot of missing values in such preference. data matrix. This incomplete data is one of the reasons to deteriorate the accuracy of recommendation system. Multiple imputation method imputes m values for each missing value. It overcomes flaws of single imputation approaches through considering the uncertainty of missing values.. The objective of this paper is to suggest multiple imputation-based collaborative filtering approach for recommendation system to improve the accuracy in prediction performance. The experimental works show that the proposed approach provides better performance than the traditional Collaborative filtering approach, especially in case that there are a lot of missing values in dataset used for recommendation system.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1999.04a
• /
• pp.240-241
• /
• 1999

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.2
• /
• pp.119-124
• /
• 2015

In this paper, we analyze the effect of line-width of optical sources on the performance of spectral amplitude coding (SAC) optical code division multiple-access (OCDMA) systems. For a performance analysis we use a symmetric balanced incomplete block design (BIBD) code as the code sequence because we can construct a series of code families by choosing different values of q and m. The ideal BIBD code (m=2) requires narrower line-width than the nonideal BIBD codes when the effective power is large ($P_{sr}=-10dBm$). But the nonideal BIBD codes (m>2) need narrower line-width than the ideal BIBD code when $P_{sr}=-25dBm$.

• Journal of Communications and Networks
• /
• v.14 no.6
• /
• pp.682-691
• /
• 2012

Key agreement protocol is a fundamental protocol in cryptography whereby two or more participants can agree on a common conference key in order to communicate securely among themselves. In this situation, the participants can securely send and receive messages with each other. An adversary not having access to the conference key will not be able to decrypt the messages. In this paper, we propose a novel identity-based authenticated multi user key agreement protocol employing a symmetric balanced incomplete block design. Our protocol is built on elliptic curve cryptography and takes advantage of a kind of bilinear map called Weil pairing. The protocol presented can provide an identification (ID)-based authentication service and resist different key attacks. Furthermore, our protocol is efficient and needs only two rounds for generating a common conference key. It is worth noting that the communication cost for generating a conference key in our protocol is only O($\sqrt{n}$) and the computation cost is only O($nm^2$), where $n$ implies the number of participants and m denotes the extension degree of the finite field $F_{p^m}$. In addition, in order to resist the different key attack from malicious participants, our protocol can be further extended to provide the fault tolerant property.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.2
• /
• pp.347-354
• /
• 2015

This paper deals with a method for intrablock anlaysis of balanced incomplete block designs on the basis of projections under the assumption of mixed effects model. It shows how to construct a model at each step by the stepwise procedure and discusses how to use projection for the analysis of intrablock. Projections are obtained in vector subspaces orthogonal to each other. So the estimates of the treatment effects are not affected by the block effects. The estimability of a parameter or a function of parameters is discussed and eigenvectors are dealt for the construction of estimable functions.

• Journal of the Korean Data and Information Science Society
• /
• v.1
• /
• pp.7-33
• /
• 1990

Bechhofer and Tamhane(1981) developed a theory of optimal incomplete block designs for comparing several treatments with a control. This class of designs is appropriate for comparing simultaneously $p{\geq}2$ test treatments with a control treatment (the so-called multiple comparisons with a control (MCC) problem) when the observations are taken in incomplete blocks of common size $K{\<}p+1$. In this paper we want to extend to partially BTIB designs with two associate classes for the MCC problem. We propose a new class of incomplete block designs that are partially balanced with respect to test treatments. Because the class of designs that we consider is larger than the class of designs in Bechhofer and Tamhane and provides us with designs that improve on the optimal designs in their class. We shall use the abbreviation PBTIB to refer to such designs. We study their structure and give some methods of construction. Also we describe a procedure for making exact joint confidence statements for the MCC problem in PBTIB Designs with two associate classes. We study Optimality, Admissibility considerations in PBTIB designs with two associate classes.