• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.4
• /
• pp.285-294
• /
• 2007

In this paper, we investigate a novel online estimation algorithm for dynamic Bayesian network(DBN) parameters, given as conditional probabilities. We sequentially update the parameter adjustment rule based on observation data. We apply our algorithm to two well known representations of DBNs: to a first-order Markov Chain(MC) model and to a Hidden Markov Model(HMM). A sliding window allows efficient adaptive computation in real time. We also examine the stochastic convergence and stability of the learning algorithm.

• Management Science and Financial Engineering
• /
• v.19 no.2
• /
• pp.49-53
• /
• 2013

A Markov-chain Monte Carlo sampling algorithm samples a new point around the latest sample due to the Markov property, which prevents it from sampling from multi-modal distributions since the corresponding chain often fails to search entire support of the target distribution. In this paper, to overcome this problem, mode switching scheme is applied to the conventional MCMC algorithms. The algorithm separates the reducible Markov chain into several mutually exclusive classes and use mode switching scheme to increase mixing rate. Simulation results are given to illustrate the algorithm with promising results.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.16 no.1
• /
• pp.76-88
• /
• 1991

Stochastic convexity (concavity) of a stochastic process is a very useful concept for various stochastic optimization problems. In this study we first establish stochastic convexity of a certain class of Markov additive processes through probabilistic construction based on the sample path approach. A Markov additive process is abtained by integrating a functional of the underlying Markov process with respect to time, and its stochastic convexity can be utilized to provide efficient methods for optimal design or optimal operation schedule wide range of stochastic systems. We also clarify the conditions for stochastic monotonicity of the Markov process. From the result it is shown that stachstic convexity can be used for the analysis of probabilitic models based on birth and death processes, which have very wide applications area. Finally we demonstrate the validity and usefulness of the theoretical results by developing efficient methods for the optimal replacement scheduling based on the stochastic convexity property.

• The Korean Journal of Applied Statistics
• /
• v.24 no.4
• /
• pp.657-676
• /
• 2011

Properties of statistical process control procedures may not be derived analytically in many cases; however, the application of a Markov chain can solve such problems. This article shows how to derive the properties of the process control procedures using the generated Markov chains when the control statistic satisfies the Markov property. Markov chain approaches that appear in the literature (such as the statistical design and economic design of the control chart as well as the variable sampling rate design) are reviewed along with the introduction of research results for application to a new control procedure and reset chart. The joint application of a Markov chain approach and analytical solutions (when available) can guarantee the correct derivation of the properties. A Markov chain approach is recommended over simulation studies due to its precise derivation of properties and short calculation times.

• The Korean Journal of Applied Statistics
• /
• v.34 no.4
• /
• pp.537-556
• /
• 2021

Properties of statistical process control procedures may not be derived analytically in many cases; however, the application of a Markov chain can solve such problems. This article shows how to derive the properties of the process control procedures using the generated Markov chains when the control statistic satisfies the Markov property. Markov chain approaches that appear in the literature (such as the statistical design and economic design of the control chart as well as the variable sampling rate design) are reviewed along with the introduction of research results for application to a new control procedure and reset chart. The joint application of a Markov chain approach and analytical solutions (when available) can guarantee the correct derivation of the properties. A Markov chain approach is recommended over simulation studies due to its precise derivation of properties and short calculation times.

• Journal of applied mathematics & informatics
• /
• v.30 no.3_4
• /
• pp.541-553
• /
• 2012

In this paper, we study some limit properties of the harmonic mean of random transition probability for a second-order nonhomogeneous Markov chain on the generalized gambling system indexed by a tree by constructing a nonnegative martingale. As corollary, we obtain the property of the harmonic mean and the arithmetic mean of random transition probability for a second-order nonhomogeneous Markov chain indexed by a double root tree.

• Genomics & Informatics
• /
• v.16 no.3
• /
• pp.65-70
• /
• 2018

The non-coding DNA in eukaryotic genomes encodes a language which programs chromatin accessibility, transcription factor binding, and various other activities. The objective of this short report was to determine the impact of primary DNA sequence on the epigenomic landscape across 200-base pair genomic units by integrating nine publicly available ChromHMM Browser Extensible Data files of the Encyclopedia of DNA Elements (ENCODE) project. The nucleotide frequency profiles of nine chromatin annotations with the units of 200 bp were analyzed and integrative Markov chains were built to detect the Markov properties of the DNA sequences in some of the active chromatin states of different ChromHMM regions. Our aim was to identify the possible relationship between DNA sequences and the newly built chromatin states based on the integrated ChromHMM datasets of different cells and tissue types.

• Genomics & Informatics
• /
• v.16 no.4
• /
• pp.27.1-27.6
• /
• 2018

The non-coding DNA in eukaryotic genomes encodes a language that programs chromatin accessibility, transcription factor binding, and various other activities. The objective of this study was to determine the effect of the primary DNA sequence on the epigenomic landscape across a 200-base pair of genomic units by integrating 127 publicly available ChromHMM BED files from the Roadmap Genomics project. Nucleotide frequency profiles of 127 chromatin annotations stratified by chromatin variability were analyzed and integrative hidden Markov models were built to detect Markov properties of chromatin regions. Our aim was to identify the relationship between DNA sequence units and their chromatin variability based on integrated ChromHMM datasets of different cell and tissue types.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.425-426
• /
• 2016

In this paper, we proposed an algorithm based on movement prediction using Markov chain in delay tolerant networks(DTNs). The existing prediction algorithms require additional information such as a node's schedule and connectivity between nodes. However, network reliability is lowered when additional information is unknown. To solve this problem, we proposed an algorithm for predicting a movement path of the node by using Markov chain. The proposed algorithm maps speed and direction for a node into state, and predict movement path of the node using transition probability matrix generated by Markov chain. As the result, proposed algorithm show that the proposed algorithms has competitive delivery ratio but with less average latency.

• Communications for Statistical Applications and Methods
• /
• v.3 no.2
• /
• pp.249-273
• /
• 1996

This paper reviews and develops several statistical models for extreme values, based on threshold methodology. Extreme values of a time series are modeled in terms of tails which are defined as truncated forms of original variables, and Markov property is imposed on the tails. Tails of the generalized extreme value distribution and a multivariate extreme value distributively, of the tails of the series. These models are then applied to real ozone data series collected in the Chicago area. A major concern is given to detecting any possible trend in the extreme values.