• Journal of Information Processing Systems
• /
• v.10 no.1
• /
• pp.119-131
• /
• 2014

In recent literature on traffic scheduling, the combination of the two-dimensional discrete-time Markov chain (DTMC) and the Markov modulated Poisson process (MMPP) is used to analyze the capacity of VoIP traffic in the cognitive radio system. The performance of the cognitive radio system solely depends on the accuracy of spectrum sensing techniques, the minimization of false alarms, and the scheduling of traffic channels. In this paper, we only emphasize the scheduling of traffic channels (i.e., traffic handling techniques for the primary user [PU] and the secondary user [SU]). We consider the following three different traffic models: the cross-layer analytical model, M/G/1(m) traffic, and the IEEE 802.16e/m scheduling approach to evaluate the performance of the VoIP services of the cognitive radio system from the context of blocking probability and throughput.

• Proceedings of the KSR Conference
• /
• 1998.11a
• /
• pp.280-287
• /
• 1998

In this paper, Dynamic Fault Tree algorithm(DFT algorithm) is presented. This new algorithm provides a concise representation of dynamic fault tolerance system structure with redundancy, dynamic redundancy management and complex fault ＆ error recovery techniques. And it allows the modeler to define a dynamic fault tree model with the relative advantages of both fault tree and Markov models that captures the system structure and dynamic behavior. This algorithm applies to TMR and Dual-Duplex systems with the dynamic behavior and show that this algorithm captured the dynamic behavior in these systems with fault ＆ error recovery technique, sequence-dependent failures and the use dynamic spare. The DFT algorithm for solving the problems of the systems is more effective than the Markov and Fault tree analysis model.

• Journal of Korean Society on Water Environment
• /
• v.36 no.5
• /
• pp.353-363
• /
• 2020

Hydrologic models can be classified into two types: those for understanding physical processes and those for predicting hydrologic quantities. This study deals with how to use the model to predict today's stream flow based on the system's knowledge of yesterday's state and the model parameters. In this regard, for the model to generate accurate predictions, the uncertainty of the parameters and appropriate estimates of the state variables are required. In this study, a relatively simple hydrologic partitioning model is proposed that can explicitly implement the hydrologic partitioning process, and the posterior distribution of the parameters of the proposed model is estimated using the Markov chain Monte Carlo approach. Further, the application method of the ensemble Kalman filter is proposed for updating the normalized soil moisture, which is the state variable of the model, by linking the information on the posterior distribution of the parameters and by assimilating the observed steam flow data. The stochastically and recursively estimated stream flows using the data assimilation technique revealed better representation of the observed data than the stream flows predicted using the deterministic model. Therefore, the ensemble Kalman filter in conjunction with the Markov chain Monte Carlo approach could be a reliable and effective method for forecasting daily stream flow, and it could also be a suitable method for routinely updating and monitoring the watershed-averaged soil moisture.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.94-99
• /
• 2015

With the recent machine learning paradigm of using nonparametric Bayesian statistics and statistical inference based on random sampling, the Dirichlet distribution finds many uses in a variety of graphical models. It is a multivariate generalization of the gamma distribution and is defined on a continuous (K-1)-simplex. This paper presents a sampling method for a Dirichlet distribution for the problem of dividing an integer X into a sequence of K integers which sum to X. The target samples in our problem are all positive integer vectors when multiplied by a given X. They must be sampled from the correspondingly gridded simplex. In this paper we develop a Markov Chain Monte Carlo (MCMC) proposal distribution for the neighborhood grid points on the simplex and then present the complete algorithm based on the Metropolis-Hastings algorithm. The proposed algorithm can be used for the Markov model, HMM, and Semi-Markov model for accurate state-duration modeling. It can also be used for the Gamma-Dirichlet HMM to model q the global-local duration distributions.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.157-165
• /
• 2011

It is challenging to detect foreground objects when background includes an illumination variation, shadow or structural variation due to its motion. Basically pixel-based background models including codebook-based modeling suffer from statistical randomness of each pixel. This paper proposes an algorithm that incorporates Markov random field model into pixel-based background modeling to achieve more accurate foreground detection. Under the assumptions the distance between the pixel on the input imaging and the corresponding background model and the difference between the scene estimates of the spatio-temporally neighboring pixels are exponentially distributed, a recursive approach for estimating the MRF regularizing parameters is proposed. The proposed method alternates between estimating the parameters with the intermediate foreground detection and estimating the foreground detection with the estimated parameters, after computing it with random initial parameters. Extensive experiment is conducted with several videos recorded both indoors and outdoors to compare the proposed method with the standard codebook-based algorithm.

• East Asian mathematical journal
• /
• v.38 no.5
• /
• pp.617-641
• /
• 2022

In this study, we first present a brief overview of the Korean general insurance market. We then explore the characteristics of the loss ratios of the Korean general insurance industry and apply Markov regime-switching methodology to model the loss ratios of these insurance companies by line of business based on changes in economic regimes. This study applies a number of confirmatory tests such as Zivot-Andrews test (2002), the Chow (1960) test and the Bai and Perron (1998) to confirm the presence of structural breaks in the time series of the loss ratios by line of business. Then, we employ Markov regime-switching methodology to model these loss ratios. We find empirical evidence that the loss ratios reported by insurance companies in Korea is characterized by two distinct regimes; a regime with high volatility and a regime with low volatility, except for vehicle insurance. Our analyses suggest that macro-economic conditions have significant explanatory effect on loss ratios but the direction of effect differs based on the line of business and the regime. Unlike previous studies that have applied linear regressions or divided the samples into different periods and then apply linear regressions to model loss ratios, we argue for the application of Markov regime-switching methodology, which are able to automatically distinguish the different regimes that may be associated with the movements of loss ratios based on differing economic conditions and regulatory upheavals. This study provides a more in depth understanding of loss ratios in the general insurance industry and will be of value to insurance practitioners in modelling the loss ratios associated with their businesses to aid in their decision making. The results may also provide a basis for further studies in other markets apart from Korea as well as for shaping policy decisions related to loss ratios.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.3
• /
• pp.186-199
• /
• 2013

We pose pattern classification as a density estimation problem where we consider mixtures of generative models under partially labeled data setups. Unlike traditional approaches that estimate density everywhere in data space, we focus on the density along the decision boundary that can yield more discriminative models with superior classification performance. We extend our earlier work on the recursive estimation method for discriminative mixture models to semi-supervised learning setups where some of the data points lack class labels. Our model exploits the mixture structure in the functional gradient framework: it searches for the base mixture component model in a greedy fashion, maximizing the conditional class likelihoods for the labeled data and at the same time minimizing the uncertainty of class label prediction for unlabeled data points. The objective can be effectively imposed as individual mixture component learning on weighted data, hence our mixture learning typically becomes highly efficient for popular base generative models like Gaussians or hidden Markov models. Moreover, apart from the expectation-maximization algorithm, the proposed recursive estimation has several advantages including the lack of need for a pre-determined mixture order and robustness to the choice of initial parameters. We demonstrate the benefits of the proposed approach on a comprehensive set of evaluations consisting of diverse time-series classification problems in semi-supervised scenarios.

• Spatial Information Research
• /
• v.11 no.3
• /
• pp.227-240
• /
• 2003

The primary focus of this study is to provide a general methodology which can be utilized to understand and analyze environmental issues such as long term ecosystem dynamics and land use/cover change by development of 2D dynamic landscape models and model-based simulation. Change processes in land cover and ecosystem function can be understood in terms of the spatial and temporal distribution of land cover resources. In development of a system to understand major processes of change and obtain predictive information, first of all, spatial heterogeneity is to be taken into account because landscape spatial pattern affects on land cover change and interaction between different land cover types. Therefore, the relationship between pattern and processes is to be included in the research. Landscape modeling requires different approach depending on the definition, assumption, and rules employed for mechanism behind the processes such as spatial event process, land degradation, deforestration, desertification, and change in an urban environment. The rule-based models are described in the paper for land cover change by natural fires. Finally, a case study is presented as an example using spatial modeling and simulation to study and synthesize patterns and processes at different scales ranging from fine-scale to global scale.

• Journal of Korea Water Resources Association
• /
• v.43 no.4
• /
• pp.337-351
• /
• 2010

There is a growing dissatisfaction with use of conventional statistical methods for the prediction of extreme events. Conventional methodology for modeling extreme event consists of adopting an asymptotic model to describe stochastic variation. However asymptotically motivated models remain the centerpiece of our modeling strategy, since without such an asymptotic basis, models have no rational for extrapolation beyond the level of observed data. Also, this asymptotic models ignored or overestimate the uncertainty and finally decrease the reliability of uncertainty. Therefore this article provide the research example of the extreme rainfall event and the methodology to reduce the uncertainty. In this study, the Bayesian MCMC (Bayesian Markov Chain Monte Carlo) and the MLE (Maximum Likelihood Estimation) methods using a quadratic approximation are applied to perform the at-site rainfall frequency analysis. Especially, the GEV distribution and Gumbel distribution which frequently used distribution in the fields of rainfall frequency distribution are used and compared. Also, the results of two distribution are analyzed and compared in the aspect of uncertainty.

• ETRI Journal
• /
• v.35 no.1
• /
• pp.100-108
• /
• 2013

In this paper, a feature extraction (FE) method is proposed that is comparable to the traditional FE methods used in automatic speech recognition systems. Unlike the conventional spectral-based FE methods, the proposed method evaluates the similarities between an embedded speech signal and a set of predefined speech attractor models in the reconstructed phase space (RPS) domain. In the first step, a set of Gaussian mixture models is trained to represent the speech attractors in the RPS. Next, for a new input speech frame, a posterior-probability-based feature vector is evaluated, which represents the similarity between the embedded frame and the learned speech attractors. We conduct experiments for a speech recognition task utilizing a toolkit based on hidden Markov models, over FARSDAT, a well-known Persian speech corpus. Through the proposed FE method, we gain 3.11% absolute phoneme error rate improvement in comparison to the baseline system, which exploits the mel-frequency cepstral coefficient FE method.