• Communications for Statistical Applications and Methods
• /
• v.4 no.2
• /
• pp.497-505
• /
• 1997

We attempt to get a probabilistic model of a queueing system in the maximum entropy condition. Applying the maximum entropy principle to the queueing system, we obtain the most uncertain probability model compatible with the available information expressed by moments.

• Bulletin of the Korean Mathematical Society
• /
• v.55 no.5
• /
• pp.1563-1575
• /
• 2018

In this paper, our central focus is upon gamma and beta q-distributions from a probabilistic viewpoint. The gamma and the beta q-distributions are characterized by investing the nature of the joint q-probability density function through the q-independence property and the q-Laplace transform.

• The Korean Journal of Applied Statistics
• /
• v.34 no.6
• /
• pp.905-922
• /
• 2021

Cluster analysis is one of unsupervised learning techniques used for discovering clusters when there is no prior knowledge of group membership. K-means, one of the commonly used cluster analysis techniques, may fail when the number of variables becomes large. In such high-dimensional cases, it is common to perform tandem analysis, K-means cluster analysis after reducing the number of variables using dimension reduction methods. However, there is no guarantee that the reduced dimension reveals the cluster structure properly. Principal component analysis may mask the structure of clusters, especially when there are large variances for variables that are not related to cluster structure. To overcome this, techniques that perform dimension reduction and cluster analysis simultaneously have been suggested. This study proposes probabilistic reduced K-means, the transition of reduced K-means (De Soete and Caroll, 1994) into a probabilistic framework. Simulation shows that the proposed method performs better than tandem clustering or clustering without any dimension reduction. When the number of the variables is larger than the number of samples in each cluster, probabilistic reduced K-means show better formation of clusters than non-probabilistic reduced K-means. In the application to a real data set, it revealed similar or better cluster structure compared to other methods.

• Communications for Statistical Applications and Methods
• /
• v.8 no.2
• /
• pp.453-464
• /
• 2001

A commercial nuclear power station contains at least tow emergency diesel generators(EDG) to control the risk of severe core damage during station blackout accidents. Therefore, the reliability of the EDG's to start and load-run on demand must be maintained at a sufficiently high level. Probabilistic safety assessments(PSA) are increasingly being used to quantify the public risk of operating potentially hazardous systems such as nuclear power reactors. In this paper, to perform PSA, we will introduce three different types of data and use Bayes procedure to estimate the error rate of nuclear power plant EDG, and using practical examples, illustrate which method is more reasonable in our situation.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.5 no.4
• /
• pp.109-120
• /
• 2001

Live load data were collected with a systematic manner from a survey of a refrigeration stores. Using the collected floor live load survey data, the basic statistics, a histogram of the uniformly distributed loads, and the equivalent uniformly distributed loads are computed for various structural members. Based on the above results, the maximum values of a combined live loads during the design life have been estimated and compared with current design live loads. The ultimate goals of this study are to develop probabilistic live load models to analyze survey data of domestic refrigeration stores, and to propose design live loads for structural types.

• Steel and Composite Structures
• /
• v.21 no.1
• /
• pp.93-107
• /
• 2016

Seismic fragility analysis is a probabilistic decision-making framework which is widely implemented for evaluating vulnerability of a building under earthquake loading. It requires ingredient named probabilistic model and commonly developed using statistics requiring collecting data in large quantities. Preparation of such a data-base is often costly and time-consuming. Therefore, in this paper, by developing generic seismic drift demand model for regular-multi-story steel moment resisting frames is tried to present a novel application of the probabilistic decision-making analysis to practical purposes. To this end, a demand model which is a linear function of intensity measure in logarithmic space is developed to predict overall maximum inter-story drift. Next, the model is coupled with a set of regression-based equations which are capable of directly estimating unknown statistical characteristics of the model parameters.To explicitly address uncertainties arise from randomness and lack of knowledge, the Bayesian regression inference is employed, when these relations are developed. The developed demand model is then employed in a Seismic Fragility Analysis (SFA) for two designed building. The accuracy of the results is also assessed by comparison with the results directly obtained from Incremental Dynamic analysis.

• Korean Journal of Construction Engineering and Management
• /
• v.8 no.3
• /
• pp.76-86
• /
• 2007

Construction development work invents profit as those finalize object, and a make or break success of project depends on correct analysis and forecast business feasibility at project early. Business feasibility study would be decision-making under precarious situation because is connoting uncertainty that is future. estimate at present visual point essentially. Under uncertainty, a decision-making method is based on probability theory of statistics, but business feasibility study had applied with not feasibility study by probabilistic decision method but it by determinism derision method so far. Therefore in this study doing decision-making by a probability theory method for successful project at early business feasibility study, it present a probabilistic study method that use simulation that can supply a little more correct and reliable data to decision-maker As result, a probabilistic study method is more suitable than deterministic study method as technique for a financial feasibility study of construction development work. Making good use of this probabilistic study method at important business or careful decision-making, because efficient Judgment that is based accuracy and authoritativeness may become available.

• The Korean Journal of Applied Statistics
• /
• v.33 no.2
• /
• pp.185-201
• /
• 2020

Scenario population projection reflects the high probability of future realization and ease of statistical interpretation. Statistics Korea (2019) also presents the results of 30 combinations, including special scenarios, as official statistics. However, deterministic population projections provide limited information about future uncertainties with several limitations that are not probabilistic. The deterministic population projections are scenario-based estimates and show a perfect autocorrelation of three factors (birth, death, movement) of population variation over time. Therefore, international organizations UN, the Max Planck Population Research Institute (MPIDR) of Germany and the Vienna Population Research Institute (VID) of Austria have suggested stochastic based population estimates. In addition, some National Statistics Offices have also adopted this method to provide information along with the scenario results. This paper calculates the demographics of Korea based on a probabilistic or stochastic basis and then draws the pros and cons and show implications of the scenario (deterministic) population projections.

• Korean Journal of Metals and Materials
• /
• v.48 no.9
• /
• pp.791-797
• /
• 2010

The creep crack growth rate (da/dt) of the Cr-Mo steels tested by pre-crack and the voltage (or resistance) variables were related into fracture parameter (Ct), crack growth coefficient (H), and an exponent (q) in the parts of Base, weld and HAZ. The fracture parameter (Ct) has various variables relating to the specimen and crack shape, applied stress, and creep strain curve. The H and q was inferred by OLS regression (ordinary least square method), and the H values were solved in statistics and probability assessment, which were attained fromPDF's distributions (probability density function). The HAZ part has the highest value of q by OLS regression and the widest distribution of H by PDF of WEIBULL, which means that the crack sensitivity of HAZ should be cautioned against the creep crack growth and failure.

• The Korean Journal of Applied Statistics
• /
• v.32 no.5
• /
• pp.763-782
• /
• 2019

This paper proposes a probabilistic document ranking model incorporating term dependencies. Document ranking is a fundamental information retrieval task. The task is to sort documents in a collection according to the relevance to the user query (Qin et al., Information Retrieval Journal, 13, 346-374, 2010). A probabilistic model is a model for computing the conditional probability of the relevance of each document given query. Most of the widely used models assume the term independence because it is challenging to compute the joint probabilities of multiple terms. Words in natural language texts are obviously highly correlated. In this paper, we assume a multinomial distribution model to calculate the relevance probability of a document by considering the dependency structure of words, and propose an information retrieval model to rank a document by estimating the probability with the maximum entropy method. The results of the ranking simulation experiment in various multinomial situations show better retrieval results than a model that assumes the independence of words. The results of document ranking experiments using real-world datasets LETOR OHSUMED also show better retrieval results.