• Communications for Statistical Applications and Methods
• /
• v.26 no.2
• /
• pp.205-216
• /
• 2019

Diagnostic tests in medical fields detect or diagnose a disease with results measured by continuous or discrete ordinal data. The performance of a diagnostic test is summarized using the receiver operating characteristic (ROC) curve and the area under the curve (AUC). The diagnostic test is considered clinically useful if the outcomes in actually-positive cases are higher than actually-negative cases and the ROC curve is concave. In this study, we apply the stochastic ordering method in a Bayesian hierarchical model to estimate the proper ROC curve and AUC when the diagnostic test results are measured in discrete ordinal data. We compare the conventional binormal model and binormal model under stochastic ordering. The simulation results and real data analysis for breast cancer indicate that the binormal model under stochastic ordering can be used to estimate the proper ROC curve with a small bias even though the sample sizes were small or the sample size of actually-negative cases varied from actually-positive cases. Therefore, it is appropriate to consider the binormal model under stochastic ordering in the presence of large differences for a sample size between actually-negative and actually-positive groups.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.5 no.4
• /
• pp.65-73
• /
• 1985

A stochastic dynamic analysis using Mode-Acceleration Method was formulated and examined in this paper. A computer program was developed using this theory and model offshore structure was analyzed by the program. Results show that the stochastic dynamic analysis using the Mode-Acceleration Method is superior to that using Mode Displacement Method. The method using the theory developed in this paper was proved to be very reliable, economic and potential.

• Structural Engineering and Mechanics
• /
• v.55 no.3
• /
• pp.525-534
• /
• 2015

A new structural dynamic fuzzy reliability analysis under stochastic loads which are applied several times is proposed in this paper. The fuzzy reliability prediction models based on time responses with and without strength degeneration are established using the stress-strength interference theory. The random loads are applied several times and fuzzy structural strength is analyzed. The efficiency of the proposed method is demonstrated numerically through an example. The results have shown that the proposed method is practicable, feasible and gives a reasonably accurate prediction. The analysis shows that the probabilistic reliability is a special case of fuzzy reliability and fuzzy reliability of structural strength without degeneration is also a special case of fuzzy reliability with structural strength degeneration.

• Structural Engineering and Mechanics
• /
• v.62 no.6
• /
• pp.703-708
• /
• 2017

The goal of this study is to evaluate behavior uncertainties of structures by using interval finite element analysis based on interval factor method as a specific non-stochastic tool. The interval finite element method, i.e., interval FEM, is a finite element method that uses interval parameters in situations where it is not possible to get reliable probabilistic characteristics of the structure. The present method solves the uncertainty problems of a 2D solid structure, in which structural characteristics are assumed to be represented as interval parameters. An interval analysis method using interval factors is applied to obtain the solution. Numerical applications verify the intuitive effectiveness of the present method to investigate structural uncertainties such as displacement and stress without the application of probability theory.

• The Journal of Fisheries Business Administration
• /
• v.43 no.2
• /
• pp.67-77
• /
• 2012

Based on the survey on aquaculture management status in Nohwa-eup, Bogil-myeon, Wando-eup in Wando region, this study aimed to estimate productive efficiencies of abalone aquaculture production using a stochastic frontier approach (SFA) and to find out their determinants. In the analysis, a Cobb-Douglas production function with an inefficiency term that follows an halfnormal distribution was assumed for the estimation of productive efficiencies. Then, based on the outcomes of productive efficiencies, determinants of productive efficiency were investigated using a tobit regression model. Results showed that the average inefficiency was estimated to be 10% and the production size would be a statistically significant variable for the production. In addition, it was shown that the cage installing method would be an important factor affecting to the level of productive efficiency.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1998.10a
• /
• pp.11-18
• /
• 1998

In this paper the stochastic analysis of semi-infinite domain is presented using the weighted integral method, which is expanded to include the infinite finite elements. The semi-infinite domain can be thought as to have more uncertainties than the ordinary finite domain in material constants, which shows the needs of and the importance of the stochastic finite element analysis. The Bettess's infinite element is adopted with the theoretical decomposition of the strain matrix to calculate the deviatoric stiffness of the semi-infinite domains. The calculated value of mean and the covariance of the displacement are revealed to be larger than those given by the finite domain assumptions giving the rational results which should be considered in the design of structures on semi-infinite domains.

• Journal of the Korea Society for Simulation
• /
• v.9 no.2
• /
• pp.89-102
• /
• 2000

In this paper, we consider an optimal allocation of constant service efforts in queueing network to maximize the system throughput. For this purpose, using the perturbation analysis, we apply a stochastic optimization algorithm to two types of queueing systems. Our simulation results indicate that the estimates obtained from a stochastic optimization algorithm for a two-tandem queuing network are very accurate, and those for closed loop manufacturing system are a little apart from the known optimal allocation. We find that as simulation time increases for obtaining a new gradient (performance measure with respect to decision variables) by perturbation algorithm, the estimates tend to be more stable. Thus, we consider that it would be more desirable to have more accurate sensitivity of performance measure by enlarging simulation time rather than more searching steps with less accurate sensitivity. We realize that more experiments on various types of systems are needed to identify such a relationship with regards to stopping rule, the size of moving step, and updating period for sensitivity.

• Journal of Industrial Technology
• /
• v.23 no.A
• /
• pp.15-20
• /
• 2003

Stochastic simulation technique has advantages over deterministic simulation in various engineering analysis, since stochastic simulation can take into consideration of scattering of various design variables, which is inherent characteristics of physical world. In this work, Monte-Carlo simulation mothod in ADAMS/Insight for steady-state cornering and J-turn behavior of a truck with design variables like hard points and busing stiffnesses have performed to achieve better dynamic performance. The main purpose is to improve understeer gradient at steady-state cornering and minimize peak lateral acceleration and peak yaw rate at J-turn. Through correlation analysis, design variables that have high impacts on the cornering behavior were selected, and significant performance improvement has been achieved by appropriately changing the high impact design variables.

• Structural Engineering and Mechanics
• /
• v.8 no.1
• /
• pp.53-72
• /
• 1999

The most important features of linear soil-foundation-structure interaction are reviewed, using stochastic modeling and considering kinematic interaction, inertial interaction, and structural distortion as three separate stages of the dynamic response to the free-field motion. The way in which each of the three dynamic stages modifies the spectral density of the motion is studied, with the emphasis being on interpretation of these results, rather than on the development of new analysis techniques. Structural distortion and inertial interaction analysis are shown to be precisely modeled as linear filtering operations. Kinematic interaction, though, is more complicated, even though it has a filter-like effect on the frequency content of the motion.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.699-705
• /
• 2009

This paper reviews methods used to perform reliability and availability analysis of the network system composed by nodes and links. The combination of nodes and links forms virtual connections (VC). The failure of several VCs cause failure of whole network system. Petri Net models are used to analyze the reliability and availability. Stochastic reward nets (SRN) is an extension of stochastic Petri nets provides modelling facilities for network system analysis.