• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.184-191
• /
• 2020

With the emergence of the 4th Industrial Revolution, core technologies that will lead the 4th Industrial Revolution such as AI (artificial intelligence), big data, and Internet of Things (IOT) are also at the center of the topic of the general public. In particular, there is a growing trend of attempts to present future visions by discovering new models by using them for big data analysis based on data collected in a specific field, and inferring and predicting new values with the models. In order to obtain the reliability and sophistication of statistics as a result of big data analysis, it is necessary to analyze the meaning of each variable, the correlation between the variables, and multicollinearity. If the data is classified differently from the hypothesis test from the beginning, even if the analysis is performed well, unreliable results will be obtained. In other words, prior to big data analysis, it is necessary to ensure that data is well classified according to the purpose of analysis. Therefore, in this study, data is classified using a decision tree technique and a random forest technique among classification analysis, which is a machine learning technique that implements AI technology. And by evaluating the degree of classification of the data, we try to find a way to improve the classification and analysis rate of the data.

• Journal of applied mathematics & informatics
• /
• v.6 no.2
• /
• pp.369-378
• /
• 1999

In This study we examine the applicability of Newton's method and the modified Newton's method for a, pp.oximating a lo-cally unique solution of a nonlinear equation in a Banach space. We assume that the newton-Kantorovich hypothesis for Newton's method is violated but the corresponding condition for the modified Newton method holds. Under these conditions there is no guaran-tee that Newton's method starting from the same initial guess as the modified Newton's method converges. Hence it seems that we must always use the modified Newton method under these condi-tions. However we provide a numerical example to demonstrate that in practice this may not be a good decision.

• Structural Engineering and Mechanics
• /
• v.59 no.4
• /
• pp.739-759
• /
• 2016

The failure of civil engineering systems is a consequence of decision making under uncertain conditions. Generally, buried flexible pipes are designed for their transversal behavior to prevent from the important failure mode of buckling. However, the interaction effects between soil and pipe are neglected and the uncertainties in their properties are usually not considered in pipe design. In this regard, the present research paper evaluates the effects of these uncertainties on the uncertainty of the critical buckling hoop force of flexible pipes shallowly buried using the subgrade reaction theory (Winkler model) and First-Order Second-Moment (FOSM) method. The results show that the structural uncertainties of the studied pipes and those of the soil properties have a significant effect on the uncertainty of the critical buckling hoop force, and therefore taking into account these latter in the design of the shallowly flexible pipes for their buckling behavior is required.

• Structural Engineering and Mechanics
• /
• v.57 no.6
• /
• pp.1125-1142
• /
• 2016

Tunneling is one of the challenging tasks in civil engineering because it involves a variety of decision making and engineering judgment based on knowledge and experience. One of the challenges is to construct tunnels in risky areas under shallow overburden. In order to prevent the collapse of ceilings and walls of a large tunnels, in such conditions, either a sequential excavation method (SEM) or ground reinforcing method, or a combination of both, can be utilized. This research deals with the numerical modeling of L-profiles and pipe fore-poling pre-support systems in the adit tunnel in northwestern Iran. The first part of the adit tunnel has been drilled in alluvial material with very weak geotechnical parameters. Despite applying an SEM in constructing this tunnel, analyzing the results of numerical modeling done using FLAC3D, as well as observations during drilling, indicate the tunnel instability. To improve operational safety and to prevent collapse, pre-support systems, including pipe fore-poling and L-profiles were designed and implemented. The results of the numerical modeling coupled with monitoring during operation, as well as the results of instrumentation, indicate the efficacy of both these methods in tunnel collapse prevention. Moreover, the results of modeling using FLAC3D and SECTION BUILDER suggest a double angle with equal legs ($2L100{\times}100{\times}10mm$) in both box profile and tee array as an alternative section to pipe fore-poling system while neither $L80{\times}80{\times}8mm$ nor $2L80{\times}80{\times}8mm$ can sustain the axial and shear stresses exerted on pipe fore-poling system.

• Nuclear Engineering and Technology
• /
• v.28 no.2
• /
• pp.129-136
• /
• 1996

Influence diagram method is applied to containment performance analysis of Young-Gwang 3&4 in an effort to overcome some drawbacks of current containment performance analysis method. Event tee methodology has been adopted as a containment performance analysis method. There are, however, some drawbacks on event tree methodology. This study is to overcome three major drawbacks of the current containment performance analysis method : 1) Event tree cannot express dependency between events explicitly. 2) Accident Progression Event Tree (APET) cannot represent entire containment system. 3) It is difficult to consider decision making problem. To resolve these problems, influence diagrams, is proposed. In the present ok, the applicability of the influence diagrams has been demonstrated for YGN 3&4 containment performance analysis and accident management strategy assessments of this study are in good agreement with those of YGN 3&4 IPE. Sensitivity analysis has been peformed to identify relative important variables for each early containment failure, late containment and basemat melt-though. In addition, influence diagrams are used to assess two accident management strategies : 1) RCS depressurization, 2) cavity flooding. It is shown that influence diagrams can be applied to the containment performance analysis.