An improved bidirectional generative adversarial network model for multivariate estimation of correlated and imbalanced tunnel construction parameters

Estimation of construction parameters is crucial for optimizing tunnel construction schedule.Due to the influence of routine activities and occasional risk events,these parameters are usually correlated and imbalanced.To solve this issue,an improved bidirectional generative adversarial network(BiGAN)model with a joint discriminator structure and zero-centered gradient penalty(0-GP)is proposed.In this model,in order to improve the capability of original BiGAN in learning imbalanced parameters,the joint discriminator separately discriminates the routine activities and risk event durations to balance their influence weights.Then,the self-attention mechanism is embedded so that the discriminator can pay more attention to the imbalanced parameters.Finally,the 0-GP is adapted for the loss of the discrimi-nator to improve its convergence and stability.A case study of a tunnel in China shows that the improved BiGAN can obtain parameter estimates consistent with the classical Gauss mixture model,without the need of tedious and complex correlation analysis.The proposed joint discriminator can increase the ability of BiGAN in estimating imbalanced construction parameters,and the 0-GP can ensure the stability and convergence of the model.

Fuzzy Synthetic Evaluation of Water Quality of Naoli River Using Parameter Correlation Analysis

In order to improve the effectiveness of Fuzzy Synthetic Evaluation (FSE) models, a Parameter Correlation Analysis (PCA) was introduced into the FSE and a case study was carried out in the Naoli River in the Sanjiang Plain, Northeast China. The basic principle of the PCA is that the pairs of parameters which are highly correlated and linear with each other would contribute the same information to an assessment and one of them should be eliminated. The method of the PCA is that a correlation relationship among candidate parameters is examined before the FSE. If there is an apparent nonlinear or curvilinear relationship between two parameters, then both will be retained; if the correlation is significant (p<0.01), and the scatter plot suggests a linear relationship, then one of them will be deleted. However, which one will be deleted? For solving this problem, a sensitivity test was conducted and the higher sensitivity parameters remained. The results indicate that the original data should be preprocessed through the PCA for redundancy and variability. The study shows that introducing the PCA into the FSE can simplify the FSE calculation process greatly, while the results have not been changed much.

Weighted Parameterized Correlation Coefficients of Indeterminacy Fuzzy Multisets and Their Multicriteria Group Decision Making Method with Different Decision Risks

Real-life data introduce noise,uncertainty,and imprecision to statistical projects;it is advantageous to consider strategies to overcome these information expressions and processing problems.Neutrosophic(indeterminate)numbers can flexibly and conveniently represent the hybrid information of the partial determinacy and partial indeterminacy in an indeterminate setting,while a fuzzy multiset is a vital mathematical tool in the expression and processing of multi-valued fuzzy information with different and/or same fuzzy values.If neutrosophic numbers are introduced into fuzzy sequences in a fuzzy multiset,the introduced neutrosophic number sequences can be constructed as the neutrosophic number multiset or indeterminate fuzzy multiset.Motivated based on the idea,this study first proposes an indeterminate fuzzy multiset,where each element in a universe set can be repeated more than once with the different and/or identical indeterminate membership values.Then,we propose the parameterized correlation coefficients of indeterminate fuzzy multisets based on the de-neutrosophication of transforming indeterminate fuzzy multisets into the parameterized fuzzy multisets by a parameter(the parameterized de-neutrosophication method).Since indeterminate decision-making issues need to be handled by an indeterminate decision-making method,a group decision-making method using the weighted parameterized correlation coefficients of indeterminate fuzzy multisets is developed along with decision makers’different decision risks(small,moderate,and large risks)so as to handle multicriteria group decision-making problems in indeterminate fuzzy multiset setting.Finally,the developed group decision-making approach is used in an example on a selection problem of slope design schemes for an open-pit mine to demonstrate its usability and flexibility in the indeterminate group decision-making problem with indeterminate fuzzy multisets.

THE FUZZY SYNTHETIC JUDGEMENT OF CORRELATING PARAMETER OF FIGHTER DESIGN

An expression of correlating parameter is developed which can be used to synthetically express the close combat maneuverability of fighters by the method of fuzzy mathematics. On the basis of analysis of fighter maneuvering performances, this paper proposes the parameters ωA,ωs, and SEP to measure the maneuvering performances. The linear weighted method, which is one of the basic methods of transforming several objects to a single object in mathematics programming, is used to determine the form of the correlating parameter expression. The focal point of this paper's work is to determine the weight coefficients of maneuvering performances in the expression. In order to solve this problem, the inverse problem of synthetic judgement in fuzzy mathematics is employed. The development of the equation of fuzzy relationship in this paper is based on the judgement data, which are gathered from many experts working in aeronautical field. Therefore, the expression of correlating parameter developed by this paper can be used in the design object at aircraft conceptual design stage and the judgement of synthetical measurement of the maneuverability of fighters.

Isobaric Vapor-Liquid Equilibrium of Binary Systems： p-Xylene ＋ （Acetic Acid, Methyl Acetate and n-Propyl Acetate） and Methyl Acetate ＋ n-Propyl Acetate in an Acetic Acid Dehydration Process

The vapor-liquid equilibrium data of four binary systems (acetic acid +p-xylene, methyl acetate +n-propyl acetate, n-propyl acetate +p-xylene and methyl acetate +p-xylene) are measured at 101.33 kPa with Ellis equilibrium still, and then both the NRTL and UNIQUAC models are used in combination with the HOC model for correlating and estimating the vapor-liquid equilibrium of these four binary systems. The estimated binary VLE results using correlated parameters agree well with the measured data except the methyl acetate +p-xylene system which easily causes bumping and liquid rushing out of the sampling tap due to their dramatically different boiling points. The correlation results by NRTL and UNIQUAC models have little difference on the average absolute deviations of temperature and composition of vapor phase, and the results by NRTL model are slightly better than those by UNIQUAC model except for the methyl acetate +n-propyl acetate system, for which the latter gives more accurate correlations.

Discovery of new characterizations of parameter distributions in a semiempirical mass model:an investigation by dividing an overdetermined system into numerous balanced subsystems

We propose and test a new method of estimating the model parameters of the phenomenological BetheWeizsacker mass formula.Based on the Monte Carlo sampling of a large dataset,we obtain,for the first time,a Cauchy-type parameter distribution formed by the exact solutions of linear equation systems.Using the maximum likelihood estimation,the location and scale parameters are evaluated.The estimated results are compared with those obtained by solving overdetermined systems,e.g.,the solutions of the traditional least-squares method.Parameter correlations and uncertainty propagation are briefly discussed.As expected,it is also found that improvements in theoretical modeling(e.g.,considering microscopic corrections)decrease the parameter and propagation uncertainties.

Correlation of quantitative perfusion parameters on dynamic contrast-enhanced MRI with prognostic factors and subtypes of breast carcinoma

Objective To investigate whether correlation existsbetween quantitative perfusion parameters obtained from dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI)and different prognostic factors or immunohistochemical subtypes of breast cancers.Methods A retrospective analysis of DCE-MRI was performed in

The correlation between molecular structure parameters of O-ethyl N-isopropyl phosphoro(thioureido)thioates and their retention data in RP-HPLC

A retention prediction system(RPS)of seven O-ethyl N-isopropyl phosphoro(thioureido)- thioates in reversed phase HPLC was investigated.The system is based on the solvent selectivity triangle concept.Three molecular structure parameters(hydrophobicity Ⅱ,substituent length L, and substituent maximum width B_5)were used to describe the quantitative structure-retention relation- ships.With these quantitative relationships,the retention behaviours of other eight homologs for different mobile phase composition were predicted.The predicted values were consistent with the measured values within relative error of 10%,which means that it is possible to apply the reported method to predict retention values for qualitative purposes for different mobile phase compositions.

Complex permittivity spectra of binary polar liquids using time domain reflectometry

The study of complex properties in a binary mixture of polar liquids has been carried out in the frequency range of 10 MHz to 30 GHz at 293 K and 298 K temperatures using time domain reflectometry.The complex properties of polar liquids in binary mixture give information about the frequency dispersion in the dielectric permittivity(ε')and dielectric loss(ε").The information regarding the orientation of electric dipoles in a polar liquid mixture is given by Kirkwood parameters.The Bruggeman parameters are used as the indicator of liquid1 and liquid2 interaction.Molar entropy(ΔS)and molar enthalpy(ΔH)are also discussed at the end of the paper.