Biomedical subjects

Guang Wu

Publications and source records attributed to Guang Wu.

41 records · Page 3Linked to original sources

PubMed1998

A multilayer recurrent neural network for solving continuous-time algebraic Riccati equations.

A multilayer recurrent neural network is proposed for solving continuous-time algebraic matrix Riccati equations in real time. The proposed recurrent neural network consists of four bidirectionally connected layers. Each layer consists of an array of neurons. The proposed recurrent neural network is shown to be capable of solving algebraic Riccati equations and synthesizing linear-quadratic control systems in real time. Analytical results on stability of the recurrent neural network and solvability of algebraic Riccati equations by use of the recurrent neural network are discussed. The operating characteristics of the recurrent neural network are also demonstrated through three illustrative examples.

Journal Article↗

PubMedDate not supplied

Random analysis of amino acid pairs sensitive to variants in human coagulation factor IX precursor.

In this study, we used a random approach to determine which amino acid pairs in human coagulation factor IX precursor are more sensitive to its 99 variants. The results show that the randomly unpredictable amino acid pairs are more sensitive to variants.

Amino Acid Sequence↗

PubMedDate not supplied

Squared correlation coefficient of measured values versus predicted values in linear and monoexponential regressions.

The correlation coefficient of measured values vs predicted values is widely used in pharmacokinetic and biopharmaceutical settings. When using linear and monoexponential regressions, we notice an interesting characteristic of the squared correlation coefficient of measured values vs predicted values, i.e. the squared correlation coefficient of measured y1 vs predicted (lambda)y2 is a constant regardless of different values of regression coefficients and is equal to the squared correlation coefficient of measured x1 vs measured y1.

Forecasting↗

PubMedDate not supplied

An extremely strange observation on the equations for calculation of correlation coefficient.

Various equations are used to calculate the correlation coefficient, these equations are presumed equally. However we find the extraordinary results when using r = square root of ((sigma(ŷi - y)2) / (sigma(yi - y)2)) and r2 = (sigma(yi - y)2 - sigma(yi - ŷi)2) / (sigma(yi - y)2) to calculate the correlation coefficient, for example, a line within 95% confidence band of a regressed line. The results are so extraordinary that we do not know whether or not we can still call the results as correlation coefficient, however we are sure that these results need to be presented.

Linear Models↗

PubMedDate not supplied

Calculation of steady-state distribution delay between central and peripheral compartments in two-compartment models with infusion regimen.

A lag time may exist between blood drug concentration and drug effect. Various factors can contribute to the lag time, among which the drug distribution delay is a significant one. The drug distribution delay can also exist between different compartments. An equation was derived to calculate the steady-state drug concentration delay between central and peripheral compartments in a two-compartment model with infusion regimen.

Algorithms↗