No abstract

Herein, we show differences in blood serum of asymptomatic and symptomatic pregnant women infected with COVID-19 and correlate them with laboratory indexes, ATR FTIR and multivariate machine learning methods. We collected the sera of COVID-19 diagnosed pregnant women, in the second trimester (n = 12), third-trimester (n = 7), and second-trimester with severe symptoms (n = 7) compared to the healthy pregnant (n = 11) women, which makes a total of 37 participants. To assign the accuracy of FTIR spectra regions where peak shifts occurred, the Random Forest algorithm, traditional C5.0 single decision tree algorithm and deep neural network approach were used. We verified the correspondence between the FTIR results and the laboratory indexes such as: the count of peripheral blood cells, biochemical parameters, and coagulation indicators of pregnant women. CH 2 scissoring, amide II, amide I vibrations could be used to differentiate the groups. The accuracy calculated by machine learning methods was higher than 90%. We also developed a method based on the dynamics of the absorbance spectra allowing to determine the differences between the spectra of healthy and COVID-19 patients. Laboratory indexes of biochemical parameters associated with COVID-19 validate changes in the total amount of proteins, albumin and lipase.

No abstract

In this paper, we consider transition system models of behaviour of Physarum machines in terms of rough set theory. A Physarum machine, a biological computing device implemented in the plasmodium of Physarum polycephalum (true slime mould), is a natural transition system. In the behaviour of Physarum machines, one can notice some ambiguity in Physarum motions that influences exact anticipation of states of machines in time. To model this ambiguity, we propose to use rough set models created over transition systems. Rough sets are an appropriate tool to deal with rough (ambiguous, imprecise) concepts in the universe of discourse.