Covid-19 Diagnosis by Artificial Intelligence Based on Vibraimage Measurement of Behavioral Parameters

The hypothesis of behavioral parameters dependence measured from person’s head movements in quasi-stationary state on COVID-19 disease is discussed. Method for determining the dependence of vestibular-emotional reflex parameters on COVID-19, various diseases and pathologies are proposed. Micro-movements of a head for representatives of the control group (with a confirmed absence of COVID-19 disease) and a group of patients with a confirmed diagnosis of COVID-19 were studied using vibraimage technology. Parameters and criteria for the diagnosis of COVID-19 for training artificial intelligence (AI) on the control group and the patient group are proposed. 3-layer (one hidden layer) feedforward neural network (40 + 20 + 1 sigmoid neurons) was developed for AI training. AI was firstly trained on the primary sample of patients and a control group. Study of a random sample of people with trained AI was carried out and the possibility of detecting COVID-19 using the proposed method was proved a week before the onset of clinical symptoms of the disease. Number of COVID-19 diagnostic parameters was increased to 26 and AI was trained on a sample of 536 measurements, 268 patient measurement results and 268 measurement results in the control group. The achieved diagnostic accuracy was more than 99%, 4 errors per 536 measurements (2 false positive and 2 false negative), specificity 99.25% and sensitivity 99.25%. The issues of improving the accuracy and reliability of the proposed method for diagnosing COVID-19 are discussed. Further ways to improve the characteristics and applicability of the proposed method of diagnosis and self-diagnosis of COVID-19 are outlined.

Evolution of stress fields during the supercontinent cycle

We investigate the evolution of stress fields during the supercontinent cycle using the 2D Cartesian geometry model of thermochemical convection with the non-Newtonian rheology in the presence of floating deformable continents.In the course of the simulation,the supercontinent cycle is implemented several times.The number of continents considered in our model as a function of time oscillates around 3.The lifetime of a supercontinent depends on its dimension.Our results suggest that immediately before a supercontinent breakup,the over-lithostatic horizontal stresses in it(referring to the mean value by the computational area)are tensile and can reach-250 MPa.At the same time,a vast area beneath a supercontinent with an upward flow exhibits clearly the over-lithostatic compressive horizontal stresses of 50-100 МРа.The reason for the difference in stresses in the supercontinent and the underlying mantle is a sharp difference in their viscosity.In large parts of the mantle,the over-lithostatic horizontal stresses are in the range of±25 MPa,while the horizontal stresses along subduction zones and continental margins are significantly larger.During the process of continent-to-continent collisions,the compressive stresses can approximately reach 130 MPa,while within the subcontinental mantle,the tensile over-lithostatic stresses are about-50 MPa.The dynamic topography reflects the main features of the su-percontinent cycle and correlates with real ones.Before the breakup and immediately after the disin-tegration of the supercontinent,continents experience maximum uplift.During the supercontinent cycle,topographic heights of continents typically vary within the interval of about±1.5 km,relatively to a mean value.Topographic maxima of orogenic formations to about 2-4 km are detected along continent-to-continent collisions as well as when adjacent subduction zones interact with continental margins.