Susceptible, infective, recovered, and hospitalized/isolated individuals are placed on the cells of a n × n square lattice, where in each cell is occupied by a single individual, or is vacant. At discrete time units (typically one day each) all susceptibles and infectives execute a random movement and when a coincidence of the two types occurs at some cell the susceptible is converted to infective status according to some probability in the range 0.03-0.05. Infectives are labeled by the number of days since originally infected. At each time increment the age label of the infectives is increased by one unit. When the label reaches a specified number like 15 or 20 days the infectives recover according to a specified probability, e.g. 0.8, or become isolated/hospitalized. Upon reaching some specified age the latter types either recover or die. Probabilities for the movements and conversions from one status to another are implemented by random number generation. Simulations were carried out to investigate the effect of several probability and age parameters, the size of population (proportional to n × n) and density (related to fraction of occupied cells), and the size of the movements. Mid-term gradual conversion of susceptibles to isolated was explored as an intervention policy. Most simulations were carried out for a 50 × 50 or 100 × 100 lattice.

The analyst often must deal with data that represents the history of changes in various objects over time, with time series. They are the ones that are most interesting from the point of view of many analysis tasks, and especially forecasting.

For analysis tasks, time counts are of interest-values recorded at some, usually equidistant, points in time. Counts can be taken at various intervals: in a minute, an hour, a day, a week, a month, or a year, depending on how much detail the process should be analyzed. In time series analysis problems, we are dealing with discrete time, when each observation of a parameter forms a time frame. We can say the same about the behavior of COVID-19 over time.

This paper solves the problem of predicting COVID-19 diseases in Moscow and the Russian Federation using neural networks. This approach is useful when it is necessary to overcome difficulties related to non-stationarity, incompleteness, unknown distribution of data, or when statistical methods are not completely satisfactory. The problem of forecasting is solved using the analytical platform Deductor Studio, developed by specialists of Intersoft Lab of the Russian Federation. When solving this problem, we used mechanisms for clearing data from noise and anomalies, which ensured the quality of building a forecast model and obtaining forecast values for tens of days ahead. The principle of time series forecasting was also demonstrated: import, seasonal detection, cleaning, smoothing, building a predictive model, and predicting COVID-19 diseases in Moscow and the Russian Federation using neural technologies for twenty days ahead.

With the long-term outbreak of the COVID-19 around the world, identi- fying high-risk areas is becoming a new research boom. In this paper, we propose a novel regression method namely Regular Linear Kernel Regression (RLKR) for COVID-19 high-risk areas exploration. We explain in detail how the canonical linear kernel regression method is linked to the identification of high-risk areas for COVID-19. Furthermore, the consistence condition of Kernel Selection, which is closely related to the identification of high-risk areas, is given with two mild assumptions. Finally, the RLKR method was verified by simulation experiments and applied for COVID-19 high-risk area Exploration.

Dengue and co-infection with typhoid infection is increasingly recognized as one of the world's emerging infectious diseases. We have appraised Complete Blood Count (CBC) parameters and serological NS1, IgG/IgM rapid test data along with survey questionnaire of 314 suspected dengue and typhoid patients with Acute Febrile Illness (AFI) symptoms patients from the different villages of Sonepat district, Haryana to predict dengue and co-infection with typhoid model. Among those suspected patients, 50 dengue positive (14 primaries and 37 secondary infections) in age groups 10-39 years, 86 typhoid positive (64 primaries and 22 secondary infections) in age groups 10-49 years, 8 co-infection cases in age groups 10-29 year and 40-49 years mostly were reported respectively. As per bayesian analysis model and logistic regression model, TLC<4000 cells/cmm (leukopenia) of dengue, MCH>32 pg of typhoid and MCV<83 fL of co-infection was mostly statistically significant (p<0.05) among different clinical parameters with high ROC value (area ± SE) with 61-71% accuracy of disease diagnosis evaluation. We identified important CBC parameters to qualify the distinction of dengue, typhoid and co-infection patients with AFI and for more confirmation, a further investigation should be designed for early diagnosis and treatment for the patients.