ABSTRACT
The processes of intellectual monitoring in emergencies are studied. The intelligent monitoring system is an environment for creating and using intelligent agents to provide knowledge of decision-making processes. In emergencies, objects acquire new properties quickly, and the informativeness of the results of previous observations decreases. To increase the power of data mining tools, monitoring agents are combined into agent functionalities with a multi-tier structure. The paper presents the results of research on the processes of formation of multi-echelon polyagent functionals. The efficiency of construction of a multi-echelon polyagent functional in solving the problem of predicting the incidence of the population of Ukraine on Covid-19 in conditions of low informativeness of the results of observations has been experimentally confirmed. © 2021 Copyright for this paper by its authors
ABSTRACT
The research aim is to improve the efficiency of poly-agent functional monitoring information system by feedback creation. The signs list at the entrance functionality varies according to the characteristics of the signal at the output. The signal characteristics at the functional output are improved by changing the features list of the results of observations at its input. Building poly-agent functionalities by the monitoring information system (MIS) is improved. The MIS is a software implementation of the information technology of intelligent monitoring (ITLM). This paper describes the use of ITLM for forecasting the incidence of COVID-19 disease in the Ukrainian population. The information technology is designed to work under conditions of crisis monitoring. During the pandemic, the properties of the monitoring objects change, and the informativeness of the accumulated results of monitoring decreases. It is proposed to adapt the list of features of the array of input data (AID) to change the informativeness of the observation results. A method for informativeness identifying the AID features of a poly-agent functional based on the results of constructing agents with structural tasks is proposed. AID increasing informativeness by signs list optimizing according to signals' characteristics at the agents' output with the structural tasks of MIS is experimentally confirmed. © 2021 Elsevier B.V.. All rights reserved.