Applying information methods, neural networks and genetic algorithms for solving the problem of selecting a scheme of treatment

Abstract

Recently, bionic-based IT solutions for monitoring developing biosystems have become a promising scientific trend. Biosystems evolving over millions of years have formed struc-tures, such as genetic, immune and neural systems that ensure their balanced development and the availability of the necessary information means to control and adaptively manage them in a changing environment. At the present time, attempts are made to use artificial information pro-cessing systems that structurally reflect the functioning of biosystems. Particular attention is paid to the development of models and methods that fully consider the specific nature of each research object. The present study is aimed to consider ways to minimize the possibility of a human or-ganism transition to an unfavorable state through the selection of control activities sequence. To solve the problem, we developed a bionic model based on combining information approach-es, neural networks, and a genetic algorithm. The functions of the model elements and their in-teraction are considered in the paper. A special focus is on the neuro-evolutionary interaction. The description of the software implemented in the programming language Python is described. Test-control groups and cross-validations weres used to evaluate the effectiveness of solutions based on bionic modeling. It was experimentally proved that the proposed method is effective for selecting and applying control activities.