The proposed multivariate method of qualitative analysis of models of electrophysiological processes is an approach that allows to solve problems of classification of excitability of cells which cannot be solved by other traditional methods, for example stability theory, or boundary cycles. As a whole, the method combines the Monte Carlo approach for the formation of training kits and the data mining classification algorithms: the sequential coverage method with the generation of classification

more »

... rules and the induction method of the decision tree. The advantages of the classification rules, which can be built on the 5th step of the algorithm, are that they correspond to the natural reflection of knowledge in the thinking of people and are more expressive. In addition, the sequential coverage algorithm is easier to implement and debug than the recursive algorithms of decision trees, and its computational complexity is simpler than that of finite state machines. The decision tree induction method, being more complex to implement, allows visualization and a priori probability values for the type of cell excitability based on the relationship between the initial values and the velocity parameters in the Hodgkin-Huxley model. The developed method consists of 5 stages. The approach is proven in the form of software in the Java-class package.