No abstract

No abstract

The article deals with the problems of analyzing multi-agent models of population dynamics. The problems studied are caused by a number of uncertainties associated with variables, boundary conditions, initial states, parameter values, etc. Given problems could be found in tasks associated with cyber security of critical infrastructures (e.g. DDoS attacks, computer worms, etc.). To solve this problem, a linguistic fuzzy model has been developed, which allows describing systems of population dynamics in a more realistic way. Population dynamics is described by a set of rules, each of which involves entry and exit in the form of fuzzy sets or fuzzy functions, which are applied iteratively. The complexity of describing the processes of population dynamics systems, the presence of fuzzification and defuzzification algorithms, and the use of fuzzy sets and linguistic variables make it necessary to develop new methods for analyzing such systems. The approaches proposed in the article to the study of systems of population dynamics make it possible to apply a unified description of processes of different nature in the form of a production set of rules.

The article considers the problem of machine learning of a wrist prosthesis control system with a non-invasive biosignal reading system. The task is solved within the framework of information-extreme intelligent data analysis technology, which is based on maximizing the system’s information productivity in machine learning. The idea of information-extreme machine learning of the control system for recognition of electromyographic biosignals, as in artificial neural networks, consists in adapting the input information description to the maximum total probability of making correct classification decisions. However, unlike neuro-like structures, the proposed method was developed within a functional approach to modeling the cognitive processes of the natural intelligence of forming and making classification decisions. As a result, the proposed method acquires the properties of adaptability to the intersection of classes in the space of recognition features and flexibility when retraining the system due to the recognition class alphabet expansion. In addition, the decision rules constructed within the framework of the geometric approach are practically invariant to the multidimensionality of the space of recognition features. The difference between the developed method and the well-known methods of information-extreme machine learning is the use of a sparse training matrix, which allows for reducing the degree of intersection of recognition classes significantly. The optimization parameter of the input information description, the training dataset, is the quantization level of electromyographic biosignals. As an optimization criterion is considered the modified Kullback information measure. The proposed machine learning algorithm results are shown in the example of recognition of six finger movements and wrist.

No abstract