Anzeige
Erschienen in:
2016 | OriginalPaper | Buchkapitel
Integration of Bayesian Classifier and Perceptron for Problem Identification on Dynamics Signature Using a Genetic Algorithm for the Identification Threshold Selection
verfasst von : Evgeny Kostyuchenko, Mihail Gurakov, Egor Krivonosov, Maxim Tomyshev, Roman Mescheryakov, Ilya Hodashinskiy
Erschienen in: Advances in Neural Networks – ISNN 2016
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
An approach to the integration of multiple methods of user authentication and example of multi-classifier Bayesian and neural network is presented. The approach offers to find the convolution of outputs from multiple classifiers based on the complementary functions and to carry out the selection of the identification thresholds for each of the users. A number of complementary functions that use fundamentally different mathematical functions is analyzed. It is shown the practical need in metaheuristic algorithms for selecting the identification thresholds by comparison with the classic gradient method. The effectiveness some of the proposed series of multi-function, compared with the single use Bayes classifier and neural network is showed.