Year: 2021
Type: conference-paper
Abstract: The paper discusses the prospects for building decision blocks (DB) for modern security systems built on the basis of fiber optic detectors. An algorithm has been developed that makes it possible to train an artificial neural network as part of a DB. Approaches to the formation of a training sample are outlined. To reduce the dimension of the problem of recognizing informative signal features, an extreme filtering algorithm is presented, which makes it possible to increase the speed and accuracy of training.
Author: E Tsarkova
Institution: Federal Penitentiary Service
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4200210794