Analysis of possibilities to use neural network for remote control of electronic devices

• Main Authors: Maksym Holikov, Pavlo Galkin
• Format: Article
• Language: English
• Published: PC Technology Center 2018-05-01
• Series: Tehnologìčnij Audit ta Rezervi Virobnictva
• Subjects: remote control; neural network; hardware interfaces to communicate; wireless communications
• Online Access: http://journals.uran.ua/tarp/article/view/149539
• ISSN: 2226-3780; 2312-8372

The object of research in the work is the systems of remote control of electronic devices. There are wired and wireless means of implementing a remote communication channel between the slave and control devices. Analysis of existing means of creating a communication channel, found a low value of the ratio of system flexibility and data transfer rate within the created network. One of the reasons for the low ratio is the use of modules as part of a system with a high minimum operating time. Such modules are modules for filtering and decoding the received signal at the receiver side, encoding and modulation at the transmitter side. Replacing these modules with one with a significantly lower time spent will significantly improve the value of the ratio of system flexibility and data transfer rate. The ability to create a module that will have the necessary properties of time spent on work, provides a neural network. The model of a remote control system obtained during the study has several advantages, in particular, the presence of a neural network, makes it possible to reduce the time spent and to improve the accuracy of the system during the entire system operation time. This is achieved thanks to the ability of the neural network to self-learning without human intervention and its ability to analyze any input signals with different background noise values. These properties allow the replacement of elements that do not allow to increase the rate of exchange for elements of the neural network that will perform the same functions with greater speed, reliability and accuracy. The data obtained during the work proves the expediency of integrating the elements of the neural network into the remote control systems of electronic devices. Also, possible places for the integration of a neural network into the remote control system of electronic equipment have been proposed, which will improve the stability, accuracy, speed of the system.