Improved machine classification algorithm for electric rail circuits in train warning systems
There are known algorithms that implement the classification of code signals in an electric rail circuit. These algorithms, however, have some disadvantages in the form of either relatively complex implementation or reduced accuracy in the presence of noise in a code signal. In this article, we...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Omsk State Technical University, Federal State Autonoumos Educational Institution of Higher Education
2019-12-01
|
| Series: | Омский научный вестник |
| Subjects: | |
| Online Access: | https://www.omgtu.ru/general_information/media_omgtu/journal_of_omsk_research_journal/files/arhiv/2019/6%20(168)/63-69%20%D0%9F%D1%80%D0%B8%D1%81%D1%83%D1%85%D0%B8%D0%BD%D0%B0%20%D0%98.%20%D0%92.,%20%D0%91%D0%BE%D1%80%D0%B8%D1%81%D0%B5%D0%BD%D0%BA%D0%BE%20%D0%94.%20%D0%92..pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | There are known algorithms that implement the classification of
code signals in an electric rail circuit. These algorithms, however,
have some disadvantages in the form of either relatively complex
implementation or reduced accuracy in the presence of noise in
a code signal.
In this article, we present an improved classification algorithm,
which combines the simplicity of implementation and accuracy.
The algorithm is based on a neural network trained with
cyclically shifted learning examples. We explore the optimal size
of the neural network for this type of training set. At the cost
of the increased size of the neural network we streamline the
classification process and preserve its accuracy. |
|---|---|
| ISSN: | 1813-8225 2541-7541 |