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!
|
| _version_ | 1832568736423346176 |
|---|---|
| author | I. V. Prisukhina D. V. Borisenko |
| author_facet | I. V. Prisukhina D. V. Borisenko |
| author_sort | I. V. Prisukhina |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-d12a67699a4a4ad4963513d7e1f87de1 |
| institution | Kabale University |
| issn | 1813-8225 2541-7541 |
| language | English |
| publishDate | 2019-12-01 |
| publisher | Omsk State Technical University, Federal State Autonoumos Educational Institution of Higher Education |
| record_format | Article |
| series | Омский научный вестник |
| spelling | doaj-art-d12a67699a4a4ad4963513d7e1f87de12025-02-03T00:49:13ZengOmsk State Technical University, Federal State Autonoumos Educational Institution of Higher EducationОмский научный вестник1813-82252541-75412019-12-016 (168)636910.25206/1813-8225-2019-168-63-69Improved machine classification algorithm for electric rail circuits in train warning systemsI. V. Prisukhina0D. V. Borisenko1Omsk State Transport UniversityOmsk State Transport UniversityThere 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.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..pdfrail electric systemcab signalingneural networknumeric codingcloud computing |
| spellingShingle | I. V. Prisukhina D. V. Borisenko Improved machine classification algorithm for electric rail circuits in train warning systems Омский научный вестник rail electric system cab signaling neural network numeric coding cloud computing |
| title | Improved machine classification algorithm for electric rail circuits in train warning systems |
| title_full | Improved machine classification algorithm for electric rail circuits in train warning systems |
| title_fullStr | Improved machine classification algorithm for electric rail circuits in train warning systems |
| title_full_unstemmed | Improved machine classification algorithm for electric rail circuits in train warning systems |
| title_short | Improved machine classification algorithm for electric rail circuits in train warning systems |
| title_sort | improved machine classification algorithm for electric rail circuits in train warning systems |
| topic | rail electric system cab signaling neural network numeric coding cloud computing |
| url | 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 |
| work_keys_str_mv | AT ivprisukhina improvedmachineclassificationalgorithmforelectricrailcircuitsintrainwarningsystems AT dvborisenko improvedmachineclassificationalgorithmforelectricrailcircuitsintrainwarningsystems |