81747

Автор(ы): 

Автор(ов): 

4

Параметры публикации

Тип публикации: 

Статья в журнале/сборнике

Название: 

Information complexity of time-frequency distributions of signals in detection and classification problems

ISBN/ISSN: 

1099-4300

DOI: 

10.3390/e27100998

Наименование источника: 

  • Entropy

Обозначение и номер тома: 

Volume 27, Number 10

Город: 

  • Basel

Издательство: 

  • MDPI

Год издания: 

2025

Страницы: 

1-23 https://doi.org/10.3390/e27100998
Аннотация
The paper considers the problem of detecting and classifying acoustic signals based on information (entropy) criteria. A number of new information features based on timefrequency distributions are proposed, which include the spectrogram and its upgraded version, the reassigned spectrogram. To confirm and verify the proposed characteristics, modeling on synthetic signals and numerical verification of the solution of the multiclass classification problem based on machine learning methods on real hydroacoustic recordings are carried out. The obtained high classification results (F1 = 0.95) allow us to assert the advantages of using the proposed characteristics.

Библиографическая ссылка: 

Лысенко П.В., Галяев А.А., Берлин Л.М., Бабиков В.Г. Information complexity of time-frequency distributions of signals in detection and classification problems // Entropy. 2025. Volume 27, Number 10. С. 1-23 https://doi.org/10.3390/e27100998.