Solution of the Problem of Classification of Hydroacoustic Signals Based on Harmonious Wavelets and Machine Learning

Two types of real hydroacoustic signals of whales are classified based on the harmonic wavelet transform (HWT) coefficients (fast implementation), windowed Fourier transform (FT) (spectrogram), and conventional FT using the k-NN algorithm. The accuracy of the classification is estimated for various...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Pattern recognition and image analysis Ročník 30; číslo 3; s. 480 - 488
Hlavní autori: Klionskii, D. M., Kaplun, D. I., Voznesensky, A. S., Romanov, S. A., Levina, A. B., Bogaevskiy, D. V., Geppener, V. V., Razmochaeva, N. V.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Moscow Pleiades Publishing 01.07.2020
Springer Nature B.V
Predmet:
Algorithms
Applied Problems
Classification
Computer Science
Fourier transforms
Image Processing and Computer Vision
Machine learning
Neural networks
Pattern Recognition
Signal classification
Signal processing
Speech processing
Underwater acoustics
Wavelet transforms
Whales
windowed Fourier transform
spectrogram
neural networks
wavelet transform
k-NN algorithm
Fourier transform
harmonic wavelets
classification
machine learning
ISSN:1054-6618, 1555-6212
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Two types of real hydroacoustic signals of whales are classified based on the harmonic wavelet transform (HWT) coefficients (fast implementation), windowed Fourier transform (FT) (spectrogram), and conventional FT using the k-NN algorithm. The accuracy of the classification is estimated for various signal-to-noise ratios (SNRs). In order to reduce the dimension of the feature space during classification using the k-NN algorithm, the use of the modulo N reduction method is proposed. The efficiency of the use of harmonic wavelets in the classification of complex nonstationary signals is experimentally proved. The applicability of speech processing methods for the classification of underwater bioacoustic signals is confirmed. The discussed methods are initially developed taking into account the characteristics of human speech, but, nevertheless, showed good results even without being tuned to the characteristics of the classified signals. The problem of classifying two types of whales by the sounds they make using a neural network is solved.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1054-6618
1555-6212
DOI:10.1134/S1054661820030128