Wavelet scattering is a redundant time-frequency transform that was shown to be a powerful tool in signal classification. It shares the convolutional architecture with convolutional neural networks, but it offers some advantages, including faster training and small training sets. However, it introduces some redundancy along the frequency axis, especially for filters that have a high degree of overlap. This naturally leads to a need for dimensionality reduction to further increase its efficiency as a machine learning tool. In this paper, the Minimum Description Length is used to define an automatic procedure for optimizing the selection of the scattering features, even in the frequency domain. The proposed study is limited to the class of uniform sampling models. Experimental results show that the proposed method is able to automatically select the optimal sampling step that guarantees the highest classification accuracy for fixed transform parameters, when applied to audio/sound signals.

An MDL-based wavelet scattering features selection for signal classification / Bruni, Vittoria; Cardinali, MARIA LUCIA; Vitulano, Domenico. - In: AXIOMS. - ISSN 2075-1680. - 11:8(2022), p. 376. [10.3390/axioms11080376]

An MDL-based wavelet scattering features selection for signal classification

Vittoria Bruni
;
Maria Lucia Cardinali;Domenico Vitulano
2022

Abstract

Wavelet scattering is a redundant time-frequency transform that was shown to be a powerful tool in signal classification. It shares the convolutional architecture with convolutional neural networks, but it offers some advantages, including faster training and small training sets. However, it introduces some redundancy along the frequency axis, especially for filters that have a high degree of overlap. This naturally leads to a need for dimensionality reduction to further increase its efficiency as a machine learning tool. In this paper, the Minimum Description Length is used to define an automatic procedure for optimizing the selection of the scattering features, even in the frequency domain. The proposed study is limited to the class of uniform sampling models. Experimental results show that the proposed method is able to automatically select the optimal sampling step that guarantees the highest classification accuracy for fixed transform parameters, when applied to audio/sound signals.
2022
signal classification; minimum description length; support vector machine; wavelet scattering
01 Pubblicazione su rivista::01a Articolo in rivista
An MDL-based wavelet scattering features selection for signal classification / Bruni, Vittoria; Cardinali, MARIA LUCIA; Vitulano, Domenico. - In: AXIOMS. - ISSN 2075-1680. - 11:8(2022), p. 376. [10.3390/axioms11080376]
File allegati a questo prodotto
File Dimensione Formato  
Bruni_MDL-Based Wavelet_2022.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 370.7 kB
Formato Adobe PDF
370.7 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1652344
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 3
social impact