Special Issue "Adaptive Filters and Machine Learning Algorithms for Nonlinear System Identification and Processing"

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Information Theory, Probability and Statistics".

Deadline for manuscript submissions: 15 April 2022.

Special Issue Editors

Dr. Raffaele Parisi
E-Mail Website
Guest Editor
Department of Information Engineering, Electronics and Telecommunications (DIET), University of Rome “La Sapienza”, Via Eudossiana 18, 00184 Rome, Italy
Interests: signal processing; machine learning; neural networks; array processing; source localization
Dr. Alberto Carini
E-Mail Website
Guest Editor
Department of Engineering and Architecture (DIA), University of Trieste, Via Valerio 10, 34127 Trieste, Italy
Interests: signal processing; nonlinear filters; adaptive filters; audio processing; active noise control
Dr. Mirco Ravanelli
E-Mail Website
Guest Editor
Mila, Université de Montréal, Montréal, QC H3T 1J4, Canada
Interests: machine learning; deep learning; speech processing; signal processing; speech recognition
Dr. Felipe Tobar
E-Mail Website
Guest Editor
Center for Mathematical Modeling, Universidad de Chile, Santiago, Chile
Interests: machine learning; statistical signal processing; Bayesian inference

Special Issue Information

Dear Colleagues,

Linear adaptive filters have been applied to a plethora of tasks in different disciplines where adapting to changes in operating conditions is crucial. Typical application areas that benefit from the use of linear adaptive filters include telecommunication, radar, sonar, video and audio signal processing and, particularly, system identification. Among others, information-theoretic techniques have received particular attention in the community, leading to the recognized framework of adaptive information filtering. General-purpose optimization procedures for designing linear filters are, today, well established and mature, thus facilitating the design of ad hoc cost functions for specific applications of interest.

Despite the established relevance and broad scope of linear filters, practical real-world challenges often involve nonlinear systems. Nonlinearities may arise either from the dynamics of the variables of interest or even from the process of their observation. Critically, the nonlinear patterns of the objects under study may not even be known due to the impossibility of constructing a mathematical model from first principles, in which cases, the relationships among the variables of interest have to be discovered from the data. This procedure is usually referred to as machine learning and encompasses a large number of techniques ranging from signal processing, information theory and statistics to computer science, with broad applications spanning several fields.

The goal of this Special Issue is to present novel results and trends in the field of nonlinear system identification and processing by blending concepts from adaptive filtering, machine learning and information theory. In particular, the application of concepts drawn from information-theoretic learning to machine learning or adaptive filtering frameworks are particularly appealing. Interested researchers are invited to submit their most recent findings on these topics. The possible areas of interest include (but are not limited to) forecasting, system modeling, echo cancellation, denoising, dereverberation, source separation and extraction, channel equalization, and array processing, all with a particular emphasis on adaptive methods.

Dr. Raffaele Parisi
Dr. Alberto Carini
Dr. Mirco Ravanelli
Dr. Felipe Tobar
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • adaptive filters
  • machine learning
  • information theory
  • neural networks
  • nonlinear optimization
  • signal equalization
  • noise and interference cancellation
  • array processing
  • echo and noise control

Published Papers

This special issue is now open for submission.
Back to TopTop