Special Issue "Dictionary Learning Algorithms and Applications"

A special issue of Algorithms (ISSN 1999-4893).

Deadline for manuscript submissions: 15 May 2019

Special Issue Editors

Guest Editor
Prof. Dr. Bogdan Dumitrescu

Faculty of Automatic Control and Computers, University Politehnica of Bucharest, Bucuresti, Romania
Website | E-Mail
Interests: numerical methods; signal processing; optimization; sparse representations
Guest Editor
Dr. Cristian Rusu

Institute for Digital Communications, University of Edinburgh, ‎Edinburgh EH8 9YL, UK
Website | E-Mail
Interests: digital communications; dictionary learning; machine learning

Special Issue Information

Dear Colleagues,

Sparse representations have found numerous applications in signal and image processing, coding, compression, classification, modeling and other fields. Their success relies on the parsimony principle: few members of an overcomplete basis can offer a large variety of models. The overcomplete basis, or dictionary, can be fixed or adapted to the application.

Dictionary learning is the technique of designing dictionaries based on samples from the process to be modeled. In many applications, learned dictionaries offer better performance than fixed ones. There are already well established algorithms for the standard problem, but the topic is still open for variations of the learning problem and especially for applications.

We invite you to submit high quality papers to this issue on “Dictionary learning algorithms and applications”, with subjects covering the whole range from theory to applications. The topics include, but are not limited to:

- Dictionary learning (DL) algorithms and toolboxes

- Theoretical properties of DL algorithms

- New formulations and solutions of the DL problem

- Structured dictionary learning

- Manifold dictionary learning

- Kernel dictionary learning

- Incoherent frames

- Classification using sparse representations and DL

- DL applications in signal processing, machine learning, and generally in all engineering fields

Prof. Bogdan Dumitrescu
Dr. Cristian Rusu
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. Algorithms 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 1000 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

  • Dictionary learning
  • Sparse representations
  • Frames
  • Classification
  • Signal and image processing

Published Papers (2 papers)

View options order results:
result details:
Displaying articles 1-2
Export citation of selected articles as:

Research

Open AccessArticle Salt and Pepper Noise Removal with Multi-Class Dictionary Learning and L0 Norm Regularizations
Algorithms 2019, 12(1), 7; https://doi.org/10.3390/a12010007
Received: 1 December 2018 / Revised: 22 December 2018 / Accepted: 23 December 2018 / Published: 25 December 2018
PDF Full-text (3383 KB) | HTML Full-text | XML Full-text
Abstract
Images may be corrupted by salt and pepper impulse noise during image acquisitions or transmissions. Although promising denoising performances have been recently obtained with sparse representations, how to restore high-quality images remains challenging and open. In this work, image sparsity is enhanced with [...] Read more.
Images may be corrupted by salt and pepper impulse noise during image acquisitions or transmissions. Although promising denoising performances have been recently obtained with sparse representations, how to restore high-quality images remains challenging and open. In this work, image sparsity is enhanced with a fast multiclass dictionary learning, and then both the sparsity regularization and robust data fidelity are formulated as minimizations of L0-L0 norms for salt and pepper impulse noise removal. Additionally, a numerical algorithm of modified alternating direction minimization is derived to solve the proposed denoising model. Experimental results demonstrate that the proposed method outperforms the compared state-of-the-art ones on preserving image details and achieving higher objective evaluation criteria. Full article
(This article belongs to the Special Issue Dictionary Learning Algorithms and Applications)
Figures

Figure 1

Open AccessArticle Weak Fault Detection of Tapered Rolling Bearing Based on Penalty Regularization Approach
Algorithms 2018, 11(11), 184; https://doi.org/10.3390/a11110184
Received: 7 October 2018 / Revised: 31 October 2018 / Accepted: 31 October 2018 / Published: 8 November 2018
Cited by 1 | PDF Full-text (3478 KB) | HTML Full-text | XML Full-text
Abstract
Aimed at the issue of estimating the fault component from a noisy observation, a novel detection approach based on augmented Huber non-convex penalty regularization (AHNPR) is proposed. The core objectives of the proposed method are that (1) it estimates non-zero singular values (i.e., [...] Read more.
Aimed at the issue of estimating the fault component from a noisy observation, a novel detection approach based on augmented Huber non-convex penalty regularization (AHNPR) is proposed. The core objectives of the proposed method are that (1) it estimates non-zero singular values (i.e., fault component) accurately and (2) it maintains the convexity of the proposed objective cost function (OCF) by restricting the parameters of the non-convex regularization. Specifically, the AHNPR model is expressed as the L1-norm minus a generalized Huber function, which avoids the underestimation weakness of the L1-norm regularization. Furthermore, the convexity of the proposed OCF is proved via the non-diagonal characteristic of the matrix BTB, meanwhile, the non-zero singular values of the OCF is solved by the forward–backward splitting (FBS) algorithm. Last, the proposed method is validated by the simulated signal and vibration signals of tapered bearing. The results demonstrate that the proposed approach can identify weak fault information from the raw vibration signal under severe background noise, that the non-convex penalty regularization can induce sparsity of the singular values more effectively than the typical convex penalty (e.g., L1-norm fused lasso optimization (LFLO) method), and that the issue of underestimating sparse coefficients can be improved. Full article
(This article belongs to the Special Issue Dictionary Learning Algorithms and Applications)
Figures

Figure 1

Planned Papers

The below list represents only planned manuscripts. Some of these manuscripts have not been received by the Editorial Office yet. Papers submitted to MDPI journals are subject to peer-review.

Title: Dictionary learning for zonotopic approximations of multi-obstacle environments
Author: Florin Stoican, Paul Irofti
Affliation: Deptment of Automatic Control and Systems Engineering, University Politehnica of Bucharest, Romania
Abstract: Control problems involving autonomous vehicles often require a priori knowledge about existing features (obstacles, restricted or target areas, etc.). Therefore, the description of the environment is of paramount importance for the subsequent motion planning strategies. We propose the approximation of the regions of interest through a collection of zonotopic sets whose center and scaling are the result of dictionary learning procedure whose goal is to minimize the complexity of the representation while also providing a close approximation of the initial representation.

Algorithms EISSN 1999-4893 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top