An International Journal, A publication of the European Association for Signal Processing (EURASIP)

Signal Processing incorporates all aspects of the theory and practice of signal processing. It features original research work covering novel signal processing tools as well as tutorial and review articles with a focus on the signal processing issues. It is intended for a rapid dissemination of knowledge to engineers and scientists working in the research, development or practical application of signal processing.

Subject areas covered by the journal include:

    Statistical Signal Processing;
    Detection and Estimation;
    Spectral Analysis and Filtering;
    Machine Learning for Signal Processing;
    Optimization methods for Signal Processing;
    Multi-dimensional Signal Processing;
    Graph Signal Processing;
    Signal Processing over Networks;
    Signal Processing for Communications and networking;
    Biomedical Signal Processing;
    Image and Video Processing;
    Audio and Acoustic Signal Processing;
    Multimedia Signal Processing;
    Radar and Sonar Signal Processing;
    Remote Sensing;
    Data Science;
    Network Science;
    Software Developments and Open Source Initiatives;
    New Applications.

Type of Contributions:
The journal welcomes the following types of contributions.

Original research articles:
Research articles should not exceed 30 pages (single column, double spaced, including figures, tables and references) in length and must contain novel research within the scope of the journal.

Review articles:
Review articles are typically 30-60 pages (single column, double spaced, including figures tables and references) in length, and provide a comprehensive review on a scientific topic. They may be relatively broad in scope, thereby serving a tutorial function, or be quite specialized, aimed at researchers in the chosen field.

Fast Communications:
A Fast Communication is a short, self-contained article highlighting ongoing research, or reporting interesting possibly tentative ideas, or comments on previously published research. Such articles should not exceed 10 pages (single column, double spaced, including figures, tables and references) in length. The objective is to provide detailed, constructive feedback on submitted papers and publish high quality papers within a very short period of time.

Special Issue on Advances in Model-based Deep Learning
Submission Date: 2024-07-31

Mathematical models and optimization methods have played a longstanding, critical role in thedesign of signal processing and analysis systems. In the past decade, data-driven approaches - especially deep learning - have been widely adopted and have achieved state-of-the-art results in various signal and image processing applications; this, however, is at the cost of interpretability and explainability of the model and its decisions. Despite their unprecedented performance and wide adoption, black-box deep learning models come with major shortcomings: training such deep learning models requires a large amount of data and (ground truth) annotations and consumes a significant amount of computational and power resources. Moreover, the performance of deep learning models is sensitive to deviations between the training and the test set, for example due to the presence of (adversarial) noise. This special issue welcomes contributions related to innovative designs of model-aware deep learning models, novel approaches to train such models (including unsupervised, self-supervised and semi-supervised
learning) and advanced topics concerning such models (including robustness, explainability, metalearning and out-of-distribution detection).

Guest editors:

    Dr. Emilie Chouzenoux, Inria Saclay, emilie.chouzenoux@inria.fr
    Dr. Nikos Deligiannis, Vrije Univ. Brussels, ndeligia@etrovub.be
    Prof. Aleksandra Pizurica, Univ. Ghent, Aleksandra.Pizurica@ugent.be

Manuscript submission information:

The special issue topic is at the forefront of the developments of interpretable AI and at the intersection between signal processing and machine learning. In recent years, there are various important contributions that show that signal processing concepts such as low-complexity models (such as sparsity and low-rankness) and associated algorithms can offer a fundamental twist in the design of deep learning models. Such models can incorporate knowledge about the data or task at hand offering performance and interpretability advantages. Despite the progress in the field and the attention it has received, there are still various important problems that remain elusive, including the robustness of these models when the data is contaminated by (adversarial) noise, the post-hoc explainability of these models, the efficient (unsupervised) training of these models. This special issue aims at bridging this gap by welcoming contributions covering among others the following topics:

    Innovative design of model-aware deep learning models
    New model-aware deep learning architecture, including graph deep learning models and transformers
    Generative model-aware deep learning Out-of-distribution detection for model-aware deep learning
    Model-aware deep learning models by algorithmic unrolling
    Robust model-aware deep learning Model-aware deep learning for meta-learning, zero-shot and
    few-shot learning
    Unsupervised, self-supervised and semi-supervised model-aware deep learning
    Explainability and interpretability for model-aware deep learning
    Distributed and federated model-aware deep learning

Applications of model-aware deep learning in image/video processing, signal processing, computer vision, big data, and natural language processing

Important date:

Submission deadline: 31 July 2024
Deadline for acceptance: Octorber 2024

Special Issue on Trustworthy Multi-modal Signal Processing and Applications
Submission Date: 2024-12-31

Multi-modal signal processing is a hot and inevitable topic nowadays in many fields such as video processing, medical signal processing as well as intelligent decision systems. It is worth noting that most of today's large models are also driven by multi-modal data, especially visual and text data. Although various methods have been put forward for multi-modal signal processing and gained great success in past decades, it is still  challenging to make reliable decisions by using multi-modal data since the quality of different modalities as well as a modality for different samples is hard to be well guaranteed, which leads to untrustworthy predictions or decisions. Therefore, we need to design trustworthy multi-modal signal processing (TMSP) theories and methods.

Manuscript submission information:

There are two major issues that need to be further investigated in TMSP, including data reliability and model reliability. For example, missing or noisy values as well as adversarial examples often exist among multi-modal data, which makes the data unreliable. While the lack of theoretical interpretability hinders the reliability of the model. Therefore, it is an urgent demanding research task to develop trustworthy multi-modal signal processing algorithms for exploring the weaknesses of low-quality multi-modal data and unreliable learning models to enhance the trustworthiness in data processing and intelligent decision systems.

In this special issue, we seek original contributions towards cutting-edge methodologies and applications for trustworthy multi-modal signal processing and attempts to solve the remaining challenges. Researchers and practitioners in both academic and industrial communities are welcomed to share new insights of trustworthy multi-modal signal processing in the field of emerging data processing and intelligent decision systems, such as trustworthy multi-modal signal processing theories and methods, computer-aided medical diagnosis, attack and defense for intelligent decision systems, cybersecurity systems, and unmanned drivingsystems, etc.

Scope of the Special Issue:

Potential contributions may address, but are not limited to, the following topics:

⚫ Trustworthy multi-modal signal processing theories
⚫ Trustworthy multi-modal signal processing models
⚫ Trustworthy multi-modal signal processing with low-quality data
⚫ Uncertainty modeling theories for multi-modal signal processing
⚫ Uncertainty modeling theories for multi-modal data
⚫ Trustworthy multi-modal signal processing for computer vision
⚫ Trustworthy multi-modal signal processing for natural language processing
⚫ Trustworthy multi-modal signal processing social network analysis
⚫ Trustworthy multi-modal signal processing for information retrieval
⚫ Trustworthy multi-modal signal processing for medical data processing
⚫ Trustworthy multi-modal signal processing for cybersecurity systems
⚫ Trustworthy multi-modal signal processing for unmanned driving systems
⚫ Trustworthy multi-modal signal processing for bioinformatics
⚫ Self-supervised trustworthy multi-modal signal processing
⚫ Semi-supervised trustworthy multi-modal signal processing
⚫ Supervised trustworthy multi-modal signal processing
⚫ Unsupervised trustworthy multi-modal signal processing

Important Dates:

Submission Portal Open: May 1st, 2024
Submission Deadline: August 31th, 2024
Acceptance Deadline: December 31st, 2024