Special Issue "Deep Learning for Multi-Sensor Fusion"
Deadline for manuscript submissions: 1 July 2019
With the advent of deep learning, architectures with billions of parameters and trained in vast collections of data have become more and more prevalent. Deep architectures are now recognized as overcoming classic approaches provided that the learning datasets are available or synthesizable. At the same time, the development of sensor technologies has led to a diversity of sources of information that are now available to robotic systems and to inference algorithms. Extensive research efforts have been devoted in the last decades to the design of the combination of these different pieces of information, e.g., modelling source features, prior knowledge, and decisions under uncertain reasoning. Yet, although some works have shown examples where deep architectures succeeded in learning the optimal multi-source combination, important advances are still required to understand how to design such powerful architectures, to train them with respect to multi-sensor or multi-source data, and to make machine learning interact with source models and prior knowledge from the training process to the final decision.
The aim of this Special Issue is to highlight innovative developments with respect to the current challenges in processing multi-sensor or multi-source data related to designing resilient architectures. We particularly welcome contributions that will provide insights into the key mechanisms encouraging the good behaviour and robustness of the methods.
Topics include but are not limited to the following:
- Multi-source based learning with domain-specific prior knowledge constraints;
- Learning in the presence of imperfect data and/or imprecise ground truth;
- Hierarchical learning for integrating additional sources effectively;
- Autonomous navigation based on multi-sensor fusion, with a special focus on robustness to sensor failure;
- Video and audio modalities for expression and activity recognition, or for behaviour disorder detection;
- Data fusion for remote sensing and aerial photography;
- Multimodal biometric systems.
Dr. Emanuel Aldea
Dr. Francois Bremond
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. Sensors is an international peer-reviewed open access semimonthly 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.
- Deep neural architectures
- Machine learning
- Data fusion
- Imperfect data
- Image modality