E-Mail Alert

Add your e-mail address to receive forthcoming issues of this journal:

Journal Browser

Journal Browser

Special Issue "Deep Learning for Multi-Sensor Fusion"

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensor Networks".

Deadline for manuscript submissions: 1 July 2019

Special Issue Editors

Guest Editor
Prof. Sylvie Le Hegarat-Mascle

SATIE laboratory, University Paris-Saclay, rue Noezlin, Orsay 91405 cedex, France
Website | E-Mail
Interests: uncertain reasoning; pattern recognition; computer vision; machine learning for classification; remote sensing
Guest Editor
Dr. Emanuel Aldea

SATIE laboratory, University Paris-Saclay, rue Noezlin, Orsay 91405 cedex, France
Website | E-Mail
Interests: deep learning; 3D vision; robotic navigation and localization; multiple camera systems
Guest Editor
Dr. Francois Bremond

INRIA Stars team, 2004 route des Lucioles, 06902 Sophia Antipolis Cedex BP 93 France
Website | E-Mail
Phone: +33 492387659
Interests: activity recognition; action localization; people detection and tracking; human behavior analysis

Special Issue Information

Dear Colleagues,

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.
Prof. Sylvie Le Hegarat-Mascle
Dr. Emanuel Aldea
Dr. Francois Bremond
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. 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.

Keywords

  • Deep neural architectures
  • Machine learning
  • Data fusion
  • Multi-sensor
  • Imperfect data
  • Image modality

Published Papers (1 paper)

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

Research

Open AccessArticle A Novel Deep Learning Method for Intelligent Fault Diagnosis of Rotating Machinery Based on Improved CNN-SVM and Multichannel Data Fusion
Sensors 2019, 19(7), 1693; https://doi.org/10.3390/s19071693
Received: 24 February 2019 / Revised: 1 April 2019 / Accepted: 5 April 2019 / Published: 9 April 2019
PDF Full-text (7838 KB) | HTML Full-text | XML Full-text
Abstract
Intelligent fault diagnosis methods based on deep learning becomes a research hotspot in the fault diagnosis field. Automatically and accurately identifying the incipient micro-fault of rotating machinery, especially for fault orientations and severity degree, is still a major challenge in the field of [...] Read more.
Intelligent fault diagnosis methods based on deep learning becomes a research hotspot in the fault diagnosis field. Automatically and accurately identifying the incipient micro-fault of rotating machinery, especially for fault orientations and severity degree, is still a major challenge in the field of intelligent fault diagnosis. The traditional fault diagnosis methods rely on the manual feature extraction of engineers with prior knowledge. To effectively identify an incipient fault in rotating machinery, this paper proposes a novel method, namely improved the convolutional neural network-support vector machine (CNN-SVM) method. This method improves the traditional convolutional neural network (CNN) model structure by introducing the global average pooling technology and SVM. Firstly, the temporal and spatial multichannel raw data from multiple sensors is directly input into the improved CNN-Softmax model for the training of the CNN model. Secondly, the improved CNN are used for extracting representative features from the raw fault data. Finally, the extracted sparse representative feature vectors are input into SVM for fault classification. The proposed method is applied to the diagnosis multichannel vibration signal monitoring data of a rolling bearing. The results confirm that the proposed method is more effective than other existing intelligence diagnosis methods including SVM, K-nearest neighbor, back-propagation neural network, deep BP neural network, and traditional CNN. Full article
(This article belongs to the Special Issue Deep Learning for Multi-Sensor Fusion)
Figures

Figure 1

Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top