sensors-logo

Journal Browser

Journal Browser

Sensor Signal and Information Processing IV

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

Deadline for manuscript submissions: closed (31 January 2022) | Viewed by 5983

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer and Information Sciences, Northumbria University, Newcastle upon Tyne NE1 8ST, UK
Interests: machine learning; artificial intelligence; computational intelligence; data analytics
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 610056, China
Interests: audio and image processing; social signal processing; multi-physics mathematical modeling; non-destructive evaluation
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Sensor signal and information processing (SSIP) is an overarching field of research focusing on the mathematical foundations and practical applications of signal processing algorithms that learn, reason, and act. It bridges the boundary between theory and application, developing novel theoretically-inspired methodologies targeting both longstanding and emergent signal processing applications. The core of SSIP lies in its use of nonlinear and non-Gaussian signal processing methodologies combined with convex and non-convex optimization. SSIP encompasses new theoretical frameworks for statistical signal processing (e.g., hidden Markov model, latent component analysis, tensor factorization, Bayesian methods) coupled with information-theoretic learning, and novel developments in these areas specifically related to the processing of a variety of signal modalities, including audio, bio-signals, multi-physics signals, images, multispectral, and video, among others. In recent years, many signal processing algorithms have incorporated some form of computational intelligence as part of their core framework in problem-solving. These algorithms have the capacity to generalize and discover knowledge for themselves and can learn to learn new information whenever unseen data is captured.

The focus of the Special Issue will be on a broad range of sensors, signals, and information processing involving the introduction and development of new advanced theoretical and practical algorithms. Potential topics include, but are not limited to the following:

  • Biomedical signal processing and instrumentation
  • Pattern recognition and analysis
  • Machine learning for signal and image processing
  • Multimodality sensor fusion techniques
  • Compressed sensing and sparsity aware processing
  • Data science and analytics for big data
  • Deep learning: theory, algorithms, and applications
  • Multi-objective signal processing optimization
  • Multimodal information processing for healthcare, monitoring, and surveillance
  • Computer vision and 3D reconstruction with multimodal data fusion
  • Wearable sensors and IoT for personalized health monitoring and social computing
  • Non-destructive testing and evaluation for material characterization, structural integrity, defect detection and identification, and stress and lifecycle assessment
  • Signal processing for smart grid, load forecasting, and energy management
  • Precision farming combining sensors and imaging with real-time data analytics
  • Other emerging applications of signal and information processing

Prof. Dr. Wai Lok Woo
Prof. Dr. Bin Gao
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 submissions that pass pre-check are 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 2600 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.

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

24 pages, 5433 KiB  
Article
Attention Module Magnetic Flux Leakage Linked Deep Residual Network for Pipeline In-Line Inspection
by Shucong Liu, Hongjun Wang and Rui Li
Sensors 2022, 22(6), 2230; https://doi.org/10.3390/s22062230 - 14 Mar 2022
Cited by 8 | Viewed by 2574
Abstract
Pipeline operational safety is the foundation of the pipeline industry. Inspection and evaluation of defects is an important means of ensuring the safe operation of pipelines. In-line inspection of Magnetic Flux Leakage (MFL) can be used to identify and analyze potential defects. For [...] Read more.
Pipeline operational safety is the foundation of the pipeline industry. Inspection and evaluation of defects is an important means of ensuring the safe operation of pipelines. In-line inspection of Magnetic Flux Leakage (MFL) can be used to identify and analyze potential defects. For pipeline MFL identification with inspecting in long distance, there exists the issues of low identification efficiency, misjudgment and leakage judgment. To solve these problems, a pipeline MFL inspection signal identification method based on improved deep residual convolutional neural network and attention module is proposed. A improved deep residual network based on the VGG16 convolution neural network is constructed to automatically learn the features from the MFL image signals and perform the identification of pipeline features and defects. The attention modules are introduced to reduce the influence of noises and compound features on the identification results in the process of in-line inspection. The actual pipeline in-line inspection experimental results show that the proposed method can accurately classify the MFL in-line inspection image signals and effectively reduce the influence of noises on the feature identification results with an average classification accuracy of 97.7%. This method can effectively improve identification accuracy and efficiency of the pipeline MFL in-line inspection. Full article
(This article belongs to the Special Issue Sensor Signal and Information Processing IV)
Show Figures

Figure 1

15 pages, 4564 KiB  
Article
Defect Width Assessment Based on the Near-Field Magnetic Flux Leakage Method
by Erlong Li, Yiming Chen, Xiaotian Chen and Jianbo Wu
Sensors 2021, 21(16), 5424; https://doi.org/10.3390/s21165424 - 11 Aug 2021
Cited by 6 | Viewed by 2312
Abstract
Magnetic flux leakage (MFL) testing has been widely used as a non-destructive testing method for various materials. However, it is difficult to separate the influences of the defect geometrical parameters such as depth, width, and length on the received leakage signals. In this [...] Read more.
Magnetic flux leakage (MFL) testing has been widely used as a non-destructive testing method for various materials. However, it is difficult to separate the influences of the defect geometrical parameters such as depth, width, and length on the received leakage signals. In this paper, a “near-field” MFL method is proposed to quantify defect widths. Both the finite element modelling (FEM) and experimental studies are carried out to investigate the performance of the proposed method. It is found that that the distance between two peaks of the “near-field” MFL is strongly related to the defect width and lift-off value, whereas it is slightly affected by the defect depth. Based on this phenomenon, a defect width assessment relying on the “near-field” MFL method is proposed. Results show that relative judging errors are less than 5%. In addition, the analytical expression of the “near-field” MFL is also developed. Full article
(This article belongs to the Special Issue Sensor Signal and Information Processing IV)
Show Figures

Figure 1

Back to TopTop